mirror of
https://github.com/Tautulli/Tautulli.git
synced 2025-08-20 21:33:18 -07:00
Bump cherrypy from 18.8.0 to 18.9.0 (#2266)
* Bump cherrypy from 18.8.0 to 18.9.0 Bumps [cherrypy](https://github.com/cherrypy/cherrypy) from 18.8.0 to 18.9.0. - [Changelog](https://github.com/cherrypy/cherrypy/blob/main/CHANGES.rst) - [Commits](https://github.com/cherrypy/cherrypy/compare/v18.8.0...v18.9.0) --- updated-dependencies: - dependency-name: cherrypy dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Update cherrypy==18.9.0 --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: JonnyWong16 <9099342+JonnyWong16@users.noreply.github.com> [skip ci]
This commit is contained in:
dependabot[bot]
GitHub
parent
cfefa928be
commit
faef9a94c4
673 changed files with 159850 additions and 11583 deletions
1
lib/win32comext/ifilter/__init__.py
Normal file
1
lib/win32comext/ifilter/__init__.py
Normal file
|
|
@ -0,0 +1 @@
|
|||
# empty file to designate as a package.
|
||||
300
lib/win32comext/ifilter/demo/filterDemo.py
Normal file
300
lib/win32comext/ifilter/demo/filterDemo.py
Normal file
|
|
@ -0,0 +1,300 @@
|
|||
import pythoncom
|
||||
import pywintypes
|
||||
from win32com import storagecon
|
||||
from win32com.ifilter import ifilter
|
||||
from win32com.ifilter.ifiltercon import *
|
||||
|
||||
|
||||
class FileParser:
|
||||
# Property IDs for the Storage Property Set
|
||||
PIDS_BODY = 0x00000013
|
||||
|
||||
# property IDs for HTML Storage Property Set
|
||||
PIDH_DESCRIPTION = "DESCRIPTION"
|
||||
PIDH_HREF = "A.HREF"
|
||||
PIDH_IMGSRC = "IMG.SRC"
|
||||
|
||||
# conversion map to convert ifilter properties to more user friendly names
|
||||
propertyToName = {
|
||||
PSGUID_STORAGE: {PIDS_BODY: "body"},
|
||||
PSGUID_SUMMARYINFORMATION: {
|
||||
PIDSI_TITLE: "title",
|
||||
PIDSI_SUBJECT: "description",
|
||||
PIDSI_AUTHOR: "author",
|
||||
PIDSI_KEYWORDS: "keywords",
|
||||
PIDSI_COMMENTS: "comments",
|
||||
},
|
||||
PSGUID_HTMLINFORMATION: {PIDH_DESCRIPTION: "description"},
|
||||
PSGUID_HTML2_INFORMATION: {PIDH_HREF: "href", PIDH_IMGSRC: "img"},
|
||||
}
|
||||
|
||||
def __init__(self, verbose=False):
|
||||
self.f = None
|
||||
self.stg = None
|
||||
self.verbose = verbose
|
||||
|
||||
def Close(self):
|
||||
self.f = None
|
||||
self.stg = None
|
||||
|
||||
def Parse(self, fileName, maxErrors=10):
|
||||
properties = {}
|
||||
|
||||
try:
|
||||
self._bind_to_filter(fileName)
|
||||
try:
|
||||
flags = self.f.Init(
|
||||
IFILTER_INIT_APPLY_INDEX_ATTRIBUTES
|
||||
| IFILTER_INIT_APPLY_OTHER_ATTRIBUTES
|
||||
)
|
||||
if flags == IFILTER_FLAGS_OLE_PROPERTIES and self.stg is not None:
|
||||
self._trace("filter requires to get properities via ole")
|
||||
self._get_properties(properties)
|
||||
|
||||
errCnt = 0
|
||||
while True:
|
||||
try:
|
||||
# each chunk returns a tuple with the following:-
|
||||
# idChunk = The chunk identifier. each chunk has a unique identifier
|
||||
# breakType = The type of break that separates the previous chunk from the current chunk. Values are:-
|
||||
# CHUNK_NO_BREAK=0,CHUNK_EOW=1,CHUNK_EOS= 2,CHUNK_EOP= 3,CHUNK_EOC= 4
|
||||
# flags = Flags indicate whether this chunk contains a text-type or a value-type property
|
||||
# locale = The language and sublanguage associated with a chunk of text
|
||||
# attr = A tuple containing the property to be applied to the chunk. Tuple is (propertyset GUID, property ID)
|
||||
# Property ID can be a number or string
|
||||
# idChunkSource = The ID of the source of a chunk. The value of the idChunkSource member depends on the nature of the chunk
|
||||
# startSource = The offset from which the source text for a derived chunk starts in the source chunk
|
||||
# lenSource = The length in characters of the source text from which the current chunk was derived.
|
||||
# A zero value signifies character-by-character correspondence between the source text and the derived text.
|
||||
|
||||
(
|
||||
idChunk,
|
||||
breakType,
|
||||
flags,
|
||||
locale,
|
||||
attr,
|
||||
idChunkSource,
|
||||
startSource,
|
||||
lenSource,
|
||||
) = self.f.GetChunk()
|
||||
self._trace(
|
||||
"Chunk details:",
|
||||
idChunk,
|
||||
breakType,
|
||||
flags,
|
||||
locale,
|
||||
attr,
|
||||
idChunkSource,
|
||||
startSource,
|
||||
lenSource,
|
||||
)
|
||||
|
||||
# attempt to map each property to a more user friendly name. If we don't know what it is just return
|
||||
# the set guid and property id. (note: the id can be a number or a string.
|
||||
propSet = self.propertyToName.get(attr[0])
|
||||
if propSet:
|
||||
propName = propSet.get(attr[1], "%s:%s" % attr)
|
||||
else:
|
||||
propName = "%s:%s" % attr
|
||||
|
||||
except pythoncom.com_error as e:
|
||||
if e[0] == FILTER_E_END_OF_CHUNKS:
|
||||
# we have read all the chunks
|
||||
break
|
||||
elif e[0] in [
|
||||
FILTER_E_EMBEDDING_UNAVAILABLE,
|
||||
FILTER_E_LINK_UNAVAILABLE,
|
||||
]:
|
||||
# the next chunk can't be read. Also keep track of the number of times we
|
||||
# fail as some filters (ie. the Msoft office ones can get stuck here)
|
||||
errCnt += 1
|
||||
if errCnt > maxErrors:
|
||||
raise
|
||||
else:
|
||||
continue
|
||||
elif e[0] == FILTER_E_ACCESS:
|
||||
self._trace("Access denied")
|
||||
raise
|
||||
elif e[0] == FILTER_E_PASSWORD:
|
||||
self._trace("Password required")
|
||||
raise
|
||||
else:
|
||||
# any other type of error really can't be recovered from
|
||||
raise
|
||||
|
||||
# reset consecutive errors (some filters may get stuck in a lopp if embedding or link failures occurs
|
||||
errCnt = 0
|
||||
|
||||
if flags == CHUNK_TEXT:
|
||||
# its a text segment - get all available text for this chunk.
|
||||
body_chunks = properties.setdefault(propName, [])
|
||||
self._get_text(body_chunks)
|
||||
elif flags == CHUNK_VALUE:
|
||||
# its a data segment - get the value
|
||||
properties[propName] = self.f.GetValue()
|
||||
else:
|
||||
self._trace("Unknown flag returned by GetChunk:", flags)
|
||||
finally:
|
||||
self.Close()
|
||||
|
||||
except pythoncom.com_error as e:
|
||||
self._trace("ERROR processing file", e)
|
||||
raise
|
||||
|
||||
return properties
|
||||
|
||||
def _bind_to_filter(self, fileName):
|
||||
"""
|
||||
See if the file is a structured storage file or a normal file
|
||||
and then return an ifilter interface by calling the appropriate bind/load function
|
||||
"""
|
||||
if pythoncom.StgIsStorageFile(fileName):
|
||||
self.stg = pythoncom.StgOpenStorage(
|
||||
fileName, None, storagecon.STGM_READ | storagecon.STGM_SHARE_DENY_WRITE
|
||||
)
|
||||
try:
|
||||
self.f = ifilter.BindIFilterFromStorage(self.stg)
|
||||
except pythoncom.com_error as e:
|
||||
if (
|
||||
e[0] == -2147467262
|
||||
): # 0x80004002: # no interface, try the load interface (this happens for some MSoft files)
|
||||
self.f = ifilter.LoadIFilter(fileName)
|
||||
else:
|
||||
raise
|
||||
else:
|
||||
self.f = ifilter.LoadIFilter(fileName)
|
||||
self.stg = None
|
||||
|
||||
def _get_text(self, body_chunks):
|
||||
"""
|
||||
Gets all the text for a particular chunk. We need to keep calling get text till all the
|
||||
segments for this chunk are retrieved
|
||||
"""
|
||||
while True:
|
||||
try:
|
||||
body_chunks.append(self.f.GetText())
|
||||
except pythoncom.com_error as e:
|
||||
if e[0] in [
|
||||
FILTER_E_NO_MORE_TEXT,
|
||||
FILTER_E_NO_MORE_TEXT,
|
||||
FILTER_E_NO_TEXT,
|
||||
]:
|
||||
break
|
||||
else:
|
||||
raise # not one of the values we were expecting
|
||||
|
||||
def _get_properties(self, properties):
|
||||
"""
|
||||
Use OLE property sets to get base properties
|
||||
"""
|
||||
try:
|
||||
pss = self.stg.QueryInterface(pythoncom.IID_IPropertySetStorage)
|
||||
except pythoncom.com_error as e:
|
||||
self._trace("No Property information could be retrieved", e)
|
||||
return
|
||||
|
||||
ps = pss.Open(PSGUID_SUMMARYINFORMATION)
|
||||
|
||||
props = (
|
||||
PIDSI_TITLE,
|
||||
PIDSI_SUBJECT,
|
||||
PIDSI_AUTHOR,
|
||||
PIDSI_KEYWORDS,
|
||||
PIDSI_COMMENTS,
|
||||
)
|
||||
|
||||
title, subject, author, keywords, comments = ps.ReadMultiple(props)
|
||||
if title is not None:
|
||||
properties["title"] = title
|
||||
if subject is not None:
|
||||
properties["description"] = subject
|
||||
if author is not None:
|
||||
properties["author"] = author
|
||||
if keywords is not None:
|
||||
properties["keywords"] = keywords
|
||||
if comments is not None:
|
||||
properties["comments"] = comments
|
||||
|
||||
def _trace(self, *args):
|
||||
if self.verbose:
|
||||
ret = " ".join([str(arg) for arg in args])
|
||||
try:
|
||||
print(ret)
|
||||
except IOError:
|
||||
pass
|
||||
|
||||
|
||||
def _usage():
|
||||
import os
|
||||
|
||||
print("Usage: %s filename [verbose [dumpbody]]" % (os.path.basename(sys.argv[0]),))
|
||||
print()
|
||||
print("Where:-")
|
||||
print("filename = name of the file to extract text & properties from")
|
||||
print("verbose = 1=debug output, 0=no debug output (default=0)")
|
||||
print("dumpbody = 1=print text content, 0=don't print content (default=1)")
|
||||
print()
|
||||
print("e.g. to dump a word file called spam.doc go:- filterDemo.py spam.doc")
|
||||
print()
|
||||
print("by default .htm, .txt, .doc, .dot, .xls, .xlt, .ppt are supported")
|
||||
print("you can filter .pdf's by downloading adobes ifilter component. ")
|
||||
print(
|
||||
"(currently found at http://download.adobe.com/pub/adobe/acrobat/win/all/ifilter50.exe)."
|
||||
)
|
||||
print("ifilters for other filetypes are also available.")
|
||||
print()
|
||||
print(
|
||||
"This extension is only supported on win2000 & winXP - because thats the only"
|
||||
)
|
||||
print("place the ifilter stuff is supported. For more info on the API check out ")
|
||||
print("MSDN under ifilters")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import operator
|
||||
import sys
|
||||
|
||||
fName = ""
|
||||
verbose = False
|
||||
bDumpBody = True
|
||||
|
||||
if len(sys.argv) < 2:
|
||||
_usage()
|
||||
sys.exit(1)
|
||||
|
||||
try:
|
||||
fName = sys.argv[1]
|
||||
verbose = sys.argv[2] != "0"
|
||||
bDumpBody = sys.argv[3] != "0"
|
||||
except:
|
||||
pass
|
||||
|
||||
p = FileParser(verbose)
|
||||
propMap = p.Parse(fName)
|
||||
|
||||
if bDumpBody:
|
||||
print("Body")
|
||||
ch = " ".join(propMap.get("body", []))
|
||||
try:
|
||||
print(ch)
|
||||
except UnicodeError:
|
||||
print(ch.encode("iso8859-1", "ignore"))
|
||||
|
||||
print("Properties")
|
||||
for propName, propValue in propMap.items():
|
||||
print(propName, ":", end=" ")
|
||||
if propName == "body":
|
||||
print(
|
||||
"<%s length: %d>"
|
||||
% (
|
||||
propName,
|
||||
reduce(operator.add, [len(p) for p in propValue]),
|
||||
)
|
||||
)
|
||||
elif type(propValue) == type([]):
|
||||
print()
|
||||
for pv in propValue:
|
||||
print(pv)
|
||||
else:
|
||||
print(propValue)
|
||||
print()
|
||||
BIN
lib/win32comext/ifilter/ifilter.pyd
Normal file
BIN
lib/win32comext/ifilter/ifilter.pyd
Normal file
Binary file not shown.
110
lib/win32comext/ifilter/ifiltercon.py
Normal file
110
lib/win32comext/ifilter/ifiltercon.py
Normal file
|
|
@ -0,0 +1,110 @@
|
|||
# manual stuff
|
||||
from pywintypes import IID
|
||||
|
||||
PSGUID_STORAGE = IID("{B725F130-47EF-101A-A5F1-02608C9EEBAC}")
|
||||
PSGUID_SUMMARYINFORMATION = IID("{F29F85E0-4FF9-1068-AB91-08002B27B3D9}")
|
||||
PSGUID_HTMLINFORMATION = IID("{D1B5D3F0-C0B3-11CF-9A92-00A0C908DBF1}")
|
||||
PSGUID_HTML2_INFORMATION = IID("{C82BF597-B831-11D0-B733-00AA00A1EBD2}")
|
||||
|
||||
IFILTER_INIT_CANON_PARAGRAPHS = 1
|
||||
IFILTER_INIT_HARD_LINE_BREAKS = 2
|
||||
IFILTER_INIT_CANON_HYPHENS = 4
|
||||
IFILTER_INIT_CANON_SPACES = 8
|
||||
IFILTER_INIT_APPLY_INDEX_ATTRIBUTES = 16
|
||||
IFILTER_INIT_APPLY_CRAWL_ATTRIBUTES = 256
|
||||
IFILTER_INIT_APPLY_OTHER_ATTRIBUTES = 32
|
||||
IFILTER_INIT_INDEXING_ONLY = 64
|
||||
IFILTER_INIT_SEARCH_LINKS = 128
|
||||
IFILTER_INIT_FILTER_OWNED_VALUE_OK = 512
|
||||
|
||||
IFILTER_FLAGS_OLE_PROPERTIES = 1
|
||||
|
||||
CHUNK_TEXT = 0x1
|
||||
CHUNK_VALUE = 0x2
|
||||
CHUNK_NO_BREAK = 0
|
||||
CHUNK_EOW = 1
|
||||
CHUNK_EOS = 2
|
||||
CHUNK_EOP = 3
|
||||
CHUNK_EOC = 4
|
||||
|
||||
NOT_AN_ERROR = 0x00080000
|
||||
FILTER_E_END_OF_CHUNKS = -2147215616
|
||||
FILTER_E_NO_MORE_TEXT = -2147215615
|
||||
FILTER_E_NO_MORE_VALUES = -2147215614
|
||||
FILTER_E_ACCESS = -2147215613
|
||||
FILTER_W_MONIKER_CLIPPED = 0x00041704
|
||||
FILTER_E_NO_TEXT = -2147215611
|
||||
FILTER_E_NO_VALUES = -2147215610
|
||||
FILTER_E_EMBEDDING_UNAVAILABLE = -2147215609
|
||||
FILTER_E_LINK_UNAVAILABLE = -2147215608
|
||||
FILTER_S_LAST_TEXT = 0x00041709
|
||||
FILTER_S_LAST_VALUES = 0x0004170A
|
||||
FILTER_E_PASSWORD = -2147215605
|
||||
FILTER_E_UNKNOWNFORMAT = -2147215604
|
||||
|
||||
# Generated by h2py from PropIdl.h
|
||||
PROPSETFLAG_DEFAULT = 0
|
||||
PROPSETFLAG_NONSIMPLE = 1
|
||||
PROPSETFLAG_ANSI = 2
|
||||
PROPSETFLAG_UNBUFFERED = 4
|
||||
PROPSETFLAG_CASE_SENSITIVE = 8
|
||||
PROPSET_BEHAVIOR_CASE_SENSITIVE = 1
|
||||
PID_DICTIONARY = 0
|
||||
PID_CODEPAGE = 0x1
|
||||
PID_FIRST_USABLE = 0x2
|
||||
PID_FIRST_NAME_DEFAULT = 0xFFF
|
||||
PID_LOCALE = -2147483648
|
||||
PID_MODIFY_TIME = -2147483647
|
||||
PID_SECURITY = -2147483646
|
||||
PID_BEHAVIOR = -2147483645
|
||||
PID_ILLEGAL = -1
|
||||
PID_MIN_READONLY = -2147483648
|
||||
PID_MAX_READONLY = -1073741825
|
||||
PIDDI_THUMBNAIL = 0x00000002
|
||||
PIDSI_TITLE = 0x00000002
|
||||
PIDSI_SUBJECT = 0x00000003
|
||||
PIDSI_AUTHOR = 0x00000004
|
||||
PIDSI_KEYWORDS = 0x00000005
|
||||
PIDSI_COMMENTS = 0x00000006
|
||||
PIDSI_TEMPLATE = 0x00000007
|
||||
PIDSI_LASTAUTHOR = 0x00000008
|
||||
PIDSI_REVNUMBER = 0x00000009
|
||||
PIDSI_EDITTIME = 0x0000000A
|
||||
PIDSI_LASTPRINTED = 0x0000000B
|
||||
PIDSI_CREATE_DTM = 0x0000000C
|
||||
PIDSI_LASTSAVE_DTM = 0x0000000D
|
||||
PIDSI_PAGECOUNT = 0x0000000E
|
||||
PIDSI_WORDCOUNT = 0x0000000F
|
||||
PIDSI_CHARCOUNT = 0x00000010
|
||||
PIDSI_THUMBNAIL = 0x00000011
|
||||
PIDSI_APPNAME = 0x00000012
|
||||
PIDSI_DOC_SECURITY = 0x00000013
|
||||
PIDDSI_CATEGORY = 0x00000002
|
||||
PIDDSI_PRESFORMAT = 0x00000003
|
||||
PIDDSI_BYTECOUNT = 0x00000004
|
||||
PIDDSI_LINECOUNT = 0x00000005
|
||||
PIDDSI_PARCOUNT = 0x00000006
|
||||
PIDDSI_SLIDECOUNT = 0x00000007
|
||||
PIDDSI_NOTECOUNT = 0x00000008
|
||||
PIDDSI_HIDDENCOUNT = 0x00000009
|
||||
PIDDSI_MMCLIPCOUNT = 0x0000000A
|
||||
PIDDSI_SCALE = 0x0000000B
|
||||
PIDDSI_HEADINGPAIR = 0x0000000C
|
||||
PIDDSI_DOCPARTS = 0x0000000D
|
||||
PIDDSI_MANAGER = 0x0000000E
|
||||
PIDDSI_COMPANY = 0x0000000F
|
||||
PIDDSI_LINKSDIRTY = 0x00000010
|
||||
PIDMSI_EDITOR = 0x00000002
|
||||
PIDMSI_SUPPLIER = 0x00000003
|
||||
PIDMSI_SOURCE = 0x00000004
|
||||
PIDMSI_SEQUENCE_NO = 0x00000005
|
||||
PIDMSI_PROJECT = 0x00000006
|
||||
PIDMSI_STATUS = 0x00000007
|
||||
PIDMSI_OWNER = 0x00000008
|
||||
PIDMSI_RATING = 0x00000009
|
||||
PIDMSI_PRODUCTION = 0x0000000A
|
||||
PIDMSI_COPYRIGHT = 0x0000000B
|
||||
PRSPEC_INVALID = -1
|
||||
PRSPEC_LPWSTR = 0
|
||||
PRSPEC_PROPID = 1
|
||||
CCH_MAX_PROPSTG_NAME = 31
|
||||
Loading…
Add table
Add a link
Reference in a new issue