Merge pull request #1913 from clinton-hall/farewell-2.7

Farewell 2.7

azure-pipelines.yml

@@ -13,8 +13,6 @@ jobs:
     vmImage: 'Ubuntu-latest'
   strategy:
     matrix:
-      Python27:
-        python.version: '2.7'
       Python36:
         python.version: '3.6'
       Python37:
@@ -32,7 +30,7 @@ jobs:
       sudo apt-get update
       sudo apt-get install ffmpeg
     displayName: 'Install ffmpeg'
-  
+
   - task: UsePythonVersion@0
     inputs:
       versionSpec: '$(python.version)'

cleanup.py

@@ -18,7 +18,6 @@ FOLDER_STRUCTURE = {
     'libs': [
         'common',
         'custom',
-        'py2',
         'win',
     ],
     'core': [

libs/py2/backports/__init__.py

@@ -1 +0,0 @@
-__path__ = __import__('pkgutil').extend_path(__path__, __name__)

libs/py2/backports/functools_lru_cache.py

@@ -1,184 +0,0 @@
-from __future__ import absolute_import
-
-import functools
-from collections import namedtuple
-from threading import RLock
-
-_CacheInfo = namedtuple("CacheInfo", ["hits", "misses", "maxsize", "currsize"])
-
-
-@functools.wraps(functools.update_wrapper)
-def update_wrapper(wrapper,
-                   wrapped,
-                   assigned = functools.WRAPPER_ASSIGNMENTS,
-                   updated = functools.WRAPPER_UPDATES):
-    """
-    Patch two bugs in functools.update_wrapper.
-    """
-    # workaround for http://bugs.python.org/issue3445
-    assigned = tuple(attr for attr in assigned if hasattr(wrapped, attr))
-    wrapper = functools.update_wrapper(wrapper, wrapped, assigned, updated)
-    # workaround for https://bugs.python.org/issue17482
-    wrapper.__wrapped__ = wrapped
-    return wrapper
-
-
-class _HashedSeq(list):
-    __slots__ = 'hashvalue'
-
-    def __init__(self, tup, hash=hash):
-        self[:] = tup
-        self.hashvalue = hash(tup)
-
-    def __hash__(self):
-        return self.hashvalue
-
-
-def _make_key(args, kwds, typed,
-              kwd_mark=(object(),),
-              fasttypes=set([int, str, frozenset, type(None)]),
-              sorted=sorted, tuple=tuple, type=type, len=len):
-    'Make a cache key from optionally typed positional and keyword arguments'
-    key = args
-    if kwds:
-        sorted_items = sorted(kwds.items())
-        key += kwd_mark
-        for item in sorted_items:
-            key += item
-    if typed:
-        key += tuple(type(v) for v in args)
-        if kwds:
-            key += tuple(type(v) for k, v in sorted_items)
-    elif len(key) == 1 and type(key[0]) in fasttypes:
-        return key[0]
-    return _HashedSeq(key)
-
-
-def lru_cache(maxsize=100, typed=False):
-    """Least-recently-used cache decorator.
-
-    If *maxsize* is set to None, the LRU features are disabled and the cache
-    can grow without bound.
-
-    If *typed* is True, arguments of different types will be cached separately.
-    For example, f(3.0) and f(3) will be treated as distinct calls with
-    distinct results.
-
-    Arguments to the cached function must be hashable.
-
-    View the cache statistics named tuple (hits, misses, maxsize, currsize) with
-    f.cache_info().  Clear the cache and statistics with f.cache_clear().
-    Access the underlying function with f.__wrapped__.
-
-    See:  http://en.wikipedia.org/wiki/Cache_algorithms#Least_Recently_Used
-
-    """
-
-    # Users should only access the lru_cache through its public API:
-    #       cache_info, cache_clear, and f.__wrapped__
-    # The internals of the lru_cache are encapsulated for thread safety and
-    # to allow the implementation to change (including a possible C version).
-
-    def decorating_function(user_function):
-
-        cache = dict()
-        stats = [0, 0]                  # make statistics updateable non-locally
-        HITS, MISSES = 0, 1             # names for the stats fields
-        make_key = _make_key
-        cache_get = cache.get           # bound method to lookup key or return None
-        _len = len                      # localize the global len() function
-        lock = RLock()                  # because linkedlist updates aren't threadsafe
-        root = []                       # root of the circular doubly linked list
-        root[:] = [root, root, None, None]      # initialize by pointing to self
-        nonlocal_root = [root]                  # make updateable non-locally
-        PREV, NEXT, KEY, RESULT = 0, 1, 2, 3    # names for the link fields
-
-        if maxsize == 0:
-
-            def wrapper(*args, **kwds):
-                # no caching, just do a statistics update after a successful call
-                result = user_function(*args, **kwds)
-                stats[MISSES] += 1
-                return result
-
-        elif maxsize is None:
-
-            def wrapper(*args, **kwds):
-                # simple caching without ordering or size limit
-                key = make_key(args, kwds, typed)
-                result = cache_get(key, root)   # root used here as a unique not-found sentinel
-                if result is not root:
-                    stats[HITS] += 1
-                    return result
-                result = user_function(*args, **kwds)
-                cache[key] = result
-                stats[MISSES] += 1
-                return result
-
-        else:
-
-            def wrapper(*args, **kwds):
-                # size limited caching that tracks accesses by recency
-                key = make_key(args, kwds, typed) if kwds or typed else args
-                with lock:
-                    link = cache_get(key)
-                    if link is not None:
-                        # record recent use of the key by moving it to the front of the list
-                        root, = nonlocal_root
-                        link_prev, link_next, key, result = link
-                        link_prev[NEXT] = link_next
-                        link_next[PREV] = link_prev
-                        last = root[PREV]
-                        last[NEXT] = root[PREV] = link
-                        link[PREV] = last
-                        link[NEXT] = root
-                        stats[HITS] += 1
-                        return result
-                result = user_function(*args, **kwds)
-                with lock:
-                    root, = nonlocal_root
-                    if key in cache:
-                        # getting here means that this same key was added to the
-                        # cache while the lock was released.  since the link
-                        # update is already done, we need only return the
-                        # computed result and update the count of misses.
-                        pass
-                    elif _len(cache) >= maxsize:
-                        # use the old root to store the new key and result
-                        oldroot = root
-                        oldroot[KEY] = key
-                        oldroot[RESULT] = result
-                        # empty the oldest link and make it the new root
-                        root = nonlocal_root[0] = oldroot[NEXT]
-                        oldkey = root[KEY]
-                        root[KEY] = root[RESULT] = None
-                        # now update the cache dictionary for the new links
-                        del cache[oldkey]
-                        cache[key] = oldroot
-                    else:
-                        # put result in a new link at the front of the list
-                        last = root[PREV]
-                        link = [last, root, key, result]
-                        last[NEXT] = root[PREV] = cache[key] = link
-                    stats[MISSES] += 1
-                return result
-
-        def cache_info():
-            """Report cache statistics"""
-            with lock:
-                return _CacheInfo(stats[HITS], stats[MISSES], maxsize, len(cache))
-
-        def cache_clear():
-            """Clear the cache and cache statistics"""
-            with lock:
-                cache.clear()
-                root = nonlocal_root[0]
-                root[:] = [root, root, None, None]
-                stats[:] = [0, 0]
-
-        wrapper.__wrapped__ = user_function
-        wrapper.cache_info = cache_info
-        wrapper.cache_clear = cache_clear
-        return update_wrapper(wrapper, user_function)
-
-    return decorating_function

libs/py2/bs4/__init__.py

@@ -1,584 +0,0 @@
-"""Beautiful Soup
-Elixir and Tonic
-"The Screen-Scraper's Friend"
-http://www.crummy.com/software/BeautifulSoup/
-
-Beautiful Soup uses a pluggable XML or HTML parser to parse a
-(possibly invalid) document into a tree representation. Beautiful Soup
-provides methods and Pythonic idioms that make it easy to navigate,
-search, and modify the parse tree.
-
-Beautiful Soup works with Python 2.7 and up. It works better if lxml
-and/or html5lib is installed.
-
-For more than you ever wanted to know about Beautiful Soup, see the
-documentation:
-http://www.crummy.com/software/BeautifulSoup/bs4/doc/
-
-"""
-
-# Use of this source code is governed by a BSD-style license that can be
-# found in the LICENSE file.
-
-__author__ = "Leonard Richardson (leonardr@segfault.org)"
-__version__ = "4.6.3"
-__copyright__ = "Copyright (c) 2004-2018 Leonard Richardson"
-__license__ = "MIT"
-
-__all__ = ['BeautifulSoup']
-
-import os
-import re
-import sys
-import traceback
-import warnings
-
-from .builder import builder_registry, ParserRejectedMarkup
-from .dammit import UnicodeDammit
-from .element import (
-    CData,
-    Comment,
-    DEFAULT_OUTPUT_ENCODING,
-    Declaration,
-    Doctype,
-    NavigableString,
-    PageElement,
-    ProcessingInstruction,
-    ResultSet,
-    SoupStrainer,
-    Tag,
-    )
-
-# The very first thing we do is give a useful error if someone is
-# running this code under Python 3 without converting it.
-'You are trying to run the Python 2 version of Beautiful Soup under Python 3. This will not work.'<>'You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).'
-
-class BeautifulSoup(Tag):
-    """
-    This class defines the basic interface called by the tree builders.
-
-    These methods will be called by the parser:
-      reset()
-      feed(markup)
-
-    The tree builder may call these methods from its feed() implementation:
-      handle_starttag(name, attrs) # See note about return value
-      handle_endtag(name)
-      handle_data(data) # Appends to the current data node
-      endData(containerClass=NavigableString) # Ends the current data node
-
-    No matter how complicated the underlying parser is, you should be
-    able to build a tree using 'start tag' events, 'end tag' events,
-    'data' events, and "done with data" events.
-
-    If you encounter an empty-element tag (aka a self-closing tag,
-    like HTML's <br> tag), call handle_starttag and then
-    handle_endtag.
-    """
-    ROOT_TAG_NAME = u'[document]'
-
-    # If the end-user gives no indication which tree builder they
-    # want, look for one with these features.
-    DEFAULT_BUILDER_FEATURES = ['html', 'fast']
-
-    ASCII_SPACES = '\x20\x0a\x09\x0c\x0d'
-
-    NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available %(markup_type)s parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nThe code that caused this warning is on line %(line_number)s of the file %(filename)s. To get rid of this warning, pass the additional argument 'features=\"%(parser)s\"' to the BeautifulSoup constructor.\n"
-
-    def __init__(self, markup="", features=None, builder=None,
-                 parse_only=None, from_encoding=None, exclude_encodings=None,
-                 **kwargs):
-        """Constructor.
-
-        :param markup: A string or a file-like object representing
-        markup to be parsed.
-
-        :param features: Desirable features of the parser to be used. This
-        may be the name of a specific parser ("lxml", "lxml-xml",
-        "html.parser", or "html5lib") or it may be the type of markup
-        to be used ("html", "html5", "xml"). It's recommended that you
-        name a specific parser, so that Beautiful Soup gives you the
-        same results across platforms and virtual environments.
-
-        :param builder: A specific TreeBuilder to use instead of looking one
-        up based on `features`. You shouldn't need to use this.
-
-        :param parse_only: A SoupStrainer. Only parts of the document
-        matching the SoupStrainer will be considered. This is useful
-        when parsing part of a document that would otherwise be too
-        large to fit into memory.
-
-        :param from_encoding: A string indicating the encoding of the
-        document to be parsed. Pass this in if Beautiful Soup is
-        guessing wrongly about the document's encoding.
-
-        :param exclude_encodings: A list of strings indicating
-        encodings known to be wrong. Pass this in if you don't know
-        the document's encoding but you know Beautiful Soup's guess is
-        wrong.
-
-        :param kwargs: For backwards compatibility purposes, the
-        constructor accepts certain keyword arguments used in
-        Beautiful Soup 3. None of these arguments do anything in
-        Beautiful Soup 4 and there's no need to actually pass keyword
-        arguments into the constructor.
-        """
-
-        if 'convertEntities' in kwargs:
-            warnings.warn(
-                "BS4 does not respect the convertEntities argument to the "
-                "BeautifulSoup constructor. Entities are always converted "
-                "to Unicode characters.")
-
-        if 'markupMassage' in kwargs:
-            del kwargs['markupMassage']
-            warnings.warn(
-                "BS4 does not respect the markupMassage argument to the "
-                "BeautifulSoup constructor. The tree builder is responsible "
-                "for any necessary markup massage.")
-
-        if 'smartQuotesTo' in kwargs:
-            del kwargs['smartQuotesTo']
-            warnings.warn(
-                "BS4 does not respect the smartQuotesTo argument to the "
-                "BeautifulSoup constructor. Smart quotes are always converted "
-                "to Unicode characters.")
-
-        if 'selfClosingTags' in kwargs:
-            del kwargs['selfClosingTags']
-            warnings.warn(
-                "BS4 does not respect the selfClosingTags argument to the "
-                "BeautifulSoup constructor. The tree builder is responsible "
-                "for understanding self-closing tags.")
-
-        if 'isHTML' in kwargs:
-            del kwargs['isHTML']
-            warnings.warn(
-                "BS4 does not respect the isHTML argument to the "
-                "BeautifulSoup constructor. Suggest you use "
-                "features='lxml' for HTML and features='lxml-xml' for "
-                "XML.")
-
-        def deprecated_argument(old_name, new_name):
-            if old_name in kwargs:
-                warnings.warn(
-                    'The "%s" argument to the BeautifulSoup constructor '
-                    'has been renamed to "%s."' % (old_name, new_name))
-                value = kwargs[old_name]
-                del kwargs[old_name]
-                return value
-            return None
-
-        parse_only = parse_only or deprecated_argument(
-            "parseOnlyThese", "parse_only")
-
-        from_encoding = from_encoding or deprecated_argument(
-            "fromEncoding", "from_encoding")
-
-        if from_encoding and isinstance(markup, unicode):
-            warnings.warn("You provided Unicode markup but also provided a value for from_encoding. Your from_encoding will be ignored.")
-            from_encoding = None
-
-        if len(kwargs) > 0:
-            arg = kwargs.keys().pop()
-            raise TypeError(
-                "__init__() got an unexpected keyword argument '%s'" % arg)
-
-        if builder is None:
-            original_features = features
-            if isinstance(features, basestring):
-                features = [features]
-            if features is None or len(features) == 0:
-                features = self.DEFAULT_BUILDER_FEATURES
-            builder_class = builder_registry.lookup(*features)
-            if builder_class is None:
-                raise FeatureNotFound(
-                    "Couldn't find a tree builder with the features you "
-                    "requested: %s. Do you need to install a parser library?"
-                    % ",".join(features))
-            builder = builder_class()
-            if not (original_features == builder.NAME or
-                    original_features in builder.ALTERNATE_NAMES):
-                if builder.is_xml:
-                    markup_type = "XML"
-                else:
-                    markup_type = "HTML"
-
-                # This code adapted from warnings.py so that we get the same line
-                # of code as our warnings.warn() call gets, even if the answer is wrong
-                # (as it may be in a multithreading situation).
-                caller = None
-                try:
-                    caller = sys._getframe(1)
-                except ValueError:
-                    pass
-                if caller:
-                    globals = caller.f_globals
-                    line_number = caller.f_lineno
-                else:
-                    globals = sys.__dict__
-                    line_number= 1                    
-                filename = globals.get('__file__')
-                if filename:
-                    fnl = filename.lower()
-                    if fnl.endswith((".pyc", ".pyo")):
-                        filename = filename[:-1]
-                if filename:
-                    # If there is no filename at all, the user is most likely in a REPL,
-                    # and the warning is not necessary.
-                    values = dict(
-                        filename=filename,
-                        line_number=line_number,
-                        parser=builder.NAME,
-                        markup_type=markup_type
-                    )
-                    warnings.warn(self.NO_PARSER_SPECIFIED_WARNING % values, stacklevel=2)
-
-        self.builder = builder
-        self.is_xml = builder.is_xml
-        self.known_xml = self.is_xml
-        self.builder.soup = self
-
-        self.parse_only = parse_only
-
-        if hasattr(markup, 'read'):        # It's a file-type object.
-            markup = markup.read()
-        elif len(markup) <= 256 and (
-                (isinstance(markup, bytes) and not b'<' in markup)
-                or (isinstance(markup, unicode) and not u'<' in markup)
-        ):
-            # Print out warnings for a couple beginner problems
-            # involving passing non-markup to Beautiful Soup.
-            # Beautiful Soup will still parse the input as markup,
-            # just in case that's what the user really wants.
-            if (isinstance(markup, unicode)
-                and not os.path.supports_unicode_filenames):
-                possible_filename = markup.encode("utf8")
-            else:
-                possible_filename = markup
-            is_file = False
-            try:
-                is_file = os.path.exists(possible_filename)
-            except Exception, e:
-                # This is almost certainly a problem involving
-                # characters not valid in filenames on this
-                # system. Just let it go.
-                pass
-            if is_file:
-                if isinstance(markup, unicode):
-                    markup = markup.encode("utf8")
-                warnings.warn(
-                    '"%s" looks like a filename, not markup. You should'
-                    ' probably open this file and pass the filehandle into'
-                    ' Beautiful Soup.' % markup)
-            self._check_markup_is_url(markup)
-
-        for (self.markup, self.original_encoding, self.declared_html_encoding,
-         self.contains_replacement_characters) in (
-             self.builder.prepare_markup(
-                 markup, from_encoding, exclude_encodings=exclude_encodings)):
-            self.reset()
-            try:
-                self._feed()
-                break
-            except ParserRejectedMarkup:
-                pass
-
-        # Clear out the markup and remove the builder's circular
-        # reference to this object.
-        self.markup = None
-        self.builder.soup = None
-
-    def __copy__(self):
-        copy = type(self)(
-            self.encode('utf-8'), builder=self.builder, from_encoding='utf-8'
-        )
-
-        # Although we encoded the tree to UTF-8, that may not have
-        # been the encoding of the original markup. Set the copy's
-        # .original_encoding to reflect the original object's
-        # .original_encoding.
-        copy.original_encoding = self.original_encoding
-        return copy
-
-    def __getstate__(self):
-        # Frequently a tree builder can't be pickled.
-        d = dict(self.__dict__)
-        if 'builder' in d and not self.builder.picklable:
-            d['builder'] = None
-        return d
-
-    @staticmethod
-    def _check_markup_is_url(markup):
-        """ 
-        Check if markup looks like it's actually a url and raise a warning 
-        if so. Markup can be unicode or str (py2) / bytes (py3).
-        """
-        if isinstance(markup, bytes):
-            space = b' '
-            cant_start_with = (b"http:", b"https:")
-        elif isinstance(markup, unicode):
-            space = u' '
-            cant_start_with = (u"http:", u"https:")
-        else:
-            return
-
-        if any(markup.startswith(prefix) for prefix in cant_start_with):
-            if not space in markup:
-                if isinstance(markup, bytes):
-                    decoded_markup = markup.decode('utf-8', 'replace')
-                else:
-                    decoded_markup = markup
-                warnings.warn(
-                    '"%s" looks like a URL. Beautiful Soup is not an'
-                    ' HTTP client. You should probably use an HTTP client like'
-                    ' requests to get the document behind the URL, and feed'
-                    ' that document to Beautiful Soup.' % decoded_markup
-                )
-
-    def _feed(self):
-        # Convert the document to Unicode.
-        self.builder.reset()
-
-        self.builder.feed(self.markup)
-        # Close out any unfinished strings and close all the open tags.
-        self.endData()
-        while self.currentTag.name != self.ROOT_TAG_NAME:
-            self.popTag()
-
-    def reset(self):
-        Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME)
-        self.hidden = 1
-        self.builder.reset()
-        self.current_data = []
-        self.currentTag = None
-        self.tagStack = []
-        self.preserve_whitespace_tag_stack = []
-        self.pushTag(self)
-
-    def new_tag(self, name, namespace=None, nsprefix=None, attrs={}, **kwattrs):
-        """Create a new tag associated with this soup."""
-        kwattrs.update(attrs)
-        return Tag(None, self.builder, name, namespace, nsprefix, kwattrs)
-
-    def new_string(self, s, subclass=NavigableString):
-        """Create a new NavigableString associated with this soup."""
-        return subclass(s)
-
-    def insert_before(self, successor):
-        raise NotImplementedError("BeautifulSoup objects don't support insert_before().")
-
-    def insert_after(self, successor):
-        raise NotImplementedError("BeautifulSoup objects don't support insert_after().")
-
-    def popTag(self):
-        tag = self.tagStack.pop()
-        if self.preserve_whitespace_tag_stack and tag == self.preserve_whitespace_tag_stack[-1]:
-            self.preserve_whitespace_tag_stack.pop()
-        #print "Pop", tag.name
-        if self.tagStack:
-            self.currentTag = self.tagStack[-1]
-        return self.currentTag
-
-    def pushTag(self, tag):
-        #print "Push", tag.name
-        if self.currentTag:
-            self.currentTag.contents.append(tag)
-        self.tagStack.append(tag)
-        self.currentTag = self.tagStack[-1]
-        if tag.name in self.builder.preserve_whitespace_tags:
-            self.preserve_whitespace_tag_stack.append(tag)
-
-    def endData(self, containerClass=NavigableString):
-        if self.current_data:
-            current_data = u''.join(self.current_data)
-            # If whitespace is not preserved, and this string contains
-            # nothing but ASCII spaces, replace it with a single space
-            # or newline.
-            if not self.preserve_whitespace_tag_stack:
-                strippable = True
-                for i in current_data:
-                    if i not in self.ASCII_SPACES:
-                        strippable = False
-                        break
-                if strippable:
-                    if '\n' in current_data:
-                        current_data = '\n'
-                    else:
-                        current_data = ' '
-
-            # Reset the data collector.
-            self.current_data = []
-
-            # Should we add this string to the tree at all?
-            if self.parse_only and len(self.tagStack) <= 1 and \
-                   (not self.parse_only.text or \
-                    not self.parse_only.search(current_data)):
-                return
-
-            o = containerClass(current_data)
-            self.object_was_parsed(o)
-
-    def object_was_parsed(self, o, parent=None, most_recent_element=None):
-        """Add an object to the parse tree."""
-        parent = parent or self.currentTag
-        previous_element = most_recent_element or self._most_recent_element
-
-        next_element = previous_sibling = next_sibling = None
-        if isinstance(o, Tag):
-            next_element = o.next_element
-            next_sibling = o.next_sibling
-            previous_sibling = o.previous_sibling
-            if not previous_element:
-                previous_element = o.previous_element
-
-        o.setup(parent, previous_element, next_element, previous_sibling, next_sibling)
-
-        self._most_recent_element = o
-        parent.contents.append(o)
-
-        if parent.next_sibling:
-            # This node is being inserted into an element that has
-            # already been parsed. Deal with any dangling references.
-            index = len(parent.contents)-1
-            while index >= 0:
-                if parent.contents[index] is o:
-                    break
-                index -= 1
-            else:
-                raise ValueError(
-                    "Error building tree: supposedly %r was inserted "
-                    "into %r after the fact, but I don't see it!" % (
-                        o, parent
-                    )
-                )
-            if index == 0:
-                previous_element = parent
-                previous_sibling = None
-            else:
-                previous_element = previous_sibling = parent.contents[index-1]
-            if index == len(parent.contents)-1:
-                next_element = parent.next_sibling
-                next_sibling = None
-            else:
-                next_element = next_sibling = parent.contents[index+1]
-
-            o.previous_element = previous_element
-            if previous_element:
-                previous_element.next_element = o
-            o.next_element = next_element
-            if next_element:
-                next_element.previous_element = o
-            o.next_sibling = next_sibling
-            if next_sibling:
-                next_sibling.previous_sibling = o
-            o.previous_sibling = previous_sibling
-            if previous_sibling:
-                previous_sibling.next_sibling = o
-
-    def _popToTag(self, name, nsprefix=None, inclusivePop=True):
-        """Pops the tag stack up to and including the most recent
-        instance of the given tag. If inclusivePop is false, pops the tag
-        stack up to but *not* including the most recent instqance of
-        the given tag."""
-        #print "Popping to %s" % name
-        if name == self.ROOT_TAG_NAME:
-            # The BeautifulSoup object itself can never be popped.
-            return
-
-        most_recently_popped = None
-
-        stack_size = len(self.tagStack)
-        for i in range(stack_size - 1, 0, -1):
-            t = self.tagStack[i]
-            if (name == t.name and nsprefix == t.prefix):
-                if inclusivePop:
-                    most_recently_popped = self.popTag()
-                break
-            most_recently_popped = self.popTag()
-
-        return most_recently_popped
-
-    def handle_starttag(self, name, namespace, nsprefix, attrs):
-        """Push a start tag on to the stack.
-
-        If this method returns None, the tag was rejected by the
-        SoupStrainer. You should proceed as if the tag had not occurred
-        in the document. For instance, if this was a self-closing tag,
-        don't call handle_endtag.
-        """
-
-        # print "Start tag %s: %s" % (name, attrs)
-        self.endData()
-
-        if (self.parse_only and len(self.tagStack) <= 1
-            and (self.parse_only.text
-                 or not self.parse_only.search_tag(name, attrs))):
-            return None
-
-        tag = Tag(self, self.builder, name, namespace, nsprefix, attrs,
-                  self.currentTag, self._most_recent_element)
-        if tag is None:
-            return tag
-        if self._most_recent_element:
-            self._most_recent_element.next_element = tag
-        self._most_recent_element = tag
-        self.pushTag(tag)
-        return tag
-
-    def handle_endtag(self, name, nsprefix=None):
-        #print "End tag: " + name
-        self.endData()
-        self._popToTag(name, nsprefix)
-
-    def handle_data(self, data):
-        self.current_data.append(data)
-
-    def decode(self, pretty_print=False,
-               eventual_encoding=DEFAULT_OUTPUT_ENCODING,
-               formatter="minimal"):
-        """Returns a string or Unicode representation of this document.
-        To get Unicode, pass None for encoding."""
-
-        if self.is_xml:
-            # Print the XML declaration
-            encoding_part = ''
-            if eventual_encoding != None:
-                encoding_part = ' encoding="%s"' % eventual_encoding
-            prefix = u'<?xml version="1.0"%s?>\n' % encoding_part
-        else:
-            prefix = u''
-        if not pretty_print:
-            indent_level = None
-        else:
-            indent_level = 0
-        return prefix + super(BeautifulSoup, self).decode(
-            indent_level, eventual_encoding, formatter)
-
-# Alias to make it easier to type import: 'from bs4 import _soup'
-_s = BeautifulSoup
-_soup = BeautifulSoup
-
-class BeautifulStoneSoup(BeautifulSoup):
-    """Deprecated interface to an XML parser."""
-
-    def __init__(self, *args, **kwargs):
-        kwargs['features'] = 'xml'
-        warnings.warn(
-            'The BeautifulStoneSoup class is deprecated. Instead of using '
-            'it, pass features="xml" into the BeautifulSoup constructor.')
-        super(BeautifulStoneSoup, self).__init__(*args, **kwargs)
-
-
-class StopParsing(Exception):
-    pass
-
-class FeatureNotFound(ValueError):
-    pass
-
-
-#By default, act as an HTML pretty-printer.
-if __name__ == '__main__':
-    import sys
-    soup = BeautifulSoup(sys.stdin)
-    print soup.prettify()

libs/py2/bs4/builder/__init__.py

@@ -1,339 +0,0 @@
-# Use of this source code is governed by a BSD-style license that can be
-# found in the LICENSE file.
-
-from collections import defaultdict
-import itertools
-import sys
-from bs4.element import (
-    CharsetMetaAttributeValue,
-    ContentMetaAttributeValue,
-    HTMLAwareEntitySubstitution,
-    whitespace_re
-    )
-
-__all__ = [
-    'HTMLTreeBuilder',
-    'SAXTreeBuilder',
-    'TreeBuilder',
-    'TreeBuilderRegistry',
-    ]
-
-# Some useful features for a TreeBuilder to have.
-FAST = 'fast'
-PERMISSIVE = 'permissive'
-STRICT = 'strict'
-XML = 'xml'
-HTML = 'html'
-HTML_5 = 'html5'
-
-
-class TreeBuilderRegistry(object):
-
-    def __init__(self):
-        self.builders_for_feature = defaultdict(list)
-        self.builders = []
-
-    def register(self, treebuilder_class):
-        """Register a treebuilder based on its advertised features."""
-        for feature in treebuilder_class.features:
-            self.builders_for_feature[feature].insert(0, treebuilder_class)
-        self.builders.insert(0, treebuilder_class)
-
-    def lookup(self, *features):
-        if len(self.builders) == 0:
-            # There are no builders at all.
-            return None
-
-        if len(features) == 0:
-            # They didn't ask for any features. Give them the most
-            # recently registered builder.
-            return self.builders[0]
-
-        # Go down the list of features in order, and eliminate any builders
-        # that don't match every feature.
-        features = list(features)
-        features.reverse()
-        candidates = None
-        candidate_set = None
-        while len(features) > 0:
-            feature = features.pop()
-            we_have_the_feature = self.builders_for_feature.get(feature, [])
-            if len(we_have_the_feature) > 0:
-                if candidates is None:
-                    candidates = we_have_the_feature
-                    candidate_set = set(candidates)
-                else:
-                    # Eliminate any candidates that don't have this feature.
-                    candidate_set = candidate_set.intersection(
-                        set(we_have_the_feature))
-
-        # The only valid candidates are the ones in candidate_set.
-        # Go through the original list of candidates and pick the first one
-        # that's in candidate_set.
-        if candidate_set is None:
-            return None
-        for candidate in candidates:
-            if candidate in candidate_set:
-                return candidate
-        return None
-
-# The BeautifulSoup class will take feature lists from developers and use them
-# to look up builders in this registry.
-builder_registry = TreeBuilderRegistry()
-
-class TreeBuilder(object):
-    """Turn a document into a Beautiful Soup object tree."""
-
-    NAME = "[Unknown tree builder]"
-    ALTERNATE_NAMES = []
-    features = []
-
-    is_xml = False
-    picklable = False
-    preserve_whitespace_tags = set()
-    empty_element_tags = None # A tag will be considered an empty-element
-                              # tag when and only when it has no contents.
-    
-    # A value for these tag/attribute combinations is a space- or
-    # comma-separated list of CDATA, rather than a single CDATA.
-    cdata_list_attributes = {}
-
-
-    def __init__(self):
-        self.soup = None
-
-    def reset(self):
-        pass
-
-    def can_be_empty_element(self, tag_name):
-        """Might a tag with this name be an empty-element tag?
-
-        The final markup may or may not actually present this tag as
-        self-closing.
-
-        For instance: an HTMLBuilder does not consider a <p> tag to be
-        an empty-element tag (it's not in
-        HTMLBuilder.empty_element_tags). This means an empty <p> tag
-        will be presented as "<p></p>", not "<p />".
-
-        The default implementation has no opinion about which tags are
-        empty-element tags, so a tag will be presented as an
-        empty-element tag if and only if it has no contents.
-        "<foo></foo>" will become "<foo />", and "<foo>bar</foo>" will
-        be left alone.
-        """
-        if self.empty_element_tags is None:
-            return True
-        return tag_name in self.empty_element_tags
-        
-    def feed(self, markup):
-        raise NotImplementedError()
-
-    def prepare_markup(self, markup, user_specified_encoding=None,
-                       document_declared_encoding=None):
-        return markup, None, None, False
-
-    def test_fragment_to_document(self, fragment):
-        """Wrap an HTML fragment to make it look like a document.
-
-        Different parsers do this differently. For instance, lxml
-        introduces an empty <head> tag, and html5lib
-        doesn't. Abstracting this away lets us write simple tests
-        which run HTML fragments through the parser and compare the
-        results against other HTML fragments.
-
-        This method should not be used outside of tests.
-        """
-        return fragment
-
-    def set_up_substitutions(self, tag):
-        return False
-
-    def _replace_cdata_list_attribute_values(self, tag_name, attrs):
-        """Replaces class="foo bar" with class=["foo", "bar"]
-
-        Modifies its input in place.
-        """
-        if not attrs:
-            return attrs
-        if self.cdata_list_attributes:
-            universal = self.cdata_list_attributes.get('*', [])
-            tag_specific = self.cdata_list_attributes.get(
-                tag_name.lower(), None)
-            for attr in attrs.keys():
-                if attr in universal or (tag_specific and attr in tag_specific):
-                    # We have a "class"-type attribute whose string
-                    # value is a whitespace-separated list of
-                    # values. Split it into a list.
-                    value = attrs[attr]
-                    if isinstance(value, basestring):
-                        values = whitespace_re.split(value)
-                    else:
-                        # html5lib sometimes calls setAttributes twice
-                        # for the same tag when rearranging the parse
-                        # tree. On the second call the attribute value
-                        # here is already a list.  If this happens,
-                        # leave the value alone rather than trying to
-                        # split it again.
-                        values = value
-                    attrs[attr] = values
-        return attrs
-
-class SAXTreeBuilder(TreeBuilder):
-    """A Beautiful Soup treebuilder that listens for SAX events."""
-
-    def feed(self, markup):
-        raise NotImplementedError()
-
-    def close(self):
-        pass
-
-    def startElement(self, name, attrs):
-        attrs = dict((key[1], value) for key, value in list(attrs.items()))
-        #print "Start %s, %r" % (name, attrs)
-        self.soup.handle_starttag(name, attrs)
-
-    def endElement(self, name):
-        #print "End %s" % name
-        self.soup.handle_endtag(name)
-
-    def startElementNS(self, nsTuple, nodeName, attrs):
-        # Throw away (ns, nodeName) for now.
-        self.startElement(nodeName, attrs)
-
-    def endElementNS(self, nsTuple, nodeName):
-        # Throw away (ns, nodeName) for now.
-        self.endElement(nodeName)
-        #handler.endElementNS((ns, node.nodeName), node.nodeName)
-
-    def startPrefixMapping(self, prefix, nodeValue):
-        # Ignore the prefix for now.
-        pass
-
-    def endPrefixMapping(self, prefix):
-        # Ignore the prefix for now.
-        # handler.endPrefixMapping(prefix)
-        pass
-
-    def characters(self, content):
-        self.soup.handle_data(content)
-
-    def startDocument(self):
-        pass
-
-    def endDocument(self):
-        pass
-
-
-class HTMLTreeBuilder(TreeBuilder):
-    """This TreeBuilder knows facts about HTML.
-
-    Such as which tags are empty-element tags.
-    """
-
-    preserve_whitespace_tags = HTMLAwareEntitySubstitution.preserve_whitespace_tags
-    empty_element_tags = set([
-        # These are from HTML5.
-        'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
-        
-        # These are from earlier versions of HTML and are removed in HTML5.
-        'basefont', 'bgsound', 'command', 'frame', 'image', 'isindex', 'nextid', 'spacer'
-    ])
-
-    # The HTML standard defines these as block-level elements. Beautiful
-    # Soup does not treat these elements differently from other elements,
-    # but it may do so eventually, and this information is available if
-    # you need to use it.
-    block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"])
-    
-    # The HTML standard defines these attributes as containing a
-    # space-separated list of values, not a single value. That is,
-    # class="foo bar" means that the 'class' attribute has two values,
-    # 'foo' and 'bar', not the single value 'foo bar'.  When we
-    # encounter one of these attributes, we will parse its value into
-    # a list of values if possible. Upon output, the list will be
-    # converted back into a string.
-    cdata_list_attributes = {
-        "*" : ['class', 'accesskey', 'dropzone'],
-        "a" : ['rel', 'rev'],
-        "link" :  ['rel', 'rev'],
-        "td" : ["headers"],
-        "th" : ["headers"],
-        "td" : ["headers"],
-        "form" : ["accept-charset"],
-        "object" : ["archive"],
-
-        # These are HTML5 specific, as are *.accesskey and *.dropzone above.
-        "area" : ["rel"],
-        "icon" : ["sizes"],
-        "iframe" : ["sandbox"],
-        "output" : ["for"],
-        }
-
-    def set_up_substitutions(self, tag):
-        # We are only interested in <meta> tags
-        if tag.name != 'meta':
-            return False
-
-        http_equiv = tag.get('http-equiv')
-        content = tag.get('content')
-        charset = tag.get('charset')
-
-        # We are interested in <meta> tags that say what encoding the
-        # document was originally in. This means HTML 5-style <meta>
-        # tags that provide the "charset" attribute. It also means
-        # HTML 4-style <meta> tags that provide the "content"
-        # attribute and have "http-equiv" set to "content-type".
-        #
-        # In both cases we will replace the value of the appropriate
-        # attribute with a standin object that can take on any
-        # encoding.
-        meta_encoding = None
-        if charset is not None:
-            # HTML 5 style:
-            # <meta charset="utf8">
-            meta_encoding = charset
-            tag['charset'] = CharsetMetaAttributeValue(charset)
-
-        elif (content is not None and http_equiv is not None
-              and http_equiv.lower() == 'content-type'):
-            # HTML 4 style:
-            # <meta http-equiv="content-type" content="text/html; charset=utf8">
-            tag['content'] = ContentMetaAttributeValue(content)
-
-        return (meta_encoding is not None)
-
-def register_treebuilders_from(module):
-    """Copy TreeBuilders from the given module into this module."""
-    # I'm fairly sure this is not the best way to do this.
-    this_module = sys.modules['bs4.builder']
-    for name in module.__all__:
-        obj = getattr(module, name)
-
-        if issubclass(obj, TreeBuilder):
-            setattr(this_module, name, obj)
-            this_module.__all__.append(name)
-            # Register the builder while we're at it.
-            this_module.builder_registry.register(obj)
-
-class ParserRejectedMarkup(Exception):
-    pass
-
-# Builders are registered in reverse order of priority, so that custom
-# builder registrations will take precedence. In general, we want lxml
-# to take precedence over html5lib, because it's faster. And we only
-# want to use HTMLParser as a last result.
-from . import _htmlparser
-register_treebuilders_from(_htmlparser)
-try:
-    from . import _html5lib
-    register_treebuilders_from(_html5lib)
-except ImportError:
-    # They don't have html5lib installed.
-    pass
-try:
-    from . import _lxml
-    register_treebuilders_from(_lxml)
-except ImportError:
-    # They don't have lxml installed.
-    pass

libs/py2/bs4/builder/_html5lib.py

@@ -1,426 +0,0 @@
-# Use of this source code is governed by a BSD-style license that can be
-# found in the LICENSE file.
-
-__all__ = [
-    'HTML5TreeBuilder',
-    ]
-
-import warnings
-import re
-from bs4.builder import (
-    PERMISSIVE,
-    HTML,
-    HTML_5,
-    HTMLTreeBuilder,
-    )
-from bs4.element import (
-    NamespacedAttribute,
-    whitespace_re,
-)
-import html5lib
-from html5lib.constants import (
-    namespaces,
-    prefixes,
-    )
-from bs4.element import (
-    Comment,
-    Doctype,
-    NavigableString,
-    Tag,
-    )
-
-try:
-    # Pre-0.99999999
-    from html5lib.treebuilders import _base as treebuilder_base
-    new_html5lib = False
-except ImportError, e:
-    # 0.99999999 and up
-    from html5lib.treebuilders import base as treebuilder_base
-    new_html5lib = True
-
-class HTML5TreeBuilder(HTMLTreeBuilder):
-    """Use html5lib to build a tree."""
-
-    NAME = "html5lib"
-
-    features = [NAME, PERMISSIVE, HTML_5, HTML]
-
-    def prepare_markup(self, markup, user_specified_encoding,
-                       document_declared_encoding=None, exclude_encodings=None):
-        # Store the user-specified encoding for use later on.
-        self.user_specified_encoding = user_specified_encoding
-
-        # document_declared_encoding and exclude_encodings aren't used
-        # ATM because the html5lib TreeBuilder doesn't use
-        # UnicodeDammit.
-        if exclude_encodings:
-            warnings.warn("You provided a value for exclude_encoding, but the html5lib tree builder doesn't support exclude_encoding.")
-        yield (markup, None, None, False)
-
-    # These methods are defined by Beautiful Soup.
-    def feed(self, markup):
-        if self.soup.parse_only is not None:
-            warnings.warn("You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.")
-        parser = html5lib.HTMLParser(tree=self.create_treebuilder)
-
-        extra_kwargs = dict()
-        if not isinstance(markup, unicode):
-            if new_html5lib:
-                extra_kwargs['override_encoding'] = self.user_specified_encoding
-            else:
-                extra_kwargs['encoding'] = self.user_specified_encoding
-        doc = parser.parse(markup, **extra_kwargs)
-
-        # Set the character encoding detected by the tokenizer.
-        if isinstance(markup, unicode):
-            # We need to special-case this because html5lib sets
-            # charEncoding to UTF-8 if it gets Unicode input.
-            doc.original_encoding = None
-        else:
-            original_encoding = parser.tokenizer.stream.charEncoding[0]
-            if not isinstance(original_encoding, basestring):
-                # In 0.99999999 and up, the encoding is an html5lib
-                # Encoding object. We want to use a string for compatibility
-                # with other tree builders.
-                original_encoding = original_encoding.name
-            doc.original_encoding = original_encoding
-
-    def create_treebuilder(self, namespaceHTMLElements):
-        self.underlying_builder = TreeBuilderForHtml5lib(
-            namespaceHTMLElements, self.soup)
-        return self.underlying_builder
-
-    def test_fragment_to_document(self, fragment):
-        """See `TreeBuilder`."""
-        return u'<html><head></head><body>%s</body></html>' % fragment
-
-
-class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
-
-    def __init__(self, namespaceHTMLElements, soup=None):
-        if soup:
-            self.soup = soup
-        else:
-            from bs4 import BeautifulSoup
-            self.soup = BeautifulSoup("", "html.parser")
-        super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
-
-    def documentClass(self):
-        self.soup.reset()
-        return Element(self.soup, self.soup, None)
-
-    def insertDoctype(self, token):
-        name = token["name"]
-        publicId = token["publicId"]
-        systemId = token["systemId"]
-
-        doctype = Doctype.for_name_and_ids(name, publicId, systemId)
-        self.soup.object_was_parsed(doctype)
-
-    def elementClass(self, name, namespace):
-        tag = self.soup.new_tag(name, namespace)
-        return Element(tag, self.soup, namespace)
-
-    def commentClass(self, data):
-        return TextNode(Comment(data), self.soup)
-
-    def fragmentClass(self):
-        from bs4 import BeautifulSoup
-        self.soup = BeautifulSoup("", "html.parser")
-        self.soup.name = "[document_fragment]"
-        return Element(self.soup, self.soup, None)
-
-    def appendChild(self, node):
-        # XXX This code is not covered by the BS4 tests.
-        self.soup.append(node.element)
-
-    def getDocument(self):
-        return self.soup
-
-    def getFragment(self):
-        return treebuilder_base.TreeBuilder.getFragment(self).element
-
-    def testSerializer(self, element):
-        from bs4 import BeautifulSoup
-        rv = []
-        doctype_re = re.compile(r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
-
-        def serializeElement(element, indent=0):
-            if isinstance(element, BeautifulSoup):
-                pass
-            if isinstance(element, Doctype):
-                m = doctype_re.match(element)
-                if m:
-                    name = m.group(1)
-                    if m.lastindex > 1:
-                        publicId = m.group(2) or ""
-                        systemId = m.group(3) or m.group(4) or ""
-                        rv.append("""|%s<!DOCTYPE %s "%s" "%s">""" %
-                                  (' ' * indent, name, publicId, systemId))
-                    else:
-                        rv.append("|%s<!DOCTYPE %s>" % (' ' * indent, name))
-                else:
-                    rv.append("|%s<!DOCTYPE >" % (' ' * indent,))
-            elif isinstance(element, Comment):
-                rv.append("|%s<!-- %s -->" % (' ' * indent, element))
-            elif isinstance(element, NavigableString):
-                rv.append("|%s\"%s\"" % (' ' * indent, element))
-            else:
-                if element.namespace:
-                    name = "%s %s" % (prefixes[element.namespace],
-                                      element.name)
-                else:
-                    name = element.name
-                rv.append("|%s<%s>" % (' ' * indent, name))
-                if element.attrs:
-                    attributes = []
-                    for name, value in element.attrs.items():
-                        if isinstance(name, NamespacedAttribute):
-                            name = "%s %s" % (prefixes[name.namespace], name.name)
-                        if isinstance(value, list):
-                            value = " ".join(value)
-                        attributes.append((name, value))
-
-                    for name, value in sorted(attributes):
-                        rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
-                indent += 2
-                for child in element.children:
-                    serializeElement(child, indent)
-        serializeElement(element, 0)
-
-        return "\n".join(rv)
-
-class AttrList(object):
-    def __init__(self, element):
-        self.element = element
-        self.attrs = dict(self.element.attrs)
-    def __iter__(self):
-        return list(self.attrs.items()).__iter__()
-    def __setitem__(self, name, value):
-        # If this attribute is a multi-valued attribute for this element,
-        # turn its value into a list.
-        list_attr = HTML5TreeBuilder.cdata_list_attributes
-        if (name in list_attr['*']
-            or (self.element.name in list_attr
-                and name in list_attr[self.element.name])):
-            # A node that is being cloned may have already undergone
-            # this procedure.
-            if not isinstance(value, list):
-                value = whitespace_re.split(value)
-        self.element[name] = value
-    def items(self):
-        return list(self.attrs.items())
-    def keys(self):
-        return list(self.attrs.keys())
-    def __len__(self):
-        return len(self.attrs)
-    def __getitem__(self, name):
-        return self.attrs[name]
-    def __contains__(self, name):
-        return name in list(self.attrs.keys())
-
-
-class Element(treebuilder_base.Node):
-    def __init__(self, element, soup, namespace):
-        treebuilder_base.Node.__init__(self, element.name)
-        self.element = element
-        self.soup = soup
-        self.namespace = namespace
-
-    def appendChild(self, node):
-        string_child = child = None
-        if isinstance(node, basestring):
-            # Some other piece of code decided to pass in a string
-            # instead of creating a TextElement object to contain the
-            # string.
-            string_child = child = node
-        elif isinstance(node, Tag):
-            # Some other piece of code decided to pass in a Tag
-            # instead of creating an Element object to contain the
-            # Tag.
-            child = node
-        elif node.element.__class__ == NavigableString:
-            string_child = child = node.element
-            node.parent = self
-        else:
-            child = node.element
-            node.parent = self
-
-        if not isinstance(child, basestring) and child.parent is not None:
-            node.element.extract()
-
-        if (string_child and self.element.contents
-            and self.element.contents[-1].__class__ == NavigableString):
-            # We are appending a string onto another string.
-            # TODO This has O(n^2) performance, for input like
-            # "a</a>a</a>a</a>..."
-            old_element = self.element.contents[-1]
-            new_element = self.soup.new_string(old_element + string_child)
-            old_element.replace_with(new_element)
-            self.soup._most_recent_element = new_element
-        else:
-            if isinstance(node, basestring):
-                # Create a brand new NavigableString from this string.
-                child = self.soup.new_string(node)
-
-            # Tell Beautiful Soup to act as if it parsed this element
-            # immediately after the parent's last descendant. (Or
-            # immediately after the parent, if it has no children.)
-            if self.element.contents:
-                most_recent_element = self.element._last_descendant(False)
-            elif self.element.next_element is not None:
-                # Something from further ahead in the parse tree is
-                # being inserted into this earlier element. This is
-                # very annoying because it means an expensive search
-                # for the last element in the tree.
-                most_recent_element = self.soup._last_descendant()
-            else:
-                most_recent_element = self.element
-
-            self.soup.object_was_parsed(
-                child, parent=self.element,
-                most_recent_element=most_recent_element)
-
-    def getAttributes(self):
-        if isinstance(self.element, Comment):
-            return {}
-        return AttrList(self.element)
-
-    def setAttributes(self, attributes):
-
-        if attributes is not None and len(attributes) > 0:
-
-            converted_attributes = []
-            for name, value in list(attributes.items()):
-                if isinstance(name, tuple):
-                    new_name = NamespacedAttribute(*name)
-                    del attributes[name]
-                    attributes[new_name] = value
-
-            self.soup.builder._replace_cdata_list_attribute_values(
-                self.name, attributes)
-            for name, value in attributes.items():
-                self.element[name] = value
-
-            # The attributes may contain variables that need substitution.
-            # Call set_up_substitutions manually.
-            #
-            # The Tag constructor called this method when the Tag was created,
-            # but we just set/changed the attributes, so call it again.
-            self.soup.builder.set_up_substitutions(self.element)
-    attributes = property(getAttributes, setAttributes)
-
-    def insertText(self, data, insertBefore=None):
-        text = TextNode(self.soup.new_string(data), self.soup)
-        if insertBefore:
-            self.insertBefore(text, insertBefore)
-        else:
-            self.appendChild(text)
-
-    def insertBefore(self, node, refNode):
-        index = self.element.index(refNode.element)
-        if (node.element.__class__ == NavigableString and self.element.contents
-            and self.element.contents[index-1].__class__ == NavigableString):
-            # (See comments in appendChild)
-            old_node = self.element.contents[index-1]
-            new_str = self.soup.new_string(old_node + node.element)
-            old_node.replace_with(new_str)
-        else:
-            self.element.insert(index, node.element)
-            node.parent = self
-
-    def removeChild(self, node):
-        node.element.extract()
-
-    def reparentChildren(self, new_parent):
-        """Move all of this tag's children into another tag."""
-        # print "MOVE", self.element.contents
-        # print "FROM", self.element
-        # print "TO", new_parent.element
-
-        element = self.element
-        new_parent_element = new_parent.element
-        # Determine what this tag's next_element will be once all the children
-        # are removed.
-        final_next_element = element.next_sibling
-
-        new_parents_last_descendant = new_parent_element._last_descendant(False, False)
-        if len(new_parent_element.contents) > 0:
-            # The new parent already contains children. We will be
-            # appending this tag's children to the end.
-            new_parents_last_child = new_parent_element.contents[-1]
-            new_parents_last_descendant_next_element = new_parents_last_descendant.next_element
-        else:
-            # The new parent contains no children.
-            new_parents_last_child = None
-            new_parents_last_descendant_next_element = new_parent_element.next_element
-
-        to_append = element.contents
-        if len(to_append) > 0:
-            # Set the first child's previous_element and previous_sibling
-            # to elements within the new parent
-            first_child = to_append[0]
-            if new_parents_last_descendant:
-                first_child.previous_element = new_parents_last_descendant
-            else:
-                first_child.previous_element = new_parent_element
-            first_child.previous_sibling = new_parents_last_child
-            if new_parents_last_descendant:
-                new_parents_last_descendant.next_element = first_child
-            else:
-                new_parent_element.next_element = first_child
-            if new_parents_last_child:
-                new_parents_last_child.next_sibling = first_child
-
-            # Find the very last element being moved. It is now the
-            # parent's last descendant. It has no .next_sibling and
-            # its .next_element is whatever the previous last
-            # descendant had.
-            last_childs_last_descendant = to_append[-1]._last_descendant(False, True)
-
-            last_childs_last_descendant.next_element = new_parents_last_descendant_next_element
-            if new_parents_last_descendant_next_element:
-                # TODO: This code has no test coverage and I'm not sure
-                # how to get html5lib to go through this path, but it's
-                # just the other side of the previous line.
-                new_parents_last_descendant_next_element.previous_element = last_childs_last_descendant
-            last_childs_last_descendant.next_sibling = None
-
-        for child in to_append:
-            child.parent = new_parent_element
-            new_parent_element.contents.append(child)
-
-        # Now that this element has no children, change its .next_element.
-        element.contents = []
-        element.next_element = final_next_element
-
-        # print "DONE WITH MOVE"
-        # print "FROM", self.element
-        # print "TO", new_parent_element
-
-    def cloneNode(self):
-        tag = self.soup.new_tag(self.element.name, self.namespace)
-        node = Element(tag, self.soup, self.namespace)
-        for key,value in self.attributes:
-            node.attributes[key] = value
-        return node
-
-    def hasContent(self):
-        return self.element.contents
-
-    def getNameTuple(self):
-        if self.namespace == None:
-            return namespaces["html"], self.name
-        else:
-            return self.namespace, self.name
-
-    nameTuple = property(getNameTuple)
-
-class TextNode(Element):
-    def __init__(self, element, soup):
-        treebuilder_base.Node.__init__(self, None)
-        self.element = element
-        self.soup = soup
-
-    def cloneNode(self):
-        raise NotImplementedError

libs/py2/bs4/builder/_htmlparser.py

@@ -1,347 +0,0 @@
-# encoding: utf-8
-"""Use the HTMLParser library to parse HTML files that aren't too bad."""
-
-# Use of this source code is governed by a BSD-style license that can be
-# found in the LICENSE file.
-
-__all__ = [
-    'HTMLParserTreeBuilder',
-    ]
-
-from HTMLParser import HTMLParser
-
-try:
-    from HTMLParser import HTMLParseError
-except ImportError, e:
-    # HTMLParseError is removed in Python 3.5. Since it can never be
-    # thrown in 3.5, we can just define our own class as a placeholder.
-    class HTMLParseError(Exception):
-        pass
-
-import sys
-import warnings
-
-# Starting in Python 3.2, the HTMLParser constructor takes a 'strict'
-# argument, which we'd like to set to False. Unfortunately,
-# http://bugs.python.org/issue13273 makes strict=True a better bet
-# before Python 3.2.3.
-#
-# At the end of this file, we monkeypatch HTMLParser so that
-# strict=True works well on Python 3.2.2.
-major, minor, release = sys.version_info[:3]
-CONSTRUCTOR_TAKES_STRICT = major == 3 and minor == 2 and release >= 3
-CONSTRUCTOR_STRICT_IS_DEPRECATED = major == 3 and minor == 3
-CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4
-
-
-from bs4.element import (
-    CData,
-    Comment,
-    Declaration,
-    Doctype,
-    ProcessingInstruction,
-    )
-from bs4.dammit import EntitySubstitution, UnicodeDammit
-
-from bs4.builder import (
-    HTML,
-    HTMLTreeBuilder,
-    STRICT,
-    )
-
-
-HTMLPARSER = 'html.parser'
-
-class BeautifulSoupHTMLParser(HTMLParser):
-
-    def __init__(self, *args, **kwargs):
-        HTMLParser.__init__(self, *args, **kwargs)
-
-        # Keep a list of empty-element tags that were encountered
-        # without an explicit closing tag. If we encounter a closing tag
-        # of this type, we'll associate it with one of those entries.
-        #
-        # This isn't a stack because we don't care about the
-        # order. It's a list of closing tags we've already handled and
-        # will ignore, assuming they ever show up.
-        self.already_closed_empty_element = []
-
-    def error(self, msg):
-        """In Python 3, HTMLParser subclasses must implement error(), although this
-        requirement doesn't appear to be documented.
-
-        In Python 2, HTMLParser implements error() as raising an exception.
-
-        In any event, this method is called only on very strange markup and our best strategy
-        is to pretend it didn't happen and keep going.
-        """
-        warnings.warn(msg)
-        
-    def handle_startendtag(self, name, attrs):
-        # This is only called when the markup looks like
-        # <tag/>.
-
-        # is_startend() tells handle_starttag not to close the tag
-        # just because its name matches a known empty-element tag. We
-        # know that this is an empty-element tag and we want to call
-        # handle_endtag ourselves.
-        tag = self.handle_starttag(name, attrs, handle_empty_element=False)
-        self.handle_endtag(name)
-        
-    def handle_starttag(self, name, attrs, handle_empty_element=True):
-        # XXX namespace
-        attr_dict = {}
-        for key, value in attrs:
-            # Change None attribute values to the empty string
-            # for consistency with the other tree builders.
-            if value is None:
-                value = ''
-            attr_dict[key] = value
-            attrvalue = '""'
-        #print "START", name
-        tag = self.soup.handle_starttag(name, None, None, attr_dict)
-        if tag and tag.is_empty_element and handle_empty_element:
-            # Unlike other parsers, html.parser doesn't send separate end tag
-            # events for empty-element tags. (It's handled in
-            # handle_startendtag, but only if the original markup looked like
-            # <tag/>.)
-            #
-            # So we need to call handle_endtag() ourselves. Since we
-            # know the start event is identical to the end event, we
-            # don't want handle_endtag() to cross off any previous end
-            # events for tags of this name.
-            self.handle_endtag(name, check_already_closed=False)
-
-            # But we might encounter an explicit closing tag for this tag
-            # later on. If so, we want to ignore it.
-            self.already_closed_empty_element.append(name)
-            
-    def handle_endtag(self, name, check_already_closed=True):
-        #print "END", name
-        if check_already_closed and name in self.already_closed_empty_element:
-            # This is a redundant end tag for an empty-element tag.
-            # We've already called handle_endtag() for it, so just
-            # check it off the list.
-            # print "ALREADY CLOSED", name
-            self.already_closed_empty_element.remove(name)
-        else:
-            self.soup.handle_endtag(name)
-
-    def handle_data(self, data):
-        self.soup.handle_data(data)
-
-    def handle_charref(self, name):
-        # XXX workaround for a bug in HTMLParser. Remove this once
-        # it's fixed in all supported versions.
-        # http://bugs.python.org/issue13633
-        if name.startswith('x'):
-            real_name = int(name.lstrip('x'), 16)
-        elif name.startswith('X'):
-            real_name = int(name.lstrip('X'), 16)
-        else:
-            real_name = int(name)
-
-        data = None
-        if real_name < 256:
-            # HTML numeric entities are supposed to reference Unicode
-            # code points, but sometimes they reference code points in
-            # some other encoding (ahem, Windows-1252). E.g. &#147;
-            # instead of &#201; for LEFT DOUBLE QUOTATION MARK. This
-            # code tries to detect this situation and compensate.
-            for encoding in (self.soup.original_encoding, 'windows-1252'):
-                if not encoding:
-                    continue
-                try:
-                    data = bytearray([real_name]).decode(encoding)
-                except UnicodeDecodeError, e:
-                    pass
-        if not data:
-            try:
-                data = unichr(real_name)
-            except (ValueError, OverflowError), e:
-                pass
-        data = data or u"\N{REPLACEMENT CHARACTER}"
-        self.handle_data(data)
-
-    def handle_entityref(self, name):
-        character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
-        if character is not None:
-            data = character
-        else:
-            # If this were XML, it would be ambiguous whether "&foo"
-            # was an character entity reference with a missing
-            # semicolon or the literal string "&foo". Since this is
-            # HTML, we have a complete list of all character entity references,
-            # and this one wasn't found, so assume it's the literal string "&foo".
-            data = "&%s" % name
-        self.handle_data(data)
-
-    def handle_comment(self, data):
-        self.soup.endData()
-        self.soup.handle_data(data)
-        self.soup.endData(Comment)
-
-    def handle_decl(self, data):
-        self.soup.endData()
-        if data.startswith("DOCTYPE "):
-            data = data[len("DOCTYPE "):]
-        elif data == 'DOCTYPE':
-            # i.e. "<!DOCTYPE>"
-            data = ''
-        self.soup.handle_data(data)
-        self.soup.endData(Doctype)
-
-    def unknown_decl(self, data):
-        if data.upper().startswith('CDATA['):
-            cls = CData
-            data = data[len('CDATA['):]
-        else:
-            cls = Declaration
-        self.soup.endData()
-        self.soup.handle_data(data)
-        self.soup.endData(cls)
-
-    def handle_pi(self, data):
-        self.soup.endData()
-        self.soup.handle_data(data)
-        self.soup.endData(ProcessingInstruction)
-
-
-class HTMLParserTreeBuilder(HTMLTreeBuilder):
-
-    is_xml = False
-    picklable = True
-    NAME = HTMLPARSER
-    features = [NAME, HTML, STRICT]
-
-    def __init__(self, *args, **kwargs):
-        if CONSTRUCTOR_TAKES_STRICT and not CONSTRUCTOR_STRICT_IS_DEPRECATED:
-            kwargs['strict'] = False
-        if CONSTRUCTOR_TAKES_CONVERT_CHARREFS:
-            kwargs['convert_charrefs'] = False
-        self.parser_args = (args, kwargs)
-
-    def prepare_markup(self, markup, user_specified_encoding=None,
-                       document_declared_encoding=None, exclude_encodings=None):
-        """
-        :return: A 4-tuple (markup, original encoding, encoding
-        declared within markup, whether any characters had to be
-        replaced with REPLACEMENT CHARACTER).
-        """
-        if isinstance(markup, unicode):
-            yield (markup, None, None, False)
-            return
-
-        try_encodings = [user_specified_encoding, document_declared_encoding]
-        dammit = UnicodeDammit(markup, try_encodings, is_html=True,
-                               exclude_encodings=exclude_encodings)
-        yield (dammit.markup, dammit.original_encoding,
-               dammit.declared_html_encoding,
-               dammit.contains_replacement_characters)
-
-    def feed(self, markup):
-        args, kwargs = self.parser_args
-        parser = BeautifulSoupHTMLParser(*args, **kwargs)
-        parser.soup = self.soup
-        try:
-            parser.feed(markup)
-            parser.close()
-        except HTMLParseError, e:
-            warnings.warn(RuntimeWarning(
-                "Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
-            raise e
-        parser.already_closed_empty_element = []
-
-# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some
-# 3.2.3 code. This ensures they don't treat markup like <p></p> as a
-# string.
-#
-# XXX This code can be removed once most Python 3 users are on 3.2.3.
-if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT:
-    import re
-    attrfind_tolerant = re.compile(
-        r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
-        r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
-    HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant
-
-    locatestarttagend = re.compile(r"""
-  <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
-  (?:\s+                             # whitespace before attribute name
-    (?:[a-zA-Z_][-.:a-zA-Z0-9_]*     # attribute name
-      (?:\s*=\s*                     # value indicator
-        (?:'[^']*'                   # LITA-enclosed value
-          |\"[^\"]*\"                # LIT-enclosed value
-          |[^'\">\s]+                # bare value
-         )
-       )?
-     )
-   )*
-  \s*                                # trailing whitespace
-""", re.VERBOSE)
-    BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend
-
-    from html.parser import tagfind, attrfind
-
-    def parse_starttag(self, i):
-        self.__starttag_text = None
-        endpos = self.check_for_whole_start_tag(i)
-        if endpos < 0:
-            return endpos
-        rawdata = self.rawdata
-        self.__starttag_text = rawdata[i:endpos]
-
-        # Now parse the data between i+1 and j into a tag and attrs
-        attrs = []
-        match = tagfind.match(rawdata, i+1)
-        assert match, 'unexpected call to parse_starttag()'
-        k = match.end()
-        self.lasttag = tag = rawdata[i+1:k].lower()
-        while k < endpos:
-            if self.strict:
-                m = attrfind.match(rawdata, k)
-            else:
-                m = attrfind_tolerant.match(rawdata, k)
-            if not m:
-                break
-            attrname, rest, attrvalue = m.group(1, 2, 3)
-            if not rest:
-                attrvalue = None
-            elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
-                 attrvalue[:1] == '"' == attrvalue[-1:]:
-                attrvalue = attrvalue[1:-1]
-            if attrvalue:
-                attrvalue = self.unescape(attrvalue)
-            attrs.append((attrname.lower(), attrvalue))
-            k = m.end()
-
-        end = rawdata[k:endpos].strip()
-        if end not in (">", "/>"):
-            lineno, offset = self.getpos()
-            if "\n" in self.__starttag_text:
-                lineno = lineno + self.__starttag_text.count("\n")
-                offset = len(self.__starttag_text) \
-                         - self.__starttag_text.rfind("\n")
-            else:
-                offset = offset + len(self.__starttag_text)
-            if self.strict:
-                self.error("junk characters in start tag: %r"
-                           % (rawdata[k:endpos][:20],))
-            self.handle_data(rawdata[i:endpos])
-            return endpos
-        if end.endswith('/>'):
-            # XHTML-style empty tag: <span attr="value" />
-            self.handle_startendtag(tag, attrs)
-        else:
-            self.handle_starttag(tag, attrs)
-            if tag in self.CDATA_CONTENT_ELEMENTS:
-                self.set_cdata_mode(tag)
-        return endpos
-
-    def set_cdata_mode(self, elem):
-        self.cdata_elem = elem.lower()
-        self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
-
-    BeautifulSoupHTMLParser.parse_starttag = parse_starttag
-    BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode
-
-    CONSTRUCTOR_TAKES_STRICT = True

libs/py2/bs4/builder/_lxml.py

@@ -1,262 +0,0 @@
-# Use of this source code is governed by a BSD-style license that can be
-# found in the LICENSE file.
-__all__ = [
-    'LXMLTreeBuilderForXML',
-    'LXMLTreeBuilder',
-    ]
-
-try:
-    from collections.abc import Callable # Python 3.6
-except ImportError , e:
-    from collections import Callable
-
-from io import BytesIO
-from StringIO import StringIO
-from lxml import etree
-from bs4.element import (
-    Comment,
-    Doctype,
-    NamespacedAttribute,
-    ProcessingInstruction,
-    XMLProcessingInstruction,
-)
-from bs4.builder import (
-    FAST,
-    HTML,
-    HTMLTreeBuilder,
-    PERMISSIVE,
-    ParserRejectedMarkup,
-    TreeBuilder,
-    XML)
-from bs4.dammit import EncodingDetector
-
-LXML = 'lxml'
-
-class LXMLTreeBuilderForXML(TreeBuilder):
-    DEFAULT_PARSER_CLASS = etree.XMLParser
-
-    is_xml = True
-    processing_instruction_class = XMLProcessingInstruction
-
-    NAME = "lxml-xml"
-    ALTERNATE_NAMES = ["xml"]
-
-    # Well, it's permissive by XML parser standards.
-    features = [NAME, LXML, XML, FAST, PERMISSIVE]
-
-    CHUNK_SIZE = 512
-
-    # This namespace mapping is specified in the XML Namespace
-    # standard.
-    DEFAULT_NSMAPS = {'http://www.w3.org/XML/1998/namespace' : "xml"}
-
-    def default_parser(self, encoding):
-        # This can either return a parser object or a class, which
-        # will be instantiated with default arguments.
-        if self._default_parser is not None:
-            return self._default_parser
-        return etree.XMLParser(
-            target=self, strip_cdata=False, recover=True, encoding=encoding)
-
-    def parser_for(self, encoding):
-        # Use the default parser.
-        parser = self.default_parser(encoding)
-
-        if isinstance(parser, Callable):
-            # Instantiate the parser with default arguments
-            parser = parser(target=self, strip_cdata=False, encoding=encoding)
-        return parser
-
-    def __init__(self, parser=None, empty_element_tags=None):
-        # TODO: Issue a warning if parser is present but not a
-        # callable, since that means there's no way to create new
-        # parsers for different encodings.
-        self._default_parser = parser
-        if empty_element_tags is not None:
-            self.empty_element_tags = set(empty_element_tags)
-        self.soup = None
-        self.nsmaps = [self.DEFAULT_NSMAPS]
-
-    def _getNsTag(self, tag):
-        # Split the namespace URL out of a fully-qualified lxml tag
-        # name. Copied from lxml's src/lxml/sax.py.
-        if tag[0] == '{':
-            return tuple(tag[1:].split('}', 1))
-        else:
-            return (None, tag)
-
-    def prepare_markup(self, markup, user_specified_encoding=None,
-                       exclude_encodings=None,
-                       document_declared_encoding=None):
-        """
-        :yield: A series of 4-tuples.
-         (markup, encoding, declared encoding,
-          has undergone character replacement)
-
-        Each 4-tuple represents a strategy for parsing the document.
-        """
-        # Instead of using UnicodeDammit to convert the bytestring to
-        # Unicode using different encodings, use EncodingDetector to
-        # iterate over the encodings, and tell lxml to try to parse
-        # the document as each one in turn.
-        is_html = not self.is_xml
-        if is_html:
-            self.processing_instruction_class = ProcessingInstruction
-        else:
-            self.processing_instruction_class = XMLProcessingInstruction
-
-        if isinstance(markup, unicode):
-            # We were given Unicode. Maybe lxml can parse Unicode on
-            # this system?
-            yield markup, None, document_declared_encoding, False
-
-        if isinstance(markup, unicode):
-            # No, apparently not. Convert the Unicode to UTF-8 and
-            # tell lxml to parse it as UTF-8.
-            yield (markup.encode("utf8"), "utf8",
-                   document_declared_encoding, False)
-
-        try_encodings = [user_specified_encoding, document_declared_encoding]
-        detector = EncodingDetector(
-            markup, try_encodings, is_html, exclude_encodings)
-        for encoding in detector.encodings:
-            yield (detector.markup, encoding, document_declared_encoding, False)
-
-    def feed(self, markup):
-        if isinstance(markup, bytes):
-            markup = BytesIO(markup)
-        elif isinstance(markup, unicode):
-            markup = StringIO(markup)
-
-        # Call feed() at least once, even if the markup is empty,
-        # or the parser won't be initialized.
-        data = markup.read(self.CHUNK_SIZE)
-        try:
-            self.parser = self.parser_for(self.soup.original_encoding)
-            self.parser.feed(data)
-            while len(data) != 0:
-                # Now call feed() on the rest of the data, chunk by chunk.
-                data = markup.read(self.CHUNK_SIZE)
-                if len(data) != 0:
-                    self.parser.feed(data)
-            self.parser.close()
-        except (UnicodeDecodeError, LookupError, etree.ParserError), e:
-            raise ParserRejectedMarkup(str(e))
-
-    def close(self):
-        self.nsmaps = [self.DEFAULT_NSMAPS]
-
-    def start(self, name, attrs, nsmap={}):
-        # Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
-        attrs = dict(attrs)
-        nsprefix = None
-        # Invert each namespace map as it comes in.
-        if len(nsmap) == 0 and len(self.nsmaps) > 1:
-                # There are no new namespaces for this tag, but
-                # non-default namespaces are in play, so we need a
-                # separate tag stack to know when they end.
-                self.nsmaps.append(None)
-        elif len(nsmap) > 0:
-            # A new namespace mapping has come into play.
-            inverted_nsmap = dict((value, key) for key, value in nsmap.items())
-            self.nsmaps.append(inverted_nsmap)
-            # Also treat the namespace mapping as a set of attributes on the
-            # tag, so we can recreate it later.
-            attrs = attrs.copy()
-            for prefix, namespace in nsmap.items():
-                attribute = NamespacedAttribute(
-                    "xmlns", prefix, "http://www.w3.org/2000/xmlns/")
-                attrs[attribute] = namespace
-
-        # Namespaces are in play. Find any attributes that came in
-        # from lxml with namespaces attached to their names, and
-        # turn then into NamespacedAttribute objects.
-        new_attrs = {}
-        for attr, value in attrs.items():
-            namespace, attr = self._getNsTag(attr)
-            if namespace is None:
-                new_attrs[attr] = value
-            else:
-                nsprefix = self._prefix_for_namespace(namespace)
-                attr = NamespacedAttribute(nsprefix, attr, namespace)
-                new_attrs[attr] = value
-        attrs = new_attrs
-
-        namespace, name = self._getNsTag(name)
-        nsprefix = self._prefix_for_namespace(namespace)
-        self.soup.handle_starttag(name, namespace, nsprefix, attrs)
-
-    def _prefix_for_namespace(self, namespace):
-        """Find the currently active prefix for the given namespace."""
-        if namespace is None:
-            return None
-        for inverted_nsmap in reversed(self.nsmaps):
-            if inverted_nsmap is not None and namespace in inverted_nsmap:
-                return inverted_nsmap[namespace]
-        return None
-
-    def end(self, name):
-        self.soup.endData()
-        completed_tag = self.soup.tagStack[-1]
-        namespace, name = self._getNsTag(name)
-        nsprefix = None
-        if namespace is not None:
-            for inverted_nsmap in reversed(self.nsmaps):
-                if inverted_nsmap is not None and namespace in inverted_nsmap:
-                    nsprefix = inverted_nsmap[namespace]
-                    break
-        self.soup.handle_endtag(name, nsprefix)
-        if len(self.nsmaps) > 1:
-            # This tag, or one of its parents, introduced a namespace
-            # mapping, so pop it off the stack.
-            self.nsmaps.pop()
-
-    def pi(self, target, data):
-        self.soup.endData()
-        self.soup.handle_data(target + ' ' + data)
-        self.soup.endData(self.processing_instruction_class)
-
-    def data(self, content):
-        self.soup.handle_data(content)
-
-    def doctype(self, name, pubid, system):
-        self.soup.endData()
-        doctype = Doctype.for_name_and_ids(name, pubid, system)
-        self.soup.object_was_parsed(doctype)
-
-    def comment(self, content):
-        "Handle comments as Comment objects."
-        self.soup.endData()
-        self.soup.handle_data(content)
-        self.soup.endData(Comment)
-
-    def test_fragment_to_document(self, fragment):
-        """See `TreeBuilder`."""
-        return u'<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
-
-
-class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
-
-    NAME = LXML
-    ALTERNATE_NAMES = ["lxml-html"]
-
-    features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE]
-    is_xml = False
-    processing_instruction_class = ProcessingInstruction
-
-    def default_parser(self, encoding):
-        return etree.HTMLParser
-
-    def feed(self, markup):
-        encoding = self.soup.original_encoding
-        try:
-            self.parser = self.parser_for(encoding)
-            self.parser.feed(markup)
-            self.parser.close()
-        except (UnicodeDecodeError, LookupError, etree.ParserError), e:
-            raise ParserRejectedMarkup(str(e))
-
-
-    def test_fragment_to_document(self, fragment):
-        """See `TreeBuilder`."""
-        return u'<html><body>%s</body></html>' % fragment

libs/py2/bs4/dammit.py

@@ -1,842 +0,0 @@
-# -*- coding: utf-8 -*-
-"""Beautiful Soup bonus library: Unicode, Dammit
-
-This library converts a bytestream to Unicode through any means
-necessary. It is heavily based on code from Mark Pilgrim's Universal
-Feed Parser. It works best on XML and HTML, but it does not rewrite the
-XML or HTML to reflect a new encoding; that's the tree builder's job.
-"""
-# Use of this source code is governed by a BSD-style license that can be
-# found in the LICENSE file.
-__license__ = "MIT"
-
-import codecs
-from htmlentitydefs import codepoint2name
-import re
-import logging
-import string
-
-# Import a library to autodetect character encodings.
-chardet_type = None
-try:
-    # First try the fast C implementation.
-    #  PyPI package: cchardet
-    import cchardet
-    def chardet_dammit(s):
-        return cchardet.detect(s)['encoding']
-except ImportError:
-    try:
-        # Fall back to the pure Python implementation
-        #  Debian package: python-chardet
-        #  PyPI package: chardet
-        import chardet
-        def chardet_dammit(s):
-            return chardet.detect(s)['encoding']
-        #import chardet.constants
-        #chardet.constants._debug = 1
-    except ImportError:
-        # No chardet available.
-        def chardet_dammit(s):
-            return None
-
-# Available from http://cjkpython.i18n.org/.
-try:
-    import iconv_codec
-except ImportError:
-    pass
-
-xml_encoding_re = re.compile(
-    '^<\\?.*encoding=[\'"](.*?)[\'"].*\\?>'.encode(), re.I)
-html_meta_re = re.compile(
-    '<\\s*meta[^>]+charset\\s*=\\s*["\']?([^>]*?)[ /;\'">]'.encode(), re.I)
-
-class EntitySubstitution(object):
-
-    """Substitute XML or HTML entities for the corresponding characters."""
-
-    def _populate_class_variables():
-        lookup = {}
-        reverse_lookup = {}
-        characters_for_re = []
-        for codepoint, name in list(codepoint2name.items()):
-            character = unichr(codepoint)
-            if codepoint != 34:
-                # There's no point in turning the quotation mark into
-                # &quot;, unless it happens within an attribute value, which
-                # is handled elsewhere.
-                characters_for_re.append(character)
-                lookup[character] = name
-            # But we do want to turn &quot; into the quotation mark.
-            reverse_lookup[name] = character
-        re_definition = "[%s]" % "".join(characters_for_re)
-        return lookup, reverse_lookup, re.compile(re_definition)
-    (CHARACTER_TO_HTML_ENTITY, HTML_ENTITY_TO_CHARACTER,
-     CHARACTER_TO_HTML_ENTITY_RE) = _populate_class_variables()
-
-    CHARACTER_TO_XML_ENTITY = {
-        "'": "apos",
-        '"': "quot",
-        "&": "amp",
-        "<": "lt",
-        ">": "gt",
-        }
-
-    BARE_AMPERSAND_OR_BRACKET = re.compile("([<>]|"
-                                           "&(?!#\\d+;|#x[0-9a-fA-F]+;|\\w+;)"
-                                           ")")
-
-    AMPERSAND_OR_BRACKET = re.compile("([<>&])")
-
-    @classmethod
-    def _substitute_html_entity(cls, matchobj):
-        entity = cls.CHARACTER_TO_HTML_ENTITY.get(matchobj.group(0))
-        return "&%s;" % entity
-
-    @classmethod
-    def _substitute_xml_entity(cls, matchobj):
-        """Used with a regular expression to substitute the
-        appropriate XML entity for an XML special character."""
-        entity = cls.CHARACTER_TO_XML_ENTITY[matchobj.group(0)]
-        return "&%s;" % entity
-
-    @classmethod
-    def quoted_attribute_value(self, value):
-        """Make a value into a quoted XML attribute, possibly escaping it.
-
-         Most strings will be quoted using double quotes.
-
-          Bob's Bar -> "Bob's Bar"
-
-         If a string contains double quotes, it will be quoted using
-         single quotes.
-
-          Welcome to "my bar" -> 'Welcome to "my bar"'
-
-         If a string contains both single and double quotes, the
-         double quotes will be escaped, and the string will be quoted
-         using double quotes.
-
-          Welcome to "Bob's Bar" -> "Welcome to &quot;Bob's bar&quot;
-        """
-        quote_with = '"'
-        if '"' in value:
-            if "'" in value:
-                # The string contains both single and double
-                # quotes.  Turn the double quotes into
-                # entities. We quote the double quotes rather than
-                # the single quotes because the entity name is
-                # "&quot;" whether this is HTML or XML.  If we
-                # quoted the single quotes, we'd have to decide
-                # between &apos; and &squot;.
-                replace_with = "&quot;"
-                value = value.replace('"', replace_with)
-            else:
-                # There are double quotes but no single quotes.
-                # We can use single quotes to quote the attribute.
-                quote_with = "'"
-        return quote_with + value + quote_with
-
-    @classmethod
-    def substitute_xml(cls, value, make_quoted_attribute=False):
-        """Substitute XML entities for special XML characters.
-
-        :param value: A string to be substituted. The less-than sign
-          will become &lt;, the greater-than sign will become &gt;,
-          and any ampersands will become &amp;. If you want ampersands
-          that appear to be part of an entity definition to be left
-          alone, use substitute_xml_containing_entities() instead.
-
-        :param make_quoted_attribute: If True, then the string will be
-         quoted, as befits an attribute value.
-        """
-        # Escape angle brackets and ampersands.
-        value = cls.AMPERSAND_OR_BRACKET.sub(
-            cls._substitute_xml_entity, value)
-
-        if make_quoted_attribute:
-            value = cls.quoted_attribute_value(value)
-        return value
-
-    @classmethod
-    def substitute_xml_containing_entities(
-        cls, value, make_quoted_attribute=False):
-        """Substitute XML entities for special XML characters.
-
-        :param value: A string to be substituted. The less-than sign will
-          become &lt;, the greater-than sign will become &gt;, and any
-          ampersands that are not part of an entity defition will
-          become &amp;.
-
-        :param make_quoted_attribute: If True, then the string will be
-         quoted, as befits an attribute value.
-        """
-        # Escape angle brackets, and ampersands that aren't part of
-        # entities.
-        value = cls.BARE_AMPERSAND_OR_BRACKET.sub(
-            cls._substitute_xml_entity, value)
-
-        if make_quoted_attribute:
-            value = cls.quoted_attribute_value(value)
-        return value
-
-    @classmethod
-    def substitute_html(cls, s):
-        """Replace certain Unicode characters with named HTML entities.
-
-        This differs from data.encode(encoding, 'xmlcharrefreplace')
-        in that the goal is to make the result more readable (to those
-        with ASCII displays) rather than to recover from
-        errors. There's absolutely nothing wrong with a UTF-8 string
-        containg a LATIN SMALL LETTER E WITH ACUTE, but replacing that
-        character with "&eacute;" will make it more readable to some
-        people.
-        """
-        return cls.CHARACTER_TO_HTML_ENTITY_RE.sub(
-            cls._substitute_html_entity, s)
-
-
-class EncodingDetector:
-    """Suggests a number of possible encodings for a bytestring.
-
-    Order of precedence:
-
-    1. Encodings you specifically tell EncodingDetector to try first
-    (the override_encodings argument to the constructor).
-
-    2. An encoding declared within the bytestring itself, either in an
-    XML declaration (if the bytestring is to be interpreted as an XML
-    document), or in a <meta> tag (if the bytestring is to be
-    interpreted as an HTML document.)
-
-    3. An encoding detected through textual analysis by chardet,
-    cchardet, or a similar external library.
-
-    4. UTF-8.
-
-    5. Windows-1252.
-    """
-    def __init__(self, markup, override_encodings=None, is_html=False,
-                 exclude_encodings=None):
-        self.override_encodings = override_encodings or []
-        exclude_encodings = exclude_encodings or []
-        self.exclude_encodings = set([x.lower() for x in exclude_encodings])
-        self.chardet_encoding = None
-        self.is_html = is_html
-        self.declared_encoding = None
-
-        # First order of business: strip a byte-order mark.
-        self.markup, self.sniffed_encoding = self.strip_byte_order_mark(markup)
-
-    def _usable(self, encoding, tried):
-        if encoding is not None:
-            encoding = encoding.lower()
-            if encoding in self.exclude_encodings:
-                return False
-            if encoding not in tried:
-                tried.add(encoding)
-                return True
-        return False
-
-    @property
-    def encodings(self):
-        """Yield a number of encodings that might work for this markup."""
-        tried = set()
-        for e in self.override_encodings:
-            if self._usable(e, tried):
-                yield e
-
-        # Did the document originally start with a byte-order mark
-        # that indicated its encoding?
-        if self._usable(self.sniffed_encoding, tried):
-            yield self.sniffed_encoding
-
-        # Look within the document for an XML or HTML encoding
-        # declaration.
-        if self.declared_encoding is None:
-            self.declared_encoding = self.find_declared_encoding(
-                self.markup, self.is_html)
-        if self._usable(self.declared_encoding, tried):
-            yield self.declared_encoding
-
-        # Use third-party character set detection to guess at the
-        # encoding.
-        if self.chardet_encoding is None:
-            self.chardet_encoding = chardet_dammit(self.markup)
-        if self._usable(self.chardet_encoding, tried):
-            yield self.chardet_encoding
-
-        # As a last-ditch effort, try utf-8 and windows-1252.
-        for e in ('utf-8', 'windows-1252'):
-            if self._usable(e, tried):
-                yield e
-
-    @classmethod
-    def strip_byte_order_mark(cls, data):
-        """If a byte-order mark is present, strip it and return the encoding it implies."""
-        encoding = None
-        if isinstance(data, unicode):
-            # Unicode data cannot have a byte-order mark.
-            return data, encoding
-        if (len(data) >= 4) and (data[:2] == b'\xfe\xff') \
-               and (data[2:4] != '\x00\x00'):
-            encoding = 'utf-16be'
-            data = data[2:]
-        elif (len(data) >= 4) and (data[:2] == b'\xff\xfe') \
-                 and (data[2:4] != '\x00\x00'):
-            encoding = 'utf-16le'
-            data = data[2:]
-        elif data[:3] == b'\xef\xbb\xbf':
-            encoding = 'utf-8'
-            data = data[3:]
-        elif data[:4] == b'\x00\x00\xfe\xff':
-            encoding = 'utf-32be'
-            data = data[4:]
-        elif data[:4] == b'\xff\xfe\x00\x00':
-            encoding = 'utf-32le'
-            data = data[4:]
-        return data, encoding
-
-    @classmethod
-    def find_declared_encoding(cls, markup, is_html=False, search_entire_document=False):
-        """Given a document, tries to find its declared encoding.
-
-        An XML encoding is declared at the beginning of the document.
-
-        An HTML encoding is declared in a <meta> tag, hopefully near the
-        beginning of the document.
-        """
-        if search_entire_document:
-            xml_endpos = html_endpos = len(markup)
-        else:
-            xml_endpos = 1024
-            html_endpos = max(2048, int(len(markup) * 0.05))
-
-        declared_encoding = None
-        declared_encoding_match = xml_encoding_re.search(markup, endpos=xml_endpos)
-        if not declared_encoding_match and is_html:
-            declared_encoding_match = html_meta_re.search(markup, endpos=html_endpos)
-        if declared_encoding_match is not None:
-            declared_encoding = declared_encoding_match.groups()[0].decode(
-                'ascii', 'replace')
-        if declared_encoding:
-            return declared_encoding.lower()
-        return None
-
-class UnicodeDammit:
-    """A class for detecting the encoding of a *ML document and
-    converting it to a Unicode string. If the source encoding is
-    windows-1252, can replace MS smart quotes with their HTML or XML
-    equivalents."""
-
-    # This dictionary maps commonly seen values for "charset" in HTML
-    # meta tags to the corresponding Python codec names. It only covers
-    # values that aren't in Python's aliases and can't be determined
-    # by the heuristics in find_codec.
-    CHARSET_ALIASES = {"macintosh": "mac-roman",
-                       "x-sjis": "shift-jis"}
-
-    ENCODINGS_WITH_SMART_QUOTES = [
-        "windows-1252",
-        "iso-8859-1",
-        "iso-8859-2",
-        ]
-
-    def __init__(self, markup, override_encodings=[],
-                 smart_quotes_to=None, is_html=False, exclude_encodings=[]):
-        self.smart_quotes_to = smart_quotes_to
-        self.tried_encodings = []
-        self.contains_replacement_characters = False
-        self.is_html = is_html
-        self.log = logging.getLogger(__name__)
-        self.detector = EncodingDetector(
-            markup, override_encodings, is_html, exclude_encodings)
-
-        # Short-circuit if the data is in Unicode to begin with.
-        if isinstance(markup, unicode) or markup == '':
-            self.markup = markup
-            self.unicode_markup = unicode(markup)
-            self.original_encoding = None
-            return
-
-        # The encoding detector may have stripped a byte-order mark.
-        # Use the stripped markup from this point on.
-        self.markup = self.detector.markup
-
-        u = None
-        for encoding in self.detector.encodings:
-            markup = self.detector.markup
-            u = self._convert_from(encoding)
-            if u is not None:
-                break
-
-        if not u:
-            # None of the encodings worked. As an absolute last resort,
-            # try them again with character replacement.
-
-            for encoding in self.detector.encodings:
-                if encoding != "ascii":
-                    u = self._convert_from(encoding, "replace")
-                if u is not None:
-                    self.log.warning(
-                            "Some characters could not be decoded, and were "
-                            "replaced with REPLACEMENT CHARACTER."
-                    )
-                    self.contains_replacement_characters = True
-                    break
-
-        # If none of that worked, we could at this point force it to
-        # ASCII, but that would destroy so much data that I think
-        # giving up is better.
-        self.unicode_markup = u
-        if not u:
-            self.original_encoding = None
-
-    def _sub_ms_char(self, match):
-        """Changes a MS smart quote character to an XML or HTML
-        entity, or an ASCII character."""
-        orig = match.group(1)
-        if self.smart_quotes_to == 'ascii':
-            sub = self.MS_CHARS_TO_ASCII.get(orig).encode()
-        else:
-            sub = self.MS_CHARS.get(orig)
-            if type(sub) == tuple:
-                if self.smart_quotes_to == 'xml':
-                    sub = '&#x'.encode() + sub[1].encode() + ';'.encode()
-                else:
-                    sub = '&'.encode() + sub[0].encode() + ';'.encode()
-            else:
-                sub = sub.encode()
-        return sub
-
-    def _convert_from(self, proposed, errors="strict"):
-        proposed = self.find_codec(proposed)
-        if not proposed or (proposed, errors) in self.tried_encodings:
-            return None
-        self.tried_encodings.append((proposed, errors))
-        markup = self.markup
-        # Convert smart quotes to HTML if coming from an encoding
-        # that might have them.
-        if (self.smart_quotes_to is not None
-            and proposed in self.ENCODINGS_WITH_SMART_QUOTES):
-            smart_quotes_re = b"([\x80-\x9f])"
-            smart_quotes_compiled = re.compile(smart_quotes_re)
-            markup = smart_quotes_compiled.sub(self._sub_ms_char, markup)
-
-        try:
-            #print "Trying to convert document to %s (errors=%s)" % (
-            #    proposed, errors)
-            u = self._to_unicode(markup, proposed, errors)
-            self.markup = u
-            self.original_encoding = proposed
-        except Exception as e:
-            #print "That didn't work!"
-            #print e
-            return None
-        #print "Correct encoding: %s" % proposed
-        return self.markup
-
-    def _to_unicode(self, data, encoding, errors="strict"):
-        '''Given a string and its encoding, decodes the string into Unicode.
-        %encoding is a string recognized by encodings.aliases'''
-        return unicode(data, encoding, errors)
-
-    @property
-    def declared_html_encoding(self):
-        if not self.is_html:
-            return None
-        return self.detector.declared_encoding
-
-    def find_codec(self, charset):
-        value = (self._codec(self.CHARSET_ALIASES.get(charset, charset))
-               or (charset and self._codec(charset.replace("-", "")))
-               or (charset and self._codec(charset.replace("-", "_")))
-               or (charset and charset.lower())
-               or charset
-                )
-        if value:
-            return value.lower()
-        return None
-
-    def _codec(self, charset):
-        if not charset:
-            return charset
-        codec = None
-        try:
-            codecs.lookup(charset)
-            codec = charset
-        except (LookupError, ValueError):
-            pass
-        return codec
-
-
-    # A partial mapping of ISO-Latin-1 to HTML entities/XML numeric entities.
-    MS_CHARS = {b'\x80': ('euro', '20AC'),
-                b'\x81': ' ',
-                b'\x82': ('sbquo', '201A'),
-                b'\x83': ('fnof', '192'),
-                b'\x84': ('bdquo', '201E'),
-                b'\x85': ('hellip', '2026'),
-                b'\x86': ('dagger', '2020'),
-                b'\x87': ('Dagger', '2021'),
-                b'\x88': ('circ', '2C6'),
-                b'\x89': ('permil', '2030'),
-                b'\x8A': ('Scaron', '160'),
-                b'\x8B': ('lsaquo', '2039'),
-                b'\x8C': ('OElig', '152'),
-                b'\x8D': '?',
-                b'\x8E': ('#x17D', '17D'),
-                b'\x8F': '?',
-                b'\x90': '?',
-                b'\x91': ('lsquo', '2018'),
-                b'\x92': ('rsquo', '2019'),
-                b'\x93': ('ldquo', '201C'),
-                b'\x94': ('rdquo', '201D'),
-                b'\x95': ('bull', '2022'),
-                b'\x96': ('ndash', '2013'),
-                b'\x97': ('mdash', '2014'),
-                b'\x98': ('tilde', '2DC'),
-                b'\x99': ('trade', '2122'),
-                b'\x9a': ('scaron', '161'),
-                b'\x9b': ('rsaquo', '203A'),
-                b'\x9c': ('oelig', '153'),
-                b'\x9d': '?',
-                b'\x9e': ('#x17E', '17E'),
-                b'\x9f': ('Yuml', ''),}
-
-    # A parochial partial mapping of ISO-Latin-1 to ASCII. Contains
-    # horrors like stripping diacritical marks to turn á into a, but also
-    # contains non-horrors like turning “ into ".
-    MS_CHARS_TO_ASCII = {
-        b'\x80' : 'EUR',
-        b'\x81' : ' ',
-        b'\x82' : ',',
-        b'\x83' : 'f',
-        b'\x84' : ',,',
-        b'\x85' : '...',
-        b'\x86' : '+',
-        b'\x87' : '++',
-        b'\x88' : '^',
-        b'\x89' : '%',
-        b'\x8a' : 'S',
-        b'\x8b' : '<',
-        b'\x8c' : 'OE',
-        b'\x8d' : '?',
-        b'\x8e' : 'Z',
-        b'\x8f' : '?',
-        b'\x90' : '?',
-        b'\x91' : "'",
-        b'\x92' : "'",
-        b'\x93' : '"',
-        b'\x94' : '"',
-        b'\x95' : '*',
-        b'\x96' : '-',
-        b'\x97' : '--',
-        b'\x98' : '~',
-        b'\x99' : '(TM)',
-        b'\x9a' : 's',
-        b'\x9b' : '>',
-        b'\x9c' : 'oe',
-        b'\x9d' : '?',
-        b'\x9e' : 'z',
-        b'\x9f' : 'Y',
-        b'\xa0' : ' ',
-        b'\xa1' : '!',
-        b'\xa2' : 'c',
-        b'\xa3' : 'GBP',
-        b'\xa4' : '$', #This approximation is especially parochial--this is the
-                       #generic currency symbol.
-        b'\xa5' : 'YEN',
-        b'\xa6' : '|',
-        b'\xa7' : 'S',
-        b'\xa8' : '..',
-        b'\xa9' : '',
-        b'\xaa' : '(th)',
-        b'\xab' : '<<',
-        b'\xac' : '!',
-        b'\xad' : ' ',
-        b'\xae' : '(R)',
-        b'\xaf' : '-',
-        b'\xb0' : 'o',
-        b'\xb1' : '+-',
-        b'\xb2' : '2',
-        b'\xb3' : '3',
-        b'\xb4' : ("'", 'acute'),
-        b'\xb5' : 'u',
-        b'\xb6' : 'P',
-        b'\xb7' : '*',
-        b'\xb8' : ',',
-        b'\xb9' : '1',
-        b'\xba' : '(th)',
-        b'\xbb' : '>>',
-        b'\xbc' : '1/4',
-        b'\xbd' : '1/2',
-        b'\xbe' : '3/4',
-        b'\xbf' : '?',
-        b'\xc0' : 'A',
-        b'\xc1' : 'A',
-        b'\xc2' : 'A',
-        b'\xc3' : 'A',
-        b'\xc4' : 'A',
-        b'\xc5' : 'A',
-        b'\xc6' : 'AE',
-        b'\xc7' : 'C',
-        b'\xc8' : 'E',
-        b'\xc9' : 'E',
-        b'\xca' : 'E',
-        b'\xcb' : 'E',
-        b'\xcc' : 'I',
-        b'\xcd' : 'I',
-        b'\xce' : 'I',
-        b'\xcf' : 'I',
-        b'\xd0' : 'D',
-        b'\xd1' : 'N',
-        b'\xd2' : 'O',
-        b'\xd3' : 'O',
-        b'\xd4' : 'O',
-        b'\xd5' : 'O',
-        b'\xd6' : 'O',
-        b'\xd7' : '*',
-        b'\xd8' : 'O',
-        b'\xd9' : 'U',
-        b'\xda' : 'U',
-        b'\xdb' : 'U',
-        b'\xdc' : 'U',
-        b'\xdd' : 'Y',
-        b'\xde' : 'b',
-        b'\xdf' : 'B',
-        b'\xe0' : 'a',
-        b'\xe1' : 'a',
-        b'\xe2' : 'a',
-        b'\xe3' : 'a',
-        b'\xe4' : 'a',
-        b'\xe5' : 'a',
-        b'\xe6' : 'ae',
-        b'\xe7' : 'c',
-        b'\xe8' : 'e',
-        b'\xe9' : 'e',
-        b'\xea' : 'e',
-        b'\xeb' : 'e',
-        b'\xec' : 'i',
-        b'\xed' : 'i',
-        b'\xee' : 'i',
-        b'\xef' : 'i',
-        b'\xf0' : 'o',
-        b'\xf1' : 'n',
-        b'\xf2' : 'o',
-        b'\xf3' : 'o',
-        b'\xf4' : 'o',
-        b'\xf5' : 'o',
-        b'\xf6' : 'o',
-        b'\xf7' : '/',
-        b'\xf8' : 'o',
-        b'\xf9' : 'u',
-        b'\xfa' : 'u',
-        b'\xfb' : 'u',
-        b'\xfc' : 'u',
-        b'\xfd' : 'y',
-        b'\xfe' : 'b',
-        b'\xff' : 'y',
-        }
-
-    # A map used when removing rogue Windows-1252/ISO-8859-1
-    # characters in otherwise UTF-8 documents.
-    #
-    # Note that \x81, \x8d, \x8f, \x90, and \x9d are undefined in
-    # Windows-1252.
-    WINDOWS_1252_TO_UTF8 = {
-        0x80 : b'\xe2\x82\xac', # €
-        0x82 : b'\xe2\x80\x9a', # ‚
-        0x83 : b'\xc6\x92',     # ƒ
-        0x84 : b'\xe2\x80\x9e', # „
-        0x85 : b'\xe2\x80\xa6', # …
-        0x86 : b'\xe2\x80\xa0', # †
-        0x87 : b'\xe2\x80\xa1', # ‡
-        0x88 : b'\xcb\x86',     # ˆ
-        0x89 : b'\xe2\x80\xb0', # ‰
-        0x8a : b'\xc5\xa0',     # Š
-        0x8b : b'\xe2\x80\xb9', # ‹
-        0x8c : b'\xc5\x92',     # Œ
-        0x8e : b'\xc5\xbd',     # Ž
-        0x91 : b'\xe2\x80\x98', # ‘
-        0x92 : b'\xe2\x80\x99', # ’
-        0x93 : b'\xe2\x80\x9c', # “
-        0x94 : b'\xe2\x80\x9d', # ”
-        0x95 : b'\xe2\x80\xa2', # •
-        0x96 : b'\xe2\x80\x93', # –
-        0x97 : b'\xe2\x80\x94', # —
-        0x98 : b'\xcb\x9c',     # ˜
-        0x99 : b'\xe2\x84\xa2', # ™
-        0x9a : b'\xc5\xa1',     # š
-        0x9b : b'\xe2\x80\xba', # ›
-        0x9c : b'\xc5\x93',     # œ
-        0x9e : b'\xc5\xbe',     # ž
-        0x9f : b'\xc5\xb8',     # Ÿ
-        0xa0 : b'\xc2\xa0',     #  
-        0xa1 : b'\xc2\xa1',     # ¡
-        0xa2 : b'\xc2\xa2',     # ¢
-        0xa3 : b'\xc2\xa3',     # £
-        0xa4 : b'\xc2\xa4',     # ¤
-        0xa5 : b'\xc2\xa5',     # ¥
-        0xa6 : b'\xc2\xa6',     # ¦
-        0xa7 : b'\xc2\xa7',     # §
-        0xa8 : b'\xc2\xa8',     # ¨
-        0xa9 : b'\xc2\xa9',     # ©
-        0xaa : b'\xc2\xaa',     # ª
-        0xab : b'\xc2\xab',     # «
-        0xac : b'\xc2\xac',     # ¬
-        0xad : b'\xc2\xad',     # ­
-        0xae : b'\xc2\xae',     # ®
-        0xaf : b'\xc2\xaf',     # ¯
-        0xb0 : b'\xc2\xb0',     # °
-        0xb1 : b'\xc2\xb1',     # ±
-        0xb2 : b'\xc2\xb2',     # ²
-        0xb3 : b'\xc2\xb3',     # ³
-        0xb4 : b'\xc2\xb4',     # ´
-        0xb5 : b'\xc2\xb5',     # µ
-        0xb6 : b'\xc2\xb6',     # ¶
-        0xb7 : b'\xc2\xb7',     # ·
-        0xb8 : b'\xc2\xb8',     # ¸
-        0xb9 : b'\xc2\xb9',     # ¹
-        0xba : b'\xc2\xba',     # º
-        0xbb : b'\xc2\xbb',     # »
-        0xbc : b'\xc2\xbc',     # ¼
-        0xbd : b'\xc2\xbd',     # ½
-        0xbe : b'\xc2\xbe',     # ¾
-        0xbf : b'\xc2\xbf',     # ¿
-        0xc0 : b'\xc3\x80',     # À
-        0xc1 : b'\xc3\x81',     # Á
-        0xc2 : b'\xc3\x82',     # Â
-        0xc3 : b'\xc3\x83',     # Ã
-        0xc4 : b'\xc3\x84',     # Ä
-        0xc5 : b'\xc3\x85',     # Å
-        0xc6 : b'\xc3\x86',     # Æ
-        0xc7 : b'\xc3\x87',     # Ç
-        0xc8 : b'\xc3\x88',     # È
-        0xc9 : b'\xc3\x89',     # É
-        0xca : b'\xc3\x8a',     # Ê
-        0xcb : b'\xc3\x8b',     # Ë
-        0xcc : b'\xc3\x8c',     # Ì
-        0xcd : b'\xc3\x8d',     # Í
-        0xce : b'\xc3\x8e',     # Î
-        0xcf : b'\xc3\x8f',     # Ï
-        0xd0 : b'\xc3\x90',     # Ð
-        0xd1 : b'\xc3\x91',     # Ñ
-        0xd2 : b'\xc3\x92',     # Ò
-        0xd3 : b'\xc3\x93',     # Ó
-        0xd4 : b'\xc3\x94',     # Ô
-        0xd5 : b'\xc3\x95',     # Õ
-        0xd6 : b'\xc3\x96',     # Ö
-        0xd7 : b'\xc3\x97',     # ×
-        0xd8 : b'\xc3\x98',     # Ø
-        0xd9 : b'\xc3\x99',     # Ù
-        0xda : b'\xc3\x9a',     # Ú
-        0xdb : b'\xc3\x9b',     # Û
-        0xdc : b'\xc3\x9c',     # Ü
-        0xdd : b'\xc3\x9d',     # Ý
-        0xde : b'\xc3\x9e',     # Þ
-        0xdf : b'\xc3\x9f',     # ß
-        0xe0 : b'\xc3\xa0',     # à
-        0xe1 : b'\xa1',         # á
-        0xe2 : b'\xc3\xa2',     # â
-        0xe3 : b'\xc3\xa3',     # ã
-        0xe4 : b'\xc3\xa4',     # ä
-        0xe5 : b'\xc3\xa5',     # å
-        0xe6 : b'\xc3\xa6',     # æ
-        0xe7 : b'\xc3\xa7',     # ç
-        0xe8 : b'\xc3\xa8',     # è
-        0xe9 : b'\xc3\xa9',     # é
-        0xea : b'\xc3\xaa',     # ê
-        0xeb : b'\xc3\xab',     # ë
-        0xec : b'\xc3\xac',     # ì
-        0xed : b'\xc3\xad',     # í
-        0xee : b'\xc3\xae',     # î
-        0xef : b'\xc3\xaf',     # ï
-        0xf0 : b'\xc3\xb0',     # ð
-        0xf1 : b'\xc3\xb1',     # ñ
-        0xf2 : b'\xc3\xb2',     # ò
-        0xf3 : b'\xc3\xb3',     # ó
-        0xf4 : b'\xc3\xb4',     # ô
-        0xf5 : b'\xc3\xb5',     # õ
-        0xf6 : b'\xc3\xb6',     # ö
-        0xf7 : b'\xc3\xb7',     # ÷
-        0xf8 : b'\xc3\xb8',     # ø
-        0xf9 : b'\xc3\xb9',     # ù
-        0xfa : b'\xc3\xba',     # ú
-        0xfb : b'\xc3\xbb',     # û
-        0xfc : b'\xc3\xbc',     # ü
-        0xfd : b'\xc3\xbd',     # ý
-        0xfe : b'\xc3\xbe',     # þ
-        }
-
-    MULTIBYTE_MARKERS_AND_SIZES = [
-        (0xc2, 0xdf, 2), # 2-byte characters start with a byte C2-DF
-        (0xe0, 0xef, 3), # 3-byte characters start with E0-EF
-        (0xf0, 0xf4, 4), # 4-byte characters start with F0-F4
-        ]
-
-    FIRST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[0][0]
-    LAST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[-1][1]
-
-    @classmethod
-    def detwingle(cls, in_bytes, main_encoding="utf8",
-                  embedded_encoding="windows-1252"):
-        """Fix characters from one encoding embedded in some other encoding.
-
-        Currently the only situation supported is Windows-1252 (or its
-        subset ISO-8859-1), embedded in UTF-8.
-
-        The input must be a bytestring. If you've already converted
-        the document to Unicode, you're too late.
-
-        The output is a bytestring in which `embedded_encoding`
-        characters have been converted to their `main_encoding`
-        equivalents.
-        """
-        if embedded_encoding.replace('_', '-').lower() not in (
-            'windows-1252', 'windows_1252'):
-            raise NotImplementedError(
-                "Windows-1252 and ISO-8859-1 are the only currently supported "
-                "embedded encodings.")
-
-        if main_encoding.lower() not in ('utf8', 'utf-8'):
-            raise NotImplementedError(
-                "UTF-8 is the only currently supported main encoding.")
-
-        byte_chunks = []
-
-        chunk_start = 0
-        pos = 0
-        while pos < len(in_bytes):
-            byte = in_bytes[pos]
-            if not isinstance(byte, int):
-                # Python 2.x
-                byte = ord(byte)
-            if (byte >= cls.FIRST_MULTIBYTE_MARKER
-                and byte <= cls.LAST_MULTIBYTE_MARKER):
-                # This is the start of a UTF-8 multibyte character. Skip
-                # to the end.
-                for start, end, size in cls.MULTIBYTE_MARKERS_AND_SIZES:
-                    if byte >= start and byte <= end:
-                        pos += size
-                        break
-            elif byte >= 0x80 and byte in cls.WINDOWS_1252_TO_UTF8:
-                # We found a Windows-1252 character!
-                # Save the string up to this point as a chunk.
-                byte_chunks.append(in_bytes[chunk_start:pos])
-
-                # Now translate the Windows-1252 character into UTF-8
-                # and add it as another, one-byte chunk.
-                byte_chunks.append(cls.WINDOWS_1252_TO_UTF8[byte])
-                pos += 1
-                chunk_start = pos
-            else:
-                # Go on to the next character.
-                pos += 1
-        if chunk_start == 0:
-            # The string is unchanged.
-            return in_bytes
-        else:
-            # Store the final chunk.
-            byte_chunks.append(in_bytes[chunk_start:])
-        return b''.join(byte_chunks)
-

libs/py2/bs4/diagnose.py

@@ -1,225 +0,0 @@
-"""Diagnostic functions, mainly for use when doing tech support."""
-
-# Use of this source code is governed by a BSD-style license that can be
-# found in the LICENSE file.
-__license__ = "MIT"
-
-import cProfile
-from StringIO import StringIO
-from HTMLParser import HTMLParser
-import bs4
-from bs4 import BeautifulSoup, __version__
-from bs4.builder import builder_registry
-
-import os
-import pstats
-import random
-import tempfile
-import time
-import traceback
-import sys
-import cProfile
-
-def diagnose(data):
-    """Diagnostic suite for isolating common problems."""
-    print "Diagnostic running on Beautiful Soup %s" % __version__
-    print "Python version %s" % sys.version
-
-    basic_parsers = ["html.parser", "html5lib", "lxml"]
-    for name in basic_parsers:
-        for builder in builder_registry.builders:
-            if name in builder.features:
-                break
-        else:
-            basic_parsers.remove(name)
-            print (
-                "I noticed that %s is not installed. Installing it may help." %
-                name)
-
-    if 'lxml' in basic_parsers:
-        basic_parsers.append("lxml-xml")
-        try:
-            from lxml import etree
-            print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))
-        except ImportError, e:
-            print (
-                "lxml is not installed or couldn't be imported.")
-
-
-    if 'html5lib' in basic_parsers:
-        try:
-            import html5lib
-            print "Found html5lib version %s" % html5lib.__version__
-        except ImportError, e:
-            print (
-                "html5lib is not installed or couldn't be imported.")
-
-    if hasattr(data, 'read'):
-        data = data.read()
-    elif data.startswith("http:") or data.startswith("https:"):
-        print '"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data
-        print "You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup."
-        return
-    else:
-        try:
-            if os.path.exists(data):
-                print '"%s" looks like a filename. Reading data from the file.' % data
-                with open(data) as fp:
-                    data = fp.read()
-        except ValueError:
-            # This can happen on some platforms when the 'filename' is
-            # too long. Assume it's data and not a filename.
-            pass
-        print
-
-    for parser in basic_parsers:
-        print "Trying to parse your markup with %s" % parser
-        success = False
-        try:
-            soup = BeautifulSoup(data, features=parser)
-            success = True
-        except Exception, e:
-            print "%s could not parse the markup." % parser
-            traceback.print_exc()
-        if success:
-            print "Here's what %s did with the markup:" % parser
-            print soup.prettify()
-
-        print "-" * 80
-
-def lxml_trace(data, html=True, **kwargs):
-    """Print out the lxml events that occur during parsing.
-
-    This lets you see how lxml parses a document when no Beautiful
-    Soup code is running.
-    """
-    from lxml import etree
-    for event, element in etree.iterparse(StringIO(data), html=html, **kwargs):
-        print("%s, %4s, %s" % (event, element.tag, element.text))
-
-class AnnouncingParser(HTMLParser):
-    """Announces HTMLParser parse events, without doing anything else."""
-
-    def _p(self, s):
-        print(s)
-
-    def handle_starttag(self, name, attrs):
-        self._p("%s START" % name)
-
-    def handle_endtag(self, name):
-        self._p("%s END" % name)
-
-    def handle_data(self, data):
-        self._p("%s DATA" % data)
-
-    def handle_charref(self, name):
-        self._p("%s CHARREF" % name)
-
-    def handle_entityref(self, name):
-        self._p("%s ENTITYREF" % name)
-
-    def handle_comment(self, data):
-        self._p("%s COMMENT" % data)
-
-    def handle_decl(self, data):
-        self._p("%s DECL" % data)
-
-    def unknown_decl(self, data):
-        self._p("%s UNKNOWN-DECL" % data)
-
-    def handle_pi(self, data):
-        self._p("%s PI" % data)
-
-def htmlparser_trace(data):
-    """Print out the HTMLParser events that occur during parsing.
-
-    This lets you see how HTMLParser parses a document when no
-    Beautiful Soup code is running.
-    """
-    parser = AnnouncingParser()
-    parser.feed(data)
-
-_vowels = "aeiou"
-_consonants = "bcdfghjklmnpqrstvwxyz"
-
-def rword(length=5):
-    "Generate a random word-like string."
-    s = ''
-    for i in range(length):
-        if i % 2 == 0:
-            t = _consonants
-        else:
-            t = _vowels
-        s += random.choice(t)
-    return s
-
-def rsentence(length=4):
-    "Generate a random sentence-like string."
-    return " ".join(rword(random.randint(4,9)) for i in range(length))
-        
-def rdoc(num_elements=1000):
-    """Randomly generate an invalid HTML document."""
-    tag_names = ['p', 'div', 'span', 'i', 'b', 'script', 'table']
-    elements = []
-    for i in range(num_elements):
-        choice = random.randint(0,3)
-        if choice == 0:
-            # New tag.
-            tag_name = random.choice(tag_names)
-            elements.append("<%s>" % tag_name)
-        elif choice == 1:
-            elements.append(rsentence(random.randint(1,4)))
-        elif choice == 2:
-            # Close a tag.
-            tag_name = random.choice(tag_names)
-            elements.append("</%s>" % tag_name)
-    return "<html>" + "\n".join(elements) + "</html>"
-
-def benchmark_parsers(num_elements=100000):
-    """Very basic head-to-head performance benchmark."""
-    print "Comparative parser benchmark on Beautiful Soup %s" % __version__
-    data = rdoc(num_elements)
-    print "Generated a large invalid HTML document (%d bytes)." % len(data)
-    
-    for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
-        success = False
-        try:
-            a = time.time()
-            soup = BeautifulSoup(data, parser)
-            b = time.time()
-            success = True
-        except Exception, e:
-            print "%s could not parse the markup." % parser
-            traceback.print_exc()
-        if success:
-            print "BS4+%s parsed the markup in %.2fs." % (parser, b-a)
-
-    from lxml import etree
-    a = time.time()
-    etree.HTML(data)
-    b = time.time()
-    print "Raw lxml parsed the markup in %.2fs." % (b-a)
-
-    import html5lib
-    parser = html5lib.HTMLParser()
-    a = time.time()
-    parser.parse(data)
-    b = time.time()
-    print "Raw html5lib parsed the markup in %.2fs." % (b-a)
-
-def profile(num_elements=100000, parser="lxml"):
-
-    filehandle = tempfile.NamedTemporaryFile()
-    filename = filehandle.name
-
-    data = rdoc(num_elements)
-    vars = dict(bs4=bs4, data=data, parser=parser)
-    cProfile.runctx('bs4.BeautifulSoup(data, parser)' , vars, vars, filename)
-
-    stats = pstats.Stats(filename)
-    # stats.strip_dirs()
-    stats.sort_stats("cumulative")
-    stats.print_stats('_html5lib|bs4', 50)
-
-if __name__ == '__main__':
-    diagnose(sys.stdin.read())

libs/py2/bs4/testing.py

@@ -1,810 +0,0 @@
-# encoding: utf-8
-"""Helper classes for tests."""
-
-# Use of this source code is governed by a BSD-style license that can be
-# found in the LICENSE file.
-__license__ = "MIT"
-
-import pickle
-import copy
-import functools
-import unittest
-from unittest import TestCase
-from bs4 import BeautifulSoup
-from bs4.element import (
-    CharsetMetaAttributeValue,
-    Comment,
-    ContentMetaAttributeValue,
-    Doctype,
-    SoupStrainer,
-)
-
-from bs4.builder import HTMLParserTreeBuilder
-default_builder = HTMLParserTreeBuilder
-
-
-class SoupTest(unittest.TestCase):
-
-    @property
-    def default_builder(self):
-        return default_builder()
-
-    def soup(self, markup, **kwargs):
-        """Build a Beautiful Soup object from markup."""
-        builder = kwargs.pop('builder', self.default_builder)
-        return BeautifulSoup(markup, builder=builder, **kwargs)
-
-    def document_for(self, markup):
-        """Turn an HTML fragment into a document.
-
-        The details depend on the builder.
-        """
-        return self.default_builder.test_fragment_to_document(markup)
-
-    def assertSoupEquals(self, to_parse, compare_parsed_to=None):
-        builder = self.default_builder
-        obj = BeautifulSoup(to_parse, builder=builder)
-        if compare_parsed_to is None:
-            compare_parsed_to = to_parse
-
-        self.assertEqual(obj.decode(), self.document_for(compare_parsed_to))
-
-    def assertConnectedness(self, element):
-        """Ensure that next_element and previous_element are properly
-        set for all descendants of the given element.
-        """
-        earlier = None
-        for e in element.descendants:
-            if earlier:
-                self.assertEqual(e, earlier.next_element)
-                self.assertEqual(earlier, e.previous_element)
-            earlier = e
-
-class HTMLTreeBuilderSmokeTest(object):
-
-    """A basic test of a treebuilder's competence.
-
-    Any HTML treebuilder, present or future, should be able to pass
-    these tests. With invalid markup, there's room for interpretation,
-    and different parsers can handle it differently. But with the
-    markup in these tests, there's not much room for interpretation.
-    """
-
-    def test_empty_element_tags(self):
-        """Verify that all HTML4 and HTML5 empty element (aka void element) tags
-        are handled correctly.
-        """
-        for name in [
-                'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
-                'spacer', 'frame'
-        ]:
-            soup = self.soup("")
-            new_tag = soup.new_tag(name)
-            self.assertEqual(True, new_tag.is_empty_element)
-    
-    def test_pickle_and_unpickle_identity(self):
-        # Pickling a tree, then unpickling it, yields a tree identical
-        # to the original.
-        tree = self.soup("<a><b>foo</a>")
-        dumped = pickle.dumps(tree, 2)
-        loaded = pickle.loads(dumped)
-        self.assertEqual(loaded.__class__, BeautifulSoup)
-        self.assertEqual(loaded.decode(), tree.decode())
-
-    def assertDoctypeHandled(self, doctype_fragment):
-        """Assert that a given doctype string is handled correctly."""
-        doctype_str, soup = self._document_with_doctype(doctype_fragment)
-
-        # Make sure a Doctype object was created.
-        doctype = soup.contents[0]
-        self.assertEqual(doctype.__class__, Doctype)
-        self.assertEqual(doctype, doctype_fragment)
-        self.assertEqual(str(soup)[:len(doctype_str)], doctype_str)
-
-        # Make sure that the doctype was correctly associated with the
-        # parse tree and that the rest of the document parsed.
-        self.assertEqual(soup.p.contents[0], 'foo')
-
-    def _document_with_doctype(self, doctype_fragment):
-        """Generate and parse a document with the given doctype."""
-        doctype = '<!DOCTYPE %s>' % doctype_fragment
-        markup = doctype + '\n<p>foo</p>'
-        soup = self.soup(markup)
-        return doctype, soup
-
-    def test_normal_doctypes(self):
-        """Make sure normal, everyday HTML doctypes are handled correctly."""
-        self.assertDoctypeHandled("html")
-        self.assertDoctypeHandled(
-            'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"')
-
-    def test_empty_doctype(self):
-        soup = self.soup("<!DOCTYPE>")
-        doctype = soup.contents[0]
-        self.assertEqual("", doctype.strip())
-
-    def test_public_doctype_with_url(self):
-        doctype = 'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"'
-        self.assertDoctypeHandled(doctype)
-
-    def test_system_doctype(self):
-        self.assertDoctypeHandled('foo SYSTEM "http://www.example.com/"')
-
-    def test_namespaced_system_doctype(self):
-        # We can handle a namespaced doctype with a system ID.
-        self.assertDoctypeHandled('xsl:stylesheet SYSTEM "htmlent.dtd"')
-
-    def test_namespaced_public_doctype(self):
-        # Test a namespaced doctype with a public id.
-        self.assertDoctypeHandled('xsl:stylesheet PUBLIC "htmlent.dtd"')
-
-    def test_real_xhtml_document(self):
-        """A real XHTML document should come out more or less the same as it went in."""
-        markup = b"""<?xml version="1.0" encoding="utf-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
-<html xmlns="http://www.w3.org/1999/xhtml">
-<head><title>Hello.</title></head>
-<body>Goodbye.</body>
-</html>"""
-        soup = self.soup(markup)
-        self.assertEqual(
-            soup.encode("utf-8").replace(b"\n", b""),
-            markup.replace(b"\n", b""))
-
-    def test_namespaced_html(self):
-        """When a namespaced XML document is parsed as HTML it should
-        be treated as HTML with weird tag names.
-        """
-        markup = b"""<ns1:foo>content</ns1:foo><ns1:foo/><ns2:foo/>"""
-        soup = self.soup(markup)
-        self.assertEqual(2, len(soup.find_all("ns1:foo")))
-        
-    def test_processing_instruction(self):
-        # We test both Unicode and bytestring to verify that
-        # process_markup correctly sets processing_instruction_class
-        # even when the markup is already Unicode and there is no
-        # need to process anything.
-        markup = u"""<?PITarget PIContent?>"""
-        soup = self.soup(markup)
-        self.assertEqual(markup, soup.decode())
-
-        markup = b"""<?PITarget PIContent?>"""
-        soup = self.soup(markup)
-        self.assertEqual(markup, soup.encode("utf8"))
-
-    def test_deepcopy(self):
-        """Make sure you can copy the tree builder.
-
-        This is important because the builder is part of a
-        BeautifulSoup object, and we want to be able to copy that.
-        """
-        copy.deepcopy(self.default_builder)
-
-    def test_p_tag_is_never_empty_element(self):
-        """A <p> tag is never designated as an empty-element tag.
-
-        Even if the markup shows it as an empty-element tag, it
-        shouldn't be presented that way.
-        """
-        soup = self.soup("<p/>")
-        self.assertFalse(soup.p.is_empty_element)
-        self.assertEqual(str(soup.p), "<p></p>")
-
-    def test_unclosed_tags_get_closed(self):
-        """A tag that's not closed by the end of the document should be closed.
-
-        This applies to all tags except empty-element tags.
-        """
-        self.assertSoupEquals("<p>", "<p></p>")
-        self.assertSoupEquals("<b>", "<b></b>")
-
-        self.assertSoupEquals("<br>", "<br/>")
-
-    def test_br_is_always_empty_element_tag(self):
-        """A <br> tag is designated as an empty-element tag.
-
-        Some parsers treat <br></br> as one <br/> tag, some parsers as
-        two tags, but it should always be an empty-element tag.
-        """
-        soup = self.soup("<br></br>")
-        self.assertTrue(soup.br.is_empty_element)
-        self.assertEqual(str(soup.br), "<br/>")
-
-    def test_nested_formatting_elements(self):
-        self.assertSoupEquals("<em><em></em></em>")
-
-    def test_double_head(self):
-        html = '''<!DOCTYPE html>
-<html>
-<head>
-<title>Ordinary HEAD element test</title>
-</head>
-<script type="text/javascript">
-alert("Help!");
-</script>
-<body>
-Hello, world!
-</body>
-</html>
-'''
-        soup = self.soup(html)
-        self.assertEqual("text/javascript", soup.find('script')['type'])
-
-    def test_comment(self):
-        # Comments are represented as Comment objects.
-        markup = "<p>foo<!--foobar-->baz</p>"
-        self.assertSoupEquals(markup)
-
-        soup = self.soup(markup)
-        comment = soup.find(text="foobar")
-        self.assertEqual(comment.__class__, Comment)
-
-        # The comment is properly integrated into the tree.
-        foo = soup.find(text="foo")
-        self.assertEqual(comment, foo.next_element)
-        baz = soup.find(text="baz")
-        self.assertEqual(comment, baz.previous_element)
-
-    def test_preserved_whitespace_in_pre_and_textarea(self):
-        """Whitespace must be preserved in <pre> and <textarea> tags,
-        even if that would mean not prettifying the markup.
-        """
-        pre_markup = "<pre>   </pre>"
-        textarea_markup = "<textarea> woo\nwoo  </textarea>"
-        self.assertSoupEquals(pre_markup)
-        self.assertSoupEquals(textarea_markup)
-
-        soup = self.soup(pre_markup)
-        self.assertEqual(soup.pre.prettify(), pre_markup)
-
-        soup = self.soup(textarea_markup)
-        self.assertEqual(soup.textarea.prettify(), textarea_markup)
-
-        soup = self.soup("<textarea></textarea>")
-        self.assertEqual(soup.textarea.prettify(), "<textarea></textarea>")
-
-    def test_nested_inline_elements(self):
-        """Inline elements can be nested indefinitely."""
-        b_tag = "<b>Inside a B tag</b>"
-        self.assertSoupEquals(b_tag)
-
-        nested_b_tag = "<p>A <i>nested <b>tag</b></i></p>"
-        self.assertSoupEquals(nested_b_tag)
-
-        double_nested_b_tag = "<p>A <a>doubly <i>nested <b>tag</b></i></a></p>"
-        self.assertSoupEquals(nested_b_tag)
-
-    def test_nested_block_level_elements(self):
-        """Block elements can be nested."""
-        soup = self.soup('<blockquote><p><b>Foo</b></p></blockquote>')
-        blockquote = soup.blockquote
-        self.assertEqual(blockquote.p.b.string, 'Foo')
-        self.assertEqual(blockquote.b.string, 'Foo')
-
-    def test_correctly_nested_tables(self):
-        """One table can go inside another one."""
-        markup = ('<table id="1">'
-                  '<tr>'
-                  "<td>Here's another table:"
-                  '<table id="2">'
-                  '<tr><td>foo</td></tr>'
-                  '</table></td>')
-
-        self.assertSoupEquals(
-            markup,
-            '<table id="1"><tr><td>Here\'s another table:'
-            '<table id="2"><tr><td>foo</td></tr></table>'
-            '</td></tr></table>')
-
-        self.assertSoupEquals(
-            "<table><thead><tr><td>Foo</td></tr></thead>"
-            "<tbody><tr><td>Bar</td></tr></tbody>"
-            "<tfoot><tr><td>Baz</td></tr></tfoot></table>")
-
-    def test_deeply_nested_multivalued_attribute(self):
-        # html5lib can set the attributes of the same tag many times
-        # as it rearranges the tree. This has caused problems with
-        # multivalued attributes.
-        markup = '<table><div><div class="css"></div></div></table>'
-        soup = self.soup(markup)
-        self.assertEqual(["css"], soup.div.div['class'])
-
-    def test_multivalued_attribute_on_html(self):
-        # html5lib uses a different API to set the attributes ot the
-        # <html> tag. This has caused problems with multivalued
-        # attributes.
-        markup = '<html class="a b"></html>'
-        soup = self.soup(markup)
-        self.assertEqual(["a", "b"], soup.html['class'])
-
-    def test_angle_brackets_in_attribute_values_are_escaped(self):
-        self.assertSoupEquals('<a b="<a>"></a>', '<a b="&lt;a&gt;"></a>')
-
-    def test_strings_resembling_character_entity_references(self):
-        # "&T" and "&p" look like incomplete character entities, but they are
-        # not.
-        self.assertSoupEquals(
-            u"<p>&bull; AT&T is in the s&p 500</p>",
-            u"<p>\u2022 AT&amp;T is in the s&amp;p 500</p>"
-        )
-
-    def test_entities_in_foreign_document_encoding(self):
-        # &#147; and &#148; are invalid numeric entities referencing
-        # Windows-1252 characters. &#45; references a character common
-        # to Windows-1252 and Unicode, and &#9731; references a
-        # character only found in Unicode.
-        #
-        # All of these entities should be converted to Unicode
-        # characters.
-        markup = "<p>&#147;Hello&#148; &#45;&#9731;</p>"
-        soup = self.soup(markup)
-        self.assertEquals(u"“Hello” -☃", soup.p.string)
-        
-    def test_entities_in_attributes_converted_to_unicode(self):
-        expect = u'<p id="pi\N{LATIN SMALL LETTER N WITH TILDE}ata"></p>'
-        self.assertSoupEquals('<p id="pi&#241;ata"></p>', expect)
-        self.assertSoupEquals('<p id="pi&#xf1;ata"></p>', expect)
-        self.assertSoupEquals('<p id="pi&#Xf1;ata"></p>', expect)
-        self.assertSoupEquals('<p id="pi&ntilde;ata"></p>', expect)
-
-    def test_entities_in_text_converted_to_unicode(self):
-        expect = u'<p>pi\N{LATIN SMALL LETTER N WITH TILDE}ata</p>'
-        self.assertSoupEquals("<p>pi&#241;ata</p>", expect)
-        self.assertSoupEquals("<p>pi&#xf1;ata</p>", expect)
-        self.assertSoupEquals("<p>pi&#Xf1;ata</p>", expect)
-        self.assertSoupEquals("<p>pi&ntilde;ata</p>", expect)
-
-    def test_quot_entity_converted_to_quotation_mark(self):
-        self.assertSoupEquals("<p>I said &quot;good day!&quot;</p>",
-                              '<p>I said "good day!"</p>')
-
-    def test_out_of_range_entity(self):
-        expect = u"\N{REPLACEMENT CHARACTER}"
-        self.assertSoupEquals("&#10000000000000;", expect)
-        self.assertSoupEquals("&#x10000000000000;", expect)
-        self.assertSoupEquals("&#1000000000;", expect)
-        
-    def test_multipart_strings(self):
-        "Mostly to prevent a recurrence of a bug in the html5lib treebuilder."
-        soup = self.soup("<html><h2>\nfoo</h2><p></p></html>")
-        self.assertEqual("p", soup.h2.string.next_element.name)
-        self.assertEqual("p", soup.p.name)
-        self.assertConnectedness(soup)
-
-    def test_empty_element_tags(self):
-        """Verify consistent handling of empty-element tags,
-        no matter how they come in through the markup.
-        """
-        self.assertSoupEquals('<br/><br/><br/>', "<br/><br/><br/>")
-        self.assertSoupEquals('<br /><br /><br />', "<br/><br/><br/>")
-        
-    def test_head_tag_between_head_and_body(self):
-        "Prevent recurrence of a bug in the html5lib treebuilder."
-        content = """<html><head></head>
-  <link></link>
-  <body>foo</body>
-</html>
-"""
-        soup = self.soup(content)
-        self.assertNotEqual(None, soup.html.body)
-        self.assertConnectedness(soup)
-
-    def test_multiple_copies_of_a_tag(self):
-        "Prevent recurrence of a bug in the html5lib treebuilder."
-        content = """<!DOCTYPE html>
-<html>
- <body>
-   <article id="a" >
-   <div><a href="1"></div>
-   <footer>
-     <a href="2"></a>
-   </footer>
-  </article>
-  </body>
-</html>
-"""
-        soup = self.soup(content)
-        self.assertConnectedness(soup.article)
-
-    def test_basic_namespaces(self):
-        """Parsers don't need to *understand* namespaces, but at the
-        very least they should not choke on namespaces or lose
-        data."""
-
-        markup = b'<html xmlns="http://www.w3.org/1999/xhtml" xmlns:mathml="http://www.w3.org/1998/Math/MathML" xmlns:svg="http://www.w3.org/2000/svg"><head></head><body><mathml:msqrt>4</mathml:msqrt><b svg:fill="red"></b></body></html>'
-        soup = self.soup(markup)
-        self.assertEqual(markup, soup.encode())
-        html = soup.html
-        self.assertEqual('http://www.w3.org/1999/xhtml', soup.html['xmlns'])
-        self.assertEqual(
-            'http://www.w3.org/1998/Math/MathML', soup.html['xmlns:mathml'])
-        self.assertEqual(
-            'http://www.w3.org/2000/svg', soup.html['xmlns:svg'])
-
-    def test_multivalued_attribute_value_becomes_list(self):
-        markup = b'<a class="foo bar">'
-        soup = self.soup(markup)
-        self.assertEqual(['foo', 'bar'], soup.a['class'])
-
-    #
-    # Generally speaking, tests below this point are more tests of
-    # Beautiful Soup than tests of the tree builders. But parsers are
-    # weird, so we run these tests separately for every tree builder
-    # to detect any differences between them.
-    #
-
-    def test_can_parse_unicode_document(self):
-        # A seemingly innocuous document... but it's in Unicode! And
-        # it contains characters that can't be represented in the
-        # encoding found in the  declaration! The horror!
-        markup = u'<html><head><meta encoding="euc-jp"></head><body>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</body>'
-        soup = self.soup(markup)
-        self.assertEqual(u'Sacr\xe9 bleu!', soup.body.string)
-
-    def test_soupstrainer(self):
-        """Parsers should be able to work with SoupStrainers."""
-        strainer = SoupStrainer("b")
-        soup = self.soup("A <b>bold</b> <meta/> <i>statement</i>",
-                         parse_only=strainer)
-        self.assertEqual(soup.decode(), "<b>bold</b>")
-
-    def test_single_quote_attribute_values_become_double_quotes(self):
-        self.assertSoupEquals("<foo attr='bar'></foo>",
-                              '<foo attr="bar"></foo>')
-
-    def test_attribute_values_with_nested_quotes_are_left_alone(self):
-        text = """<foo attr='bar "brawls" happen'>a</foo>"""
-        self.assertSoupEquals(text)
-
-    def test_attribute_values_with_double_nested_quotes_get_quoted(self):
-        text = """<foo attr='bar "brawls" happen'>a</foo>"""
-        soup = self.soup(text)
-        soup.foo['attr'] = 'Brawls happen at "Bob\'s Bar"'
-        self.assertSoupEquals(
-            soup.foo.decode(),
-            """<foo attr="Brawls happen at &quot;Bob\'s Bar&quot;">a</foo>""")
-
-    def test_ampersand_in_attribute_value_gets_escaped(self):
-        self.assertSoupEquals('<this is="really messed up & stuff"></this>',
-                              '<this is="really messed up &amp; stuff"></this>')
-
-        self.assertSoupEquals(
-            '<a href="http://example.org?a=1&b=2;3">foo</a>',
-            '<a href="http://example.org?a=1&amp;b=2;3">foo</a>')
-
-    def test_escaped_ampersand_in_attribute_value_is_left_alone(self):
-        self.assertSoupEquals('<a href="http://example.org?a=1&amp;b=2;3"></a>')
-
-    def test_entities_in_strings_converted_during_parsing(self):
-        # Both XML and HTML entities are converted to Unicode characters
-        # during parsing.
-        text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
-        expected = u"<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>"
-        self.assertSoupEquals(text, expected)
-
-    def test_smart_quotes_converted_on_the_way_in(self):
-        # Microsoft smart quotes are converted to Unicode characters during
-        # parsing.
-        quote = b"<p>\x91Foo\x92</p>"
-        soup = self.soup(quote)
-        self.assertEqual(
-            soup.p.string,
-            u"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
-
-    def test_non_breaking_spaces_converted_on_the_way_in(self):
-        soup = self.soup("<a>&nbsp;&nbsp;</a>")
-        self.assertEqual(soup.a.string, u"\N{NO-BREAK SPACE}" * 2)
-
-    def test_entities_converted_on_the_way_out(self):
-        text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
-        expected = u"<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>".encode("utf-8")
-        soup = self.soup(text)
-        self.assertEqual(soup.p.encode("utf-8"), expected)
-
-    def test_real_iso_latin_document(self):
-        # Smoke test of interrelated functionality, using an
-        # easy-to-understand document.
-
-        # Here it is in Unicode. Note that it claims to be in ISO-Latin-1.
-        unicode_html = u'<html><head><meta content="text/html; charset=ISO-Latin-1" http-equiv="Content-type"/></head><body><p>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</p></body></html>'
-
-        # That's because we're going to encode it into ISO-Latin-1, and use
-        # that to test.
-        iso_latin_html = unicode_html.encode("iso-8859-1")
-
-        # Parse the ISO-Latin-1 HTML.
-        soup = self.soup(iso_latin_html)
-        # Encode it to UTF-8.
-        result = soup.encode("utf-8")
-
-        # What do we expect the result to look like? Well, it would
-        # look like unicode_html, except that the META tag would say
-        # UTF-8 instead of ISO-Latin-1.
-        expected = unicode_html.replace("ISO-Latin-1", "utf-8")
-
-        # And, of course, it would be in UTF-8, not Unicode.
-        expected = expected.encode("utf-8")
-
-        # Ta-da!
-        self.assertEqual(result, expected)
-
-    def test_real_shift_jis_document(self):
-        # Smoke test to make sure the parser can handle a document in
-        # Shift-JIS encoding, without choking.
-        shift_jis_html = (
-            b'<html><head></head><body><pre>'
-            b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
-            b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
-            b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B'
-            b'</pre></body></html>')
-        unicode_html = shift_jis_html.decode("shift-jis")
-        soup = self.soup(unicode_html)
-
-        # Make sure the parse tree is correctly encoded to various
-        # encodings.
-        self.assertEqual(soup.encode("utf-8"), unicode_html.encode("utf-8"))
-        self.assertEqual(soup.encode("euc_jp"), unicode_html.encode("euc_jp"))
-
-    def test_real_hebrew_document(self):
-        # A real-world test to make sure we can convert ISO-8859-9 (a
-        # Hebrew encoding) to UTF-8.
-        hebrew_document = b'<html><head><title>Hebrew (ISO 8859-8) in Visual Directionality</title></head><body><h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\xed\xe5\xec\xf9</body></html>'
-        soup = self.soup(
-            hebrew_document, from_encoding="iso8859-8")
-        # Some tree builders call it iso8859-8, others call it iso-8859-9.
-        # That's not a difference we really care about.
-        assert soup.original_encoding in ('iso8859-8', 'iso-8859-8')
-        self.assertEqual(
-            soup.encode('utf-8'),
-            hebrew_document.decode("iso8859-8").encode("utf-8"))
-
-    def test_meta_tag_reflects_current_encoding(self):
-        # Here's the <meta> tag saying that a document is
-        # encoded in Shift-JIS.
-        meta_tag = ('<meta content="text/html; charset=x-sjis" '
-                    'http-equiv="Content-type"/>')
-
-        # Here's a document incorporating that meta tag.
-        shift_jis_html = (
-            '<html><head>\n%s\n'
-            '<meta http-equiv="Content-language" content="ja"/>'
-            '</head><body>Shift-JIS markup goes here.') % meta_tag
-        soup = self.soup(shift_jis_html)
-
-        # Parse the document, and the charset is seemingly unaffected.
-        parsed_meta = soup.find('meta', {'http-equiv': 'Content-type'})
-        content = parsed_meta['content']
-        self.assertEqual('text/html; charset=x-sjis', content)
-
-        # But that value is actually a ContentMetaAttributeValue object.
-        self.assertTrue(isinstance(content, ContentMetaAttributeValue))
-
-        # And it will take on a value that reflects its current
-        # encoding.
-        self.assertEqual('text/html; charset=utf8', content.encode("utf8"))
-
-        # For the rest of the story, see TestSubstitutions in
-        # test_tree.py.
-
-    def test_html5_style_meta_tag_reflects_current_encoding(self):
-        # Here's the <meta> tag saying that a document is
-        # encoded in Shift-JIS.
-        meta_tag = ('<meta id="encoding" charset="x-sjis" />')
-
-        # Here's a document incorporating that meta tag.
-        shift_jis_html = (
-            '<html><head>\n%s\n'
-            '<meta http-equiv="Content-language" content="ja"/>'
-            '</head><body>Shift-JIS markup goes here.') % meta_tag
-        soup = self.soup(shift_jis_html)
-
-        # Parse the document, and the charset is seemingly unaffected.
-        parsed_meta = soup.find('meta', id="encoding")
-        charset = parsed_meta['charset']
-        self.assertEqual('x-sjis', charset)
-
-        # But that value is actually a CharsetMetaAttributeValue object.
-        self.assertTrue(isinstance(charset, CharsetMetaAttributeValue))
-
-        # And it will take on a value that reflects its current
-        # encoding.
-        self.assertEqual('utf8', charset.encode("utf8"))
-
-    def test_tag_with_no_attributes_can_have_attributes_added(self):
-        data = self.soup("<a>text</a>")
-        data.a['foo'] = 'bar'
-        self.assertEqual('<a foo="bar">text</a>', data.a.decode())
-
-class XMLTreeBuilderSmokeTest(object):
-
-    def test_pickle_and_unpickle_identity(self):
-        # Pickling a tree, then unpickling it, yields a tree identical
-        # to the original.
-        tree = self.soup("<a><b>foo</a>")
-        dumped = pickle.dumps(tree, 2)
-        loaded = pickle.loads(dumped)
-        self.assertEqual(loaded.__class__, BeautifulSoup)
-        self.assertEqual(loaded.decode(), tree.decode())
-
-    def test_docstring_generated(self):
-        soup = self.soup("<root/>")
-        self.assertEqual(
-            soup.encode(), b'<?xml version="1.0" encoding="utf-8"?>\n<root/>')
-
-    def test_xml_declaration(self):
-        markup = b"""<?xml version="1.0" encoding="utf8"?>\n<foo/>"""
-        soup = self.soup(markup)
-        self.assertEqual(markup, soup.encode("utf8"))
-
-    def test_processing_instruction(self):
-        markup = b"""<?xml version="1.0" encoding="utf8"?>\n<?PITarget PIContent?>"""
-        soup = self.soup(markup)
-        self.assertEqual(markup, soup.encode("utf8"))
-
-    def test_real_xhtml_document(self):
-        """A real XHTML document should come out *exactly* the same as it went in."""
-        markup = b"""<?xml version="1.0" encoding="utf-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
-<html xmlns="http://www.w3.org/1999/xhtml">
-<head><title>Hello.</title></head>
-<body>Goodbye.</body>
-</html>"""
-        soup = self.soup(markup)
-        self.assertEqual(
-            soup.encode("utf-8"), markup)
-
-    def test_nested_namespaces(self):
-        doc = b"""<?xml version="1.0" encoding="utf-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
-<parent xmlns="http://ns1/">
-<child xmlns="http://ns2/" xmlns:ns3="http://ns3/">
-<grandchild ns3:attr="value" xmlns="http://ns4/"/>
-</child>
-</parent>"""
-        soup = self.soup(doc)
-        self.assertEqual(doc, soup.encode())
-        
-    def test_formatter_processes_script_tag_for_xml_documents(self):
-        doc = """
-  <script type="text/javascript">
-  </script>
-"""
-        soup = BeautifulSoup(doc, "lxml-xml")
-        # lxml would have stripped this while parsing, but we can add
-        # it later.
-        soup.script.string = 'console.log("< < hey > > ");'
-        encoded = soup.encode()
-        self.assertTrue(b"&lt; &lt; hey &gt; &gt;" in encoded)
-
-    def test_can_parse_unicode_document(self):
-        markup = u'<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>'
-        soup = self.soup(markup)
-        self.assertEqual(u'Sacr\xe9 bleu!', soup.root.string)
-
-    def test_popping_namespaced_tag(self):
-        markup = '<rss xmlns:dc="foo"><dc:creator>b</dc:creator><dc:date>2012-07-02T20:33:42Z</dc:date><dc:rights>c</dc:rights><image>d</image></rss>'
-        soup = self.soup(markup)
-        self.assertEqual(
-            unicode(soup.rss), markup)
-
-    def test_docstring_includes_correct_encoding(self):
-        soup = self.soup("<root/>")
-        self.assertEqual(
-            soup.encode("latin1"),
-            b'<?xml version="1.0" encoding="latin1"?>\n<root/>')
-
-    def test_large_xml_document(self):
-        """A large XML document should come out the same as it went in."""
-        markup = (b'<?xml version="1.0" encoding="utf-8"?>\n<root>'
-                  + b'0' * (2**12)
-                  + b'</root>')
-        soup = self.soup(markup)
-        self.assertEqual(soup.encode("utf-8"), markup)
-
-
-    def test_tags_are_empty_element_if_and_only_if_they_are_empty(self):
-        self.assertSoupEquals("<p>", "<p/>")
-        self.assertSoupEquals("<p>foo</p>")
-
-    def test_namespaces_are_preserved(self):
-        markup = '<root xmlns:a="http://example.com/" xmlns:b="http://example.net/"><a:foo>This tag is in the a namespace</a:foo><b:foo>This tag is in the b namespace</b:foo></root>'
-        soup = self.soup(markup)
-        root = soup.root
-        self.assertEqual("http://example.com/", root['xmlns:a'])
-        self.assertEqual("http://example.net/", root['xmlns:b'])
-
-    def test_closing_namespaced_tag(self):
-        markup = '<p xmlns:dc="http://purl.org/dc/elements/1.1/"><dc:date>20010504</dc:date></p>'
-        soup = self.soup(markup)
-        self.assertEqual(unicode(soup.p), markup)
-
-    def test_namespaced_attributes(self):
-        markup = '<foo xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><bar xsi:schemaLocation="http://www.example.com"/></foo>'
-        soup = self.soup(markup)
-        self.assertEqual(unicode(soup.foo), markup)
-
-    def test_namespaced_attributes_xml_namespace(self):
-        markup = '<foo xml:lang="fr">bar</foo>'
-        soup = self.soup(markup)
-        self.assertEqual(unicode(soup.foo), markup)
-
-    def test_find_by_prefixed_name(self):
-        doc = """<?xml version="1.0" encoding="utf-8"?>
-<Document xmlns="http://example.com/ns0"
-    xmlns:ns1="http://example.com/ns1"
-    xmlns:ns2="http://example.com/ns2"
-    <ns1:tag>foo</ns1:tag>
-    <ns1:tag>bar</ns1:tag>
-    <ns2:tag key="value">baz</ns2:tag>
-</Document>
-"""
-        soup = self.soup(doc)
-
-        # There are three <tag> tags.
-        self.assertEqual(3, len(soup.find_all('tag')))
-
-        # But two of them are ns1:tag and one of them is ns2:tag.
-        self.assertEqual(2, len(soup.find_all('ns1:tag')))
-        self.assertEqual(1, len(soup.find_all('ns2:tag')))
-        
-        self.assertEqual(1, len(soup.find_all('ns2:tag', key='value')))
-        self.assertEqual(3, len(soup.find_all(['ns1:tag', 'ns2:tag'])))
-        
-    def test_copy_tag_preserves_namespace(self):
-        xml = """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<w:document xmlns:w="http://example.com/ns0"/>"""
-    
-        soup = self.soup(xml)
-        tag = soup.document
-        duplicate = copy.copy(tag)
-
-        # The two tags have the same namespace prefix.
-        self.assertEqual(tag.prefix, duplicate.prefix)
-
-
-class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest):
-    """Smoke test for a tree builder that supports HTML5."""
-
-    def test_real_xhtml_document(self):
-        # Since XHTML is not HTML5, HTML5 parsers are not tested to handle
-        # XHTML documents in any particular way.
-        pass
-
-    def test_html_tags_have_namespace(self):
-        markup = "<a>"
-        soup = self.soup(markup)
-        self.assertEqual("http://www.w3.org/1999/xhtml", soup.a.namespace)
-
-    def test_svg_tags_have_namespace(self):
-        markup = '<svg><circle/></svg>'
-        soup = self.soup(markup)
-        namespace = "http://www.w3.org/2000/svg"
-        self.assertEqual(namespace, soup.svg.namespace)
-        self.assertEqual(namespace, soup.circle.namespace)
-
-
-    def test_mathml_tags_have_namespace(self):
-        markup = '<math><msqrt>5</msqrt></math>'
-        soup = self.soup(markup)
-        namespace = 'http://www.w3.org/1998/Math/MathML'
-        self.assertEqual(namespace, soup.math.namespace)
-        self.assertEqual(namespace, soup.msqrt.namespace)
-
-    def test_xml_declaration_becomes_comment(self):
-        markup = '<?xml version="1.0" encoding="utf-8"?><html></html>'
-        soup = self.soup(markup)
-        self.assertTrue(isinstance(soup.contents[0], Comment))
-        self.assertEqual(soup.contents[0], '?xml version="1.0" encoding="utf-8"?')
-        self.assertEqual("html", soup.contents[0].next_element.name)
-
-def skipIf(condition, reason):
-   def nothing(test, *args, **kwargs):
-       return None
-
-   def decorator(test_item):
-       if condition:
-           return nothing
-       else:
-           return test_item
-
-   return decorator

libs/py2/bs4/tests/__init__.py

@@ -1 +0,0 @@
-"The beautifulsoup tests."

libs/py2/bs4/tests/test_builder_registry.py

@@ -1,147 +0,0 @@
-"""Tests of the builder registry."""
-
-import unittest
-import warnings
-
-from bs4 import BeautifulSoup
-from bs4.builder import (
-    builder_registry as registry,
-    HTMLParserTreeBuilder,
-    TreeBuilderRegistry,
-)
-
-try:
-    from bs4.builder import HTML5TreeBuilder
-    HTML5LIB_PRESENT = True
-except ImportError:
-    HTML5LIB_PRESENT = False
-
-try:
-    from bs4.builder import (
-        LXMLTreeBuilderForXML,
-        LXMLTreeBuilder,
-        )
-    LXML_PRESENT = True
-except ImportError:
-    LXML_PRESENT = False
-
-
-class BuiltInRegistryTest(unittest.TestCase):
-    """Test the built-in registry with the default builders registered."""
-
-    def test_combination(self):
-        if LXML_PRESENT:
-            self.assertEqual(registry.lookup('fast', 'html'),
-                             LXMLTreeBuilder)
-
-        if LXML_PRESENT:
-            self.assertEqual(registry.lookup('permissive', 'xml'),
-                             LXMLTreeBuilderForXML)
-        self.assertEqual(registry.lookup('strict', 'html'),
-                          HTMLParserTreeBuilder)
-        if HTML5LIB_PRESENT:
-            self.assertEqual(registry.lookup('html5lib', 'html'),
-                              HTML5TreeBuilder)
-
-    def test_lookup_by_markup_type(self):
-        if LXML_PRESENT:
-            self.assertEqual(registry.lookup('html'), LXMLTreeBuilder)
-            self.assertEqual(registry.lookup('xml'), LXMLTreeBuilderForXML)
-        else:
-            self.assertEqual(registry.lookup('xml'), None)
-            if HTML5LIB_PRESENT:
-                self.assertEqual(registry.lookup('html'), HTML5TreeBuilder)
-            else:
-                self.assertEqual(registry.lookup('html'), HTMLParserTreeBuilder)
-
-    def test_named_library(self):
-        if LXML_PRESENT:
-            self.assertEqual(registry.lookup('lxml', 'xml'),
-                             LXMLTreeBuilderForXML)
-            self.assertEqual(registry.lookup('lxml', 'html'),
-                             LXMLTreeBuilder)
-        if HTML5LIB_PRESENT:
-            self.assertEqual(registry.lookup('html5lib'),
-                              HTML5TreeBuilder)
-
-        self.assertEqual(registry.lookup('html.parser'),
-                          HTMLParserTreeBuilder)
-
-    def test_beautifulsoup_constructor_does_lookup(self):
-
-        with warnings.catch_warnings(record=True) as w:
-            # This will create a warning about not explicitly
-            # specifying a parser, but we'll ignore it.
-
-            # You can pass in a string.
-            BeautifulSoup("", features="html")
-            # Or a list of strings.
-            BeautifulSoup("", features=["html", "fast"])
-
-        # You'll get an exception if BS can't find an appropriate
-        # builder.
-        self.assertRaises(ValueError, BeautifulSoup,
-                          "", features="no-such-feature")
-
-class RegistryTest(unittest.TestCase):
-    """Test the TreeBuilderRegistry class in general."""
-
-    def setUp(self):
-        self.registry = TreeBuilderRegistry()
-
-    def builder_for_features(self, *feature_list):
-        cls = type('Builder_' + '_'.join(feature_list),
-                   (object,), {'features' : feature_list})
-
-        self.registry.register(cls)
-        return cls
-
-    def test_register_with_no_features(self):
-        builder = self.builder_for_features()
-
-        # Since the builder advertises no features, you can't find it
-        # by looking up features.
-        self.assertEqual(self.registry.lookup('foo'), None)
-
-        # But you can find it by doing a lookup with no features, if
-        # this happens to be the only registered builder.
-        self.assertEqual(self.registry.lookup(), builder)
-
-    def test_register_with_features_makes_lookup_succeed(self):
-        builder = self.builder_for_features('foo', 'bar')
-        self.assertEqual(self.registry.lookup('foo'), builder)
-        self.assertEqual(self.registry.lookup('bar'), builder)
-
-    def test_lookup_fails_when_no_builder_implements_feature(self):
-        builder = self.builder_for_features('foo', 'bar')
-        self.assertEqual(self.registry.lookup('baz'), None)
-
-    def test_lookup_gets_most_recent_registration_when_no_feature_specified(self):
-        builder1 = self.builder_for_features('foo')
-        builder2 = self.builder_for_features('bar')
-        self.assertEqual(self.registry.lookup(), builder2)
-
-    def test_lookup_fails_when_no_tree_builders_registered(self):
-        self.assertEqual(self.registry.lookup(), None)
-
-    def test_lookup_gets_most_recent_builder_supporting_all_features(self):
-        has_one = self.builder_for_features('foo')
-        has_the_other = self.builder_for_features('bar')
-        has_both_early = self.builder_for_features('foo', 'bar', 'baz')
-        has_both_late = self.builder_for_features('foo', 'bar', 'quux')
-        lacks_one = self.builder_for_features('bar')
-        has_the_other = self.builder_for_features('foo')
-
-        # There are two builders featuring 'foo' and 'bar', but
-        # the one that also features 'quux' was registered later.
-        self.assertEqual(self.registry.lookup('foo', 'bar'),
-                          has_both_late)
-
-        # There is only one builder featuring 'foo', 'bar', and 'baz'.
-        self.assertEqual(self.registry.lookup('foo', 'bar', 'baz'),
-                          has_both_early)
-
-    def test_lookup_fails_when_cannot_reconcile_requested_features(self):
-        builder1 = self.builder_for_features('foo', 'bar')
-        builder2 = self.builder_for_features('foo', 'baz')
-        self.assertEqual(self.registry.lookup('bar', 'baz'), None)

libs/py2/bs4/tests/test_docs.py

@@ -1,36 +0,0 @@
-"Test harness for doctests."
-
-# pylint: disable-msg=E0611,W0142
-
-__metaclass__ = type
-__all__ = [
-    'additional_tests',
-    ]
-
-import atexit
-import doctest
-import os
-#from pkg_resources import (
-#    resource_filename, resource_exists, resource_listdir, cleanup_resources)
-import unittest
-
-DOCTEST_FLAGS = (
-    doctest.ELLIPSIS |
-    doctest.NORMALIZE_WHITESPACE |
-    doctest.REPORT_NDIFF)
-
-
-# def additional_tests():
-#     "Run the doc tests (README.txt and docs/*, if any exist)"
-#     doctest_files = [
-#         os.path.abspath(resource_filename('bs4', 'README.txt'))]
-#     if resource_exists('bs4', 'docs'):
-#         for name in resource_listdir('bs4', 'docs'):
-#             if name.endswith('.txt'):
-#                 doctest_files.append(
-#                     os.path.abspath(
-#                         resource_filename('bs4', 'docs/%s' % name)))
-#     kwargs = dict(module_relative=False, optionflags=DOCTEST_FLAGS)
-#     atexit.register(cleanup_resources)
-#     return unittest.TestSuite((
-#         doctest.DocFileSuite(*doctest_files, **kwargs)))

libs/py2/bs4/tests/test_html5lib.py

@@ -1,130 +0,0 @@
-"""Tests to ensure that the html5lib tree builder generates good trees."""
-
-import warnings
-
-try:
-    from bs4.builder import HTML5TreeBuilder
-    HTML5LIB_PRESENT = True
-except ImportError, e:
-    HTML5LIB_PRESENT = False
-from bs4.element import SoupStrainer
-from bs4.testing import (
-    HTML5TreeBuilderSmokeTest,
-    SoupTest,
-    skipIf,
-)
-
-@skipIf(
-    not HTML5LIB_PRESENT,
-    "html5lib seems not to be present, not testing its tree builder.")
-class HTML5LibBuilderSmokeTest(SoupTest, HTML5TreeBuilderSmokeTest):
-    """See ``HTML5TreeBuilderSmokeTest``."""
-
-    @property
-    def default_builder(self):
-        return HTML5TreeBuilder()
-
-    def test_soupstrainer(self):
-        # The html5lib tree builder does not support SoupStrainers.
-        strainer = SoupStrainer("b")
-        markup = "<p>A <b>bold</b> statement.</p>"
-        with warnings.catch_warnings(record=True) as w:
-            soup = self.soup(markup, parse_only=strainer)
-        self.assertEqual(
-            soup.decode(), self.document_for(markup))
-
-        self.assertTrue(
-            "the html5lib tree builder doesn't support parse_only" in
-            str(w[0].message))
-
-    def test_correctly_nested_tables(self):
-        """html5lib inserts <tbody> tags where other parsers don't."""
-        markup = ('<table id="1">'
-                  '<tr>'
-                  "<td>Here's another table:"
-                  '<table id="2">'
-                  '<tr><td>foo</td></tr>'
-                  '</table></td>')
-
-        self.assertSoupEquals(
-            markup,
-            '<table id="1"><tbody><tr><td>Here\'s another table:'
-            '<table id="2"><tbody><tr><td>foo</td></tr></tbody></table>'
-            '</td></tr></tbody></table>')
-
-        self.assertSoupEquals(
-            "<table><thead><tr><td>Foo</td></tr></thead>"
-            "<tbody><tr><td>Bar</td></tr></tbody>"
-            "<tfoot><tr><td>Baz</td></tr></tfoot></table>")
-
-    def test_xml_declaration_followed_by_doctype(self):
-        markup = '''<?xml version="1.0" encoding="utf-8"?>
-<!DOCTYPE html>
-<html>
-  <head>
-  </head>
-  <body>
-   <p>foo</p>
-  </body>
-</html>'''
-        soup = self.soup(markup)
-        # Verify that we can reach the <p> tag; this means the tree is connected.
-        self.assertEqual(b"<p>foo</p>", soup.p.encode())
-
-    def test_reparented_markup(self):
-        markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>'
-        soup = self.soup(markup)
-        self.assertEqual(u"<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p></body>", soup.body.decode())
-        self.assertEqual(2, len(soup.find_all('p')))
-
-
-    def test_reparented_markup_ends_with_whitespace(self):
-        markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>\n'
-        soup = self.soup(markup)
-        self.assertEqual(u"<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p>\n</body>", soup.body.decode())
-        self.assertEqual(2, len(soup.find_all('p')))
-
-    def test_reparented_markup_containing_identical_whitespace_nodes(self):
-        """Verify that we keep the two whitespace nodes in this
-        document distinct when reparenting the adjacent <tbody> tags.
-        """
-        markup = '<table> <tbody><tbody><ims></tbody> </table>'
-        soup = self.soup(markup)
-        space1, space2 = soup.find_all(string=' ')
-        tbody1, tbody2 = soup.find_all('tbody')
-        assert space1.next_element is tbody1
-        assert tbody2.next_element is space2
-
-    def test_reparented_markup_containing_children(self):
-        markup = '<div><a>aftermath<p><noscript>target</noscript>aftermath</a></p></div>'
-        soup = self.soup(markup)
-        noscript = soup.noscript
-        self.assertEqual("target", noscript.next_element)
-        target = soup.find(string='target')
-
-        # The 'aftermath' string was duplicated; we want the second one.
-        final_aftermath = soup.find_all(string='aftermath')[-1]
-
-        # The <noscript> tag was moved beneath a copy of the <a> tag,
-        # but the 'target' string within is still connected to the
-        # (second) 'aftermath' string.
-        self.assertEqual(final_aftermath, target.next_element)
-        self.assertEqual(target, final_aftermath.previous_element)
-        
-    def test_processing_instruction(self):
-        """Processing instructions become comments."""
-        markup = b"""<?PITarget PIContent?>"""
-        soup = self.soup(markup)
-        assert str(soup).startswith("<!--?PITarget PIContent?-->")
-
-    def test_cloned_multivalue_node(self):
-        markup = b"""<a class="my_class"><p></a>"""
-        soup = self.soup(markup)
-        a1, a2 = soup.find_all('a')
-        self.assertEqual(a1, a2)
-        assert a1 is not a2
-
-    def test_foster_parenting(self):
-        markup = b"""<table><td></tbody>A"""
-        soup = self.soup(markup)
-        self.assertEqual(u"<body>A<table><tbody><tr><td></td></tr></tbody></table></body>", soup.body.decode())

libs/py2/bs4/tests/test_htmlparser.py

@@ -1,49 +0,0 @@
-"""Tests to ensure that the html.parser tree builder generates good
-trees."""
-
-from pdb import set_trace
-import pickle
-from bs4.testing import SoupTest, HTMLTreeBuilderSmokeTest
-from bs4.builder import HTMLParserTreeBuilder
-from bs4.builder._htmlparser import BeautifulSoupHTMLParser
-
-class HTMLParserTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
-
-    @property
-    def default_builder(self):
-        return HTMLParserTreeBuilder()
-
-    def test_namespaced_system_doctype(self):
-        # html.parser can't handle namespaced doctypes, so skip this one.
-        pass
-
-    def test_namespaced_public_doctype(self):
-        # html.parser can't handle namespaced doctypes, so skip this one.
-        pass
-
-    def test_builder_is_pickled(self):
-        """Unlike most tree builders, HTMLParserTreeBuilder and will
-        be restored after pickling.
-        """
-        tree = self.soup("<a><b>foo</a>")
-        dumped = pickle.dumps(tree, 2)
-        loaded = pickle.loads(dumped)
-        self.assertTrue(isinstance(loaded.builder, type(tree.builder)))
-
-    def test_redundant_empty_element_closing_tags(self):
-        self.assertSoupEquals('<br></br><br></br><br></br>', "<br/><br/><br/>")
-        self.assertSoupEquals('</br></br></br>', "")
-
-    def test_empty_element(self):
-        # This verifies that any buffered data present when the parser
-        # finishes working is handled.
-        self.assertSoupEquals("foo &# bar", "foo &amp;# bar")
-
-
-class TestHTMLParserSubclass(SoupTest):
-    def test_error(self):
-        """Verify that our HTMLParser subclass implements error() in a way
-        that doesn't cause a crash.
-        """
-        parser = BeautifulSoupHTMLParser()
-        parser.error("don't crash")

libs/py2/bs4/tests/test_lxml.py

@@ -1,82 +0,0 @@
-"""Tests to ensure that the lxml tree builder generates good trees."""
-
-import re
-import warnings
-
-try:
-    import lxml.etree
-    LXML_PRESENT = True
-    LXML_VERSION = lxml.etree.LXML_VERSION
-except ImportError, e:
-    LXML_PRESENT = False
-    LXML_VERSION = (0,)
-
-if LXML_PRESENT:
-    from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
-
-from bs4 import (
-    BeautifulSoup,
-    BeautifulStoneSoup,
-    )
-from bs4.element import Comment, Doctype, SoupStrainer
-from bs4.testing import skipIf
-from bs4.tests import test_htmlparser
-from bs4.testing import (
-    HTMLTreeBuilderSmokeTest,
-    XMLTreeBuilderSmokeTest,
-    SoupTest,
-    skipIf,
-)
-
-@skipIf(
-    not LXML_PRESENT,
-    "lxml seems not to be present, not testing its tree builder.")
-class LXMLTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
-    """See ``HTMLTreeBuilderSmokeTest``."""
-
-    @property
-    def default_builder(self):
-        return LXMLTreeBuilder()
-
-    def test_out_of_range_entity(self):
-        self.assertSoupEquals(
-            "<p>foo&#10000000000000;bar</p>", "<p>foobar</p>")
-        self.assertSoupEquals(
-            "<p>foo&#x10000000000000;bar</p>", "<p>foobar</p>")
-        self.assertSoupEquals(
-            "<p>foo&#1000000000;bar</p>", "<p>foobar</p>")
-
-    def test_entities_in_foreign_document_encoding(self):
-        # We can't implement this case correctly because by the time we
-        # hear about markup like "&#147;", it's been (incorrectly) converted into
-        # a string like u'\x93'
-        pass
-        
-    # In lxml < 2.3.5, an empty doctype causes a segfault. Skip this
-    # test if an old version of lxml is installed.
-
-    @skipIf(
-        not LXML_PRESENT or LXML_VERSION < (2,3,5,0),
-        "Skipping doctype test for old version of lxml to avoid segfault.")
-    def test_empty_doctype(self):
-        soup = self.soup("<!DOCTYPE>")
-        doctype = soup.contents[0]
-        self.assertEqual("", doctype.strip())
-
-    def test_beautifulstonesoup_is_xml_parser(self):
-        # Make sure that the deprecated BSS class uses an xml builder
-        # if one is installed.
-        with warnings.catch_warnings(record=True) as w:
-            soup = BeautifulStoneSoup("<b />")
-        self.assertEqual(u"<b/>", unicode(soup.b))
-        self.assertTrue("BeautifulStoneSoup class is deprecated" in str(w[0].message))
-
-@skipIf(
-    not LXML_PRESENT,
-    "lxml seems not to be present, not testing its XML tree builder.")
-class LXMLXMLTreeBuilderSmokeTest(SoupTest, XMLTreeBuilderSmokeTest):
-    """See ``HTMLTreeBuilderSmokeTest``."""
-
-    @property
-    def default_builder(self):
-        return LXMLTreeBuilderForXML()

libs/py2/bs4/tests/test_soup.py

@@ -1,501 +0,0 @@
-# -*- coding: utf-8 -*-
-"""Tests of Beautiful Soup as a whole."""
-
-from pdb import set_trace
-import logging
-import unittest
-import sys
-import tempfile
-
-from bs4 import (
-    BeautifulSoup,
-    BeautifulStoneSoup,
-)
-from bs4.element import (
-    CharsetMetaAttributeValue,
-    ContentMetaAttributeValue,
-    SoupStrainer,
-    NamespacedAttribute,
-    )
-import bs4.dammit
-from bs4.dammit import (
-    EntitySubstitution,
-    UnicodeDammit,
-    EncodingDetector,
-)
-from bs4.testing import (
-    SoupTest,
-    skipIf,
-)
-import warnings
-
-try:
-    from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
-    LXML_PRESENT = True
-except ImportError, e:
-    LXML_PRESENT = False
-
-PYTHON_3_PRE_3_2 = (sys.version_info[0] == 3 and sys.version_info < (3,2))
-
-class TestConstructor(SoupTest):
-
-    def test_short_unicode_input(self):
-        data = u"<h1>éé</h1>"
-        soup = self.soup(data)
-        self.assertEqual(u"éé", soup.h1.string)
-
-    def test_embedded_null(self):
-        data = u"<h1>foo\0bar</h1>"
-        soup = self.soup(data)
-        self.assertEqual(u"foo\0bar", soup.h1.string)
-
-    def test_exclude_encodings(self):
-        utf8_data = u"Räksmörgås".encode("utf-8")
-        soup = self.soup(utf8_data, exclude_encodings=["utf-8"])
-        self.assertEqual("windows-1252", soup.original_encoding)
-
-
-class TestWarnings(SoupTest):
-
-    def _no_parser_specified(self, s, is_there=True):
-        v = s.startswith(BeautifulSoup.NO_PARSER_SPECIFIED_WARNING[:80])
-        self.assertTrue(v)
-
-    def test_warning_if_no_parser_specified(self):
-        with warnings.catch_warnings(record=True) as w:
-            soup = self.soup("<a><b></b></a>")
-        msg = str(w[0].message)
-        self._assert_no_parser_specified(msg)
-
-    def test_warning_if_parser_specified_too_vague(self):
-        with warnings.catch_warnings(record=True) as w:
-            soup = self.soup("<a><b></b></a>", "html")
-        msg = str(w[0].message)
-        self._assert_no_parser_specified(msg)
-
-    def test_no_warning_if_explicit_parser_specified(self):
-        with warnings.catch_warnings(record=True) as w:
-            soup = self.soup("<a><b></b></a>", "html.parser")
-        self.assertEqual([], w)
-
-    def test_parseOnlyThese_renamed_to_parse_only(self):
-        with warnings.catch_warnings(record=True) as w:
-            soup = self.soup("<a><b></b></a>", parseOnlyThese=SoupStrainer("b"))
-        msg = str(w[0].message)
-        self.assertTrue("parseOnlyThese" in msg)
-        self.assertTrue("parse_only" in msg)
-        self.assertEqual(b"<b></b>", soup.encode())
-
-    def test_fromEncoding_renamed_to_from_encoding(self):
-        with warnings.catch_warnings(record=True) as w:
-            utf8 = b"\xc3\xa9"
-            soup = self.soup(utf8, fromEncoding="utf8")
-        msg = str(w[0].message)
-        self.assertTrue("fromEncoding" in msg)
-        self.assertTrue("from_encoding" in msg)
-        self.assertEqual("utf8", soup.original_encoding)
-
-    def test_unrecognized_keyword_argument(self):
-        self.assertRaises(
-            TypeError, self.soup, "<a>", no_such_argument=True)
-
-class TestWarnings(SoupTest):
-
-    def test_disk_file_warning(self):
-        filehandle = tempfile.NamedTemporaryFile()
-        filename = filehandle.name
-        try:
-            with warnings.catch_warnings(record=True) as w:
-                soup = self.soup(filename)
-            msg = str(w[0].message)
-            self.assertTrue("looks like a filename" in msg)
-        finally:
-            filehandle.close()
-
-        # The file no longer exists, so Beautiful Soup will no longer issue the warning.
-        with warnings.catch_warnings(record=True) as w:
-            soup = self.soup(filename)
-        self.assertEqual(0, len(w))
-
-    def test_url_warning_with_bytes_url(self):
-        with warnings.catch_warnings(record=True) as warning_list:
-            soup = self.soup(b"http://www.crummybytes.com/")
-        # Be aware this isn't the only warning that can be raised during
-        # execution..
-        self.assertTrue(any("looks like a URL" in str(w.message) 
-            for w in warning_list))
-
-    def test_url_warning_with_unicode_url(self):
-        with warnings.catch_warnings(record=True) as warning_list:
-            # note - this url must differ from the bytes one otherwise
-            # python's warnings system swallows the second warning
-            soup = self.soup(u"http://www.crummyunicode.com/")
-        self.assertTrue(any("looks like a URL" in str(w.message) 
-            for w in warning_list))
-
-    def test_url_warning_with_bytes_and_space(self):
-        with warnings.catch_warnings(record=True) as warning_list:
-            soup = self.soup(b"http://www.crummybytes.com/ is great")
-        self.assertFalse(any("looks like a URL" in str(w.message) 
-            for w in warning_list))
-
-    def test_url_warning_with_unicode_and_space(self):
-        with warnings.catch_warnings(record=True) as warning_list:
-            soup = self.soup(u"http://www.crummyuncode.com/ is great")
-        self.assertFalse(any("looks like a URL" in str(w.message) 
-            for w in warning_list))
-
-
-class TestSelectiveParsing(SoupTest):
-
-    def test_parse_with_soupstrainer(self):
-        markup = "No<b>Yes</b><a>No<b>Yes <c>Yes</c></b>"
-        strainer = SoupStrainer("b")
-        soup = self.soup(markup, parse_only=strainer)
-        self.assertEqual(soup.encode(), b"<b>Yes</b><b>Yes <c>Yes</c></b>")
-
-
-class TestEntitySubstitution(unittest.TestCase):
-    """Standalone tests of the EntitySubstitution class."""
-    def setUp(self):
-        self.sub = EntitySubstitution
-
-    def test_simple_html_substitution(self):
-        # Unicode characters corresponding to named HTML entites
-        # are substituted, and no others.
-        s = u"foo\u2200\N{SNOWMAN}\u00f5bar"
-        self.assertEqual(self.sub.substitute_html(s),
-                          u"foo&forall;\N{SNOWMAN}&otilde;bar")
-
-    def test_smart_quote_substitution(self):
-        # MS smart quotes are a common source of frustration, so we
-        # give them a special test.
-        quotes = b"\x91\x92foo\x93\x94"
-        dammit = UnicodeDammit(quotes)
-        self.assertEqual(self.sub.substitute_html(dammit.markup),
-                          "&lsquo;&rsquo;foo&ldquo;&rdquo;")
-
-    def test_xml_converstion_includes_no_quotes_if_make_quoted_attribute_is_false(self):
-        s = 'Welcome to "my bar"'
-        self.assertEqual(self.sub.substitute_xml(s, False), s)
-
-    def test_xml_attribute_quoting_normally_uses_double_quotes(self):
-        self.assertEqual(self.sub.substitute_xml("Welcome", True),
-                          '"Welcome"')
-        self.assertEqual(self.sub.substitute_xml("Bob's Bar", True),
-                          '"Bob\'s Bar"')
-
-    def test_xml_attribute_quoting_uses_single_quotes_when_value_contains_double_quotes(self):
-        s = 'Welcome to "my bar"'
-        self.assertEqual(self.sub.substitute_xml(s, True),
-                          "'Welcome to \"my bar\"'")
-
-    def test_xml_attribute_quoting_escapes_single_quotes_when_value_contains_both_single_and_double_quotes(self):
-        s = 'Welcome to "Bob\'s Bar"'
-        self.assertEqual(
-            self.sub.substitute_xml(s, True),
-            '"Welcome to &quot;Bob\'s Bar&quot;"')
-
-    def test_xml_quotes_arent_escaped_when_value_is_not_being_quoted(self):
-        quoted = 'Welcome to "Bob\'s Bar"'
-        self.assertEqual(self.sub.substitute_xml(quoted), quoted)
-
-    def test_xml_quoting_handles_angle_brackets(self):
-        self.assertEqual(
-            self.sub.substitute_xml("foo<bar>"),
-            "foo&lt;bar&gt;")
-
-    def test_xml_quoting_handles_ampersands(self):
-        self.assertEqual(self.sub.substitute_xml("AT&T"), "AT&amp;T")
-
-    def test_xml_quoting_including_ampersands_when_they_are_part_of_an_entity(self):
-        self.assertEqual(
-            self.sub.substitute_xml("&Aacute;T&T"),
-            "&amp;Aacute;T&amp;T")
-
-    def test_xml_quoting_ignoring_ampersands_when_they_are_part_of_an_entity(self):
-        self.assertEqual(
-            self.sub.substitute_xml_containing_entities("&Aacute;T&T"),
-            "&Aacute;T&amp;T")
-
-    def test_quotes_not_html_substituted(self):
-        """There's no need to do this except inside attribute values."""
-        text = 'Bob\'s "bar"'
-        self.assertEqual(self.sub.substitute_html(text), text)
-
-
-class TestEncodingConversion(SoupTest):
-    # Test Beautiful Soup's ability to decode and encode from various
-    # encodings.
-
-    def setUp(self):
-        super(TestEncodingConversion, self).setUp()
-        self.unicode_data = u'<html><head><meta charset="utf-8"/></head><body><foo>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</foo></body></html>'
-        self.utf8_data = self.unicode_data.encode("utf-8")
-        # Just so you know what it looks like.
-        self.assertEqual(
-            self.utf8_data,
-            b'<html><head><meta charset="utf-8"/></head><body><foo>Sacr\xc3\xa9 bleu!</foo></body></html>')
-
-    def test_ascii_in_unicode_out(self):
-        # ASCII input is converted to Unicode. The original_encoding
-        # attribute is set to 'utf-8', a superset of ASCII.
-        chardet = bs4.dammit.chardet_dammit
-        logging.disable(logging.WARNING)
-        try:
-            def noop(str):
-                return None
-            # Disable chardet, which will realize that the ASCII is ASCII.
-            bs4.dammit.chardet_dammit = noop
-            ascii = b"<foo>a</foo>"
-            soup_from_ascii = self.soup(ascii)
-            unicode_output = soup_from_ascii.decode()
-            self.assertTrue(isinstance(unicode_output, unicode))
-            self.assertEqual(unicode_output, self.document_for(ascii.decode()))
-            self.assertEqual(soup_from_ascii.original_encoding.lower(), "utf-8")
-        finally:
-            logging.disable(logging.NOTSET)
-            bs4.dammit.chardet_dammit = chardet
-
-    def test_unicode_in_unicode_out(self):
-        # Unicode input is left alone. The original_encoding attribute
-        # is not set.
-        soup_from_unicode = self.soup(self.unicode_data)
-        self.assertEqual(soup_from_unicode.decode(), self.unicode_data)
-        self.assertEqual(soup_from_unicode.foo.string, u'Sacr\xe9 bleu!')
-        self.assertEqual(soup_from_unicode.original_encoding, None)
-
-    def test_utf8_in_unicode_out(self):
-        # UTF-8 input is converted to Unicode. The original_encoding
-        # attribute is set.
-        soup_from_utf8 = self.soup(self.utf8_data)
-        self.assertEqual(soup_from_utf8.decode(), self.unicode_data)
-        self.assertEqual(soup_from_utf8.foo.string, u'Sacr\xe9 bleu!')
-
-    def test_utf8_out(self):
-        # The internal data structures can be encoded as UTF-8.
-        soup_from_unicode = self.soup(self.unicode_data)
-        self.assertEqual(soup_from_unicode.encode('utf-8'), self.utf8_data)
-
-    @skipIf(
-        PYTHON_3_PRE_3_2,
-        "Bad HTMLParser detected; skipping test of non-ASCII characters in attribute name.")
-    def test_attribute_name_containing_unicode_characters(self):
-        markup = u'<div><a \N{SNOWMAN}="snowman"></a></div>'
-        self.assertEqual(self.soup(markup).div.encode("utf8"), markup.encode("utf8"))
-
-class TestUnicodeDammit(unittest.TestCase):
-    """Standalone tests of UnicodeDammit."""
-
-    def test_unicode_input(self):
-        markup = u"I'm already Unicode! \N{SNOWMAN}"
-        dammit = UnicodeDammit(markup)
-        self.assertEqual(dammit.unicode_markup, markup)
-
-    def test_smart_quotes_to_unicode(self):
-        markup = b"<foo>\x91\x92\x93\x94</foo>"
-        dammit = UnicodeDammit(markup)
-        self.assertEqual(
-            dammit.unicode_markup, u"<foo>\u2018\u2019\u201c\u201d</foo>")
-
-    def test_smart_quotes_to_xml_entities(self):
-        markup = b"<foo>\x91\x92\x93\x94</foo>"
-        dammit = UnicodeDammit(markup, smart_quotes_to="xml")
-        self.assertEqual(
-            dammit.unicode_markup, "<foo>&#x2018;&#x2019;&#x201C;&#x201D;</foo>")
-
-    def test_smart_quotes_to_html_entities(self):
-        markup = b"<foo>\x91\x92\x93\x94</foo>"
-        dammit = UnicodeDammit(markup, smart_quotes_to="html")
-        self.assertEqual(
-            dammit.unicode_markup, "<foo>&lsquo;&rsquo;&ldquo;&rdquo;</foo>")
-
-    def test_smart_quotes_to_ascii(self):
-        markup = b"<foo>\x91\x92\x93\x94</foo>"
-        dammit = UnicodeDammit(markup, smart_quotes_to="ascii")
-        self.assertEqual(
-            dammit.unicode_markup, """<foo>''""</foo>""")
-
-    def test_detect_utf8(self):
-        utf8 = b"Sacr\xc3\xa9 bleu! \xe2\x98\x83"
-        dammit = UnicodeDammit(utf8)
-        self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
-        self.assertEqual(dammit.unicode_markup, u'Sacr\xe9 bleu! \N{SNOWMAN}')
-
-
-    def test_convert_hebrew(self):
-        hebrew = b"\xed\xe5\xec\xf9"
-        dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
-        self.assertEqual(dammit.original_encoding.lower(), 'iso-8859-8')
-        self.assertEqual(dammit.unicode_markup, u'\u05dd\u05d5\u05dc\u05e9')
-
-    def test_dont_see_smart_quotes_where_there_are_none(self):
-        utf_8 = b"\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
-        dammit = UnicodeDammit(utf_8)
-        self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
-        self.assertEqual(dammit.unicode_markup.encode("utf-8"), utf_8)
-
-    def test_ignore_inappropriate_codecs(self):
-        utf8_data = u"Räksmörgås".encode("utf-8")
-        dammit = UnicodeDammit(utf8_data, ["iso-8859-8"])
-        self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
-
-    def test_ignore_invalid_codecs(self):
-        utf8_data = u"Räksmörgås".encode("utf-8")
-        for bad_encoding in ['.utf8', '...', 'utF---16.!']:
-            dammit = UnicodeDammit(utf8_data, [bad_encoding])
-            self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
-
-    def test_exclude_encodings(self):
-        # This is UTF-8.
-        utf8_data = u"Räksmörgås".encode("utf-8")
-
-        # But if we exclude UTF-8 from consideration, the guess is
-        # Windows-1252.
-        dammit = UnicodeDammit(utf8_data, exclude_encodings=["utf-8"])
-        self.assertEqual(dammit.original_encoding.lower(), 'windows-1252')
-
-        # And if we exclude that, there is no valid guess at all.
-        dammit = UnicodeDammit(
-            utf8_data, exclude_encodings=["utf-8", "windows-1252"])
-        self.assertEqual(dammit.original_encoding, None)
-
-    def test_encoding_detector_replaces_junk_in_encoding_name_with_replacement_character(self):
-        detected = EncodingDetector(
-            b'<?xml version="1.0" encoding="UTF-\xdb" ?>')
-        encodings = list(detected.encodings)
-        assert u'utf-\N{REPLACEMENT CHARACTER}' in encodings
-
-    def test_detect_html5_style_meta_tag(self):
-
-        for data in (
-            b'<html><meta charset="euc-jp" /></html>',
-            b"<html><meta charset='euc-jp' /></html>",
-            b"<html><meta charset=euc-jp /></html>",
-            b"<html><meta charset=euc-jp/></html>"):
-            dammit = UnicodeDammit(data, is_html=True)
-            self.assertEqual(
-                "euc-jp", dammit.original_encoding)
-
-    def test_last_ditch_entity_replacement(self):
-        # This is a UTF-8 document that contains bytestrings
-        # completely incompatible with UTF-8 (ie. encoded with some other
-        # encoding).
-        #
-        # Since there is no consistent encoding for the document,
-        # Unicode, Dammit will eventually encode the document as UTF-8
-        # and encode the incompatible characters as REPLACEMENT
-        # CHARACTER.
-        #
-        # If chardet is installed, it will detect that the document
-        # can be converted into ISO-8859-1 without errors. This happens
-        # to be the wrong encoding, but it is a consistent encoding, so the
-        # code we're testing here won't run.
-        #
-        # So we temporarily disable chardet if it's present.
-        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
-<html><b>\330\250\330\252\330\261</b>
-<i>\310\322\321\220\312\321\355\344</i></html>"""
-        chardet = bs4.dammit.chardet_dammit
-        logging.disable(logging.WARNING)
-        try:
-            def noop(str):
-                return None
-            bs4.dammit.chardet_dammit = noop
-            dammit = UnicodeDammit(doc)
-            self.assertEqual(True, dammit.contains_replacement_characters)
-            self.assertTrue(u"\ufffd" in dammit.unicode_markup)
-
-            soup = BeautifulSoup(doc, "html.parser")
-            self.assertTrue(soup.contains_replacement_characters)
-        finally:
-            logging.disable(logging.NOTSET)
-            bs4.dammit.chardet_dammit = chardet
-
-    def test_byte_order_mark_removed(self):
-        # A document written in UTF-16LE will have its byte order marker stripped.
-        data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00'
-        dammit = UnicodeDammit(data)
-        self.assertEqual(u"<a>áé</a>", dammit.unicode_markup)
-        self.assertEqual("utf-16le", dammit.original_encoding)
-
-    def test_detwingle(self):
-        # Here's a UTF8 document.
-        utf8 = (u"\N{SNOWMAN}" * 3).encode("utf8")
-
-        # Here's a Windows-1252 document.
-        windows_1252 = (
-            u"\N{LEFT DOUBLE QUOTATION MARK}Hi, I like Windows!"
-            u"\N{RIGHT DOUBLE QUOTATION MARK}").encode("windows_1252")
-
-        # Through some unholy alchemy, they've been stuck together.
-        doc = utf8 + windows_1252 + utf8
-
-        # The document can't be turned into UTF-8:
-        self.assertRaises(UnicodeDecodeError, doc.decode, "utf8")
-
-        # Unicode, Dammit thinks the whole document is Windows-1252,
-        # and decodes it into "☃☃☃“Hi, I like Windows!”☃☃☃"
-
-        # But if we run it through fix_embedded_windows_1252, it's fixed:
-
-        fixed = UnicodeDammit.detwingle(doc)
-        self.assertEqual(
-            u"☃☃☃“Hi, I like Windows!”☃☃☃", fixed.decode("utf8"))
-
-    def test_detwingle_ignores_multibyte_characters(self):
-        # Each of these characters has a UTF-8 representation ending
-        # in \x93. \x93 is a smart quote if interpreted as
-        # Windows-1252. But our code knows to skip over multibyte
-        # UTF-8 characters, so they'll survive the process unscathed.
-        for tricky_unicode_char in (
-            u"\N{LATIN SMALL LIGATURE OE}", # 2-byte char '\xc5\x93'
-            u"\N{LATIN SUBSCRIPT SMALL LETTER X}", # 3-byte char '\xe2\x82\x93'
-            u"\xf0\x90\x90\x93", # This is a CJK character, not sure which one.
-            ):
-            input = tricky_unicode_char.encode("utf8")
-            self.assertTrue(input.endswith(b'\x93'))
-            output = UnicodeDammit.detwingle(input)
-            self.assertEqual(output, input)
-
-class TestNamedspacedAttribute(SoupTest):
-
-    def test_name_may_be_none(self):
-        a = NamespacedAttribute("xmlns", None)
-        self.assertEqual(a, "xmlns")
-
-    def test_attribute_is_equivalent_to_colon_separated_string(self):
-        a = NamespacedAttribute("a", "b")
-        self.assertEqual("a:b", a)
-
-    def test_attributes_are_equivalent_if_prefix_and_name_identical(self):
-        a = NamespacedAttribute("a", "b", "c")
-        b = NamespacedAttribute("a", "b", "c")
-        self.assertEqual(a, b)
-
-        # The actual namespace is not considered.
-        c = NamespacedAttribute("a", "b", None)
-        self.assertEqual(a, c)
-
-        # But name and prefix are important.
-        d = NamespacedAttribute("a", "z", "c")
-        self.assertNotEqual(a, d)
-
-        e = NamespacedAttribute("z", "b", "c")
-        self.assertNotEqual(a, e)
-
-
-class TestAttributeValueWithCharsetSubstitution(unittest.TestCase):
-
-    def test_content_meta_attribute_value(self):
-        value = CharsetMetaAttributeValue("euc-jp")
-        self.assertEqual("euc-jp", value)
-        self.assertEqual("euc-jp", value.original_value)
-        self.assertEqual("utf8", value.encode("utf8"))
-
-
-    def test_content_meta_attribute_value(self):
-        value = ContentMetaAttributeValue("text/html; charset=euc-jp")
-        self.assertEqual("text/html; charset=euc-jp", value)
-        self.assertEqual("text/html; charset=euc-jp", value.original_value)
-        self.assertEqual("text/html; charset=utf8", value.encode("utf8"))

libs/py2/concurrent/__init__.py

@@ -1,3 +0,0 @@
-from pkgutil import extend_path
-
-__path__ = extend_path(__path__, __name__)

libs/py2/concurrent/futures/__init__.py

@@ -1,23 +0,0 @@
-# Copyright 2009 Brian Quinlan. All Rights Reserved.
-# Licensed to PSF under a Contributor Agreement.
-
-"""Execute computations asynchronously using threads or processes."""
-
-__author__ = 'Brian Quinlan (brian@sweetapp.com)'
-
-from concurrent.futures._base import (FIRST_COMPLETED,
-                                      FIRST_EXCEPTION,
-                                      ALL_COMPLETED,
-                                      CancelledError,
-                                      TimeoutError,
-                                      Future,
-                                      Executor,
-                                      wait,
-                                      as_completed)
-from concurrent.futures.thread import ThreadPoolExecutor
-
-try:
-    from concurrent.futures.process import ProcessPoolExecutor
-except ImportError:
-    # some platforms don't have multiprocessing
-    pass

libs/py2/concurrent/futures/_base.py

@@ -1,667 +0,0 @@
-# Copyright 2009 Brian Quinlan. All Rights Reserved.
-# Licensed to PSF under a Contributor Agreement.
-
-import collections
-import logging
-import threading
-import itertools
-import time
-import types
-
-__author__ = 'Brian Quinlan (brian@sweetapp.com)'
-
-FIRST_COMPLETED = 'FIRST_COMPLETED'
-FIRST_EXCEPTION = 'FIRST_EXCEPTION'
-ALL_COMPLETED = 'ALL_COMPLETED'
-_AS_COMPLETED = '_AS_COMPLETED'
-
-# Possible future states (for internal use by the futures package).
-PENDING = 'PENDING'
-RUNNING = 'RUNNING'
-# The future was cancelled by the user...
-CANCELLED = 'CANCELLED'
-# ...and _Waiter.add_cancelled() was called by a worker.
-CANCELLED_AND_NOTIFIED = 'CANCELLED_AND_NOTIFIED'
-FINISHED = 'FINISHED'
-
-_FUTURE_STATES = [
-    PENDING,
-    RUNNING,
-    CANCELLED,
-    CANCELLED_AND_NOTIFIED,
-    FINISHED
-]
-
-_STATE_TO_DESCRIPTION_MAP = {
-    PENDING: "pending",
-    RUNNING: "running",
-    CANCELLED: "cancelled",
-    CANCELLED_AND_NOTIFIED: "cancelled",
-    FINISHED: "finished"
-}
-
-# Logger for internal use by the futures package.
-LOGGER = logging.getLogger("concurrent.futures")
-
-class Error(Exception):
-    """Base class for all future-related exceptions."""
-    pass
-
-class CancelledError(Error):
-    """The Future was cancelled."""
-    pass
-
-class TimeoutError(Error):
-    """The operation exceeded the given deadline."""
-    pass
-
-class _Waiter(object):
-    """Provides the event that wait() and as_completed() block on."""
-    def __init__(self):
-        self.event = threading.Event()
-        self.finished_futures = []
-
-    def add_result(self, future):
-        self.finished_futures.append(future)
-
-    def add_exception(self, future):
-        self.finished_futures.append(future)
-
-    def add_cancelled(self, future):
-        self.finished_futures.append(future)
-
-class _AsCompletedWaiter(_Waiter):
-    """Used by as_completed()."""
-
-    def __init__(self):
-        super(_AsCompletedWaiter, self).__init__()
-        self.lock = threading.Lock()
-
-    def add_result(self, future):
-        with self.lock:
-            super(_AsCompletedWaiter, self).add_result(future)
-            self.event.set()
-
-    def add_exception(self, future):
-        with self.lock:
-            super(_AsCompletedWaiter, self).add_exception(future)
-            self.event.set()
-
-    def add_cancelled(self, future):
-        with self.lock:
-            super(_AsCompletedWaiter, self).add_cancelled(future)
-            self.event.set()
-
-class _FirstCompletedWaiter(_Waiter):
-    """Used by wait(return_when=FIRST_COMPLETED)."""
-
-    def add_result(self, future):
-        super(_FirstCompletedWaiter, self).add_result(future)
-        self.event.set()
-
-    def add_exception(self, future):
-        super(_FirstCompletedWaiter, self).add_exception(future)
-        self.event.set()
-
-    def add_cancelled(self, future):
-        super(_FirstCompletedWaiter, self).add_cancelled(future)
-        self.event.set()
-
-class _AllCompletedWaiter(_Waiter):
-    """Used by wait(return_when=FIRST_EXCEPTION and ALL_COMPLETED)."""
-
-    def __init__(self, num_pending_calls, stop_on_exception):
-        self.num_pending_calls = num_pending_calls
-        self.stop_on_exception = stop_on_exception
-        self.lock = threading.Lock()
-        super(_AllCompletedWaiter, self).__init__()
-
-    def _decrement_pending_calls(self):
-        with self.lock:
-            self.num_pending_calls -= 1
-            if not self.num_pending_calls:
-                self.event.set()
-
-    def add_result(self, future):
-        super(_AllCompletedWaiter, self).add_result(future)
-        self._decrement_pending_calls()
-
-    def add_exception(self, future):
-        super(_AllCompletedWaiter, self).add_exception(future)
-        if self.stop_on_exception:
-            self.event.set()
-        else:
-            self._decrement_pending_calls()
-
-    def add_cancelled(self, future):
-        super(_AllCompletedWaiter, self).add_cancelled(future)
-        self._decrement_pending_calls()
-
-class _AcquireFutures(object):
-    """A context manager that does an ordered acquire of Future conditions."""
-
-    def __init__(self, futures):
-        self.futures = sorted(futures, key=id)
-
-    def __enter__(self):
-        for future in self.futures:
-            future._condition.acquire()
-
-    def __exit__(self, *args):
-        for future in self.futures:
-            future._condition.release()
-
-def _create_and_install_waiters(fs, return_when):
-    if return_when == _AS_COMPLETED:
-        waiter = _AsCompletedWaiter()
-    elif return_when == FIRST_COMPLETED:
-        waiter = _FirstCompletedWaiter()
-    else:
-        pending_count = sum(
-                f._state not in [CANCELLED_AND_NOTIFIED, FINISHED] for f in fs)
-
-        if return_when == FIRST_EXCEPTION:
-            waiter = _AllCompletedWaiter(pending_count, stop_on_exception=True)
-        elif return_when == ALL_COMPLETED:
-            waiter = _AllCompletedWaiter(pending_count, stop_on_exception=False)
-        else:
-            raise ValueError("Invalid return condition: %r" % return_when)
-
-    for f in fs:
-        f._waiters.append(waiter)
-
-    return waiter
-
-
-def _yield_finished_futures(fs, waiter, ref_collect):
-    """
-    Iterate on the list *fs*, yielding finished futures one by one in
-    reverse order.
-    Before yielding a future, *waiter* is removed from its waiters
-    and the future is removed from each set in the collection of sets
-    *ref_collect*.
-
-    The aim of this function is to avoid keeping stale references after
-    the future is yielded and before the iterator resumes.
-    """
-    while fs:
-        f = fs[-1]
-        for futures_set in ref_collect:
-            futures_set.remove(f)
-        with f._condition:
-            f._waiters.remove(waiter)
-        del f
-        # Careful not to keep a reference to the popped value
-        yield fs.pop()
-
-
-def as_completed(fs, timeout=None):
-    """An iterator over the given futures that yields each as it completes.
-
-    Args:
-        fs: The sequence of Futures (possibly created by different Executors) to
-            iterate over.
-        timeout: The maximum number of seconds to wait. If None, then there
-            is no limit on the wait time.
-
-    Returns:
-        An iterator that yields the given Futures as they complete (finished or
-        cancelled). If any given Futures are duplicated, they will be returned
-        once.
-
-    Raises:
-        TimeoutError: If the entire result iterator could not be generated
-            before the given timeout.
-    """
-    if timeout is not None:
-        end_time = timeout + time.time()
-
-    fs = set(fs)
-    total_futures = len(fs)
-    with _AcquireFutures(fs):
-        finished = set(
-                f for f in fs
-                if f._state in [CANCELLED_AND_NOTIFIED, FINISHED])
-        pending = fs - finished
-        waiter = _create_and_install_waiters(fs, _AS_COMPLETED)
-    finished = list(finished)
-    try:
-        for f in _yield_finished_futures(finished, waiter,
-                                         ref_collect=(fs,)):
-            f = [f]
-            yield f.pop()
-
-        while pending:
-            if timeout is None:
-                wait_timeout = None
-            else:
-                wait_timeout = end_time - time.time()
-                if wait_timeout < 0:
-                    raise TimeoutError(
-                            '%d (of %d) futures unfinished' % (
-                            len(pending), total_futures))
-
-            waiter.event.wait(wait_timeout)
-
-            with waiter.lock:
-                finished = waiter.finished_futures
-                waiter.finished_futures = []
-                waiter.event.clear()
-
-            # reverse to keep finishing order
-            finished.reverse()
-            for f in _yield_finished_futures(finished, waiter,
-                                             ref_collect=(fs, pending)):
-                f = [f]
-                yield f.pop()
-
-    finally:
-        # Remove waiter from unfinished futures
-        for f in fs:
-            with f._condition:
-                f._waiters.remove(waiter)
-
-DoneAndNotDoneFutures = collections.namedtuple(
-        'DoneAndNotDoneFutures', 'done not_done')
-def wait(fs, timeout=None, return_when=ALL_COMPLETED):
-    """Wait for the futures in the given sequence to complete.
-
-    Args:
-        fs: The sequence of Futures (possibly created by different Executors) to
-            wait upon.
-        timeout: The maximum number of seconds to wait. If None, then there
-            is no limit on the wait time.
-        return_when: Indicates when this function should return. The options
-            are:
-
-            FIRST_COMPLETED - Return when any future finishes or is
-                              cancelled.
-            FIRST_EXCEPTION - Return when any future finishes by raising an
-                              exception. If no future raises an exception
-                              then it is equivalent to ALL_COMPLETED.
-            ALL_COMPLETED -   Return when all futures finish or are cancelled.
-
-    Returns:
-        A named 2-tuple of sets. The first set, named 'done', contains the
-        futures that completed (is finished or cancelled) before the wait
-        completed. The second set, named 'not_done', contains uncompleted
-        futures.
-    """
-    with _AcquireFutures(fs):
-        done = set(f for f in fs
-                   if f._state in [CANCELLED_AND_NOTIFIED, FINISHED])
-        not_done = set(fs) - done
-
-        if (return_when == FIRST_COMPLETED) and done:
-            return DoneAndNotDoneFutures(done, not_done)
-        elif (return_when == FIRST_EXCEPTION) and done:
-            if any(f for f in done
-                   if not f.cancelled() and f.exception() is not None):
-                return DoneAndNotDoneFutures(done, not_done)
-
-        if len(done) == len(fs):
-            return DoneAndNotDoneFutures(done, not_done)
-
-        waiter = _create_and_install_waiters(fs, return_when)
-
-    waiter.event.wait(timeout)
-    for f in fs:
-        with f._condition:
-            f._waiters.remove(waiter)
-
-    done.update(waiter.finished_futures)
-    return DoneAndNotDoneFutures(done, set(fs) - done)
-
-class Future(object):
-    """Represents the result of an asynchronous computation."""
-
-    def __init__(self):
-        """Initializes the future. Should not be called by clients."""
-        self._condition = threading.Condition()
-        self._state = PENDING
-        self._result = None
-        self._exception = None
-        self._traceback = None
-        self._waiters = []
-        self._done_callbacks = []
-
-    def _invoke_callbacks(self):
-        for callback in self._done_callbacks:
-            try:
-                callback(self)
-            except Exception:
-                LOGGER.exception('exception calling callback for %r', self)
-            except BaseException:
-                # Explicitly let all other new-style exceptions through so
-                # that we can catch all old-style exceptions with a simple
-                # "except:" clause below.
-                #
-                # All old-style exception objects are instances of
-                # types.InstanceType, but "except types.InstanceType:" does
-                # not catch old-style exceptions for some reason.  Thus, the
-                # only way to catch all old-style exceptions without catching
-                # any new-style exceptions is to filter out the new-style
-                # exceptions, which all derive from BaseException.
-                raise
-            except:
-                # Because of the BaseException clause above, this handler only
-                # executes for old-style exception objects.
-                LOGGER.exception('exception calling callback for %r', self)
-
-    def __repr__(self):
-        with self._condition:
-            if self._state == FINISHED:
-                if self._exception:
-                    return '<%s at %#x state=%s raised %s>' % (
-                        self.__class__.__name__,
-                        id(self),
-                        _STATE_TO_DESCRIPTION_MAP[self._state],
-                        self._exception.__class__.__name__)
-                else:
-                    return '<%s at %#x state=%s returned %s>' % (
-                        self.__class__.__name__,
-                        id(self),
-                        _STATE_TO_DESCRIPTION_MAP[self._state],
-                        self._result.__class__.__name__)
-            return '<%s at %#x state=%s>' % (
-                    self.__class__.__name__,
-                    id(self),
-                   _STATE_TO_DESCRIPTION_MAP[self._state])
-
-    def cancel(self):
-        """Cancel the future if possible.
-
-        Returns True if the future was cancelled, False otherwise. A future
-        cannot be cancelled if it is running or has already completed.
-        """
-        with self._condition:
-            if self._state in [RUNNING, FINISHED]:
-                return False
-
-            if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
-                return True
-
-            self._state = CANCELLED
-            self._condition.notify_all()
-
-        self._invoke_callbacks()
-        return True
-
-    def cancelled(self):
-        """Return True if the future was cancelled."""
-        with self._condition:
-            return self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]
-
-    def running(self):
-        """Return True if the future is currently executing."""
-        with self._condition:
-            return self._state == RUNNING
-
-    def done(self):
-        """Return True of the future was cancelled or finished executing."""
-        with self._condition:
-            return self._state in [CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED]
-
-    def __get_result(self):
-        if self._exception:
-            if isinstance(self._exception, types.InstanceType):
-                # The exception is an instance of an old-style class, which
-                # means type(self._exception) returns types.ClassType instead
-                # of the exception's actual class type.
-                exception_type = self._exception.__class__
-            else:
-                exception_type = type(self._exception)
-            raise exception_type, self._exception, self._traceback
-        else:
-            return self._result
-
-    def add_done_callback(self, fn):
-        """Attaches a callable that will be called when the future finishes.
-
-        Args:
-            fn: A callable that will be called with this future as its only
-                argument when the future completes or is cancelled. The callable
-                will always be called by a thread in the same process in which
-                it was added. If the future has already completed or been
-                cancelled then the callable will be called immediately. These
-                callables are called in the order that they were added.
-        """
-        with self._condition:
-            if self._state not in [CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED]:
-                self._done_callbacks.append(fn)
-                return
-        fn(self)
-
-    def result(self, timeout=None):
-        """Return the result of the call that the future represents.
-
-        Args:
-            timeout: The number of seconds to wait for the result if the future
-                isn't done. If None, then there is no limit on the wait time.
-
-        Returns:
-            The result of the call that the future represents.
-
-        Raises:
-            CancelledError: If the future was cancelled.
-            TimeoutError: If the future didn't finish executing before the given
-                timeout.
-            Exception: If the call raised then that exception will be raised.
-        """
-        with self._condition:
-            if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
-                raise CancelledError()
-            elif self._state == FINISHED:
-                return self.__get_result()
-
-            self._condition.wait(timeout)
-
-            if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
-                raise CancelledError()
-            elif self._state == FINISHED:
-                return self.__get_result()
-            else:
-                raise TimeoutError()
-
-    def exception_info(self, timeout=None):
-        """Return a tuple of (exception, traceback) raised by the call that the
-        future represents.
-
-        Args:
-            timeout: The number of seconds to wait for the exception if the
-                future isn't done. If None, then there is no limit on the wait
-                time.
-
-        Returns:
-            The exception raised by the call that the future represents or None
-            if the call completed without raising.
-
-        Raises:
-            CancelledError: If the future was cancelled.
-            TimeoutError: If the future didn't finish executing before the given
-                timeout.
-        """
-        with self._condition:
-            if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
-                raise CancelledError()
-            elif self._state == FINISHED:
-                return self._exception, self._traceback
-
-            self._condition.wait(timeout)
-
-            if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
-                raise CancelledError()
-            elif self._state == FINISHED:
-                return self._exception, self._traceback
-            else:
-                raise TimeoutError()
-
-    def exception(self, timeout=None):
-        """Return the exception raised by the call that the future represents.
-
-        Args:
-            timeout: The number of seconds to wait for the exception if the
-                future isn't done. If None, then there is no limit on the wait
-                time.
-
-        Returns:
-            The exception raised by the call that the future represents or None
-            if the call completed without raising.
-
-        Raises:
-            CancelledError: If the future was cancelled.
-            TimeoutError: If the future didn't finish executing before the given
-                timeout.
-        """
-        return self.exception_info(timeout)[0]
-
-    # The following methods should only be used by Executors and in tests.
-    def set_running_or_notify_cancel(self):
-        """Mark the future as running or process any cancel notifications.
-
-        Should only be used by Executor implementations and unit tests.
-
-        If the future has been cancelled (cancel() was called and returned
-        True) then any threads waiting on the future completing (though calls
-        to as_completed() or wait()) are notified and False is returned.
-
-        If the future was not cancelled then it is put in the running state
-        (future calls to running() will return True) and True is returned.
-
-        This method should be called by Executor implementations before
-        executing the work associated with this future. If this method returns
-        False then the work should not be executed.
-
-        Returns:
-            False if the Future was cancelled, True otherwise.
-
-        Raises:
-            RuntimeError: if this method was already called or if set_result()
-                or set_exception() was called.
-        """
-        with self._condition:
-            if self._state == CANCELLED:
-                self._state = CANCELLED_AND_NOTIFIED
-                for waiter in self._waiters:
-                    waiter.add_cancelled(self)
-                # self._condition.notify_all() is not necessary because
-                # self.cancel() triggers a notification.
-                return False
-            elif self._state == PENDING:
-                self._state = RUNNING
-                return True
-            else:
-                LOGGER.critical('Future %s in unexpected state: %s',
-                                id(self),
-                                self._state)
-                raise RuntimeError('Future in unexpected state')
-
-    def set_result(self, result):
-        """Sets the return value of work associated with the future.
-
-        Should only be used by Executor implementations and unit tests.
-        """
-        with self._condition:
-            self._result = result
-            self._state = FINISHED
-            for waiter in self._waiters:
-                waiter.add_result(self)
-            self._condition.notify_all()
-        self._invoke_callbacks()
-
-    def set_exception_info(self, exception, traceback):
-        """Sets the result of the future as being the given exception
-        and traceback.
-
-        Should only be used by Executor implementations and unit tests.
-        """
-        with self._condition:
-            self._exception = exception
-            self._traceback = traceback
-            self._state = FINISHED
-            for waiter in self._waiters:
-                waiter.add_exception(self)
-            self._condition.notify_all()
-        self._invoke_callbacks()
-
-    def set_exception(self, exception):
-        """Sets the result of the future as being the given exception.
-
-        Should only be used by Executor implementations and unit tests.
-        """
-        self.set_exception_info(exception, None)
-
-class Executor(object):
-    """This is an abstract base class for concrete asynchronous executors."""
-
-    def submit(self, fn, *args, **kwargs):
-        """Submits a callable to be executed with the given arguments.
-
-        Schedules the callable to be executed as fn(*args, **kwargs) and returns
-        a Future instance representing the execution of the callable.
-
-        Returns:
-            A Future representing the given call.
-        """
-        raise NotImplementedError()
-
-    def map(self, fn, *iterables, **kwargs):
-        """Returns an iterator equivalent to map(fn, iter).
-
-        Args:
-            fn: A callable that will take as many arguments as there are
-                passed iterables.
-            timeout: The maximum number of seconds to wait. If None, then there
-                is no limit on the wait time.
-
-        Returns:
-            An iterator equivalent to: map(func, *iterables) but the calls may
-            be evaluated out-of-order.
-
-        Raises:
-            TimeoutError: If the entire result iterator could not be generated
-                before the given timeout.
-            Exception: If fn(*args) raises for any values.
-        """
-        timeout = kwargs.get('timeout')
-        if timeout is not None:
-            end_time = timeout + time.time()
-
-        fs = [self.submit(fn, *args) for args in itertools.izip(*iterables)]
-
-        # Yield must be hidden in closure so that the futures are submitted
-        # before the first iterator value is required.
-        def result_iterator():
-            try:
-                # reverse to keep finishing order
-                fs.reverse()
-                while fs:
-                    # Careful not to keep a reference to the popped future
-                    if timeout is None:
-                        yield fs.pop().result()
-                    else:
-                        yield fs.pop().result(end_time - time.time())
-            finally:
-                for future in fs:
-                    future.cancel()
-        return result_iterator()
-
-    def shutdown(self, wait=True):
-        """Clean-up the resources associated with the Executor.
-
-        It is safe to call this method several times. Otherwise, no other
-        methods can be called after this one.
-
-        Args:
-            wait: If True then shutdown will not return until all running
-                futures have finished executing and the resources used by the
-                executor have been reclaimed.
-        """
-        pass
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        self.shutdown(wait=True)
-        return False

libs/py2/concurrent/futures/process.py

@@ -1,363 +0,0 @@
-# Copyright 2009 Brian Quinlan. All Rights Reserved.
-# Licensed to PSF under a Contributor Agreement.
-
-"""Implements ProcessPoolExecutor.
-
-The follow diagram and text describe the data-flow through the system:
-
-|======================= In-process =====================|== Out-of-process ==|
-
-+----------+     +----------+       +--------+     +-----------+    +---------+
-|          |  => | Work Ids |    => |        |  => | Call Q    | => |         |
-|          |     +----------+       |        |     +-----------+    |         |
-|          |     | ...      |       |        |     | ...       |    |         |
-|          |     | 6        |       |        |     | 5, call() |    |         |
-|          |     | 7        |       |        |     | ...       |    |         |
-| Process  |     | ...      |       | Local  |     +-----------+    | Process |
-|  Pool    |     +----------+       | Worker |                      |  #1..n  |
-| Executor |                        | Thread |                      |         |
-|          |     +----------- +     |        |     +-----------+    |         |
-|          | <=> | Work Items | <=> |        | <=  | Result Q  | <= |         |
-|          |     +------------+     |        |     +-----------+    |         |
-|          |     | 6: call()  |     |        |     | ...       |    |         |
-|          |     |    future  |     |        |     | 4, result |    |         |
-|          |     | ...        |     |        |     | 3, except |    |         |
-+----------+     +------------+     +--------+     +-----------+    +---------+
-
-Executor.submit() called:
-- creates a uniquely numbered _WorkItem and adds it to the "Work Items" dict
-- adds the id of the _WorkItem to the "Work Ids" queue
-
-Local worker thread:
-- reads work ids from the "Work Ids" queue and looks up the corresponding
-  WorkItem from the "Work Items" dict: if the work item has been cancelled then
-  it is simply removed from the dict, otherwise it is repackaged as a
-  _CallItem and put in the "Call Q". New _CallItems are put in the "Call Q"
-  until "Call Q" is full. NOTE: the size of the "Call Q" is kept small because
-  calls placed in the "Call Q" can no longer be cancelled with Future.cancel().
-- reads _ResultItems from "Result Q", updates the future stored in the
-  "Work Items" dict and deletes the dict entry
-
-Process #1..n:
-- reads _CallItems from "Call Q", executes the calls, and puts the resulting
-  _ResultItems in "Request Q"
-"""
-
-import atexit
-from concurrent.futures import _base
-import Queue as queue
-import multiprocessing
-import threading
-import weakref
-import sys
-
-__author__ = 'Brian Quinlan (brian@sweetapp.com)'
-
-# Workers are created as daemon threads and processes. This is done to allow the
-# interpreter to exit when there are still idle processes in a
-# ProcessPoolExecutor's process pool (i.e. shutdown() was not called). However,
-# allowing workers to die with the interpreter has two undesirable properties:
-#   - The workers would still be running during interpretor shutdown,
-#     meaning that they would fail in unpredictable ways.
-#   - The workers could be killed while evaluating a work item, which could
-#     be bad if the callable being evaluated has external side-effects e.g.
-#     writing to a file.
-#
-# To work around this problem, an exit handler is installed which tells the
-# workers to exit when their work queues are empty and then waits until the
-# threads/processes finish.
-
-_threads_queues = weakref.WeakKeyDictionary()
-_shutdown = False
-
-def _python_exit():
-    global _shutdown
-    _shutdown = True
-    items = list(_threads_queues.items()) if _threads_queues else ()
-    for t, q in items:
-        q.put(None)
-    for t, q in items:
-        t.join(sys.maxint)
-
-# Controls how many more calls than processes will be queued in the call queue.
-# A smaller number will mean that processes spend more time idle waiting for
-# work while a larger number will make Future.cancel() succeed less frequently
-# (Futures in the call queue cannot be cancelled).
-EXTRA_QUEUED_CALLS = 1
-
-class _WorkItem(object):
-    def __init__(self, future, fn, args, kwargs):
-        self.future = future
-        self.fn = fn
-        self.args = args
-        self.kwargs = kwargs
-
-class _ResultItem(object):
-    def __init__(self, work_id, exception=None, result=None):
-        self.work_id = work_id
-        self.exception = exception
-        self.result = result
-
-class _CallItem(object):
-    def __init__(self, work_id, fn, args, kwargs):
-        self.work_id = work_id
-        self.fn = fn
-        self.args = args
-        self.kwargs = kwargs
-
-def _process_worker(call_queue, result_queue):
-    """Evaluates calls from call_queue and places the results in result_queue.
-
-    This worker is run in a separate process.
-
-    Args:
-        call_queue: A multiprocessing.Queue of _CallItems that will be read and
-            evaluated by the worker.
-        result_queue: A multiprocessing.Queue of _ResultItems that will written
-            to by the worker.
-        shutdown: A multiprocessing.Event that will be set as a signal to the
-            worker that it should exit when call_queue is empty.
-    """
-    while True:
-        call_item = call_queue.get(block=True)
-        if call_item is None:
-            # Wake up queue management thread
-            result_queue.put(None)
-            return
-        try:
-            r = call_item.fn(*call_item.args, **call_item.kwargs)
-        except:
-            e = sys.exc_info()[1]
-            result_queue.put(_ResultItem(call_item.work_id,
-                                         exception=e))
-        else:
-            result_queue.put(_ResultItem(call_item.work_id,
-                                         result=r))
-
-def _add_call_item_to_queue(pending_work_items,
-                            work_ids,
-                            call_queue):
-    """Fills call_queue with _WorkItems from pending_work_items.
-
-    This function never blocks.
-
-    Args:
-        pending_work_items: A dict mapping work ids to _WorkItems e.g.
-            {5: <_WorkItem...>, 6: <_WorkItem...>, ...}
-        work_ids: A queue.Queue of work ids e.g. Queue([5, 6, ...]). Work ids
-            are consumed and the corresponding _WorkItems from
-            pending_work_items are transformed into _CallItems and put in
-            call_queue.
-        call_queue: A multiprocessing.Queue that will be filled with _CallItems
-            derived from _WorkItems.
-    """
-    while True:
-        if call_queue.full():
-            return
-        try:
-            work_id = work_ids.get(block=False)
-        except queue.Empty:
-            return
-        else:
-            work_item = pending_work_items[work_id]
-
-            if work_item.future.set_running_or_notify_cancel():
-                call_queue.put(_CallItem(work_id,
-                                         work_item.fn,
-                                         work_item.args,
-                                         work_item.kwargs),
-                               block=True)
-            else:
-                del pending_work_items[work_id]
-                continue
-
-def _queue_management_worker(executor_reference,
-                             processes,
-                             pending_work_items,
-                             work_ids_queue,
-                             call_queue,
-                             result_queue):
-    """Manages the communication between this process and the worker processes.
-
-    This function is run in a local thread.
-
-    Args:
-        executor_reference: A weakref.ref to the ProcessPoolExecutor that owns
-            this thread. Used to determine if the ProcessPoolExecutor has been
-            garbage collected and that this function can exit.
-        process: A list of the multiprocessing.Process instances used as
-            workers.
-        pending_work_items: A dict mapping work ids to _WorkItems e.g.
-            {5: <_WorkItem...>, 6: <_WorkItem...>, ...}
-        work_ids_queue: A queue.Queue of work ids e.g. Queue([5, 6, ...]).
-        call_queue: A multiprocessing.Queue that will be filled with _CallItems
-            derived from _WorkItems for processing by the process workers.
-        result_queue: A multiprocessing.Queue of _ResultItems generated by the
-            process workers.
-    """
-    nb_shutdown_processes = [0]
-    def shutdown_one_process():
-        """Tell a worker to terminate, which will in turn wake us again"""
-        call_queue.put(None)
-        nb_shutdown_processes[0] += 1
-    while True:
-        _add_call_item_to_queue(pending_work_items,
-                                work_ids_queue,
-                                call_queue)
-
-        result_item = result_queue.get(block=True)
-        if result_item is not None:
-            work_item = pending_work_items[result_item.work_id]
-            del pending_work_items[result_item.work_id]
-
-            if result_item.exception:
-                work_item.future.set_exception(result_item.exception)
-            else:
-                work_item.future.set_result(result_item.result)
-            # Delete references to object. See issue16284
-            del work_item
-        # Check whether we should start shutting down.
-        executor = executor_reference()
-        # No more work items can be added if:
-        #   - The interpreter is shutting down OR
-        #   - The executor that owns this worker has been collected OR
-        #   - The executor that owns this worker has been shutdown.
-        if _shutdown or executor is None or executor._shutdown_thread:
-            # Since no new work items can be added, it is safe to shutdown
-            # this thread if there are no pending work items.
-            if not pending_work_items:
-                while nb_shutdown_processes[0] < len(processes):
-                    shutdown_one_process()
-                # If .join() is not called on the created processes then
-                # some multiprocessing.Queue methods may deadlock on Mac OS
-                # X.
-                for p in processes:
-                    p.join()
-                call_queue.close()
-                return
-        del executor
-
-_system_limits_checked = False
-_system_limited = None
-def _check_system_limits():
-    global _system_limits_checked, _system_limited
-    if _system_limits_checked:
-        if _system_limited:
-            raise NotImplementedError(_system_limited)
-    _system_limits_checked = True
-    try:
-        import os
-        nsems_max = os.sysconf("SC_SEM_NSEMS_MAX")
-    except (AttributeError, ValueError):
-        # sysconf not available or setting not available
-        return
-    if nsems_max == -1:
-        # indetermine limit, assume that limit is determined
-        # by available memory only
-        return
-    if nsems_max >= 256:
-        # minimum number of semaphores available
-        # according to POSIX
-        return
-    _system_limited = "system provides too few semaphores (%d available, 256 necessary)" % nsems_max
-    raise NotImplementedError(_system_limited)
-
-
-class ProcessPoolExecutor(_base.Executor):
-    def __init__(self, max_workers=None):
-        """Initializes a new ProcessPoolExecutor instance.
-
-        Args:
-            max_workers: The maximum number of processes that can be used to
-                execute the given calls. If None or not given then as many
-                worker processes will be created as the machine has processors.
-        """
-        _check_system_limits()
-
-        if max_workers is None:
-            self._max_workers = multiprocessing.cpu_count()
-        else:
-            if max_workers <= 0:
-                raise ValueError("max_workers must be greater than 0")
-
-            self._max_workers = max_workers
-
-        # Make the call queue slightly larger than the number of processes to
-        # prevent the worker processes from idling. But don't make it too big
-        # because futures in the call queue cannot be cancelled.
-        self._call_queue = multiprocessing.Queue(self._max_workers +
-                                                 EXTRA_QUEUED_CALLS)
-        self._result_queue = multiprocessing.Queue()
-        self._work_ids = queue.Queue()
-        self._queue_management_thread = None
-        self._processes = set()
-
-        # Shutdown is a two-step process.
-        self._shutdown_thread = False
-        self._shutdown_lock = threading.Lock()
-        self._queue_count = 0
-        self._pending_work_items = {}
-
-    def _start_queue_management_thread(self):
-        # When the executor gets lost, the weakref callback will wake up
-        # the queue management thread.
-        def weakref_cb(_, q=self._result_queue):
-            q.put(None)
-        if self._queue_management_thread is None:
-            self._queue_management_thread = threading.Thread(
-                    target=_queue_management_worker,
-                    args=(weakref.ref(self, weakref_cb),
-                          self._processes,
-                          self._pending_work_items,
-                          self._work_ids,
-                          self._call_queue,
-                          self._result_queue))
-            self._queue_management_thread.daemon = True
-            self._queue_management_thread.start()
-            _threads_queues[self._queue_management_thread] = self._result_queue
-
-    def _adjust_process_count(self):
-        for _ in range(len(self._processes), self._max_workers):
-            p = multiprocessing.Process(
-                    target=_process_worker,
-                    args=(self._call_queue,
-                          self._result_queue))
-            p.start()
-            self._processes.add(p)
-
-    def submit(self, fn, *args, **kwargs):
-        with self._shutdown_lock:
-            if self._shutdown_thread:
-                raise RuntimeError('cannot schedule new futures after shutdown')
-
-            f = _base.Future()
-            w = _WorkItem(f, fn, args, kwargs)
-
-            self._pending_work_items[self._queue_count] = w
-            self._work_ids.put(self._queue_count)
-            self._queue_count += 1
-            # Wake up queue management thread
-            self._result_queue.put(None)
-
-            self._start_queue_management_thread()
-            self._adjust_process_count()
-            return f
-    submit.__doc__ = _base.Executor.submit.__doc__
-
-    def shutdown(self, wait=True):
-        with self._shutdown_lock:
-            self._shutdown_thread = True
-        if self._queue_management_thread:
-            # Wake up queue management thread
-            self._result_queue.put(None)
-            if wait:
-                self._queue_management_thread.join(sys.maxint)
-        # To reduce the risk of openning too many files, remove references to
-        # objects that use file descriptors.
-        self._queue_management_thread = None
-        self._call_queue = None
-        self._result_queue = None
-        self._processes = None
-    shutdown.__doc__ = _base.Executor.shutdown.__doc__
-
-atexit.register(_python_exit)

libs/py2/concurrent/futures/thread.py

@@ -1,160 +0,0 @@
-# Copyright 2009 Brian Quinlan. All Rights Reserved.
-# Licensed to PSF under a Contributor Agreement.
-
-"""Implements ThreadPoolExecutor."""
-
-import atexit
-from concurrent.futures import _base
-import itertools
-import Queue as queue
-import threading
-import weakref
-import sys
-
-try:
-    from multiprocessing import cpu_count
-except ImportError:
-    # some platforms don't have multiprocessing
-    def cpu_count():
-        return None
-
-__author__ = 'Brian Quinlan (brian@sweetapp.com)'
-
-# Workers are created as daemon threads. This is done to allow the interpreter
-# to exit when there are still idle threads in a ThreadPoolExecutor's thread
-# pool (i.e. shutdown() was not called). However, allowing workers to die with
-# the interpreter has two undesirable properties:
-#   - The workers would still be running during interpretor shutdown,
-#     meaning that they would fail in unpredictable ways.
-#   - The workers could be killed while evaluating a work item, which could
-#     be bad if the callable being evaluated has external side-effects e.g.
-#     writing to a file.
-#
-# To work around this problem, an exit handler is installed which tells the
-# workers to exit when their work queues are empty and then waits until the
-# threads finish.
-
-_threads_queues = weakref.WeakKeyDictionary()
-_shutdown = False
-
-def _python_exit():
-    global _shutdown
-    _shutdown = True
-    items = list(_threads_queues.items()) if _threads_queues else ()
-    for t, q in items:
-        q.put(None)
-    for t, q in items:
-        t.join(sys.maxint)
-
-atexit.register(_python_exit)
-
-class _WorkItem(object):
-    def __init__(self, future, fn, args, kwargs):
-        self.future = future
-        self.fn = fn
-        self.args = args
-        self.kwargs = kwargs
-
-    def run(self):
-        if not self.future.set_running_or_notify_cancel():
-            return
-
-        try:
-            result = self.fn(*self.args, **self.kwargs)
-        except:
-            e, tb = sys.exc_info()[1:]
-            self.future.set_exception_info(e, tb)
-        else:
-            self.future.set_result(result)
-
-def _worker(executor_reference, work_queue):
-    try:
-        while True:
-            work_item = work_queue.get(block=True)
-            if work_item is not None:
-                work_item.run()
-                # Delete references to object. See issue16284
-                del work_item
-                continue
-            executor = executor_reference()
-            # Exit if:
-            #   - The interpreter is shutting down OR
-            #   - The executor that owns the worker has been collected OR
-            #   - The executor that owns the worker has been shutdown.
-            if _shutdown or executor is None or executor._shutdown:
-                # Notice other workers
-                work_queue.put(None)
-                return
-            del executor
-    except:
-        _base.LOGGER.critical('Exception in worker', exc_info=True)
-
-
-class ThreadPoolExecutor(_base.Executor):
-
-    # Used to assign unique thread names when thread_name_prefix is not supplied.
-    _counter = itertools.count().next
-
-    def __init__(self, max_workers=None, thread_name_prefix=''):
-        """Initializes a new ThreadPoolExecutor instance.
-
-        Args:
-            max_workers: The maximum number of threads that can be used to
-                execute the given calls.
-            thread_name_prefix: An optional name prefix to give our threads.
-        """
-        if max_workers is None:
-            # Use this number because ThreadPoolExecutor is often
-            # used to overlap I/O instead of CPU work.
-            max_workers = (cpu_count() or 1) * 5
-        if max_workers <= 0:
-            raise ValueError("max_workers must be greater than 0")
-
-        self._max_workers = max_workers
-        self._work_queue = queue.Queue()
-        self._threads = set()
-        self._shutdown = False
-        self._shutdown_lock = threading.Lock()
-        self._thread_name_prefix = (thread_name_prefix or
-                                    ("ThreadPoolExecutor-%d" % self._counter()))
-
-    def submit(self, fn, *args, **kwargs):
-        with self._shutdown_lock:
-            if self._shutdown:
-                raise RuntimeError('cannot schedule new futures after shutdown')
-
-            f = _base.Future()
-            w = _WorkItem(f, fn, args, kwargs)
-
-            self._work_queue.put(w)
-            self._adjust_thread_count()
-            return f
-    submit.__doc__ = _base.Executor.submit.__doc__
-
-    def _adjust_thread_count(self):
-        # When the executor gets lost, the weakref callback will wake up
-        # the worker threads.
-        def weakref_cb(_, q=self._work_queue):
-            q.put(None)
-        # TODO(bquinlan): Should avoid creating new threads if there are more
-        # idle threads than items in the work queue.
-        num_threads = len(self._threads)
-        if num_threads < self._max_workers:
-            thread_name = '%s_%d' % (self._thread_name_prefix or self,
-                                     num_threads)
-            t = threading.Thread(name=thread_name, target=_worker,
-                                 args=(weakref.ref(self, weakref_cb),
-                                       self._work_queue))
-            t.daemon = True
-            t.start()
-            self._threads.add(t)
-            _threads_queues[t] = self._work_queue
-
-    def shutdown(self, wait=True):
-        with self._shutdown_lock:
-            self._shutdown = True
-            self._work_queue.put(None)
-        if wait:
-            for t in self._threads:
-                t.join(sys.maxint)
-    shutdown.__doc__ = _base.Executor.shutdown.__doc__

libs/py2/enum/LICENSE

@@ -1,32 +0,0 @@
-Copyright (c) 2013, Ethan Furman.
-All rights reserved.
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions
-are met:
-
-    Redistributions of source code must retain the above
-    copyright notice, this list of conditions and the
-    following disclaimer.
-
-    Redistributions in binary form must reproduce the above
-    copyright notice, this list of conditions and the following
-    disclaimer in the documentation and/or other materials
-    provided with the distribution.
-
-    Neither the name Ethan Furman nor the names of any
-    contributors may be used to endorse or promote products
-    derived from this software without specific prior written
-    permission.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
-AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
-IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
-LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
-CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
-SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
-CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
-ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.

libs/py2/enum/README

@@ -1,3 +0,0 @@
-enum34 is the new Python stdlib enum module available in Python 3.4
-backported for previous versions of Python from 2.4 to 3.3.
-tested on 2.6, 2.7, and 3.3+

libs/py2/enum/__init__.py

@@ -1,837 +0,0 @@
-"""Python Enumerations"""
-
-import sys as _sys
-
-__all__ = ['Enum', 'IntEnum', 'unique']
-
-version = 1, 1, 6
-
-pyver = float('%s.%s' % _sys.version_info[:2])
-
-try:
-    any
-except NameError:
-    def any(iterable):
-        for element in iterable:
-            if element:
-                return True
-        return False
-
-try:
-    from collections import OrderedDict
-except ImportError:
-    OrderedDict = None
-
-try:
-    basestring
-except NameError:
-    # In Python 2 basestring is the ancestor of both str and unicode
-    # in Python 3 it's just str, but was missing in 3.1
-    basestring = str
-
-try:
-    unicode
-except NameError:
-    # In Python 3 unicode no longer exists (it's just str)
-    unicode = str
-
-class _RouteClassAttributeToGetattr(object):
-    """Route attribute access on a class to __getattr__.
-
-    This is a descriptor, used to define attributes that act differently when
-    accessed through an instance and through a class.  Instance access remains
-    normal, but access to an attribute through a class will be routed to the
-    class's __getattr__ method; this is done by raising AttributeError.
-
-    """
-    def __init__(self, fget=None):
-        self.fget = fget
-
-    def __get__(self, instance, ownerclass=None):
-        if instance is None:
-            raise AttributeError()
-        return self.fget(instance)
-
-    def __set__(self, instance, value):
-        raise AttributeError("can't set attribute")
-
-    def __delete__(self, instance):
-        raise AttributeError("can't delete attribute")
-
-
-def _is_descriptor(obj):
-    """Returns True if obj is a descriptor, False otherwise."""
-    return (
-            hasattr(obj, '__get__') or
-            hasattr(obj, '__set__') or
-            hasattr(obj, '__delete__'))
-
-
-def _is_dunder(name):
-    """Returns True if a __dunder__ name, False otherwise."""
-    return (name[:2] == name[-2:] == '__' and
-            name[2:3] != '_' and
-            name[-3:-2] != '_' and
-            len(name) > 4)
-
-
-def _is_sunder(name):
-    """Returns True if a _sunder_ name, False otherwise."""
-    return (name[0] == name[-1] == '_' and
-            name[1:2] != '_' and
-            name[-2:-1] != '_' and
-            len(name) > 2)
-
-
-def _make_class_unpicklable(cls):
-    """Make the given class un-picklable."""
-    def _break_on_call_reduce(self, protocol=None):
-        raise TypeError('%r cannot be pickled' % self)
-    cls.__reduce_ex__ = _break_on_call_reduce
-    cls.__module__ = '<unknown>'
-
-
-class _EnumDict(dict):
-    """Track enum member order and ensure member names are not reused.
-
-    EnumMeta will use the names found in self._member_names as the
-    enumeration member names.
-
-    """
-    def __init__(self):
-        super(_EnumDict, self).__init__()
-        self._member_names = []
-
-    def __setitem__(self, key, value):
-        """Changes anything not dundered or not a descriptor.
-
-        If a descriptor is added with the same name as an enum member, the name
-        is removed from _member_names (this may leave a hole in the numerical
-        sequence of values).
-
-        If an enum member name is used twice, an error is raised; duplicate
-        values are not checked for.
-
-        Single underscore (sunder) names are reserved.
-
-        Note:   in 3.x __order__ is simply discarded as a not necessary piece
-                leftover from 2.x
-
-        """
-        if pyver >= 3.0 and key in ('_order_', '__order__'):
-            return
-        elif key == '__order__':
-            key = '_order_'
-        if _is_sunder(key):
-            if key != '_order_':
-                raise ValueError('_names_ are reserved for future Enum use')
-        elif _is_dunder(key):
-            pass
-        elif key in self._member_names:
-            # descriptor overwriting an enum?
-            raise TypeError('Attempted to reuse key: %r' % key)
-        elif not _is_descriptor(value):
-            if key in self:
-                # enum overwriting a descriptor?
-                raise TypeError('Key already defined as: %r' % self[key])
-            self._member_names.append(key)
-        super(_EnumDict, self).__setitem__(key, value)
-
-
-# Dummy value for Enum as EnumMeta explicity checks for it, but of course until
-# EnumMeta finishes running the first time the Enum class doesn't exist.  This
-# is also why there are checks in EnumMeta like `if Enum is not None`
-Enum = None
-
-
-class EnumMeta(type):
-    """Metaclass for Enum"""
-    @classmethod
-    def __prepare__(metacls, cls, bases):
-        return _EnumDict()
-
-    def __new__(metacls, cls, bases, classdict):
-        # an Enum class is final once enumeration items have been defined; it
-        # cannot be mixed with other types (int, float, etc.) if it has an
-        # inherited __new__ unless a new __new__ is defined (or the resulting
-        # class will fail).
-        if type(classdict) is dict:
-            original_dict = classdict
-            classdict = _EnumDict()
-            for k, v in original_dict.items():
-                classdict[k] = v
-
-        member_type, first_enum = metacls._get_mixins_(bases)
-        __new__, save_new, use_args = metacls._find_new_(classdict, member_type,
-                                                        first_enum)
-        # save enum items into separate mapping so they don't get baked into
-        # the new class
-        members = dict((k, classdict[k]) for k in classdict._member_names)
-        for name in classdict._member_names:
-            del classdict[name]
-
-        # py2 support for definition order
-        _order_ = classdict.get('_order_')
-        if _order_ is None:
-            if pyver < 3.0:
-                try:
-                    _order_ = [name for (name, value) in sorted(members.items(), key=lambda item: item[1])]
-                except TypeError:
-                    _order_ = [name for name in sorted(members.keys())]
-            else:
-                _order_ = classdict._member_names
-        else:
-            del classdict['_order_']
-            if pyver < 3.0:
-                _order_ = _order_.replace(',', ' ').split()
-                aliases = [name for name in members if name not in _order_]
-                _order_ += aliases
-
-        # check for illegal enum names (any others?)
-        invalid_names = set(members) & set(['mro'])
-        if invalid_names:
-            raise ValueError('Invalid enum member name(s): %s' % (
-                ', '.join(invalid_names), ))
-
-        # save attributes from super classes so we know if we can take
-        # the shortcut of storing members in the class dict
-        base_attributes = set([a for b in bases for a in b.__dict__])
-        # create our new Enum type
-        enum_class = super(EnumMeta, metacls).__new__(metacls, cls, bases, classdict)
-        enum_class._member_names_ = []               # names in random order
-        if OrderedDict is not None:
-            enum_class._member_map_ = OrderedDict()
-        else:
-            enum_class._member_map_ = {}             # name->value map
-        enum_class._member_type_ = member_type
-
-        # Reverse value->name map for hashable values.
-        enum_class._value2member_map_ = {}
-
-        # instantiate them, checking for duplicates as we go
-        # we instantiate first instead of checking for duplicates first in case
-        # a custom __new__ is doing something funky with the values -- such as
-        # auto-numbering ;)
-        if __new__ is None:
-            __new__ = enum_class.__new__
-        for member_name in _order_:
-            value = members[member_name]
-            if not isinstance(value, tuple):
-                args = (value, )
-            else:
-                args = value
-            if member_type is tuple:   # special case for tuple enums
-                args = (args, )     # wrap it one more time
-            if not use_args or not args:
-                enum_member = __new__(enum_class)
-                if not hasattr(enum_member, '_value_'):
-                    enum_member._value_ = value
-            else:
-                enum_member = __new__(enum_class, *args)
-                if not hasattr(enum_member, '_value_'):
-                    enum_member._value_ = member_type(*args)
-            value = enum_member._value_
-            enum_member._name_ = member_name
-            enum_member.__objclass__ = enum_class
-            enum_member.__init__(*args)
-            # If another member with the same value was already defined, the
-            # new member becomes an alias to the existing one.
-            for name, canonical_member in enum_class._member_map_.items():
-                if canonical_member.value == enum_member._value_:
-                    enum_member = canonical_member
-                    break
-            else:
-                # Aliases don't appear in member names (only in __members__).
-                enum_class._member_names_.append(member_name)
-            # performance boost for any member that would not shadow
-            # a DynamicClassAttribute (aka _RouteClassAttributeToGetattr)
-            if member_name not in base_attributes:
-                setattr(enum_class, member_name, enum_member)
-            # now add to _member_map_
-            enum_class._member_map_[member_name] = enum_member
-            try:
-                # This may fail if value is not hashable. We can't add the value
-                # to the map, and by-value lookups for this value will be
-                # linear.
-                enum_class._value2member_map_[value] = enum_member
-            except TypeError:
-                pass
-
-
-        # If a custom type is mixed into the Enum, and it does not know how
-        # to pickle itself, pickle.dumps will succeed but pickle.loads will
-        # fail.  Rather than have the error show up later and possibly far
-        # from the source, sabotage the pickle protocol for this class so
-        # that pickle.dumps also fails.
-        #
-        # However, if the new class implements its own __reduce_ex__, do not
-        # sabotage -- it's on them to make sure it works correctly.  We use
-        # __reduce_ex__ instead of any of the others as it is preferred by
-        # pickle over __reduce__, and it handles all pickle protocols.
-        unpicklable = False
-        if '__reduce_ex__' not in classdict:
-            if member_type is not object:
-                methods = ('__getnewargs_ex__', '__getnewargs__',
-                        '__reduce_ex__', '__reduce__')
-                if not any(m in member_type.__dict__ for m in methods):
-                    _make_class_unpicklable(enum_class)
-                    unpicklable = True
-
-
-        # double check that repr and friends are not the mixin's or various
-        # things break (such as pickle)
-        for name in ('__repr__', '__str__', '__format__', '__reduce_ex__'):
-            class_method = getattr(enum_class, name)
-            obj_method = getattr(member_type, name, None)
-            enum_method = getattr(first_enum, name, None)
-            if name not in classdict and class_method is not enum_method:
-                if name == '__reduce_ex__' and unpicklable:
-                    continue
-                setattr(enum_class, name, enum_method)
-
-        # method resolution and int's are not playing nice
-        # Python's less than 2.6 use __cmp__
-
-        if pyver < 2.6:
-
-            if issubclass(enum_class, int):
-                setattr(enum_class, '__cmp__', getattr(int, '__cmp__'))
-
-        elif pyver < 3.0:
-
-            if issubclass(enum_class, int):
-                for method in (
-                        '__le__',
-                        '__lt__',
-                        '__gt__',
-                        '__ge__',
-                        '__eq__',
-                        '__ne__',
-                        '__hash__',
-                        ):
-                    setattr(enum_class, method, getattr(int, method))
-
-        # replace any other __new__ with our own (as long as Enum is not None,
-        # anyway) -- again, this is to support pickle
-        if Enum is not None:
-            # if the user defined their own __new__, save it before it gets
-            # clobbered in case they subclass later
-            if save_new:
-                setattr(enum_class, '__member_new__', enum_class.__dict__['__new__'])
-            setattr(enum_class, '__new__', Enum.__dict__['__new__'])
-        return enum_class
-
-    def __bool__(cls):
-        """
-        classes/types should always be True.
-        """
-        return True
-
-    def __call__(cls, value, names=None, module=None, type=None, start=1):
-        """Either returns an existing member, or creates a new enum class.
-
-        This method is used both when an enum class is given a value to match
-        to an enumeration member (i.e. Color(3)) and for the functional API
-        (i.e. Color = Enum('Color', names='red green blue')).
-
-        When used for the functional API: `module`, if set, will be stored in
-        the new class' __module__ attribute; `type`, if set, will be mixed in
-        as the first base class.
-
-        Note: if `module` is not set this routine will attempt to discover the
-        calling module by walking the frame stack; if this is unsuccessful
-        the resulting class will not be pickleable.
-
-        """
-        if names is None:  # simple value lookup
-            return cls.__new__(cls, value)
-        # otherwise, functional API: we're creating a new Enum type
-        return cls._create_(value, names, module=module, type=type, start=start)
-
-    def __contains__(cls, member):
-        return isinstance(member, cls) and member.name in cls._member_map_
-
-    def __delattr__(cls, attr):
-        # nicer error message when someone tries to delete an attribute
-        # (see issue19025).
-        if attr in cls._member_map_:
-            raise AttributeError(
-                    "%s: cannot delete Enum member." % cls.__name__)
-        super(EnumMeta, cls).__delattr__(attr)
-
-    def __dir__(self):
-        return (['__class__', '__doc__', '__members__', '__module__'] +
-                self._member_names_)
-
-    @property
-    def __members__(cls):
-        """Returns a mapping of member name->value.
-
-        This mapping lists all enum members, including aliases. Note that this
-        is a copy of the internal mapping.
-
-        """
-        return cls._member_map_.copy()
-
-    def __getattr__(cls, name):
-        """Return the enum member matching `name`
-
-        We use __getattr__ instead of descriptors or inserting into the enum
-        class' __dict__ in order to support `name` and `value` being both
-        properties for enum members (which live in the class' __dict__) and
-        enum members themselves.
-
-        """
-        if _is_dunder(name):
-            raise AttributeError(name)
-        try:
-            return cls._member_map_[name]
-        except KeyError:
-            raise AttributeError(name)
-
-    def __getitem__(cls, name):
-        return cls._member_map_[name]
-
-    def __iter__(cls):
-        return (cls._member_map_[name] for name in cls._member_names_)
-
-    def __reversed__(cls):
-        return (cls._member_map_[name] for name in reversed(cls._member_names_))
-
-    def __len__(cls):
-        return len(cls._member_names_)
-
-    __nonzero__ = __bool__
-
-    def __repr__(cls):
-        return "<enum %r>" % cls.__name__
-
-    def __setattr__(cls, name, value):
-        """Block attempts to reassign Enum members.
-
-        A simple assignment to the class namespace only changes one of the
-        several possible ways to get an Enum member from the Enum class,
-        resulting in an inconsistent Enumeration.
-
-        """
-        member_map = cls.__dict__.get('_member_map_', {})
-        if name in member_map:
-            raise AttributeError('Cannot reassign members.')
-        super(EnumMeta, cls).__setattr__(name, value)
-
-    def _create_(cls, class_name, names=None, module=None, type=None, start=1):
-        """Convenience method to create a new Enum class.
-
-        `names` can be:
-
-        * A string containing member names, separated either with spaces or
-          commas.  Values are auto-numbered from 1.
-        * An iterable of member names.  Values are auto-numbered from 1.
-        * An iterable of (member name, value) pairs.
-        * A mapping of member name -> value.
-
-        """
-        if pyver < 3.0:
-            # if class_name is unicode, attempt a conversion to ASCII
-            if isinstance(class_name, unicode):
-                try:
-                    class_name = class_name.encode('ascii')
-                except UnicodeEncodeError:
-                    raise TypeError('%r is not representable in ASCII' % class_name)
-        metacls = cls.__class__
-        if type is None:
-            bases = (cls, )
-        else:
-            bases = (type, cls)
-        classdict = metacls.__prepare__(class_name, bases)
-        _order_ = []
-
-        # special processing needed for names?
-        if isinstance(names, basestring):
-            names = names.replace(',', ' ').split()
-        if isinstance(names, (tuple, list)) and isinstance(names[0], basestring):
-            names = [(e, i+start) for (i, e) in enumerate(names)]
-
-        # Here, names is either an iterable of (name, value) or a mapping.
-        item = None  # in case names is empty
-        for item in names:
-            if isinstance(item, basestring):
-                member_name, member_value = item, names[item]
-            else:
-                member_name, member_value = item
-            classdict[member_name] = member_value
-            _order_.append(member_name)
-        # only set _order_ in classdict if name/value was not from a mapping
-        if not isinstance(item, basestring):
-            classdict['_order_'] = ' '.join(_order_)
-        enum_class = metacls.__new__(metacls, class_name, bases, classdict)
-
-        # TODO: replace the frame hack if a blessed way to know the calling
-        # module is ever developed
-        if module is None:
-            try:
-                module = _sys._getframe(2).f_globals['__name__']
-            except (AttributeError, ValueError):
-                pass
-        if module is None:
-            _make_class_unpicklable(enum_class)
-        else:
-            enum_class.__module__ = module
-
-        return enum_class
-
-    @staticmethod
-    def _get_mixins_(bases):
-        """Returns the type for creating enum members, and the first inherited
-        enum class.
-
-        bases: the tuple of bases that was given to __new__
-
-        """
-        if not bases or Enum is None:
-            return object, Enum
-
-
-        # double check that we are not subclassing a class with existing
-        # enumeration members; while we're at it, see if any other data
-        # type has been mixed in so we can use the correct __new__
-        member_type = first_enum = None
-        for base in bases:
-            if  (base is not Enum and
-                    issubclass(base, Enum) and
-                    base._member_names_):
-                raise TypeError("Cannot extend enumerations")
-        # base is now the last base in bases
-        if not issubclass(base, Enum):
-            raise TypeError("new enumerations must be created as "
-                    "`ClassName([mixin_type,] enum_type)`")
-
-        # get correct mix-in type (either mix-in type of Enum subclass, or
-        # first base if last base is Enum)
-        if not issubclass(bases[0], Enum):
-            member_type = bases[0]     # first data type
-            first_enum = bases[-1]  # enum type
-        else:
-            for base in bases[0].__mro__:
-                # most common: (IntEnum, int, Enum, object)
-                # possible:    (<Enum 'AutoIntEnum'>, <Enum 'IntEnum'>,
-                #               <class 'int'>, <Enum 'Enum'>,
-                #               <class 'object'>)
-                if issubclass(base, Enum):
-                    if first_enum is None:
-                        first_enum = base
-                else:
-                    if member_type is None:
-                        member_type = base
-
-        return member_type, first_enum
-
-    if pyver < 3.0:
-        @staticmethod
-        def _find_new_(classdict, member_type, first_enum):
-            """Returns the __new__ to be used for creating the enum members.
-
-            classdict: the class dictionary given to __new__
-            member_type: the data type whose __new__ will be used by default
-            first_enum: enumeration to check for an overriding __new__
-
-            """
-            # now find the correct __new__, checking to see of one was defined
-            # by the user; also check earlier enum classes in case a __new__ was
-            # saved as __member_new__
-            __new__ = classdict.get('__new__', None)
-            if __new__:
-                return None, True, True      # __new__, save_new, use_args
-
-            N__new__ = getattr(None, '__new__')
-            O__new__ = getattr(object, '__new__')
-            if Enum is None:
-                E__new__ = N__new__
-            else:
-                E__new__ = Enum.__dict__['__new__']
-            # check all possibles for __member_new__ before falling back to
-            # __new__
-            for method in ('__member_new__', '__new__'):
-                for possible in (member_type, first_enum):
-                    try:
-                        target = possible.__dict__[method]
-                    except (AttributeError, KeyError):
-                        target = getattr(possible, method, None)
-                    if target not in [
-                            None,
-                            N__new__,
-                            O__new__,
-                            E__new__,
-                            ]:
-                        if method == '__member_new__':
-                            classdict['__new__'] = target
-                            return None, False, True
-                        if isinstance(target, staticmethod):
-                            target = target.__get__(member_type)
-                        __new__ = target
-                        break
-                if __new__ is not None:
-                    break
-            else:
-                __new__ = object.__new__
-
-            # if a non-object.__new__ is used then whatever value/tuple was
-            # assigned to the enum member name will be passed to __new__ and to the
-            # new enum member's __init__
-            if __new__ is object.__new__:
-                use_args = False
-            else:
-                use_args = True
-
-            return __new__, False, use_args
-    else:
-        @staticmethod
-        def _find_new_(classdict, member_type, first_enum):
-            """Returns the __new__ to be used for creating the enum members.
-
-            classdict: the class dictionary given to __new__
-            member_type: the data type whose __new__ will be used by default
-            first_enum: enumeration to check for an overriding __new__
-
-            """
-            # now find the correct __new__, checking to see of one was defined
-            # by the user; also check earlier enum classes in case a __new__ was
-            # saved as __member_new__
-            __new__ = classdict.get('__new__', None)
-
-            # should __new__ be saved as __member_new__ later?
-            save_new = __new__ is not None
-
-            if __new__ is None:
-                # check all possibles for __member_new__ before falling back to
-                # __new__
-                for method in ('__member_new__', '__new__'):
-                    for possible in (member_type, first_enum):
-                        target = getattr(possible, method, None)
-                        if target not in (
-                                None,
-                                None.__new__,
-                                object.__new__,
-                                Enum.__new__,
-                                ):
-                            __new__ = target
-                            break
-                    if __new__ is not None:
-                        break
-                else:
-                    __new__ = object.__new__
-
-            # if a non-object.__new__ is used then whatever value/tuple was
-            # assigned to the enum member name will be passed to __new__ and to the
-            # new enum member's __init__
-            if __new__ is object.__new__:
-                use_args = False
-            else:
-                use_args = True
-
-            return __new__, save_new, use_args
-
-
-########################################################
-# In order to support Python 2 and 3 with a single
-# codebase we have to create the Enum methods separately
-# and then use the `type(name, bases, dict)` method to
-# create the class.
-########################################################
-temp_enum_dict = {}
-temp_enum_dict['__doc__'] = "Generic enumeration.\n\n    Derive from this class to define new enumerations.\n\n"
-
-def __new__(cls, value):
-    # all enum instances are actually created during class construction
-    # without calling this method; this method is called by the metaclass'
-    # __call__ (i.e. Color(3) ), and by pickle
-    if type(value) is cls:
-        # For lookups like Color(Color.red)
-        value = value.value
-        #return value
-    # by-value search for a matching enum member
-    # see if it's in the reverse mapping (for hashable values)
-    try:
-        if value in cls._value2member_map_:
-            return cls._value2member_map_[value]
-    except TypeError:
-        # not there, now do long search -- O(n) behavior
-        for member in cls._member_map_.values():
-            if member.value == value:
-                return member
-    raise ValueError("%s is not a valid %s" % (value, cls.__name__))
-temp_enum_dict['__new__'] = __new__
-del __new__
-
-def __repr__(self):
-    return "<%s.%s: %r>" % (
-            self.__class__.__name__, self._name_, self._value_)
-temp_enum_dict['__repr__'] = __repr__
-del __repr__
-
-def __str__(self):
-    return "%s.%s" % (self.__class__.__name__, self._name_)
-temp_enum_dict['__str__'] = __str__
-del __str__
-
-if pyver >= 3.0:
-    def __dir__(self):
-        added_behavior = [
-                m
-                for cls in self.__class__.mro()
-                for m in cls.__dict__
-                if m[0] != '_' and m not in self._member_map_
-                ]
-        return (['__class__', '__doc__', '__module__', ] + added_behavior)
-    temp_enum_dict['__dir__'] = __dir__
-    del __dir__
-
-def __format__(self, format_spec):
-    # mixed-in Enums should use the mixed-in type's __format__, otherwise
-    # we can get strange results with the Enum name showing up instead of
-    # the value
-
-    # pure Enum branch
-    if self._member_type_ is object:
-        cls = str
-        val = str(self)
-    # mix-in branch
-    else:
-        cls = self._member_type_
-        val = self.value
-    return cls.__format__(val, format_spec)
-temp_enum_dict['__format__'] = __format__
-del __format__
-
-
-####################################
-# Python's less than 2.6 use __cmp__
-
-if pyver < 2.6:
-
-    def __cmp__(self, other):
-        if type(other) is self.__class__:
-            if self is other:
-                return 0
-            return -1
-        return NotImplemented
-        raise TypeError("unorderable types: %s() and %s()" % (self.__class__.__name__, other.__class__.__name__))
-    temp_enum_dict['__cmp__'] = __cmp__
-    del __cmp__
-
-else:
-
-    def __le__(self, other):
-        raise TypeError("unorderable types: %s() <= %s()" % (self.__class__.__name__, other.__class__.__name__))
-    temp_enum_dict['__le__'] = __le__
-    del __le__
-
-    def __lt__(self, other):
-        raise TypeError("unorderable types: %s() < %s()" % (self.__class__.__name__, other.__class__.__name__))
-    temp_enum_dict['__lt__'] = __lt__
-    del __lt__
-
-    def __ge__(self, other):
-        raise TypeError("unorderable types: %s() >= %s()" % (self.__class__.__name__, other.__class__.__name__))
-    temp_enum_dict['__ge__'] = __ge__
-    del __ge__
-
-    def __gt__(self, other):
-        raise TypeError("unorderable types: %s() > %s()" % (self.__class__.__name__, other.__class__.__name__))
-    temp_enum_dict['__gt__'] = __gt__
-    del __gt__
-
-
-def __eq__(self, other):
-    if type(other) is self.__class__:
-        return self is other
-    return NotImplemented
-temp_enum_dict['__eq__'] = __eq__
-del __eq__
-
-def __ne__(self, other):
-    if type(other) is self.__class__:
-        return self is not other
-    return NotImplemented
-temp_enum_dict['__ne__'] = __ne__
-del __ne__
-
-def __hash__(self):
-    return hash(self._name_)
-temp_enum_dict['__hash__'] = __hash__
-del __hash__
-
-def __reduce_ex__(self, proto):
-    return self.__class__, (self._value_, )
-temp_enum_dict['__reduce_ex__'] = __reduce_ex__
-del __reduce_ex__
-
-# _RouteClassAttributeToGetattr is used to provide access to the `name`
-# and `value` properties of enum members while keeping some measure of
-# protection from modification, while still allowing for an enumeration
-# to have members named `name` and `value`.  This works because enumeration
-# members are not set directly on the enum class -- __getattr__ is
-# used to look them up.
-
-@_RouteClassAttributeToGetattr
-def name(self):
-    return self._name_
-temp_enum_dict['name'] = name
-del name
-
-@_RouteClassAttributeToGetattr
-def value(self):
-    return self._value_
-temp_enum_dict['value'] = value
-del value
-
-@classmethod
-def _convert(cls, name, module, filter, source=None):
-    """
-    Create a new Enum subclass that replaces a collection of global constants
-    """
-    # convert all constants from source (or module) that pass filter() to
-    # a new Enum called name, and export the enum and its members back to
-    # module;
-    # also, replace the __reduce_ex__ method so unpickling works in
-    # previous Python versions
-    module_globals = vars(_sys.modules[module])
-    if source:
-        source = vars(source)
-    else:
-        source = module_globals
-    members = dict((name, value) for name, value in source.items() if filter(name))
-    cls = cls(name, members, module=module)
-    cls.__reduce_ex__ = _reduce_ex_by_name
-    module_globals.update(cls.__members__)
-    module_globals[name] = cls
-    return cls
-temp_enum_dict['_convert'] = _convert
-del _convert
-
-Enum = EnumMeta('Enum', (object, ), temp_enum_dict)
-del temp_enum_dict
-
-# Enum has now been created
-###########################
-
-class IntEnum(int, Enum):
-    """Enum where members are also (and must be) ints"""
-
-def _reduce_ex_by_name(self, proto):
-    return self.name
-
-def unique(enumeration):
-    """Class decorator that ensures only unique members exist in an enumeration."""
-    duplicates = []
-    for name, member in enumeration.__members__.items():
-        if name != member.name:
-            duplicates.append((name, member.name))
-    if duplicates:
-        duplicate_names = ', '.join(
-                ["%s -> %s" % (alias, name) for (alias, name) in duplicates]
-                )
-        raise ValueError('duplicate names found in %r: %s' %
-                (enumeration, duplicate_names)
-                )
-    return enumeration

libs/py2/yaml/__init__.py

@@ -1,315 +0,0 @@
-
-from error import *
-
-from tokens import *
-from events import *
-from nodes import *
-
-from loader import *
-from dumper import *
-
-__version__ = '3.13'
-
-try:
-    from cyaml import *
-    __with_libyaml__ = True
-except ImportError:
-    __with_libyaml__ = False
-
-def scan(stream, Loader=Loader):
-    """
-    Scan a YAML stream and produce scanning tokens.
-    """
-    loader = Loader(stream)
-    try:
-        while loader.check_token():
-            yield loader.get_token()
-    finally:
-        loader.dispose()
-
-def parse(stream, Loader=Loader):
-    """
-    Parse a YAML stream and produce parsing events.
-    """
-    loader = Loader(stream)
-    try:
-        while loader.check_event():
-            yield loader.get_event()
-    finally:
-        loader.dispose()
-
-def compose(stream, Loader=Loader):
-    """
-    Parse the first YAML document in a stream
-    and produce the corresponding representation tree.
-    """
-    loader = Loader(stream)
-    try:
-        return loader.get_single_node()
-    finally:
-        loader.dispose()
-
-def compose_all(stream, Loader=Loader):
-    """
-    Parse all YAML documents in a stream
-    and produce corresponding representation trees.
-    """
-    loader = Loader(stream)
-    try:
-        while loader.check_node():
-            yield loader.get_node()
-    finally:
-        loader.dispose()
-
-def load(stream, Loader=Loader):
-    """
-    Parse the first YAML document in a stream
-    and produce the corresponding Python object.
-    """
-    loader = Loader(stream)
-    try:
-        return loader.get_single_data()
-    finally:
-        loader.dispose()
-
-def load_all(stream, Loader=Loader):
-    """
-    Parse all YAML documents in a stream
-    and produce corresponding Python objects.
-    """
-    loader = Loader(stream)
-    try:
-        while loader.check_data():
-            yield loader.get_data()
-    finally:
-        loader.dispose()
-
-def safe_load(stream):
-    """
-    Parse the first YAML document in a stream
-    and produce the corresponding Python object.
-    Resolve only basic YAML tags.
-    """
-    return load(stream, SafeLoader)
-
-def safe_load_all(stream):
-    """
-    Parse all YAML documents in a stream
-    and produce corresponding Python objects.
-    Resolve only basic YAML tags.
-    """
-    return load_all(stream, SafeLoader)
-
-def emit(events, stream=None, Dumper=Dumper,
-        canonical=None, indent=None, width=None,
-        allow_unicode=None, line_break=None):
-    """
-    Emit YAML parsing events into a stream.
-    If stream is None, return the produced string instead.
-    """
-    getvalue = None
-    if stream is None:
-        from StringIO import StringIO
-        stream = StringIO()
-        getvalue = stream.getvalue
-    dumper = Dumper(stream, canonical=canonical, indent=indent, width=width,
-            allow_unicode=allow_unicode, line_break=line_break)
-    try:
-        for event in events:
-            dumper.emit(event)
-    finally:
-        dumper.dispose()
-    if getvalue:
-        return getvalue()
-
-def serialize_all(nodes, stream=None, Dumper=Dumper,
-        canonical=None, indent=None, width=None,
-        allow_unicode=None, line_break=None,
-        encoding='utf-8', explicit_start=None, explicit_end=None,
-        version=None, tags=None):
-    """
-    Serialize a sequence of representation trees into a YAML stream.
-    If stream is None, return the produced string instead.
-    """
-    getvalue = None
-    if stream is None:
-        if encoding is None:
-            from StringIO import StringIO
-        else:
-            from cStringIO import StringIO
-        stream = StringIO()
-        getvalue = stream.getvalue
-    dumper = Dumper(stream, canonical=canonical, indent=indent, width=width,
-            allow_unicode=allow_unicode, line_break=line_break,
-            encoding=encoding, version=version, tags=tags,
-            explicit_start=explicit_start, explicit_end=explicit_end)
-    try:
-        dumper.open()
-        for node in nodes:
-            dumper.serialize(node)
-        dumper.close()
-    finally:
-        dumper.dispose()
-    if getvalue:
-        return getvalue()
-
-def serialize(node, stream=None, Dumper=Dumper, **kwds):
-    """
-    Serialize a representation tree into a YAML stream.
-    If stream is None, return the produced string instead.
-    """
-    return serialize_all([node], stream, Dumper=Dumper, **kwds)
-
-def dump_all(documents, stream=None, Dumper=Dumper,
-        default_style=None, default_flow_style=None,
-        canonical=None, indent=None, width=None,
-        allow_unicode=None, line_break=None,
-        encoding='utf-8', explicit_start=None, explicit_end=None,
-        version=None, tags=None):
-    """
-    Serialize a sequence of Python objects into a YAML stream.
-    If stream is None, return the produced string instead.
-    """
-    getvalue = None
-    if stream is None:
-        if encoding is None:
-            from StringIO import StringIO
-        else:
-            from cStringIO import StringIO
-        stream = StringIO()
-        getvalue = stream.getvalue
-    dumper = Dumper(stream, default_style=default_style,
-            default_flow_style=default_flow_style,
-            canonical=canonical, indent=indent, width=width,
-            allow_unicode=allow_unicode, line_break=line_break,
-            encoding=encoding, version=version, tags=tags,
-            explicit_start=explicit_start, explicit_end=explicit_end)
-    try:
-        dumper.open()
-        for data in documents:
-            dumper.represent(data)
-        dumper.close()
-    finally:
-        dumper.dispose()
-    if getvalue:
-        return getvalue()
-
-def dump(data, stream=None, Dumper=Dumper, **kwds):
-    """
-    Serialize a Python object into a YAML stream.
-    If stream is None, return the produced string instead.
-    """
-    return dump_all([data], stream, Dumper=Dumper, **kwds)
-
-def safe_dump_all(documents, stream=None, **kwds):
-    """
-    Serialize a sequence of Python objects into a YAML stream.
-    Produce only basic YAML tags.
-    If stream is None, return the produced string instead.
-    """
-    return dump_all(documents, stream, Dumper=SafeDumper, **kwds)
-
-def safe_dump(data, stream=None, **kwds):
-    """
-    Serialize a Python object into a YAML stream.
-    Produce only basic YAML tags.
-    If stream is None, return the produced string instead.
-    """
-    return dump_all([data], stream, Dumper=SafeDumper, **kwds)
-
-def add_implicit_resolver(tag, regexp, first=None,
-        Loader=Loader, Dumper=Dumper):
-    """
-    Add an implicit scalar detector.
-    If an implicit scalar value matches the given regexp,
-    the corresponding tag is assigned to the scalar.
-    first is a sequence of possible initial characters or None.
-    """
-    Loader.add_implicit_resolver(tag, regexp, first)
-    Dumper.add_implicit_resolver(tag, regexp, first)
-
-def add_path_resolver(tag, path, kind=None, Loader=Loader, Dumper=Dumper):
-    """
-    Add a path based resolver for the given tag.
-    A path is a list of keys that forms a path
-    to a node in the representation tree.
-    Keys can be string values, integers, or None.
-    """
-    Loader.add_path_resolver(tag, path, kind)
-    Dumper.add_path_resolver(tag, path, kind)
-
-def add_constructor(tag, constructor, Loader=Loader):
-    """
-    Add a constructor for the given tag.
-    Constructor is a function that accepts a Loader instance
-    and a node object and produces the corresponding Python object.
-    """
-    Loader.add_constructor(tag, constructor)
-
-def add_multi_constructor(tag_prefix, multi_constructor, Loader=Loader):
-    """
-    Add a multi-constructor for the given tag prefix.
-    Multi-constructor is called for a node if its tag starts with tag_prefix.
-    Multi-constructor accepts a Loader instance, a tag suffix,
-    and a node object and produces the corresponding Python object.
-    """
-    Loader.add_multi_constructor(tag_prefix, multi_constructor)
-
-def add_representer(data_type, representer, Dumper=Dumper):
-    """
-    Add a representer for the given type.
-    Representer is a function accepting a Dumper instance
-    and an instance of the given data type
-    and producing the corresponding representation node.
-    """
-    Dumper.add_representer(data_type, representer)
-
-def add_multi_representer(data_type, multi_representer, Dumper=Dumper):
-    """
-    Add a representer for the given type.
-    Multi-representer is a function accepting a Dumper instance
-    and an instance of the given data type or subtype
-    and producing the corresponding representation node.
-    """
-    Dumper.add_multi_representer(data_type, multi_representer)
-
-class YAMLObjectMetaclass(type):
-    """
-    The metaclass for YAMLObject.
-    """
-    def __init__(cls, name, bases, kwds):
-        super(YAMLObjectMetaclass, cls).__init__(name, bases, kwds)
-        if 'yaml_tag' in kwds and kwds['yaml_tag'] is not None:
-            cls.yaml_loader.add_constructor(cls.yaml_tag, cls.from_yaml)
-            cls.yaml_dumper.add_representer(cls, cls.to_yaml)
-
-class YAMLObject(object):
-    """
-    An object that can dump itself to a YAML stream
-    and load itself from a YAML stream.
-    """
-
-    __metaclass__ = YAMLObjectMetaclass
-    __slots__ = ()  # no direct instantiation, so allow immutable subclasses
-
-    yaml_loader = Loader
-    yaml_dumper = Dumper
-
-    yaml_tag = None
-    yaml_flow_style = None
-
-    def from_yaml(cls, loader, node):
-        """
-        Convert a representation node to a Python object.
-        """
-        return loader.construct_yaml_object(node, cls)
-    from_yaml = classmethod(from_yaml)
-
-    def to_yaml(cls, dumper, data):
-        """
-        Convert a Python object to a representation node.
-        """
-        return dumper.represent_yaml_object(cls.yaml_tag, data, cls,
-                flow_style=cls.yaml_flow_style)
-    to_yaml = classmethod(to_yaml)
-

libs/py2/yaml/composer.py

@@ -1,139 +0,0 @@
-
-__all__ = ['Composer', 'ComposerError']
-
-from error import MarkedYAMLError
-from events import *
-from nodes import *
-
-class ComposerError(MarkedYAMLError):
-    pass
-
-class Composer(object):
-
-    def __init__(self):
-        self.anchors = {}
-
-    def check_node(self):
-        # Drop the STREAM-START event.
-        if self.check_event(StreamStartEvent):
-            self.get_event()
-
-        # If there are more documents available?
-        return not self.check_event(StreamEndEvent)
-
-    def get_node(self):
-        # Get the root node of the next document.
-        if not self.check_event(StreamEndEvent):
-            return self.compose_document()
-
-    def get_single_node(self):
-        # Drop the STREAM-START event.
-        self.get_event()
-
-        # Compose a document if the stream is not empty.
-        document = None
-        if not self.check_event(StreamEndEvent):
-            document = self.compose_document()
-
-        # Ensure that the stream contains no more documents.
-        if not self.check_event(StreamEndEvent):
-            event = self.get_event()
-            raise ComposerError("expected a single document in the stream",
-                    document.start_mark, "but found another document",
-                    event.start_mark)
-
-        # Drop the STREAM-END event.
-        self.get_event()
-
-        return document
-
-    def compose_document(self):
-        # Drop the DOCUMENT-START event.
-        self.get_event()
-
-        # Compose the root node.
-        node = self.compose_node(None, None)
-
-        # Drop the DOCUMENT-END event.
-        self.get_event()
-
-        self.anchors = {}
-        return node
-
-    def compose_node(self, parent, index):
-        if self.check_event(AliasEvent):
-            event = self.get_event()
-            anchor = event.anchor
-            if anchor not in self.anchors:
-                raise ComposerError(None, None, "found undefined alias %r"
-                        % anchor.encode('utf-8'), event.start_mark)
-            return self.anchors[anchor]
-        event = self.peek_event()
-        anchor = event.anchor
-        if anchor is not None:
-            if anchor in self.anchors:
-                raise ComposerError("found duplicate anchor %r; first occurence"
-                        % anchor.encode('utf-8'), self.anchors[anchor].start_mark,
-                        "second occurence", event.start_mark)
-        self.descend_resolver(parent, index)
-        if self.check_event(ScalarEvent):
-            node = self.compose_scalar_node(anchor)
-        elif self.check_event(SequenceStartEvent):
-            node = self.compose_sequence_node(anchor)
-        elif self.check_event(MappingStartEvent):
-            node = self.compose_mapping_node(anchor)
-        self.ascend_resolver()
-        return node
-
-    def compose_scalar_node(self, anchor):
-        event = self.get_event()
-        tag = event.tag
-        if tag is None or tag == u'!':
-            tag = self.resolve(ScalarNode, event.value, event.implicit)
-        node = ScalarNode(tag, event.value,
-                event.start_mark, event.end_mark, style=event.style)
-        if anchor is not None:
-            self.anchors[anchor] = node
-        return node
-
-    def compose_sequence_node(self, anchor):
-        start_event = self.get_event()
-        tag = start_event.tag
-        if tag is None or tag == u'!':
-            tag = self.resolve(SequenceNode, None, start_event.implicit)
-        node = SequenceNode(tag, [],
-                start_event.start_mark, None,
-                flow_style=start_event.flow_style)
-        if anchor is not None:
-            self.anchors[anchor] = node
-        index = 0
-        while not self.check_event(SequenceEndEvent):
-            node.value.append(self.compose_node(node, index))
-            index += 1
-        end_event = self.get_event()
-        node.end_mark = end_event.end_mark
-        return node
-
-    def compose_mapping_node(self, anchor):
-        start_event = self.get_event()
-        tag = start_event.tag
-        if tag is None or tag == u'!':
-            tag = self.resolve(MappingNode, None, start_event.implicit)
-        node = MappingNode(tag, [],
-                start_event.start_mark, None,
-                flow_style=start_event.flow_style)
-        if anchor is not None:
-            self.anchors[anchor] = node
-        while not self.check_event(MappingEndEvent):
-            #key_event = self.peek_event()
-            item_key = self.compose_node(node, None)
-            #if item_key in node.value:
-            #    raise ComposerError("while composing a mapping", start_event.start_mark,
-            #            "found duplicate key", key_event.start_mark)
-            item_value = self.compose_node(node, item_key)
-            #node.value[item_key] = item_value
-            node.value.append((item_key, item_value))
-        end_event = self.get_event()
-        node.end_mark = end_event.end_mark
-        return node
-

libs/py2/yaml/constructor.py

@@ -1,675 +0,0 @@
-
-__all__ = ['BaseConstructor', 'SafeConstructor', 'Constructor',
-    'ConstructorError']
-
-from error import *
-from nodes import *
-
-import datetime
-
-import binascii, re, sys, types
-
-class ConstructorError(MarkedYAMLError):
-    pass
-
-class BaseConstructor(object):
-
-    yaml_constructors = {}
-    yaml_multi_constructors = {}
-
-    def __init__(self):
-        self.constructed_objects = {}
-        self.recursive_objects = {}
-        self.state_generators = []
-        self.deep_construct = False
-
-    def check_data(self):
-        # If there are more documents available?
-        return self.check_node()
-
-    def get_data(self):
-        # Construct and return the next document.
-        if self.check_node():
-            return self.construct_document(self.get_node())
-
-    def get_single_data(self):
-        # Ensure that the stream contains a single document and construct it.
-        node = self.get_single_node()
-        if node is not None:
-            return self.construct_document(node)
-        return None
-
-    def construct_document(self, node):
-        data = self.construct_object(node)
-        while self.state_generators:
-            state_generators = self.state_generators
-            self.state_generators = []
-            for generator in state_generators:
-                for dummy in generator:
-                    pass
-        self.constructed_objects = {}
-        self.recursive_objects = {}
-        self.deep_construct = False
-        return data
-
-    def construct_object(self, node, deep=False):
-        if node in self.constructed_objects:
-            return self.constructed_objects[node]
-        if deep:
-            old_deep = self.deep_construct
-            self.deep_construct = True
-        if node in self.recursive_objects:
-            raise ConstructorError(None, None,
-                    "found unconstructable recursive node", node.start_mark)
-        self.recursive_objects[node] = None
-        constructor = None
-        tag_suffix = None
-        if node.tag in self.yaml_constructors:
-            constructor = self.yaml_constructors[node.tag]
-        else:
-            for tag_prefix in self.yaml_multi_constructors:
-                if node.tag.startswith(tag_prefix):
-                    tag_suffix = node.tag[len(tag_prefix):]
-                    constructor = self.yaml_multi_constructors[tag_prefix]
-                    break
-            else:
-                if None in self.yaml_multi_constructors:
-                    tag_suffix = node.tag
-                    constructor = self.yaml_multi_constructors[None]
-                elif None in self.yaml_constructors:
-                    constructor = self.yaml_constructors[None]
-                elif isinstance(node, ScalarNode):
-                    constructor = self.__class__.construct_scalar
-                elif isinstance(node, SequenceNode):
-                    constructor = self.__class__.construct_sequence
-                elif isinstance(node, MappingNode):
-                    constructor = self.__class__.construct_mapping
-        if tag_suffix is None:
-            data = constructor(self, node)
-        else:
-            data = constructor(self, tag_suffix, node)
-        if isinstance(data, types.GeneratorType):
-            generator = data
-            data = generator.next()
-            if self.deep_construct:
-                for dummy in generator:
-                    pass
-            else:
-                self.state_generators.append(generator)
-        self.constructed_objects[node] = data
-        del self.recursive_objects[node]
-        if deep:
-            self.deep_construct = old_deep
-        return data
-
-    def construct_scalar(self, node):
-        if not isinstance(node, ScalarNode):
-            raise ConstructorError(None, None,
-                    "expected a scalar node, but found %s" % node.id,
-                    node.start_mark)
-        return node.value
-
-    def construct_sequence(self, node, deep=False):
-        if not isinstance(node, SequenceNode):
-            raise ConstructorError(None, None,
-                    "expected a sequence node, but found %s" % node.id,
-                    node.start_mark)
-        return [self.construct_object(child, deep=deep)
-                for child in node.value]
-
-    def construct_mapping(self, node, deep=False):
-        if not isinstance(node, MappingNode):
-            raise ConstructorError(None, None,
-                    "expected a mapping node, but found %s" % node.id,
-                    node.start_mark)
-        mapping = {}
-        for key_node, value_node in node.value:
-            key = self.construct_object(key_node, deep=deep)
-            try:
-                hash(key)
-            except TypeError, exc:
-                raise ConstructorError("while constructing a mapping", node.start_mark,
-                        "found unacceptable key (%s)" % exc, key_node.start_mark)
-            value = self.construct_object(value_node, deep=deep)
-            mapping[key] = value
-        return mapping
-
-    def construct_pairs(self, node, deep=False):
-        if not isinstance(node, MappingNode):
-            raise ConstructorError(None, None,
-                    "expected a mapping node, but found %s" % node.id,
-                    node.start_mark)
-        pairs = []
-        for key_node, value_node in node.value:
-            key = self.construct_object(key_node, deep=deep)
-            value = self.construct_object(value_node, deep=deep)
-            pairs.append((key, value))
-        return pairs
-
-    def add_constructor(cls, tag, constructor):
-        if not 'yaml_constructors' in cls.__dict__:
-            cls.yaml_constructors = cls.yaml_constructors.copy()
-        cls.yaml_constructors[tag] = constructor
-    add_constructor = classmethod(add_constructor)
-
-    def add_multi_constructor(cls, tag_prefix, multi_constructor):
-        if not 'yaml_multi_constructors' in cls.__dict__:
-            cls.yaml_multi_constructors = cls.yaml_multi_constructors.copy()
-        cls.yaml_multi_constructors[tag_prefix] = multi_constructor
-    add_multi_constructor = classmethod(add_multi_constructor)
-
-class SafeConstructor(BaseConstructor):
-
-    def construct_scalar(self, node):
-        if isinstance(node, MappingNode):
-            for key_node, value_node in node.value:
-                if key_node.tag == u'tag:yaml.org,2002:value':
-                    return self.construct_scalar(value_node)
-        return BaseConstructor.construct_scalar(self, node)
-
-    def flatten_mapping(self, node):
-        merge = []
-        index = 0
-        while index < len(node.value):
-            key_node, value_node = node.value[index]
-            if key_node.tag == u'tag:yaml.org,2002:merge':
-                del node.value[index]
-                if isinstance(value_node, MappingNode):
-                    self.flatten_mapping(value_node)
-                    merge.extend(value_node.value)
-                elif isinstance(value_node, SequenceNode):
-                    submerge = []
-                    for subnode in value_node.value:
-                        if not isinstance(subnode, MappingNode):
-                            raise ConstructorError("while constructing a mapping",
-                                    node.start_mark,
-                                    "expected a mapping for merging, but found %s"
-                                    % subnode.id, subnode.start_mark)
-                        self.flatten_mapping(subnode)
-                        submerge.append(subnode.value)
-                    submerge.reverse()
-                    for value in submerge:
-                        merge.extend(value)
-                else:
-                    raise ConstructorError("while constructing a mapping", node.start_mark,
-                            "expected a mapping or list of mappings for merging, but found %s"
-                            % value_node.id, value_node.start_mark)
-            elif key_node.tag == u'tag:yaml.org,2002:value':
-                key_node.tag = u'tag:yaml.org,2002:str'
-                index += 1
-            else:
-                index += 1
-        if merge:
-            node.value = merge + node.value
-
-    def construct_mapping(self, node, deep=False):
-        if isinstance(node, MappingNode):
-            self.flatten_mapping(node)
-        return BaseConstructor.construct_mapping(self, node, deep=deep)
-
-    def construct_yaml_null(self, node):
-        self.construct_scalar(node)
-        return None
-
-    bool_values = {
-        u'yes':     True,
-        u'no':      False,
-        u'true':    True,
-        u'false':   False,
-        u'on':      True,
-        u'off':     False,
-    }
-
-    def construct_yaml_bool(self, node):
-        value = self.construct_scalar(node)
-        return self.bool_values[value.lower()]
-
-    def construct_yaml_int(self, node):
-        value = str(self.construct_scalar(node))
-        value = value.replace('_', '')
-        sign = +1
-        if value[0] == '-':
-            sign = -1
-        if value[0] in '+-':
-            value = value[1:]
-        if value == '0':
-            return 0
-        elif value.startswith('0b'):
-            return sign*int(value[2:], 2)
-        elif value.startswith('0x'):
-            return sign*int(value[2:], 16)
-        elif value[0] == '0':
-            return sign*int(value, 8)
-        elif ':' in value:
-            digits = [int(part) for part in value.split(':')]
-            digits.reverse()
-            base = 1
-            value = 0
-            for digit in digits:
-                value += digit*base
-                base *= 60
-            return sign*value
-        else:
-            return sign*int(value)
-
-    inf_value = 1e300
-    while inf_value != inf_value*inf_value:
-        inf_value *= inf_value
-    nan_value = -inf_value/inf_value   # Trying to make a quiet NaN (like C99).
-
-    def construct_yaml_float(self, node):
-        value = str(self.construct_scalar(node))
-        value = value.replace('_', '').lower()
-        sign = +1
-        if value[0] == '-':
-            sign = -1
-        if value[0] in '+-':
-            value = value[1:]
-        if value == '.inf':
-            return sign*self.inf_value
-        elif value == '.nan':
-            return self.nan_value
-        elif ':' in value:
-            digits = [float(part) for part in value.split(':')]
-            digits.reverse()
-            base = 1
-            value = 0.0
-            for digit in digits:
-                value += digit*base
-                base *= 60
-            return sign*value
-        else:
-            return sign*float(value)
-
-    def construct_yaml_binary(self, node):
-        value = self.construct_scalar(node)
-        try:
-            return str(value).decode('base64')
-        except (binascii.Error, UnicodeEncodeError), exc:
-            raise ConstructorError(None, None,
-                    "failed to decode base64 data: %s" % exc, node.start_mark) 
-
-    timestamp_regexp = re.compile(
-            ur'''^(?P<year>[0-9][0-9][0-9][0-9])
-                -(?P<month>[0-9][0-9]?)
-                -(?P<day>[0-9][0-9]?)
-                (?:(?:[Tt]|[ \t]+)
-                (?P<hour>[0-9][0-9]?)
-                :(?P<minute>[0-9][0-9])
-                :(?P<second>[0-9][0-9])
-                (?:\.(?P<fraction>[0-9]*))?
-                (?:[ \t]*(?P<tz>Z|(?P<tz_sign>[-+])(?P<tz_hour>[0-9][0-9]?)
-                (?::(?P<tz_minute>[0-9][0-9]))?))?)?$''', re.X)
-
-    def construct_yaml_timestamp(self, node):
-        value = self.construct_scalar(node)
-        match = self.timestamp_regexp.match(node.value)
-        values = match.groupdict()
-        year = int(values['year'])
-        month = int(values['month'])
-        day = int(values['day'])
-        if not values['hour']:
-            return datetime.date(year, month, day)
-        hour = int(values['hour'])
-        minute = int(values['minute'])
-        second = int(values['second'])
-        fraction = 0
-        if values['fraction']:
-            fraction = values['fraction'][:6]
-            while len(fraction) < 6:
-                fraction += '0'
-            fraction = int(fraction)
-        delta = None
-        if values['tz_sign']:
-            tz_hour = int(values['tz_hour'])
-            tz_minute = int(values['tz_minute'] or 0)
-            delta = datetime.timedelta(hours=tz_hour, minutes=tz_minute)
-            if values['tz_sign'] == '-':
-                delta = -delta
-        data = datetime.datetime(year, month, day, hour, minute, second, fraction)
-        if delta:
-            data -= delta
-        return data
-
-    def construct_yaml_omap(self, node):
-        # Note: we do not check for duplicate keys, because it's too
-        # CPU-expensive.
-        omap = []
-        yield omap
-        if not isinstance(node, SequenceNode):
-            raise ConstructorError("while constructing an ordered map", node.start_mark,
-                    "expected a sequence, but found %s" % node.id, node.start_mark)
-        for subnode in node.value:
-            if not isinstance(subnode, MappingNode):
-                raise ConstructorError("while constructing an ordered map", node.start_mark,
-                        "expected a mapping of length 1, but found %s" % subnode.id,
-                        subnode.start_mark)
-            if len(subnode.value) != 1:
-                raise ConstructorError("while constructing an ordered map", node.start_mark,
-                        "expected a single mapping item, but found %d items" % len(subnode.value),
-                        subnode.start_mark)
-            key_node, value_node = subnode.value[0]
-            key = self.construct_object(key_node)
-            value = self.construct_object(value_node)
-            omap.append((key, value))
-
-    def construct_yaml_pairs(self, node):
-        # Note: the same code as `construct_yaml_omap`.
-        pairs = []
-        yield pairs
-        if not isinstance(node, SequenceNode):
-            raise ConstructorError("while constructing pairs", node.start_mark,
-                    "expected a sequence, but found %s" % node.id, node.start_mark)
-        for subnode in node.value:
-            if not isinstance(subnode, MappingNode):
-                raise ConstructorError("while constructing pairs", node.start_mark,
-                        "expected a mapping of length 1, but found %s" % subnode.id,
-                        subnode.start_mark)
-            if len(subnode.value) != 1:
-                raise ConstructorError("while constructing pairs", node.start_mark,
-                        "expected a single mapping item, but found %d items" % len(subnode.value),
-                        subnode.start_mark)
-            key_node, value_node = subnode.value[0]
-            key = self.construct_object(key_node)
-            value = self.construct_object(value_node)
-            pairs.append((key, value))
-
-    def construct_yaml_set(self, node):
-        data = set()
-        yield data
-        value = self.construct_mapping(node)
-        data.update(value)
-
-    def construct_yaml_str(self, node):
-        value = self.construct_scalar(node)
-        try:
-            return value.encode('ascii')
-        except UnicodeEncodeError:
-            return value
-
-    def construct_yaml_seq(self, node):
-        data = []
-        yield data
-        data.extend(self.construct_sequence(node))
-
-    def construct_yaml_map(self, node):
-        data = {}
-        yield data
-        value = self.construct_mapping(node)
-        data.update(value)
-
-    def construct_yaml_object(self, node, cls):
-        data = cls.__new__(cls)
-        yield data
-        if hasattr(data, '__setstate__'):
-            state = self.construct_mapping(node, deep=True)
-            data.__setstate__(state)
-        else:
-            state = self.construct_mapping(node)
-            data.__dict__.update(state)
-
-    def construct_undefined(self, node):
-        raise ConstructorError(None, None,
-                "could not determine a constructor for the tag %r" % node.tag.encode('utf-8'),
-                node.start_mark)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:null',
-        SafeConstructor.construct_yaml_null)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:bool',
-        SafeConstructor.construct_yaml_bool)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:int',
-        SafeConstructor.construct_yaml_int)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:float',
-        SafeConstructor.construct_yaml_float)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:binary',
-        SafeConstructor.construct_yaml_binary)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:timestamp',
-        SafeConstructor.construct_yaml_timestamp)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:omap',
-        SafeConstructor.construct_yaml_omap)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:pairs',
-        SafeConstructor.construct_yaml_pairs)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:set',
-        SafeConstructor.construct_yaml_set)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:str',
-        SafeConstructor.construct_yaml_str)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:seq',
-        SafeConstructor.construct_yaml_seq)
-
-SafeConstructor.add_constructor(
-        u'tag:yaml.org,2002:map',
-        SafeConstructor.construct_yaml_map)
-
-SafeConstructor.add_constructor(None,
-        SafeConstructor.construct_undefined)
-
-class Constructor(SafeConstructor):
-
-    def construct_python_str(self, node):
-        return self.construct_scalar(node).encode('utf-8')
-
-    def construct_python_unicode(self, node):
-        return self.construct_scalar(node)
-
-    def construct_python_long(self, node):
-        return long(self.construct_yaml_int(node))
-
-    def construct_python_complex(self, node):
-       return complex(self.construct_scalar(node))
-
-    def construct_python_tuple(self, node):
-        return tuple(self.construct_sequence(node))
-
-    def find_python_module(self, name, mark):
-        if not name:
-            raise ConstructorError("while constructing a Python module", mark,
-                    "expected non-empty name appended to the tag", mark)
-        try:
-            __import__(name)
-        except ImportError, exc:
-            raise ConstructorError("while constructing a Python module", mark,
-                    "cannot find module %r (%s)" % (name.encode('utf-8'), exc), mark)
-        return sys.modules[name]
-
-    def find_python_name(self, name, mark):
-        if not name:
-            raise ConstructorError("while constructing a Python object", mark,
-                    "expected non-empty name appended to the tag", mark)
-        if u'.' in name:
-            module_name, object_name = name.rsplit('.', 1)
-        else:
-            module_name = '__builtin__'
-            object_name = name
-        try:
-            __import__(module_name)
-        except ImportError, exc:
-            raise ConstructorError("while constructing a Python object", mark,
-                    "cannot find module %r (%s)" % (module_name.encode('utf-8'), exc), mark)
-        module = sys.modules[module_name]
-        if not hasattr(module, object_name):
-            raise ConstructorError("while constructing a Python object", mark,
-                    "cannot find %r in the module %r" % (object_name.encode('utf-8'),
-                        module.__name__), mark)
-        return getattr(module, object_name)
-
-    def construct_python_name(self, suffix, node):
-        value = self.construct_scalar(node)
-        if value:
-            raise ConstructorError("while constructing a Python name", node.start_mark,
-                    "expected the empty value, but found %r" % value.encode('utf-8'),
-                    node.start_mark)
-        return self.find_python_name(suffix, node.start_mark)
-
-    def construct_python_module(self, suffix, node):
-        value = self.construct_scalar(node)
-        if value:
-            raise ConstructorError("while constructing a Python module", node.start_mark,
-                    "expected the empty value, but found %r" % value.encode('utf-8'),
-                    node.start_mark)
-        return self.find_python_module(suffix, node.start_mark)
-
-    class classobj: pass
-
-    def make_python_instance(self, suffix, node,
-            args=None, kwds=None, newobj=False):
-        if not args:
-            args = []
-        if not kwds:
-            kwds = {}
-        cls = self.find_python_name(suffix, node.start_mark)
-        if newobj and isinstance(cls, type(self.classobj))  \
-                and not args and not kwds:
-            instance = self.classobj()
-            instance.__class__ = cls
-            return instance
-        elif newobj and isinstance(cls, type):
-            return cls.__new__(cls, *args, **kwds)
-        else:
-            return cls(*args, **kwds)
-
-    def set_python_instance_state(self, instance, state):
-        if hasattr(instance, '__setstate__'):
-            instance.__setstate__(state)
-        else:
-            slotstate = {}
-            if isinstance(state, tuple) and len(state) == 2:
-                state, slotstate = state
-            if hasattr(instance, '__dict__'):
-                instance.__dict__.update(state)
-            elif state:
-                slotstate.update(state)
-            for key, value in slotstate.items():
-                setattr(object, key, value)
-
-    def construct_python_object(self, suffix, node):
-        # Format:
-        #   !!python/object:module.name { ... state ... }
-        instance = self.make_python_instance(suffix, node, newobj=True)
-        yield instance
-        deep = hasattr(instance, '__setstate__')
-        state = self.construct_mapping(node, deep=deep)
-        self.set_python_instance_state(instance, state)
-
-    def construct_python_object_apply(self, suffix, node, newobj=False):
-        # Format:
-        #   !!python/object/apply       # (or !!python/object/new)
-        #   args: [ ... arguments ... ]
-        #   kwds: { ... keywords ... }
-        #   state: ... state ...
-        #   listitems: [ ... listitems ... ]
-        #   dictitems: { ... dictitems ... }
-        # or short format:
-        #   !!python/object/apply [ ... arguments ... ]
-        # The difference between !!python/object/apply and !!python/object/new
-        # is how an object is created, check make_python_instance for details.
-        if isinstance(node, SequenceNode):
-            args = self.construct_sequence(node, deep=True)
-            kwds = {}
-            state = {}
-            listitems = []
-            dictitems = {}
-        else:
-            value = self.construct_mapping(node, deep=True)
-            args = value.get('args', [])
-            kwds = value.get('kwds', {})
-            state = value.get('state', {})
-            listitems = value.get('listitems', [])
-            dictitems = value.get('dictitems', {})
-        instance = self.make_python_instance(suffix, node, args, kwds, newobj)
-        if state:
-            self.set_python_instance_state(instance, state)
-        if listitems:
-            instance.extend(listitems)
-        if dictitems:
-            for key in dictitems:
-                instance[key] = dictitems[key]
-        return instance
-
-    def construct_python_object_new(self, suffix, node):
-        return self.construct_python_object_apply(suffix, node, newobj=True)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/none',
-    Constructor.construct_yaml_null)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/bool',
-    Constructor.construct_yaml_bool)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/str',
-    Constructor.construct_python_str)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/unicode',
-    Constructor.construct_python_unicode)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/int',
-    Constructor.construct_yaml_int)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/long',
-    Constructor.construct_python_long)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/float',
-    Constructor.construct_yaml_float)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/complex',
-    Constructor.construct_python_complex)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/list',
-    Constructor.construct_yaml_seq)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/tuple',
-    Constructor.construct_python_tuple)
-
-Constructor.add_constructor(
-    u'tag:yaml.org,2002:python/dict',
-    Constructor.construct_yaml_map)
-
-Constructor.add_multi_constructor(
-    u'tag:yaml.org,2002:python/name:',
-    Constructor.construct_python_name)
-
-Constructor.add_multi_constructor(
-    u'tag:yaml.org,2002:python/module:',
-    Constructor.construct_python_module)
-
-Constructor.add_multi_constructor(
-    u'tag:yaml.org,2002:python/object:',
-    Constructor.construct_python_object)
-
-Constructor.add_multi_constructor(
-    u'tag:yaml.org,2002:python/object/apply:',
-    Constructor.construct_python_object_apply)
-
-Constructor.add_multi_constructor(
-    u'tag:yaml.org,2002:python/object/new:',
-    Constructor.construct_python_object_new)
-

libs/py2/yaml/cyaml.py

@@ -1,85 +0,0 @@
-
-__all__ = ['CBaseLoader', 'CSafeLoader', 'CLoader',
-        'CBaseDumper', 'CSafeDumper', 'CDumper']
-
-from _yaml import CParser, CEmitter
-
-from constructor import *
-
-from serializer import *
-from representer import *
-
-from resolver import *
-
-class CBaseLoader(CParser, BaseConstructor, BaseResolver):
-
-    def __init__(self, stream):
-        CParser.__init__(self, stream)
-        BaseConstructor.__init__(self)
-        BaseResolver.__init__(self)
-
-class CSafeLoader(CParser, SafeConstructor, Resolver):
-
-    def __init__(self, stream):
-        CParser.__init__(self, stream)
-        SafeConstructor.__init__(self)
-        Resolver.__init__(self)
-
-class CLoader(CParser, Constructor, Resolver):
-
-    def __init__(self, stream):
-        CParser.__init__(self, stream)
-        Constructor.__init__(self)
-        Resolver.__init__(self)
-
-class CBaseDumper(CEmitter, BaseRepresenter, BaseResolver):
-
-    def __init__(self, stream,
-            default_style=None, default_flow_style=None,
-            canonical=None, indent=None, width=None,
-            allow_unicode=None, line_break=None,
-            encoding=None, explicit_start=None, explicit_end=None,
-            version=None, tags=None):
-        CEmitter.__init__(self, stream, canonical=canonical,
-                indent=indent, width=width, encoding=encoding,
-                allow_unicode=allow_unicode, line_break=line_break,
-                explicit_start=explicit_start, explicit_end=explicit_end,
-                version=version, tags=tags)
-        Representer.__init__(self, default_style=default_style,
-                default_flow_style=default_flow_style)
-        Resolver.__init__(self)
-
-class CSafeDumper(CEmitter, SafeRepresenter, Resolver):
-
-    def __init__(self, stream,
-            default_style=None, default_flow_style=None,
-            canonical=None, indent=None, width=None,
-            allow_unicode=None, line_break=None,
-            encoding=None, explicit_start=None, explicit_end=None,
-            version=None, tags=None):
-        CEmitter.__init__(self, stream, canonical=canonical,
-                indent=indent, width=width, encoding=encoding,
-                allow_unicode=allow_unicode, line_break=line_break,
-                explicit_start=explicit_start, explicit_end=explicit_end,
-                version=version, tags=tags)
-        SafeRepresenter.__init__(self, default_style=default_style,
-                default_flow_style=default_flow_style)
-        Resolver.__init__(self)
-
-class CDumper(CEmitter, Serializer, Representer, Resolver):
-
-    def __init__(self, stream,
-            default_style=None, default_flow_style=None,
-            canonical=None, indent=None, width=None,
-            allow_unicode=None, line_break=None,
-            encoding=None, explicit_start=None, explicit_end=None,
-            version=None, tags=None):
-        CEmitter.__init__(self, stream, canonical=canonical,
-                indent=indent, width=width, encoding=encoding,
-                allow_unicode=allow_unicode, line_break=line_break,
-                explicit_start=explicit_start, explicit_end=explicit_end,
-                version=version, tags=tags)
-        Representer.__init__(self, default_style=default_style,
-                default_flow_style=default_flow_style)
-        Resolver.__init__(self)
-

libs/py2/yaml/dumper.py

@@ -1,62 +0,0 @@
-
-__all__ = ['BaseDumper', 'SafeDumper', 'Dumper']
-
-from emitter import *
-from serializer import *
-from representer import *
-from resolver import *
-
-class BaseDumper(Emitter, Serializer, BaseRepresenter, BaseResolver):
-
-    def __init__(self, stream,
-            default_style=None, default_flow_style=None,
-            canonical=None, indent=None, width=None,
-            allow_unicode=None, line_break=None,
-            encoding=None, explicit_start=None, explicit_end=None,
-            version=None, tags=None):
-        Emitter.__init__(self, stream, canonical=canonical,
-                indent=indent, width=width,
-                allow_unicode=allow_unicode, line_break=line_break)
-        Serializer.__init__(self, encoding=encoding,
-                explicit_start=explicit_start, explicit_end=explicit_end,
-                version=version, tags=tags)
-        Representer.__init__(self, default_style=default_style,
-                default_flow_style=default_flow_style)
-        Resolver.__init__(self)
-
-class SafeDumper(Emitter, Serializer, SafeRepresenter, Resolver):
-
-    def __init__(self, stream,
-            default_style=None, default_flow_style=None,
-            canonical=None, indent=None, width=None,
-            allow_unicode=None, line_break=None,
-            encoding=None, explicit_start=None, explicit_end=None,
-            version=None, tags=None):
-        Emitter.__init__(self, stream, canonical=canonical,
-                indent=indent, width=width,
-                allow_unicode=allow_unicode, line_break=line_break)
-        Serializer.__init__(self, encoding=encoding,
-                explicit_start=explicit_start, explicit_end=explicit_end,
-                version=version, tags=tags)
-        SafeRepresenter.__init__(self, default_style=default_style,
-                default_flow_style=default_flow_style)
-        Resolver.__init__(self)
-
-class Dumper(Emitter, Serializer, Representer, Resolver):
-
-    def __init__(self, stream,
-            default_style=None, default_flow_style=None,
-            canonical=None, indent=None, width=None,
-            allow_unicode=None, line_break=None,
-            encoding=None, explicit_start=None, explicit_end=None,
-            version=None, tags=None):
-        Emitter.__init__(self, stream, canonical=canonical,
-                indent=indent, width=width,
-                allow_unicode=allow_unicode, line_break=line_break)
-        Serializer.__init__(self, encoding=encoding,
-                explicit_start=explicit_start, explicit_end=explicit_end,
-                version=version, tags=tags)
-        Representer.__init__(self, default_style=default_style,
-                default_flow_style=default_flow_style)
-        Resolver.__init__(self)
-

libs/py2/yaml/error.py

@@ -1,75 +0,0 @@
-
-__all__ = ['Mark', 'YAMLError', 'MarkedYAMLError']
-
-class Mark(object):
-
-    def __init__(self, name, index, line, column, buffer, pointer):
-        self.name = name
-        self.index = index
-        self.line = line
-        self.column = column
-        self.buffer = buffer
-        self.pointer = pointer
-
-    def get_snippet(self, indent=4, max_length=75):
-        if self.buffer is None:
-            return None
-        head = ''
-        start = self.pointer
-        while start > 0 and self.buffer[start-1] not in u'\0\r\n\x85\u2028\u2029':
-            start -= 1
-            if self.pointer-start > max_length/2-1:
-                head = ' ... '
-                start += 5
-                break
-        tail = ''
-        end = self.pointer
-        while end < len(self.buffer) and self.buffer[end] not in u'\0\r\n\x85\u2028\u2029':
-            end += 1
-            if end-self.pointer > max_length/2-1:
-                tail = ' ... '
-                end -= 5
-                break
-        snippet = self.buffer[start:end].encode('utf-8')
-        return ' '*indent + head + snippet + tail + '\n'  \
-                + ' '*(indent+self.pointer-start+len(head)) + '^'
-
-    def __str__(self):
-        snippet = self.get_snippet()
-        where = "  in \"%s\", line %d, column %d"   \
-                % (self.name, self.line+1, self.column+1)
-        if snippet is not None:
-            where += ":\n"+snippet
-        return where
-
-class YAMLError(Exception):
-    pass
-
-class MarkedYAMLError(YAMLError):
-
-    def __init__(self, context=None, context_mark=None,
-            problem=None, problem_mark=None, note=None):
-        self.context = context
-        self.context_mark = context_mark
-        self.problem = problem
-        self.problem_mark = problem_mark
-        self.note = note
-
-    def __str__(self):
-        lines = []
-        if self.context is not None:
-            lines.append(self.context)
-        if self.context_mark is not None  \
-            and (self.problem is None or self.problem_mark is None
-                    or self.context_mark.name != self.problem_mark.name
-                    or self.context_mark.line != self.problem_mark.line
-                    or self.context_mark.column != self.problem_mark.column):
-            lines.append(str(self.context_mark))
-        if self.problem is not None:
-            lines.append(self.problem)
-        if self.problem_mark is not None:
-            lines.append(str(self.problem_mark))
-        if self.note is not None:
-            lines.append(self.note)
-        return '\n'.join(lines)
-

libs/py2/yaml/events.py

@@ -1,86 +0,0 @@
-
-# Abstract classes.
-
-class Event(object):
-    def __init__(self, start_mark=None, end_mark=None):
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-    def __repr__(self):
-        attributes = [key for key in ['anchor', 'tag', 'implicit', 'value']
-                if hasattr(self, key)]
-        arguments = ', '.join(['%s=%r' % (key, getattr(self, key))
-                for key in attributes])
-        return '%s(%s)' % (self.__class__.__name__, arguments)
-
-class NodeEvent(Event):
-    def __init__(self, anchor, start_mark=None, end_mark=None):
-        self.anchor = anchor
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-
-class CollectionStartEvent(NodeEvent):
-    def __init__(self, anchor, tag, implicit, start_mark=None, end_mark=None,
-            flow_style=None):
-        self.anchor = anchor
-        self.tag = tag
-        self.implicit = implicit
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-        self.flow_style = flow_style
-
-class CollectionEndEvent(Event):
-    pass
-
-# Implementations.
-
-class StreamStartEvent(Event):
-    def __init__(self, start_mark=None, end_mark=None, encoding=None):
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-        self.encoding = encoding
-
-class StreamEndEvent(Event):
-    pass
-
-class DocumentStartEvent(Event):
-    def __init__(self, start_mark=None, end_mark=None,
-            explicit=None, version=None, tags=None):
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-        self.explicit = explicit
-        self.version = version
-        self.tags = tags
-
-class DocumentEndEvent(Event):
-    def __init__(self, start_mark=None, end_mark=None,
-            explicit=None):
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-        self.explicit = explicit
-
-class AliasEvent(NodeEvent):
-    pass
-
-class ScalarEvent(NodeEvent):
-    def __init__(self, anchor, tag, implicit, value,
-            start_mark=None, end_mark=None, style=None):
-        self.anchor = anchor
-        self.tag = tag
-        self.implicit = implicit
-        self.value = value
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-        self.style = style
-
-class SequenceStartEvent(CollectionStartEvent):
-    pass
-
-class SequenceEndEvent(CollectionEndEvent):
-    pass
-
-class MappingStartEvent(CollectionStartEvent):
-    pass
-
-class MappingEndEvent(CollectionEndEvent):
-    pass
-

libs/py2/yaml/loader.py

@@ -1,40 +0,0 @@
-
-__all__ = ['BaseLoader', 'SafeLoader', 'Loader']
-
-from reader import *
-from scanner import *
-from parser import *
-from composer import *
-from constructor import *
-from resolver import *
-
-class BaseLoader(Reader, Scanner, Parser, Composer, BaseConstructor, BaseResolver):
-
-    def __init__(self, stream):
-        Reader.__init__(self, stream)
-        Scanner.__init__(self)
-        Parser.__init__(self)
-        Composer.__init__(self)
-        BaseConstructor.__init__(self)
-        BaseResolver.__init__(self)
-
-class SafeLoader(Reader, Scanner, Parser, Composer, SafeConstructor, Resolver):
-
-    def __init__(self, stream):
-        Reader.__init__(self, stream)
-        Scanner.__init__(self)
-        Parser.__init__(self)
-        Composer.__init__(self)
-        SafeConstructor.__init__(self)
-        Resolver.__init__(self)
-
-class Loader(Reader, Scanner, Parser, Composer, Constructor, Resolver):
-
-    def __init__(self, stream):
-        Reader.__init__(self, stream)
-        Scanner.__init__(self)
-        Parser.__init__(self)
-        Composer.__init__(self)
-        Constructor.__init__(self)
-        Resolver.__init__(self)
-

libs/py2/yaml/nodes.py

@@ -1,49 +0,0 @@
-
-class Node(object):
-    def __init__(self, tag, value, start_mark, end_mark):
-        self.tag = tag
-        self.value = value
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-    def __repr__(self):
-        value = self.value
-        #if isinstance(value, list):
-        #    if len(value) == 0:
-        #        value = '<empty>'
-        #    elif len(value) == 1:
-        #        value = '<1 item>'
-        #    else:
-        #        value = '<%d items>' % len(value)
-        #else:
-        #    if len(value) > 75:
-        #        value = repr(value[:70]+u' ... ')
-        #    else:
-        #        value = repr(value)
-        value = repr(value)
-        return '%s(tag=%r, value=%s)' % (self.__class__.__name__, self.tag, value)
-
-class ScalarNode(Node):
-    id = 'scalar'
-    def __init__(self, tag, value,
-            start_mark=None, end_mark=None, style=None):
-        self.tag = tag
-        self.value = value
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-        self.style = style
-
-class CollectionNode(Node):
-    def __init__(self, tag, value,
-            start_mark=None, end_mark=None, flow_style=None):
-        self.tag = tag
-        self.value = value
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-        self.flow_style = flow_style
-
-class SequenceNode(CollectionNode):
-    id = 'sequence'
-
-class MappingNode(CollectionNode):
-    id = 'mapping'
-

libs/py2/yaml/parser.py

@@ -1,589 +0,0 @@
-
-# The following YAML grammar is LL(1) and is parsed by a recursive descent
-# parser.
-#
-# stream            ::= STREAM-START implicit_document? explicit_document* STREAM-END
-# implicit_document ::= block_node DOCUMENT-END*
-# explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END*
-# block_node_or_indentless_sequence ::=
-#                       ALIAS
-#                       | properties (block_content | indentless_block_sequence)?
-#                       | block_content
-#                       | indentless_block_sequence
-# block_node        ::= ALIAS
-#                       | properties block_content?
-#                       | block_content
-# flow_node         ::= ALIAS
-#                       | properties flow_content?
-#                       | flow_content
-# properties        ::= TAG ANCHOR? | ANCHOR TAG?
-# block_content     ::= block_collection | flow_collection | SCALAR
-# flow_content      ::= flow_collection | SCALAR
-# block_collection  ::= block_sequence | block_mapping
-# flow_collection   ::= flow_sequence | flow_mapping
-# block_sequence    ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END
-# indentless_sequence   ::= (BLOCK-ENTRY block_node?)+
-# block_mapping     ::= BLOCK-MAPPING_START
-#                       ((KEY block_node_or_indentless_sequence?)?
-#                       (VALUE block_node_or_indentless_sequence?)?)*
-#                       BLOCK-END
-# flow_sequence     ::= FLOW-SEQUENCE-START
-#                       (flow_sequence_entry FLOW-ENTRY)*
-#                       flow_sequence_entry?
-#                       FLOW-SEQUENCE-END
-# flow_sequence_entry   ::= flow_node | KEY flow_node? (VALUE flow_node?)?
-# flow_mapping      ::= FLOW-MAPPING-START
-#                       (flow_mapping_entry FLOW-ENTRY)*
-#                       flow_mapping_entry?
-#                       FLOW-MAPPING-END
-# flow_mapping_entry    ::= flow_node | KEY flow_node? (VALUE flow_node?)?
-#
-# FIRST sets:
-#
-# stream: { STREAM-START }
-# explicit_document: { DIRECTIVE DOCUMENT-START }
-# implicit_document: FIRST(block_node)
-# block_node: { ALIAS TAG ANCHOR SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START }
-# flow_node: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START }
-# block_content: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR }
-# flow_content: { FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR }
-# block_collection: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START }
-# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START }
-# block_sequence: { BLOCK-SEQUENCE-START }
-# block_mapping: { BLOCK-MAPPING-START }
-# block_node_or_indentless_sequence: { ALIAS ANCHOR TAG SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START BLOCK-ENTRY }
-# indentless_sequence: { ENTRY }
-# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START }
-# flow_sequence: { FLOW-SEQUENCE-START }
-# flow_mapping: { FLOW-MAPPING-START }
-# flow_sequence_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY }
-# flow_mapping_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY }
-
-__all__ = ['Parser', 'ParserError']
-
-from error import MarkedYAMLError
-from tokens import *
-from events import *
-from scanner import *
-
-class ParserError(MarkedYAMLError):
-    pass
-
-class Parser(object):
-    # Since writing a recursive-descendant parser is a straightforward task, we
-    # do not give many comments here.
-
-    DEFAULT_TAGS = {
-        u'!':   u'!',
-        u'!!':  u'tag:yaml.org,2002:',
-    }
-
-    def __init__(self):
-        self.current_event = None
-        self.yaml_version = None
-        self.tag_handles = {}
-        self.states = []
-        self.marks = []
-        self.state = self.parse_stream_start
-
-    def dispose(self):
-        # Reset the state attributes (to clear self-references)
-        self.states = []
-        self.state = None
-
-    def check_event(self, *choices):
-        # Check the type of the next event.
-        if self.current_event is None:
-            if self.state:
-                self.current_event = self.state()
-        if self.current_event is not None:
-            if not choices:
-                return True
-            for choice in choices:
-                if isinstance(self.current_event, choice):
-                    return True
-        return False
-
-    def peek_event(self):
-        # Get the next event.
-        if self.current_event is None:
-            if self.state:
-                self.current_event = self.state()
-        return self.current_event
-
-    def get_event(self):
-        # Get the next event and proceed further.
-        if self.current_event is None:
-            if self.state:
-                self.current_event = self.state()
-        value = self.current_event
-        self.current_event = None
-        return value
-
-    # stream    ::= STREAM-START implicit_document? explicit_document* STREAM-END
-    # implicit_document ::= block_node DOCUMENT-END*
-    # explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END*
-
-    def parse_stream_start(self):
-
-        # Parse the stream start.
-        token = self.get_token()
-        event = StreamStartEvent(token.start_mark, token.end_mark,
-                encoding=token.encoding)
-
-        # Prepare the next state.
-        self.state = self.parse_implicit_document_start
-
-        return event
-
-    def parse_implicit_document_start(self):
-
-        # Parse an implicit document.
-        if not self.check_token(DirectiveToken, DocumentStartToken,
-                StreamEndToken):
-            self.tag_handles = self.DEFAULT_TAGS
-            token = self.peek_token()
-            start_mark = end_mark = token.start_mark
-            event = DocumentStartEvent(start_mark, end_mark,
-                    explicit=False)
-
-            # Prepare the next state.
-            self.states.append(self.parse_document_end)
-            self.state = self.parse_block_node
-
-            return event
-
-        else:
-            return self.parse_document_start()
-
-    def parse_document_start(self):
-
-        # Parse any extra document end indicators.
-        while self.check_token(DocumentEndToken):
-            self.get_token()
-
-        # Parse an explicit document.
-        if not self.check_token(StreamEndToken):
-            token = self.peek_token()
-            start_mark = token.start_mark
-            version, tags = self.process_directives()
-            if not self.check_token(DocumentStartToken):
-                raise ParserError(None, None,
-                        "expected '<document start>', but found %r"
-                        % self.peek_token().id,
-                        self.peek_token().start_mark)
-            token = self.get_token()
-            end_mark = token.end_mark
-            event = DocumentStartEvent(start_mark, end_mark,
-                    explicit=True, version=version, tags=tags)
-            self.states.append(self.parse_document_end)
-            self.state = self.parse_document_content
-        else:
-            # Parse the end of the stream.
-            token = self.get_token()
-            event = StreamEndEvent(token.start_mark, token.end_mark)
-            assert not self.states
-            assert not self.marks
-            self.state = None
-        return event
-
-    def parse_document_end(self):
-
-        # Parse the document end.
-        token = self.peek_token()
-        start_mark = end_mark = token.start_mark
-        explicit = False
-        if self.check_token(DocumentEndToken):
-            token = self.get_token()
-            end_mark = token.end_mark
-            explicit = True
-        event = DocumentEndEvent(start_mark, end_mark,
-                explicit=explicit)
-
-        # Prepare the next state.
-        self.state = self.parse_document_start
-
-        return event
-
-    def parse_document_content(self):
-        if self.check_token(DirectiveToken,
-                DocumentStartToken, DocumentEndToken, StreamEndToken):
-            event = self.process_empty_scalar(self.peek_token().start_mark)
-            self.state = self.states.pop()
-            return event
-        else:
-            return self.parse_block_node()
-
-    def process_directives(self):
-        self.yaml_version = None
-        self.tag_handles = {}
-        while self.check_token(DirectiveToken):
-            token = self.get_token()
-            if token.name == u'YAML':
-                if self.yaml_version is not None:
-                    raise ParserError(None, None,
-                            "found duplicate YAML directive", token.start_mark)
-                major, minor = token.value
-                if major != 1:
-                    raise ParserError(None, None,
-                            "found incompatible YAML document (version 1.* is required)",
-                            token.start_mark)
-                self.yaml_version = token.value
-            elif token.name == u'TAG':
-                handle, prefix = token.value
-                if handle in self.tag_handles:
-                    raise ParserError(None, None,
-                            "duplicate tag handle %r" % handle.encode('utf-8'),
-                            token.start_mark)
-                self.tag_handles[handle] = prefix
-        if self.tag_handles:
-            value = self.yaml_version, self.tag_handles.copy()
-        else:
-            value = self.yaml_version, None
-        for key in self.DEFAULT_TAGS:
-            if key not in self.tag_handles:
-                self.tag_handles[key] = self.DEFAULT_TAGS[key]
-        return value
-
-    # block_node_or_indentless_sequence ::= ALIAS
-    #               | properties (block_content | indentless_block_sequence)?
-    #               | block_content
-    #               | indentless_block_sequence
-    # block_node    ::= ALIAS
-    #                   | properties block_content?
-    #                   | block_content
-    # flow_node     ::= ALIAS
-    #                   | properties flow_content?
-    #                   | flow_content
-    # properties    ::= TAG ANCHOR? | ANCHOR TAG?
-    # block_content     ::= block_collection | flow_collection | SCALAR
-    # flow_content      ::= flow_collection | SCALAR
-    # block_collection  ::= block_sequence | block_mapping
-    # flow_collection   ::= flow_sequence | flow_mapping
-
-    def parse_block_node(self):
-        return self.parse_node(block=True)
-
-    def parse_flow_node(self):
-        return self.parse_node()
-
-    def parse_block_node_or_indentless_sequence(self):
-        return self.parse_node(block=True, indentless_sequence=True)
-
-    def parse_node(self, block=False, indentless_sequence=False):
-        if self.check_token(AliasToken):
-            token = self.get_token()
-            event = AliasEvent(token.value, token.start_mark, token.end_mark)
-            self.state = self.states.pop()
-        else:
-            anchor = None
-            tag = None
-            start_mark = end_mark = tag_mark = None
-            if self.check_token(AnchorToken):
-                token = self.get_token()
-                start_mark = token.start_mark
-                end_mark = token.end_mark
-                anchor = token.value
-                if self.check_token(TagToken):
-                    token = self.get_token()
-                    tag_mark = token.start_mark
-                    end_mark = token.end_mark
-                    tag = token.value
-            elif self.check_token(TagToken):
-                token = self.get_token()
-                start_mark = tag_mark = token.start_mark
-                end_mark = token.end_mark
-                tag = token.value
-                if self.check_token(AnchorToken):
-                    token = self.get_token()
-                    end_mark = token.end_mark
-                    anchor = token.value
-            if tag is not None:
-                handle, suffix = tag
-                if handle is not None:
-                    if handle not in self.tag_handles:
-                        raise ParserError("while parsing a node", start_mark,
-                                "found undefined tag handle %r" % handle.encode('utf-8'),
-                                tag_mark)
-                    tag = self.tag_handles[handle]+suffix
-                else:
-                    tag = suffix
-            #if tag == u'!':
-            #    raise ParserError("while parsing a node", start_mark,
-            #            "found non-specific tag '!'", tag_mark,
-            #            "Please check 'http://pyyaml.org/wiki/YAMLNonSpecificTag' and share your opinion.")
-            if start_mark is None:
-                start_mark = end_mark = self.peek_token().start_mark
-            event = None
-            implicit = (tag is None or tag == u'!')
-            if indentless_sequence and self.check_token(BlockEntryToken):
-                end_mark = self.peek_token().end_mark
-                event = SequenceStartEvent(anchor, tag, implicit,
-                        start_mark, end_mark)
-                self.state = self.parse_indentless_sequence_entry
-            else:
-                if self.check_token(ScalarToken):
-                    token = self.get_token()
-                    end_mark = token.end_mark
-                    if (token.plain and tag is None) or tag == u'!':
-                        implicit = (True, False)
-                    elif tag is None:
-                        implicit = (False, True)
-                    else:
-                        implicit = (False, False)
-                    event = ScalarEvent(anchor, tag, implicit, token.value,
-                            start_mark, end_mark, style=token.style)
-                    self.state = self.states.pop()
-                elif self.check_token(FlowSequenceStartToken):
-                    end_mark = self.peek_token().end_mark
-                    event = SequenceStartEvent(anchor, tag, implicit,
-                            start_mark, end_mark, flow_style=True)
-                    self.state = self.parse_flow_sequence_first_entry
-                elif self.check_token(FlowMappingStartToken):
-                    end_mark = self.peek_token().end_mark
-                    event = MappingStartEvent(anchor, tag, implicit,
-                            start_mark, end_mark, flow_style=True)
-                    self.state = self.parse_flow_mapping_first_key
-                elif block and self.check_token(BlockSequenceStartToken):
-                    end_mark = self.peek_token().start_mark
-                    event = SequenceStartEvent(anchor, tag, implicit,
-                            start_mark, end_mark, flow_style=False)
-                    self.state = self.parse_block_sequence_first_entry
-                elif block and self.check_token(BlockMappingStartToken):
-                    end_mark = self.peek_token().start_mark
-                    event = MappingStartEvent(anchor, tag, implicit,
-                            start_mark, end_mark, flow_style=False)
-                    self.state = self.parse_block_mapping_first_key
-                elif anchor is not None or tag is not None:
-                    # Empty scalars are allowed even if a tag or an anchor is
-                    # specified.
-                    event = ScalarEvent(anchor, tag, (implicit, False), u'',
-                            start_mark, end_mark)
-                    self.state = self.states.pop()
-                else:
-                    if block:
-                        node = 'block'
-                    else:
-                        node = 'flow'
-                    token = self.peek_token()
-                    raise ParserError("while parsing a %s node" % node, start_mark,
-                            "expected the node content, but found %r" % token.id,
-                            token.start_mark)
-        return event
-
-    # block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END
-
-    def parse_block_sequence_first_entry(self):
-        token = self.get_token()
-        self.marks.append(token.start_mark)
-        return self.parse_block_sequence_entry()
-
-    def parse_block_sequence_entry(self):
-        if self.check_token(BlockEntryToken):
-            token = self.get_token()
-            if not self.check_token(BlockEntryToken, BlockEndToken):
-                self.states.append(self.parse_block_sequence_entry)
-                return self.parse_block_node()
-            else:
-                self.state = self.parse_block_sequence_entry
-                return self.process_empty_scalar(token.end_mark)
-        if not self.check_token(BlockEndToken):
-            token = self.peek_token()
-            raise ParserError("while parsing a block collection", self.marks[-1],
-                    "expected <block end>, but found %r" % token.id, token.start_mark)
-        token = self.get_token()
-        event = SequenceEndEvent(token.start_mark, token.end_mark)
-        self.state = self.states.pop()
-        self.marks.pop()
-        return event
-
-    # indentless_sequence ::= (BLOCK-ENTRY block_node?)+
-
-    def parse_indentless_sequence_entry(self):
-        if self.check_token(BlockEntryToken):
-            token = self.get_token()
-            if not self.check_token(BlockEntryToken,
-                    KeyToken, ValueToken, BlockEndToken):
-                self.states.append(self.parse_indentless_sequence_entry)
-                return self.parse_block_node()
-            else:
-                self.state = self.parse_indentless_sequence_entry
-                return self.process_empty_scalar(token.end_mark)
-        token = self.peek_token()
-        event = SequenceEndEvent(token.start_mark, token.start_mark)
-        self.state = self.states.pop()
-        return event
-
-    # block_mapping     ::= BLOCK-MAPPING_START
-    #                       ((KEY block_node_or_indentless_sequence?)?
-    #                       (VALUE block_node_or_indentless_sequence?)?)*
-    #                       BLOCK-END
-
-    def parse_block_mapping_first_key(self):
-        token = self.get_token()
-        self.marks.append(token.start_mark)
-        return self.parse_block_mapping_key()
-
-    def parse_block_mapping_key(self):
-        if self.check_token(KeyToken):
-            token = self.get_token()
-            if not self.check_token(KeyToken, ValueToken, BlockEndToken):
-                self.states.append(self.parse_block_mapping_value)
-                return self.parse_block_node_or_indentless_sequence()
-            else:
-                self.state = self.parse_block_mapping_value
-                return self.process_empty_scalar(token.end_mark)
-        if not self.check_token(BlockEndToken):
-            token = self.peek_token()
-            raise ParserError("while parsing a block mapping", self.marks[-1],
-                    "expected <block end>, but found %r" % token.id, token.start_mark)
-        token = self.get_token()
-        event = MappingEndEvent(token.start_mark, token.end_mark)
-        self.state = self.states.pop()
-        self.marks.pop()
-        return event
-
-    def parse_block_mapping_value(self):
-        if self.check_token(ValueToken):
-            token = self.get_token()
-            if not self.check_token(KeyToken, ValueToken, BlockEndToken):
-                self.states.append(self.parse_block_mapping_key)
-                return self.parse_block_node_or_indentless_sequence()
-            else:
-                self.state = self.parse_block_mapping_key
-                return self.process_empty_scalar(token.end_mark)
-        else:
-            self.state = self.parse_block_mapping_key
-            token = self.peek_token()
-            return self.process_empty_scalar(token.start_mark)
-
-    # flow_sequence     ::= FLOW-SEQUENCE-START
-    #                       (flow_sequence_entry FLOW-ENTRY)*
-    #                       flow_sequence_entry?
-    #                       FLOW-SEQUENCE-END
-    # flow_sequence_entry   ::= flow_node | KEY flow_node? (VALUE flow_node?)?
-    #
-    # Note that while production rules for both flow_sequence_entry and
-    # flow_mapping_entry are equal, their interpretations are different.
-    # For `flow_sequence_entry`, the part `KEY flow_node? (VALUE flow_node?)?`
-    # generate an inline mapping (set syntax).
-
-    def parse_flow_sequence_first_entry(self):
-        token = self.get_token()
-        self.marks.append(token.start_mark)
-        return self.parse_flow_sequence_entry(first=True)
-
-    def parse_flow_sequence_entry(self, first=False):
-        if not self.check_token(FlowSequenceEndToken):
-            if not first:
-                if self.check_token(FlowEntryToken):
-                    self.get_token()
-                else:
-                    token = self.peek_token()
-                    raise ParserError("while parsing a flow sequence", self.marks[-1],
-                            "expected ',' or ']', but got %r" % token.id, token.start_mark)
-            
-            if self.check_token(KeyToken):
-                token = self.peek_token()
-                event = MappingStartEvent(None, None, True,
-                        token.start_mark, token.end_mark,
-                        flow_style=True)
-                self.state = self.parse_flow_sequence_entry_mapping_key
-                return event
-            elif not self.check_token(FlowSequenceEndToken):
-                self.states.append(self.parse_flow_sequence_entry)
-                return self.parse_flow_node()
-        token = self.get_token()
-        event = SequenceEndEvent(token.start_mark, token.end_mark)
-        self.state = self.states.pop()
-        self.marks.pop()
-        return event
-
-    def parse_flow_sequence_entry_mapping_key(self):
-        token = self.get_token()
-        if not self.check_token(ValueToken,
-                FlowEntryToken, FlowSequenceEndToken):
-            self.states.append(self.parse_flow_sequence_entry_mapping_value)
-            return self.parse_flow_node()
-        else:
-            self.state = self.parse_flow_sequence_entry_mapping_value
-            return self.process_empty_scalar(token.end_mark)
-
-    def parse_flow_sequence_entry_mapping_value(self):
-        if self.check_token(ValueToken):
-            token = self.get_token()
-            if not self.check_token(FlowEntryToken, FlowSequenceEndToken):
-                self.states.append(self.parse_flow_sequence_entry_mapping_end)
-                return self.parse_flow_node()
-            else:
-                self.state = self.parse_flow_sequence_entry_mapping_end
-                return self.process_empty_scalar(token.end_mark)
-        else:
-            self.state = self.parse_flow_sequence_entry_mapping_end
-            token = self.peek_token()
-            return self.process_empty_scalar(token.start_mark)
-
-    def parse_flow_sequence_entry_mapping_end(self):
-        self.state = self.parse_flow_sequence_entry
-        token = self.peek_token()
-        return MappingEndEvent(token.start_mark, token.start_mark)
-
-    # flow_mapping  ::= FLOW-MAPPING-START
-    #                   (flow_mapping_entry FLOW-ENTRY)*
-    #                   flow_mapping_entry?
-    #                   FLOW-MAPPING-END
-    # flow_mapping_entry    ::= flow_node | KEY flow_node? (VALUE flow_node?)?
-
-    def parse_flow_mapping_first_key(self):
-        token = self.get_token()
-        self.marks.append(token.start_mark)
-        return self.parse_flow_mapping_key(first=True)
-
-    def parse_flow_mapping_key(self, first=False):
-        if not self.check_token(FlowMappingEndToken):
-            if not first:
-                if self.check_token(FlowEntryToken):
-                    self.get_token()
-                else:
-                    token = self.peek_token()
-                    raise ParserError("while parsing a flow mapping", self.marks[-1],
-                            "expected ',' or '}', but got %r" % token.id, token.start_mark)
-            if self.check_token(KeyToken):
-                token = self.get_token()
-                if not self.check_token(ValueToken,
-                        FlowEntryToken, FlowMappingEndToken):
-                    self.states.append(self.parse_flow_mapping_value)
-                    return self.parse_flow_node()
-                else:
-                    self.state = self.parse_flow_mapping_value
-                    return self.process_empty_scalar(token.end_mark)
-            elif not self.check_token(FlowMappingEndToken):
-                self.states.append(self.parse_flow_mapping_empty_value)
-                return self.parse_flow_node()
-        token = self.get_token()
-        event = MappingEndEvent(token.start_mark, token.end_mark)
-        self.state = self.states.pop()
-        self.marks.pop()
-        return event
-
-    def parse_flow_mapping_value(self):
-        if self.check_token(ValueToken):
-            token = self.get_token()
-            if not self.check_token(FlowEntryToken, FlowMappingEndToken):
-                self.states.append(self.parse_flow_mapping_key)
-                return self.parse_flow_node()
-            else:
-                self.state = self.parse_flow_mapping_key
-                return self.process_empty_scalar(token.end_mark)
-        else:
-            self.state = self.parse_flow_mapping_key
-            token = self.peek_token()
-            return self.process_empty_scalar(token.start_mark)
-
-    def parse_flow_mapping_empty_value(self):
-        self.state = self.parse_flow_mapping_key
-        return self.process_empty_scalar(self.peek_token().start_mark)
-
-    def process_empty_scalar(self, mark):
-        return ScalarEvent(None, None, (True, False), u'', mark, mark)
-

libs/py2/yaml/reader.py

@@ -1,190 +0,0 @@
-# This module contains abstractions for the input stream. You don't have to
-# looks further, there are no pretty code.
-#
-# We define two classes here.
-#
-#   Mark(source, line, column)
-# It's just a record and its only use is producing nice error messages.
-# Parser does not use it for any other purposes.
-#
-#   Reader(source, data)
-# Reader determines the encoding of `data` and converts it to unicode.
-# Reader provides the following methods and attributes:
-#   reader.peek(length=1) - return the next `length` characters
-#   reader.forward(length=1) - move the current position to `length` characters.
-#   reader.index - the number of the current character.
-#   reader.line, stream.column - the line and the column of the current character.
-
-__all__ = ['Reader', 'ReaderError']
-
-from error import YAMLError, Mark
-
-import codecs, re
-
-class ReaderError(YAMLError):
-
-    def __init__(self, name, position, character, encoding, reason):
-        self.name = name
-        self.character = character
-        self.position = position
-        self.encoding = encoding
-        self.reason = reason
-
-    def __str__(self):
-        if isinstance(self.character, str):
-            return "'%s' codec can't decode byte #x%02x: %s\n"  \
-                    "  in \"%s\", position %d"    \
-                    % (self.encoding, ord(self.character), self.reason,
-                            self.name, self.position)
-        else:
-            return "unacceptable character #x%04x: %s\n"    \
-                    "  in \"%s\", position %d"    \
-                    % (self.character, self.reason,
-                            self.name, self.position)
-
-class Reader(object):
-    # Reader:
-    # - determines the data encoding and converts it to unicode,
-    # - checks if characters are in allowed range,
-    # - adds '\0' to the end.
-
-    # Reader accepts
-    #  - a `str` object,
-    #  - a `unicode` object,
-    #  - a file-like object with its `read` method returning `str`,
-    #  - a file-like object with its `read` method returning `unicode`.
-
-    # Yeah, it's ugly and slow.
-
-    def __init__(self, stream):
-        self.name = None
-        self.stream = None
-        self.stream_pointer = 0
-        self.eof = True
-        self.buffer = u''
-        self.pointer = 0
-        self.raw_buffer = None
-        self.raw_decode = None
-        self.encoding = None
-        self.index = 0
-        self.line = 0
-        self.column = 0
-        if isinstance(stream, unicode):
-            self.name = "<unicode string>"
-            self.check_printable(stream)
-            self.buffer = stream+u'\0'
-        elif isinstance(stream, str):
-            self.name = "<string>"
-            self.raw_buffer = stream
-            self.determine_encoding()
-        else:
-            self.stream = stream
-            self.name = getattr(stream, 'name', "<file>")
-            self.eof = False
-            self.raw_buffer = ''
-            self.determine_encoding()
-
-    def peek(self, index=0):
-        try:
-            return self.buffer[self.pointer+index]
-        except IndexError:
-            self.update(index+1)
-            return self.buffer[self.pointer+index]
-
-    def prefix(self, length=1):
-        if self.pointer+length >= len(self.buffer):
-            self.update(length)
-        return self.buffer[self.pointer:self.pointer+length]
-
-    def forward(self, length=1):
-        if self.pointer+length+1 >= len(self.buffer):
-            self.update(length+1)
-        while length:
-            ch = self.buffer[self.pointer]
-            self.pointer += 1
-            self.index += 1
-            if ch in u'\n\x85\u2028\u2029'  \
-                    or (ch == u'\r' and self.buffer[self.pointer] != u'\n'):
-                self.line += 1
-                self.column = 0
-            elif ch != u'\uFEFF':
-                self.column += 1
-            length -= 1
-
-    def get_mark(self):
-        if self.stream is None:
-            return Mark(self.name, self.index, self.line, self.column,
-                    self.buffer, self.pointer)
-        else:
-            return Mark(self.name, self.index, self.line, self.column,
-                    None, None)
-
-    def determine_encoding(self):
-        while not self.eof and len(self.raw_buffer) < 2:
-            self.update_raw()
-        if not isinstance(self.raw_buffer, unicode):
-            if self.raw_buffer.startswith(codecs.BOM_UTF16_LE):
-                self.raw_decode = codecs.utf_16_le_decode
-                self.encoding = 'utf-16-le'
-            elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE):
-                self.raw_decode = codecs.utf_16_be_decode
-                self.encoding = 'utf-16-be'
-            else:
-                self.raw_decode = codecs.utf_8_decode
-                self.encoding = 'utf-8'
-        self.update(1)
-
-    NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]')
-    def check_printable(self, data):
-        match = self.NON_PRINTABLE.search(data)
-        if match:
-            character = match.group()
-            position = self.index+(len(self.buffer)-self.pointer)+match.start()
-            raise ReaderError(self.name, position, ord(character),
-                    'unicode', "special characters are not allowed")
-
-    def update(self, length):
-        if self.raw_buffer is None:
-            return
-        self.buffer = self.buffer[self.pointer:]
-        self.pointer = 0
-        while len(self.buffer) < length:
-            if not self.eof:
-                self.update_raw()
-            if self.raw_decode is not None:
-                try:
-                    data, converted = self.raw_decode(self.raw_buffer,
-                            'strict', self.eof)
-                except UnicodeDecodeError, exc:
-                    character = exc.object[exc.start]
-                    if self.stream is not None:
-                        position = self.stream_pointer-len(self.raw_buffer)+exc.start
-                    else:
-                        position = exc.start
-                    raise ReaderError(self.name, position, character,
-                            exc.encoding, exc.reason)
-            else:
-                data = self.raw_buffer
-                converted = len(data)
-            self.check_printable(data)
-            self.buffer += data
-            self.raw_buffer = self.raw_buffer[converted:]
-            if self.eof:
-                self.buffer += u'\0'
-                self.raw_buffer = None
-                break
-
-    def update_raw(self, size=1024):
-        data = self.stream.read(size)
-        if data:
-            self.raw_buffer += data
-            self.stream_pointer += len(data)
-        else:
-            self.eof = True
-
-#try:
-#    import psyco
-#    psyco.bind(Reader)
-#except ImportError:
-#    pass
-

libs/py2/yaml/representer.py

@@ -1,486 +0,0 @@
-
-__all__ = ['BaseRepresenter', 'SafeRepresenter', 'Representer',
-    'RepresenterError']
-
-from error import *
-from nodes import *
-
-import datetime
-
-import sys, copy_reg, types
-
-class RepresenterError(YAMLError):
-    pass
-
-class BaseRepresenter(object):
-
-    yaml_representers = {}
-    yaml_multi_representers = {}
-
-    def __init__(self, default_style=None, default_flow_style=None):
-        self.default_style = default_style
-        self.default_flow_style = default_flow_style
-        self.represented_objects = {}
-        self.object_keeper = []
-        self.alias_key = None
-
-    def represent(self, data):
-        node = self.represent_data(data)
-        self.serialize(node)
-        self.represented_objects = {}
-        self.object_keeper = []
-        self.alias_key = None
-
-    def get_classobj_bases(self, cls):
-        bases = [cls]
-        for base in cls.__bases__:
-            bases.extend(self.get_classobj_bases(base))
-        return bases
-
-    def represent_data(self, data):
-        if self.ignore_aliases(data):
-            self.alias_key = None
-        else:
-            self.alias_key = id(data)
-        if self.alias_key is not None:
-            if self.alias_key in self.represented_objects:
-                node = self.represented_objects[self.alias_key]
-                #if node is None:
-                #    raise RepresenterError("recursive objects are not allowed: %r" % data)
-                return node
-            #self.represented_objects[alias_key] = None
-            self.object_keeper.append(data)
-        data_types = type(data).__mro__
-        if type(data) is types.InstanceType:
-            data_types = self.get_classobj_bases(data.__class__)+list(data_types)
-        if data_types[0] in self.yaml_representers:
-            node = self.yaml_representers[data_types[0]](self, data)
-        else:
-            for data_type in data_types:
-                if data_type in self.yaml_multi_representers:
-                    node = self.yaml_multi_representers[data_type](self, data)
-                    break
-            else:
-                if None in self.yaml_multi_representers:
-                    node = self.yaml_multi_representers[None](self, data)
-                elif None in self.yaml_representers:
-                    node = self.yaml_representers[None](self, data)
-                else:
-                    node = ScalarNode(None, unicode(data))
-        #if alias_key is not None:
-        #    self.represented_objects[alias_key] = node
-        return node
-
-    def add_representer(cls, data_type, representer):
-        if not 'yaml_representers' in cls.__dict__:
-            cls.yaml_representers = cls.yaml_representers.copy()
-        cls.yaml_representers[data_type] = representer
-    add_representer = classmethod(add_representer)
-
-    def add_multi_representer(cls, data_type, representer):
-        if not 'yaml_multi_representers' in cls.__dict__:
-            cls.yaml_multi_representers = cls.yaml_multi_representers.copy()
-        cls.yaml_multi_representers[data_type] = representer
-    add_multi_representer = classmethod(add_multi_representer)
-
-    def represent_scalar(self, tag, value, style=None):
-        if style is None:
-            style = self.default_style
-        node = ScalarNode(tag, value, style=style)
-        if self.alias_key is not None:
-            self.represented_objects[self.alias_key] = node
-        return node
-
-    def represent_sequence(self, tag, sequence, flow_style=None):
-        value = []
-        node = SequenceNode(tag, value, flow_style=flow_style)
-        if self.alias_key is not None:
-            self.represented_objects[self.alias_key] = node
-        best_style = True
-        for item in sequence:
-            node_item = self.represent_data(item)
-            if not (isinstance(node_item, ScalarNode) and not node_item.style):
-                best_style = False
-            value.append(node_item)
-        if flow_style is None:
-            if self.default_flow_style is not None:
-                node.flow_style = self.default_flow_style
-            else:
-                node.flow_style = best_style
-        return node
-
-    def represent_mapping(self, tag, mapping, flow_style=None):
-        value = []
-        node = MappingNode(tag, value, flow_style=flow_style)
-        if self.alias_key is not None:
-            self.represented_objects[self.alias_key] = node
-        best_style = True
-        if hasattr(mapping, 'items'):
-            mapping = mapping.items()
-            mapping.sort()
-        for item_key, item_value in mapping:
-            node_key = self.represent_data(item_key)
-            node_value = self.represent_data(item_value)
-            if not (isinstance(node_key, ScalarNode) and not node_key.style):
-                best_style = False
-            if not (isinstance(node_value, ScalarNode) and not node_value.style):
-                best_style = False
-            value.append((node_key, node_value))
-        if flow_style is None:
-            if self.default_flow_style is not None:
-                node.flow_style = self.default_flow_style
-            else:
-                node.flow_style = best_style
-        return node
-
-    def ignore_aliases(self, data):
-        return False
-
-class SafeRepresenter(BaseRepresenter):
-
-    def ignore_aliases(self, data):
-        if data is None:
-            return True
-        if isinstance(data, tuple) and data == ():
-            return True
-        if isinstance(data, (str, unicode, bool, int, float)):
-            return True
-
-    def represent_none(self, data):
-        return self.represent_scalar(u'tag:yaml.org,2002:null',
-                u'null')
-
-    def represent_str(self, data):
-        tag = None
-        style = None
-        try:
-            data = unicode(data, 'ascii')
-            tag = u'tag:yaml.org,2002:str'
-        except UnicodeDecodeError:
-            try:
-                data = unicode(data, 'utf-8')
-                tag = u'tag:yaml.org,2002:str'
-            except UnicodeDecodeError:
-                data = data.encode('base64')
-                tag = u'tag:yaml.org,2002:binary'
-                style = '|'
-        return self.represent_scalar(tag, data, style=style)
-
-    def represent_unicode(self, data):
-        return self.represent_scalar(u'tag:yaml.org,2002:str', data)
-
-    def represent_bool(self, data):
-        if data:
-            value = u'true'
-        else:
-            value = u'false'
-        return self.represent_scalar(u'tag:yaml.org,2002:bool', value)
-
-    def represent_int(self, data):
-        return self.represent_scalar(u'tag:yaml.org,2002:int', unicode(data))
-
-    def represent_long(self, data):
-        return self.represent_scalar(u'tag:yaml.org,2002:int', unicode(data))
-
-    inf_value = 1e300
-    while repr(inf_value) != repr(inf_value*inf_value):
-        inf_value *= inf_value
-
-    def represent_float(self, data):
-        if data != data or (data == 0.0 and data == 1.0):
-            value = u'.nan'
-        elif data == self.inf_value:
-            value = u'.inf'
-        elif data == -self.inf_value:
-            value = u'-.inf'
-        else:
-            value = unicode(repr(data)).lower()
-            # Note that in some cases `repr(data)` represents a float number
-            # without the decimal parts.  For instance:
-            #   >>> repr(1e17)
-            #   '1e17'
-            # Unfortunately, this is not a valid float representation according
-            # to the definition of the `!!float` tag.  We fix this by adding
-            # '.0' before the 'e' symbol.
-            if u'.' not in value and u'e' in value:
-                value = value.replace(u'e', u'.0e', 1)
-        return self.represent_scalar(u'tag:yaml.org,2002:float', value)
-
-    def represent_list(self, data):
-        #pairs = (len(data) > 0 and isinstance(data, list))
-        #if pairs:
-        #    for item in data:
-        #        if not isinstance(item, tuple) or len(item) != 2:
-        #            pairs = False
-        #            break
-        #if not pairs:
-            return self.represent_sequence(u'tag:yaml.org,2002:seq', data)
-        #value = []
-        #for item_key, item_value in data:
-        #    value.append(self.represent_mapping(u'tag:yaml.org,2002:map',
-        #        [(item_key, item_value)]))
-        #return SequenceNode(u'tag:yaml.org,2002:pairs', value)
-
-    def represent_dict(self, data):
-        return self.represent_mapping(u'tag:yaml.org,2002:map', data)
-
-    def represent_set(self, data):
-        value = {}
-        for key in data:
-            value[key] = None
-        return self.represent_mapping(u'tag:yaml.org,2002:set', value)
-
-    def represent_date(self, data):
-        value = unicode(data.isoformat())
-        return self.represent_scalar(u'tag:yaml.org,2002:timestamp', value)
-
-    def represent_datetime(self, data):
-        value = unicode(data.isoformat(' '))
-        return self.represent_scalar(u'tag:yaml.org,2002:timestamp', value)
-
-    def represent_yaml_object(self, tag, data, cls, flow_style=None):
-        if hasattr(data, '__getstate__'):
-            state = data.__getstate__()
-        else:
-            state = data.__dict__.copy()
-        return self.represent_mapping(tag, state, flow_style=flow_style)
-
-    def represent_undefined(self, data):
-        raise RepresenterError("cannot represent an object: %s" % data)
-
-SafeRepresenter.add_representer(type(None),
-        SafeRepresenter.represent_none)
-
-SafeRepresenter.add_representer(str,
-        SafeRepresenter.represent_str)
-
-SafeRepresenter.add_representer(unicode,
-        SafeRepresenter.represent_unicode)
-
-SafeRepresenter.add_representer(bool,
-        SafeRepresenter.represent_bool)
-
-SafeRepresenter.add_representer(int,
-        SafeRepresenter.represent_int)
-
-SafeRepresenter.add_representer(long,
-        SafeRepresenter.represent_long)
-
-SafeRepresenter.add_representer(float,
-        SafeRepresenter.represent_float)
-
-SafeRepresenter.add_representer(list,
-        SafeRepresenter.represent_list)
-
-SafeRepresenter.add_representer(tuple,
-        SafeRepresenter.represent_list)
-
-SafeRepresenter.add_representer(dict,
-        SafeRepresenter.represent_dict)
-
-SafeRepresenter.add_representer(set,
-        SafeRepresenter.represent_set)
-
-SafeRepresenter.add_representer(datetime.date,
-        SafeRepresenter.represent_date)
-
-SafeRepresenter.add_representer(datetime.datetime,
-        SafeRepresenter.represent_datetime)
-
-SafeRepresenter.add_representer(None,
-        SafeRepresenter.represent_undefined)
-
-class Representer(SafeRepresenter):
-
-    def represent_str(self, data):
-        tag = None
-        style = None
-        try:
-            data = unicode(data, 'ascii')
-            tag = u'tag:yaml.org,2002:str'
-        except UnicodeDecodeError:
-            try:
-                data = unicode(data, 'utf-8')
-                tag = u'tag:yaml.org,2002:python/str'
-            except UnicodeDecodeError:
-                data = data.encode('base64')
-                tag = u'tag:yaml.org,2002:binary'
-                style = '|'
-        return self.represent_scalar(tag, data, style=style)
-
-    def represent_unicode(self, data):
-        tag = None
-        try:
-            data.encode('ascii')
-            tag = u'tag:yaml.org,2002:python/unicode'
-        except UnicodeEncodeError:
-            tag = u'tag:yaml.org,2002:str'
-        return self.represent_scalar(tag, data)
-
-    def represent_long(self, data):
-        tag = u'tag:yaml.org,2002:int'
-        if int(data) is not data:
-            tag = u'tag:yaml.org,2002:python/long'
-        return self.represent_scalar(tag, unicode(data))
-
-    def represent_complex(self, data):
-        if data.imag == 0.0:
-            data = u'%r' % data.real
-        elif data.real == 0.0:
-            data = u'%rj' % data.imag
-        elif data.imag > 0:
-            data = u'%r+%rj' % (data.real, data.imag)
-        else:
-            data = u'%r%rj' % (data.real, data.imag)
-        return self.represent_scalar(u'tag:yaml.org,2002:python/complex', data)
-
-    def represent_tuple(self, data):
-        return self.represent_sequence(u'tag:yaml.org,2002:python/tuple', data)
-
-    def represent_name(self, data):
-        name = u'%s.%s' % (data.__module__, data.__name__)
-        return self.represent_scalar(u'tag:yaml.org,2002:python/name:'+name, u'')
-
-    def represent_module(self, data):
-        return self.represent_scalar(
-                u'tag:yaml.org,2002:python/module:'+data.__name__, u'')
-
-    def represent_instance(self, data):
-        # For instances of classic classes, we use __getinitargs__ and
-        # __getstate__ to serialize the data.
-
-        # If data.__getinitargs__ exists, the object must be reconstructed by
-        # calling cls(**args), where args is a tuple returned by
-        # __getinitargs__. Otherwise, the cls.__init__ method should never be
-        # called and the class instance is created by instantiating a trivial
-        # class and assigning to the instance's __class__ variable.
-
-        # If data.__getstate__ exists, it returns the state of the object.
-        # Otherwise, the state of the object is data.__dict__.
-
-        # We produce either a !!python/object or !!python/object/new node.
-        # If data.__getinitargs__ does not exist and state is a dictionary, we
-        # produce a !!python/object node . Otherwise we produce a
-        # !!python/object/new node.
-
-        cls = data.__class__
-        class_name = u'%s.%s' % (cls.__module__, cls.__name__)
-        args = None
-        state = None
-        if hasattr(data, '__getinitargs__'):
-            args = list(data.__getinitargs__())
-        if hasattr(data, '__getstate__'):
-            state = data.__getstate__()
-        else:
-            state = data.__dict__
-        if args is None and isinstance(state, dict):
-            return self.represent_mapping(
-                    u'tag:yaml.org,2002:python/object:'+class_name, state)
-        if isinstance(state, dict) and not state:
-            return self.represent_sequence(
-                    u'tag:yaml.org,2002:python/object/new:'+class_name, args)
-        value = {}
-        if args:
-            value['args'] = args
-        value['state'] = state
-        return self.represent_mapping(
-                u'tag:yaml.org,2002:python/object/new:'+class_name, value)
-
-    def represent_object(self, data):
-        # We use __reduce__ API to save the data. data.__reduce__ returns
-        # a tuple of length 2-5:
-        #   (function, args, state, listitems, dictitems)
-
-        # For reconstructing, we calls function(*args), then set its state,
-        # listitems, and dictitems if they are not None.
-
-        # A special case is when function.__name__ == '__newobj__'. In this
-        # case we create the object with args[0].__new__(*args).
-
-        # Another special case is when __reduce__ returns a string - we don't
-        # support it.
-
-        # We produce a !!python/object, !!python/object/new or
-        # !!python/object/apply node.
-
-        cls = type(data)
-        if cls in copy_reg.dispatch_table:
-            reduce = copy_reg.dispatch_table[cls](data)
-        elif hasattr(data, '__reduce_ex__'):
-            reduce = data.__reduce_ex__(2)
-        elif hasattr(data, '__reduce__'):
-            reduce = data.__reduce__()
-        else:
-            raise RepresenterError("cannot represent object: %r" % data)
-        reduce = (list(reduce)+[None]*5)[:5]
-        function, args, state, listitems, dictitems = reduce
-        args = list(args)
-        if state is None:
-            state = {}
-        if listitems is not None:
-            listitems = list(listitems)
-        if dictitems is not None:
-            dictitems = dict(dictitems)
-        if function.__name__ == '__newobj__':
-            function = args[0]
-            args = args[1:]
-            tag = u'tag:yaml.org,2002:python/object/new:'
-            newobj = True
-        else:
-            tag = u'tag:yaml.org,2002:python/object/apply:'
-            newobj = False
-        function_name = u'%s.%s' % (function.__module__, function.__name__)
-        if not args and not listitems and not dictitems \
-                and isinstance(state, dict) and newobj:
-            return self.represent_mapping(
-                    u'tag:yaml.org,2002:python/object:'+function_name, state)
-        if not listitems and not dictitems  \
-                and isinstance(state, dict) and not state:
-            return self.represent_sequence(tag+function_name, args)
-        value = {}
-        if args:
-            value['args'] = args
-        if state or not isinstance(state, dict):
-            value['state'] = state
-        if listitems:
-            value['listitems'] = listitems
-        if dictitems:
-            value['dictitems'] = dictitems
-        return self.represent_mapping(tag+function_name, value)
-
-Representer.add_representer(str,
-        Representer.represent_str)
-
-Representer.add_representer(unicode,
-        Representer.represent_unicode)
-
-Representer.add_representer(long,
-        Representer.represent_long)
-
-Representer.add_representer(complex,
-        Representer.represent_complex)
-
-Representer.add_representer(tuple,
-        Representer.represent_tuple)
-
-Representer.add_representer(type,
-        Representer.represent_name)
-
-Representer.add_representer(types.ClassType,
-        Representer.represent_name)
-
-Representer.add_representer(types.FunctionType,
-        Representer.represent_name)
-
-Representer.add_representer(types.BuiltinFunctionType,
-        Representer.represent_name)
-
-Representer.add_representer(types.ModuleType,
-        Representer.represent_module)
-
-Representer.add_multi_representer(types.InstanceType,
-        Representer.represent_instance)
-
-Representer.add_multi_representer(object,
-        Representer.represent_object)
-

libs/py2/yaml/resolver.py

@@ -1,227 +0,0 @@
-
-__all__ = ['BaseResolver', 'Resolver']
-
-from error import *
-from nodes import *
-
-import re
-
-class ResolverError(YAMLError):
-    pass
-
-class BaseResolver(object):
-
-    DEFAULT_SCALAR_TAG = u'tag:yaml.org,2002:str'
-    DEFAULT_SEQUENCE_TAG = u'tag:yaml.org,2002:seq'
-    DEFAULT_MAPPING_TAG = u'tag:yaml.org,2002:map'
-
-    yaml_implicit_resolvers = {}
-    yaml_path_resolvers = {}
-
-    def __init__(self):
-        self.resolver_exact_paths = []
-        self.resolver_prefix_paths = []
-
-    def add_implicit_resolver(cls, tag, regexp, first):
-        if not 'yaml_implicit_resolvers' in cls.__dict__:
-            implicit_resolvers = {}
-            for key in cls.yaml_implicit_resolvers:
-                implicit_resolvers[key] = cls.yaml_implicit_resolvers[key][:]
-            cls.yaml_implicit_resolvers = implicit_resolvers
-        if first is None:
-            first = [None]
-        for ch in first:
-            cls.yaml_implicit_resolvers.setdefault(ch, []).append((tag, regexp))
-    add_implicit_resolver = classmethod(add_implicit_resolver)
-
-    def add_path_resolver(cls, tag, path, kind=None):
-        # Note: `add_path_resolver` is experimental.  The API could be changed.
-        # `new_path` is a pattern that is matched against the path from the
-        # root to the node that is being considered.  `node_path` elements are
-        # tuples `(node_check, index_check)`.  `node_check` is a node class:
-        # `ScalarNode`, `SequenceNode`, `MappingNode` or `None`.  `None`
-        # matches any kind of a node.  `index_check` could be `None`, a boolean
-        # value, a string value, or a number.  `None` and `False` match against
-        # any _value_ of sequence and mapping nodes.  `True` matches against
-        # any _key_ of a mapping node.  A string `index_check` matches against
-        # a mapping value that corresponds to a scalar key which content is
-        # equal to the `index_check` value.  An integer `index_check` matches
-        # against a sequence value with the index equal to `index_check`.
-        if not 'yaml_path_resolvers' in cls.__dict__:
-            cls.yaml_path_resolvers = cls.yaml_path_resolvers.copy()
-        new_path = []
-        for element in path:
-            if isinstance(element, (list, tuple)):
-                if len(element) == 2:
-                    node_check, index_check = element
-                elif len(element) == 1:
-                    node_check = element[0]
-                    index_check = True
-                else:
-                    raise ResolverError("Invalid path element: %s" % element)
-            else:
-                node_check = None
-                index_check = element
-            if node_check is str:
-                node_check = ScalarNode
-            elif node_check is list:
-                node_check = SequenceNode
-            elif node_check is dict:
-                node_check = MappingNode
-            elif node_check not in [ScalarNode, SequenceNode, MappingNode]  \
-                    and not isinstance(node_check, basestring)  \
-                    and node_check is not None:
-                raise ResolverError("Invalid node checker: %s" % node_check)
-            if not isinstance(index_check, (basestring, int))   \
-                    and index_check is not None:
-                raise ResolverError("Invalid index checker: %s" % index_check)
-            new_path.append((node_check, index_check))
-        if kind is str:
-            kind = ScalarNode
-        elif kind is list:
-            kind = SequenceNode
-        elif kind is dict:
-            kind = MappingNode
-        elif kind not in [ScalarNode, SequenceNode, MappingNode]    \
-                and kind is not None:
-            raise ResolverError("Invalid node kind: %s" % kind)
-        cls.yaml_path_resolvers[tuple(new_path), kind] = tag
-    add_path_resolver = classmethod(add_path_resolver)
-
-    def descend_resolver(self, current_node, current_index):
-        if not self.yaml_path_resolvers:
-            return
-        exact_paths = {}
-        prefix_paths = []
-        if current_node:
-            depth = len(self.resolver_prefix_paths)
-            for path, kind in self.resolver_prefix_paths[-1]:
-                if self.check_resolver_prefix(depth, path, kind,
-                        current_node, current_index):
-                    if len(path) > depth:
-                        prefix_paths.append((path, kind))
-                    else:
-                        exact_paths[kind] = self.yaml_path_resolvers[path, kind]
-        else:
-            for path, kind in self.yaml_path_resolvers:
-                if not path:
-                    exact_paths[kind] = self.yaml_path_resolvers[path, kind]
-                else:
-                    prefix_paths.append((path, kind))
-        self.resolver_exact_paths.append(exact_paths)
-        self.resolver_prefix_paths.append(prefix_paths)
-
-    def ascend_resolver(self):
-        if not self.yaml_path_resolvers:
-            return
-        self.resolver_exact_paths.pop()
-        self.resolver_prefix_paths.pop()
-
-    def check_resolver_prefix(self, depth, path, kind,
-            current_node, current_index):
-        node_check, index_check = path[depth-1]
-        if isinstance(node_check, basestring):
-            if current_node.tag != node_check:
-                return
-        elif node_check is not None:
-            if not isinstance(current_node, node_check):
-                return
-        if index_check is True and current_index is not None:
-            return
-        if (index_check is False or index_check is None)    \
-                and current_index is None:
-            return
-        if isinstance(index_check, basestring):
-            if not (isinstance(current_index, ScalarNode)
-                    and index_check == current_index.value):
-                return
-        elif isinstance(index_check, int) and not isinstance(index_check, bool):
-            if index_check != current_index:
-                return
-        return True
-
-    def resolve(self, kind, value, implicit):
-        if kind is ScalarNode and implicit[0]:
-            if value == u'':
-                resolvers = self.yaml_implicit_resolvers.get(u'', [])
-            else:
-                resolvers = self.yaml_implicit_resolvers.get(value[0], [])
-            resolvers += self.yaml_implicit_resolvers.get(None, [])
-            for tag, regexp in resolvers:
-                if regexp.match(value):
-                    return tag
-            implicit = implicit[1]
-        if self.yaml_path_resolvers:
-            exact_paths = self.resolver_exact_paths[-1]
-            if kind in exact_paths:
-                return exact_paths[kind]
-            if None in exact_paths:
-                return exact_paths[None]
-        if kind is ScalarNode:
-            return self.DEFAULT_SCALAR_TAG
-        elif kind is SequenceNode:
-            return self.DEFAULT_SEQUENCE_TAG
-        elif kind is MappingNode:
-            return self.DEFAULT_MAPPING_TAG
-
-class Resolver(BaseResolver):
-    pass
-
-Resolver.add_implicit_resolver(
-        u'tag:yaml.org,2002:bool',
-        re.compile(ur'''^(?:yes|Yes|YES|no|No|NO
-                    |true|True|TRUE|false|False|FALSE
-                    |on|On|ON|off|Off|OFF)$''', re.X),
-        list(u'yYnNtTfFoO'))
-
-Resolver.add_implicit_resolver(
-        u'tag:yaml.org,2002:float',
-        re.compile(ur'''^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+][0-9]+)?
-                    |\.[0-9_]+(?:[eE][-+][0-9]+)?
-                    |[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]*
-                    |[-+]?\.(?:inf|Inf|INF)
-                    |\.(?:nan|NaN|NAN))$''', re.X),
-        list(u'-+0123456789.'))
-
-Resolver.add_implicit_resolver(
-        u'tag:yaml.org,2002:int',
-        re.compile(ur'''^(?:[-+]?0b[0-1_]+
-                    |[-+]?0[0-7_]+
-                    |[-+]?(?:0|[1-9][0-9_]*)
-                    |[-+]?0x[0-9a-fA-F_]+
-                    |[-+]?[1-9][0-9_]*(?::[0-5]?[0-9])+)$''', re.X),
-        list(u'-+0123456789'))
-
-Resolver.add_implicit_resolver(
-        u'tag:yaml.org,2002:merge',
-        re.compile(ur'^(?:<<)$'),
-        [u'<'])
-
-Resolver.add_implicit_resolver(
-        u'tag:yaml.org,2002:null',
-        re.compile(ur'''^(?: ~
-                    |null|Null|NULL
-                    | )$''', re.X),
-        [u'~', u'n', u'N', u''])
-
-Resolver.add_implicit_resolver(
-        u'tag:yaml.org,2002:timestamp',
-        re.compile(ur'''^(?:[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]
-                    |[0-9][0-9][0-9][0-9] -[0-9][0-9]? -[0-9][0-9]?
-                     (?:[Tt]|[ \t]+)[0-9][0-9]?
-                     :[0-9][0-9] :[0-9][0-9] (?:\.[0-9]*)?
-                     (?:[ \t]*(?:Z|[-+][0-9][0-9]?(?::[0-9][0-9])?))?)$''', re.X),
-        list(u'0123456789'))
-
-Resolver.add_implicit_resolver(
-        u'tag:yaml.org,2002:value',
-        re.compile(ur'^(?:=)$'),
-        [u'='])
-
-# The following resolver is only for documentation purposes. It cannot work
-# because plain scalars cannot start with '!', '&', or '*'.
-Resolver.add_implicit_resolver(
-        u'tag:yaml.org,2002:yaml',
-        re.compile(ur'^(?:!|&|\*)$'),
-        list(u'!&*'))
-

libs/py2/yaml/serializer.py

@@ -1,111 +0,0 @@
-
-__all__ = ['Serializer', 'SerializerError']
-
-from error import YAMLError
-from events import *
-from nodes import *
-
-class SerializerError(YAMLError):
-    pass
-
-class Serializer(object):
-
-    ANCHOR_TEMPLATE = u'id%03d'
-
-    def __init__(self, encoding=None,
-            explicit_start=None, explicit_end=None, version=None, tags=None):
-        self.use_encoding = encoding
-        self.use_explicit_start = explicit_start
-        self.use_explicit_end = explicit_end
-        self.use_version = version
-        self.use_tags = tags
-        self.serialized_nodes = {}
-        self.anchors = {}
-        self.last_anchor_id = 0
-        self.closed = None
-
-    def open(self):
-        if self.closed is None:
-            self.emit(StreamStartEvent(encoding=self.use_encoding))
-            self.closed = False
-        elif self.closed:
-            raise SerializerError("serializer is closed")
-        else:
-            raise SerializerError("serializer is already opened")
-
-    def close(self):
-        if self.closed is None:
-            raise SerializerError("serializer is not opened")
-        elif not self.closed:
-            self.emit(StreamEndEvent())
-            self.closed = True
-
-    #def __del__(self):
-    #    self.close()
-
-    def serialize(self, node):
-        if self.closed is None:
-            raise SerializerError("serializer is not opened")
-        elif self.closed:
-            raise SerializerError("serializer is closed")
-        self.emit(DocumentStartEvent(explicit=self.use_explicit_start,
-            version=self.use_version, tags=self.use_tags))
-        self.anchor_node(node)
-        self.serialize_node(node, None, None)
-        self.emit(DocumentEndEvent(explicit=self.use_explicit_end))
-        self.serialized_nodes = {}
-        self.anchors = {}
-        self.last_anchor_id = 0
-
-    def anchor_node(self, node):
-        if node in self.anchors:
-            if self.anchors[node] is None:
-                self.anchors[node] = self.generate_anchor(node)
-        else:
-            self.anchors[node] = None
-            if isinstance(node, SequenceNode):
-                for item in node.value:
-                    self.anchor_node(item)
-            elif isinstance(node, MappingNode):
-                for key, value in node.value:
-                    self.anchor_node(key)
-                    self.anchor_node(value)
-
-    def generate_anchor(self, node):
-        self.last_anchor_id += 1
-        return self.ANCHOR_TEMPLATE % self.last_anchor_id
-
-    def serialize_node(self, node, parent, index):
-        alias = self.anchors[node]
-        if node in self.serialized_nodes:
-            self.emit(AliasEvent(alias))
-        else:
-            self.serialized_nodes[node] = True
-            self.descend_resolver(parent, index)
-            if isinstance(node, ScalarNode):
-                detected_tag = self.resolve(ScalarNode, node.value, (True, False))
-                default_tag = self.resolve(ScalarNode, node.value, (False, True))
-                implicit = (node.tag == detected_tag), (node.tag == default_tag)
-                self.emit(ScalarEvent(alias, node.tag, implicit, node.value,
-                    style=node.style))
-            elif isinstance(node, SequenceNode):
-                implicit = (node.tag
-                            == self.resolve(SequenceNode, node.value, True))
-                self.emit(SequenceStartEvent(alias, node.tag, implicit,
-                    flow_style=node.flow_style))
-                index = 0
-                for item in node.value:
-                    self.serialize_node(item, node, index)
-                    index += 1
-                self.emit(SequenceEndEvent())
-            elif isinstance(node, MappingNode):
-                implicit = (node.tag
-                            == self.resolve(MappingNode, node.value, True))
-                self.emit(MappingStartEvent(alias, node.tag, implicit,
-                    flow_style=node.flow_style))
-                for key, value in node.value:
-                    self.serialize_node(key, node, None)
-                    self.serialize_node(value, node, key)
-                self.emit(MappingEndEvent())
-            self.ascend_resolver()
-

libs/py2/yaml/tokens.py

@@ -1,104 +0,0 @@
-
-class Token(object):
-    def __init__(self, start_mark, end_mark):
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-    def __repr__(self):
-        attributes = [key for key in self.__dict__
-                if not key.endswith('_mark')]
-        attributes.sort()
-        arguments = ', '.join(['%s=%r' % (key, getattr(self, key))
-                for key in attributes])
-        return '%s(%s)' % (self.__class__.__name__, arguments)
-
-#class BOMToken(Token):
-#    id = '<byte order mark>'
-
-class DirectiveToken(Token):
-    id = '<directive>'
-    def __init__(self, name, value, start_mark, end_mark):
-        self.name = name
-        self.value = value
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-
-class DocumentStartToken(Token):
-    id = '<document start>'
-
-class DocumentEndToken(Token):
-    id = '<document end>'
-
-class StreamStartToken(Token):
-    id = '<stream start>'
-    def __init__(self, start_mark=None, end_mark=None,
-            encoding=None):
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-        self.encoding = encoding
-
-class StreamEndToken(Token):
-    id = '<stream end>'
-
-class BlockSequenceStartToken(Token):
-    id = '<block sequence start>'
-
-class BlockMappingStartToken(Token):
-    id = '<block mapping start>'
-
-class BlockEndToken(Token):
-    id = '<block end>'
-
-class FlowSequenceStartToken(Token):
-    id = '['
-
-class FlowMappingStartToken(Token):
-    id = '{'
-
-class FlowSequenceEndToken(Token):
-    id = ']'
-
-class FlowMappingEndToken(Token):
-    id = '}'
-
-class KeyToken(Token):
-    id = '?'
-
-class ValueToken(Token):
-    id = ':'
-
-class BlockEntryToken(Token):
-    id = '-'
-
-class FlowEntryToken(Token):
-    id = ','
-
-class AliasToken(Token):
-    id = '<alias>'
-    def __init__(self, value, start_mark, end_mark):
-        self.value = value
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-
-class AnchorToken(Token):
-    id = '<anchor>'
-    def __init__(self, value, start_mark, end_mark):
-        self.value = value
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-
-class TagToken(Token):
-    id = '<tag>'
-    def __init__(self, value, start_mark, end_mark):
-        self.value = value
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-
-class ScalarToken(Token):
-    id = '<scalar>'
-    def __init__(self, value, plain, start_mark, end_mark, style=None):
-        self.value = value
-        self.plain = plain
-        self.start_mark = start_mark
-        self.end_mark = end_mark
-        self.style = style
-

libs/requirements-py2.txt

@@ -1,5 +0,0 @@
-backports.functools-lru-cache
-beautifulsoup4
-enum34
-futures
-pyyaml

setup.py

@@ -73,8 +73,6 @@ setup(
         'Operating System :: POSIX',
         'Operating System :: Unix',
         'Programming Language :: Python',
-        'Programming Language :: Python :: 2',
-        'Programming Language :: Python :: 2.7',
         'Programming Language :: Python :: 3',
         'Programming Language :: Python :: 3.4',
         'Programming Language :: Python :: 3.5',

tox.ini

@@ -4,12 +4,11 @@
 envlist =
     clean,
     check,
-    {py27, py35, py36, py37},
+    {py35, py36, py37},
     report
 
 [testenv]
 basepython =
-    py27: {env:TOXPYTHON:python2.7}
     py35: {env:TOXPYTHON:python3.5}
     py36: {env:TOXPYTHON:python3.6}
     py37: {env:TOXPYTHON:python3.7}