Current Dir: /snap/core22/2955/usr/lib/python3.10/
[DIR] asyncio [ delete | rename ]
[DIR] collections [ delete | rename ]
[DIR] concurrent [ delete | rename ]
[DIR] ctypes [ delete | rename ]
[DIR] curses [ delete | rename ]
[DIR] dbm [ delete | rename ]
[DIR] distutils [ delete | rename ]
[DIR] email [ delete | rename ]
[DIR] encodings [ delete | rename ]
[DIR] html [ delete | rename ]
[DIR] http [ delete | rename ]
[DIR] importlib [ delete | rename ]
[DIR] json [ delete | rename ]
[DIR] lib-dynload [ delete | rename ]
[DIR] lib2to3 [ delete | rename ]
[DIR] logging [ delete | rename ]
[DIR] multiprocessing [ delete | rename ]
[DIR] pydoc_data [ delete | rename ]
[DIR] sqlite3 [ delete | rename ]
[DIR] test [ delete | rename ]
[DIR] unittest [ delete | rename ]
[DIR] urllib [ delete | rename ]
[DIR] venv [ delete | rename ]
[DIR] wsgiref [ delete | rename ]
[DIR] xml [ delete | rename ]
[DIR] xmlrpc [ delete | rename ]
[DIR] zoneinfo [ delete | rename ]
[DIR] __pycache__ [ delete | rename ]
[FILE] abc.py [ edit | delete | rename ]
[FILE] aifc.py [ edit | delete | rename ]
[FILE] antigravity.py [ edit | delete | rename ]
[FILE] argparse.py [ edit | delete | rename ]
[FILE] ast.py [ edit | delete | rename ]
[FILE] asynchat.py [ edit | delete | rename ]
[FILE] asyncore.py [ edit | delete | rename ]
[FILE] base64.py [ edit | delete | rename ]
[FILE] bdb.py [ edit | delete | rename ]
[FILE] binhex.py [ edit | delete | rename ]
[FILE] bisect.py [ edit | delete | rename ]
[FILE] bz2.py [ edit | delete | rename ]
[FILE] calendar.py [ edit | delete | rename ]
[FILE] cgi.py [ edit | delete | rename ]
[FILE] cgitb.py [ edit | delete | rename ]
[FILE] chunk.py [ edit | delete | rename ]
[FILE] cmd.py [ edit | delete | rename ]
[FILE] code.py [ edit | delete | rename ]
[FILE] codecs.py [ edit | delete | rename ]
[FILE] codeop.py [ edit | delete | rename ]
[FILE] colorsys.py [ edit | delete | rename ]
[FILE] compileall.py [ edit | delete | rename ]
[FILE] configparser.py [ edit | delete | rename ]
[FILE] contextlib.py [ edit | delete | rename ]
[FILE] contextvars.py [ edit | delete | rename ]
[FILE] copy.py [ edit | delete | rename ]
[FILE] copyreg.py [ edit | delete | rename ]
[FILE] cProfile.py [ edit | delete | rename ]
[FILE] crypt.py [ edit | delete | rename ]
[FILE] csv.py [ edit | delete | rename ]
[FILE] dataclasses.py [ edit | delete | rename ]
[FILE] datetime.py [ edit | delete | rename ]
[FILE] decimal.py [ edit | delete | rename ]
[FILE] difflib.py [ edit | delete | rename ]
[FILE] dis.py [ edit | delete | rename ]
[FILE] doctest.py [ edit | delete | rename ]
[FILE] enum.py [ edit | delete | rename ]
[FILE] filecmp.py [ edit | delete | rename ]
[FILE] fileinput.py [ edit | delete | rename ]
[FILE] fnmatch.py [ edit | delete | rename ]
[FILE] fractions.py [ edit | delete | rename ]
[FILE] ftplib.py [ edit | delete | rename ]
[FILE] functools.py [ edit | delete | rename ]
[FILE] genericpath.py [ edit | delete | rename ]
[FILE] getopt.py [ edit | delete | rename ]
[FILE] getpass.py [ edit | delete | rename ]
[FILE] gettext.py [ edit | delete | rename ]
[FILE] glob.py [ edit | delete | rename ]
[FILE] graphlib.py [ edit | delete | rename ]
[FILE] gzip.py [ edit | delete | rename ]
[FILE] hashlib.py [ edit | delete | rename ]
[FILE] heapq.py [ edit | delete | rename ]
[FILE] hmac.py [ edit | delete | rename ]
[FILE] imaplib.py [ edit | delete | rename ]
[FILE] imghdr.py [ edit | delete | rename ]
[FILE] imp.py [ edit | delete | rename ]
[FILE] inspect.py [ edit | delete | rename ]
[FILE] io.py [ edit | delete | rename ]
[FILE] ipaddress.py [ edit | delete | rename ]
[FILE] keyword.py [ edit | delete | rename ]
[FILE] LICENSE.txt [ edit | delete | rename ]
[FILE] linecache.py [ edit | delete | rename ]
[FILE] locale.py [ edit | delete | rename ]
[FILE] lzma.py [ edit | delete | rename ]
[FILE] mailbox.py [ edit | delete | rename ]
[FILE] mailcap.py [ edit | delete | rename ]
[FILE] mimetypes.py [ edit | delete | rename ]
[FILE] modulefinder.py [ edit | delete | rename ]
[FILE] netrc.py [ edit | delete | rename ]
[FILE] nntplib.py [ edit | delete | rename ]
[FILE] ntpath.py [ edit | delete | rename ]
[FILE] nturl2path.py [ edit | delete | rename ]
[FILE] numbers.py [ edit | delete | rename ]
[FILE] opcode.py [ edit | delete | rename ]
[FILE] operator.py [ edit | delete | rename ]
[FILE] optparse.py [ edit | delete | rename ]
[FILE] os.py [ edit | delete | rename ]
[FILE] pathlib.py [ edit | delete | rename ]
[FILE] pdb.py [ edit | delete | rename ]
[FILE] pickle.py [ edit | delete | rename ]
[FILE] pickletools.py [ edit | delete | rename ]
[FILE] pipes.py [ edit | delete | rename ]
[FILE] pkgutil.py [ edit | delete | rename ]
[FILE] platform.py [ edit | delete | rename ]
[FILE] plistlib.py [ edit | delete | rename ]
[FILE] poplib.py [ edit | delete | rename ]
[FILE] posixpath.py [ edit | delete | rename ]
[FILE] pprint.py [ edit | delete | rename ]
[FILE] profile.py [ edit | delete | rename ]
[FILE] pstats.py [ edit | delete | rename ]
[FILE] pty.py [ edit | delete | rename ]
[FILE] pyclbr.py [ edit | delete | rename ]
[FILE] pydoc.py [ edit | delete | rename ]
[FILE] py_compile.py [ edit | delete | rename ]
[FILE] queue.py [ edit | delete | rename ]
[FILE] quopri.py [ edit | delete | rename ]
[FILE] random.py [ edit | delete | rename ]
[FILE] re.py [ edit | delete | rename ]
[FILE] reprlib.py [ edit | delete | rename ]
[FILE] rlcompleter.py [ edit | delete | rename ]
[FILE] runpy.py [ edit | delete | rename ]
[FILE] sched.py [ edit | delete | rename ]
[FILE] secrets.py [ edit | delete | rename ]
[FILE] selectors.py [ edit | delete | rename ]
[FILE] shelve.py [ edit | delete | rename ]
[FILE] shlex.py [ edit | delete | rename ]
[FILE] shutil.py [ edit | delete | rename ]
[FILE] signal.py [ edit | delete | rename ]
[FILE] site.py [ edit | delete | rename ]
[FILE] sitecustomize.py [ edit | delete | rename ]
[FILE] smtpd.py [ edit | delete | rename ]
[FILE] smtplib.py [ edit | delete | rename ]
[FILE] sndhdr.py [ edit | delete | rename ]
[FILE] socket.py [ edit | delete | rename ]
[FILE] socketserver.py [ edit | delete | rename ]
[FILE] sre_compile.py [ edit | delete | rename ]
[FILE] sre_constants.py [ edit | delete | rename ]
[FILE] sre_parse.py [ edit | delete | rename ]
[FILE] ssl.py [ edit | delete | rename ]
[FILE] stat.py [ edit | delete | rename ]
[FILE] statistics.py [ edit | delete | rename ]
[FILE] string.py [ edit | delete | rename ]
[FILE] stringprep.py [ edit | delete | rename ]
[FILE] struct.py [ edit | delete | rename ]
[FILE] subprocess.py [ edit | delete | rename ]
[FILE] sunau.py [ edit | delete | rename ]
[FILE] symtable.py [ edit | delete | rename ]
[FILE] sysconfig.py [ edit | delete | rename ]
[FILE] tabnanny.py [ edit | delete | rename ]
[FILE] tarfile.py [ edit | delete | rename ]
[FILE] telnetlib.py [ edit | delete | rename ]
[FILE] tempfile.py [ edit | delete | rename ]
[FILE] textwrap.py [ edit | delete | rename ]
[FILE] this.py [ edit | delete | rename ]
[FILE] threading.py [ edit | delete | rename ]
[FILE] timeit.py [ edit | delete | rename ]
[FILE] token.py [ edit | delete | rename ]
[FILE] tokenize.py [ edit | delete | rename ]
[FILE] trace.py [ edit | delete | rename ]
[FILE] traceback.py [ edit | delete | rename ]
[FILE] tracemalloc.py [ edit | delete | rename ]
[FILE] tty.py [ edit | delete | rename ]
[FILE] turtle.py [ edit | delete | rename ]
[FILE] types.py [ edit | delete | rename ]
[FILE] typing.py [ edit | delete | rename ]
[FILE] uu.py [ edit | delete | rename ]
[FILE] uuid.py [ edit | delete | rename ]
[FILE] warnings.py [ edit | delete | rename ]
[FILE] wave.py [ edit | delete | rename ]
[FILE] weakref.py [ edit | delete | rename ]
[FILE] webbrowser.py [ edit | delete | rename ]
[FILE] xdrlib.py [ edit | delete | rename ]
[FILE] zipapp.py [ edit | delete | rename ]
[FILE] zipfile.py [ edit | delete | rename ]
[FILE] zipimport.py [ edit | delete | rename ]
[FILE] _aix_support.py [ edit | delete | rename ]
[FILE] _bootsubprocess.py [ edit | delete | rename ]
[FILE] _collections_abc.py [ edit | delete | rename ]
[FILE] _compat_pickle.py [ edit | delete | rename ]
[FILE] _compression.py [ edit | delete | rename ]
[FILE] _distutils_system_mod.py [ edit | delete | rename ]
[FILE] _markupbase.py [ edit | delete | rename ]
[FILE] _osx_support.py [ edit | delete | rename ]
[FILE] _pydecimal.py [ edit | delete | rename ]
[FILE] _pyio.py [ edit | delete | rename ]
[FILE] _py_abc.py [ edit | delete | rename ]
[FILE] _sitebuiltins.py [ edit | delete | rename ]
[FILE] _strptime.py [ edit | delete | rename ]
[FILE] _sysconfigdata__linux_x86_64-linux-gnu.py [ edit | delete | rename ]
[FILE] _sysconfigdata__x86_64-linux-gnu.py [ edit | delete | rename ]
[FILE] _threading_local.py [ edit | delete | rename ]
[FILE] _weakrefset.py [ edit | delete | rename ]
[FILE] __future__.py [ edit | delete | rename ]
[FILE] __phello__.foo.py [ edit | delete | rename ]
Viewing: /snap/core22/2955/usr/lib/python3.10/_markupbase.py
"""Shared support for scanning document type declarations in HTML and XHTML.
This module is used as a foundation for the html.parser module. It has no
documented public API and should not be used directly.
"""
import re
_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match
_declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match
_commentclose = re.compile(r'--\s*>')
_markedsectionclose = re.compile(r']\s*]\s*>')
# An analysis of the MS-Word extensions is available at
# http://www.planetpublish.com/xmlarena/xap/Thursday/WordtoXML.pdf
_msmarkedsectionclose = re.compile(r']\s*>')
del re
class ParserBase:
"""Parser base class which provides some common support methods used
by the SGML/HTML and XHTML parsers."""
def __init__(self):
if self.__class__ is ParserBase:
raise RuntimeError(
"_markupbase.ParserBase must be subclassed")
def reset(self):
self.lineno = 1
self.offset = 0
def getpos(self):
"""Return current line number and offset."""
return self.lineno, self.offset
# Internal -- update line number and offset. This should be
# called for each piece of data exactly once, in order -- in other
# words the concatenation of all the input strings to this
# function should be exactly the entire input.
def updatepos(self, i, j):
if i >= j:
return j
rawdata = self.rawdata
nlines = rawdata.count("\n", i, j)
if nlines:
self.lineno = self.lineno + nlines
pos = rawdata.rindex("\n", i, j) # Should not fail
self.offset = j-(pos+1)
else:
self.offset = self.offset + j-i
return j
_decl_otherchars = ''
# Internal -- parse declaration (for use by subclasses).
def parse_declaration(self, i):
# This is some sort of declaration; in "HTML as
# deployed," this should only be the document type
# declaration ("<!DOCTYPE html...>").
# ISO 8879:1986, however, has more complex
# declaration syntax for elements in <!...>, including:
# --comment--
# [marked section]
# name in the following list: ENTITY, DOCTYPE, ELEMENT,
# ATTLIST, NOTATION, SHORTREF, USEMAP,
# LINKTYPE, LINK, IDLINK, USELINK, SYSTEM
rawdata = self.rawdata
j = i + 2
assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
if rawdata[j:j+1] == ">":
# the empty comment <!>
return j + 1
if rawdata[j:j+1] in ("-", ""):
# Start of comment followed by buffer boundary,
# or just a buffer boundary.
return -1
# A simple, practical version could look like: ((name|stringlit) S*) + '>'
n = len(rawdata)
if rawdata[j:j+2] == '--': #comment
# Locate --.*-- as the body of the comment
return self.parse_comment(i)
elif rawdata[j] == '[': #marked section
# Locate [statusWord [...arbitrary SGML...]] as the body of the marked section
# Where statusWord is one of TEMP, CDATA, IGNORE, INCLUDE, RCDATA
# Note that this is extended by Microsoft Office "Save as Web" function
# to include [if...] and [endif].
return self.parse_marked_section(i)
else: #all other declaration elements
decltype, j = self._scan_name(j, i)
if j < 0:
return j
if decltype == "doctype":
self._decl_otherchars = ''
while j < n:
c = rawdata[j]
if c == ">":
# end of declaration syntax
data = rawdata[i+2:j]
if decltype == "doctype":
self.handle_decl(data)
else:
# According to the HTML5 specs sections "8.2.4.44 Bogus
# comment state" and "8.2.4.45 Markup declaration open
# state", a comment token should be emitted.
# Calling unknown_decl provides more flexibility though.
self.unknown_decl(data)
return j + 1
if c in "\"'":
m = _declstringlit_match(rawdata, j)
if not m:
return -1 # incomplete
j = m.end()
elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ":
name, j = self._scan_name(j, i)
elif c in self._decl_otherchars:
j = j + 1
elif c == "[":
# this could be handled in a separate doctype parser
if decltype == "doctype":
j = self._parse_doctype_subset(j + 1, i)
elif decltype in {"attlist", "linktype", "link", "element"}:
# must tolerate []'d groups in a content model in an element declaration
# also in data attribute specifications of attlist declaration
# also link type declaration subsets in linktype declarations
# also link attribute specification lists in link declarations
raise AssertionError("unsupported '[' char in %s declaration" % decltype)
else:
raise AssertionError("unexpected '[' char in declaration")
else:
raise AssertionError("unexpected %r char in declaration" % rawdata[j])
if j < 0:
return j
return -1 # incomplete
# Internal -- parse a marked section
# Override this to handle MS-word extension syntax <![if word]>content<![endif]>
def parse_marked_section(self, i, report=1):
rawdata= self.rawdata
assert rawdata[i:i+3] == '<![', "unexpected call to parse_marked_section()"
sectName, j = self._scan_name( i+3, i )
if j < 0:
return j
if sectName in {"temp", "cdata", "ignore", "include", "rcdata"}:
# look for standard ]]> ending
match= _markedsectionclose.search(rawdata, i+3)
elif sectName in {"if", "else", "endif"}:
# look for MS Office ]> ending
match= _msmarkedsectionclose.search(rawdata, i+3)
else:
raise AssertionError(
'unknown status keyword %r in marked section' % rawdata[i+3:j]
)
if not match:
return -1
if report:
j = match.start(0)
self.unknown_decl(rawdata[i+3: j])
return match.end(0)
# Internal -- parse comment, return length or -1 if not terminated
def parse_comment(self, i, report=1):
rawdata = self.rawdata
if rawdata[i:i+4] != '<!--':
raise AssertionError('unexpected call to parse_comment()')
match = _commentclose.search(rawdata, i+4)
if not match:
return -1
if report:
j = match.start(0)
self.handle_comment(rawdata[i+4: j])
return match.end(0)
# Internal -- scan past the internal subset in a <!DOCTYPE declaration,
# returning the index just past any whitespace following the trailing ']'.
def _parse_doctype_subset(self, i, declstartpos):
rawdata = self.rawdata
n = len(rawdata)
j = i
while j < n:
c = rawdata[j]
if c == "<":
s = rawdata[j:j+2]
if s == "<":
# end of buffer; incomplete
return -1
if s != "<!":
self.updatepos(declstartpos, j + 1)
raise AssertionError(
"unexpected char in internal subset (in %r)" % s
)
if (j + 2) == n:
# end of buffer; incomplete
return -1
if (j + 4) > n:
# end of buffer; incomplete
return -1
if rawdata[j:j+4] == "<!--":
j = self.parse_comment(j, report=0)
if j < 0:
return j
continue
name, j = self._scan_name(j + 2, declstartpos)
if j == -1:
return -1
if name not in {"attlist", "element", "entity", "notation"}:
self.updatepos(declstartpos, j + 2)
raise AssertionError(
"unknown declaration %r in internal subset" % name
)
# handle the individual names
meth = getattr(self, "_parse_doctype_" + name)
j = meth(j, declstartpos)
if j < 0:
return j
elif c == "%":
# parameter entity reference
if (j + 1) == n:
# end of buffer; incomplete
return -1
s, j = self._scan_name(j + 1, declstartpos)
if j < 0:
return j
if rawdata[j] == ";":
j = j + 1
elif c == "]":
j = j + 1
while j < n and rawdata[j].isspace():
j = j + 1
if j < n:
if rawdata[j] == ">":
return j
self.updatepos(declstartpos, j)
raise AssertionError("unexpected char after internal subset")
else:
return -1
elif c.isspace():
j = j + 1
else:
self.updatepos(declstartpos, j)
raise AssertionError("unexpected char %r in internal subset" % c)
# end of buffer reached
return -1
# Internal -- scan past <!ELEMENT declarations
def _parse_doctype_element(self, i, declstartpos):
name, j = self._scan_name(i, declstartpos)
if j == -1:
return -1
# style content model; just skip until '>'
rawdata = self.rawdata
if '>' in rawdata[j:]:
return rawdata.find(">", j) + 1
return -1
# Internal -- scan past <!ATTLIST declarations
def _parse_doctype_attlist(self, i, declstartpos):
rawdata = self.rawdata
name, j = self._scan_name(i, declstartpos)
c = rawdata[j:j+1]
if c == "":
return -1
if c == ">":
return j + 1
while 1:
# scan a series of attribute descriptions; simplified:
# name type [value] [#constraint]
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
c = rawdata[j:j+1]
if c == "":
return -1
if c == "(":
# an enumerated type; look for ')'
if ")" in rawdata[j:]:
j = rawdata.find(")", j) + 1
else:
return -1
while rawdata[j:j+1].isspace():
j = j + 1
if not rawdata[j:]:
# end of buffer, incomplete
return -1
else:
name, j = self._scan_name(j, declstartpos)
c = rawdata[j:j+1]
if not c:
return -1
if c in "'\"":
m = _declstringlit_match(rawdata, j)
if m:
j = m.end()
else:
return -1
c = rawdata[j:j+1]
if not c:
return -1
if c == "#":
if rawdata[j:] == "#":
# end of buffer
return -1
name, j = self._scan_name(j + 1, declstartpos)
if j < 0:
return j
c = rawdata[j:j+1]
if not c:
return -1
if c == '>':
# all done
return j + 1
# Internal -- scan past <!NOTATION declarations
def _parse_doctype_notation(self, i, declstartpos):
name, j = self._scan_name(i, declstartpos)
if j < 0:
return j
rawdata = self.rawdata
while 1:
c = rawdata[j:j+1]
if not c:
# end of buffer; incomplete
return -1
if c == '>':
return j + 1
if c in "'\"":
m = _declstringlit_match(rawdata, j)
if not m:
return -1
j = m.end()
else:
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
# Internal -- scan past <!ENTITY declarations
def _parse_doctype_entity(self, i, declstartpos):
rawdata = self.rawdata
if rawdata[i:i+1] == "%":
j = i + 1
while 1:
c = rawdata[j:j+1]
if not c:
return -1
if c.isspace():
j = j + 1
else:
break
else:
j = i
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
while 1:
c = self.rawdata[j:j+1]
if not c:
return -1
if c in "'\"":
m = _declstringlit_match(rawdata, j)
if m:
j = m.end()
else:
return -1 # incomplete
elif c == ">":
return j + 1
else:
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
# Internal -- scan a name token and the new position and the token, or
# return -1 if we've reached the end of the buffer.
def _scan_name(self, i, declstartpos):
rawdata = self.rawdata
n = len(rawdata)
if i == n:
return None, -1
m = _declname_match(rawdata, i)
if m:
s = m.group()
name = s.strip()
if (i + len(s)) == n:
return None, -1 # end of buffer
return name.lower(), m.end()
else:
self.updatepos(declstartpos, i)
raise AssertionError(
"expected name token at %r" % rawdata[declstartpos:declstartpos+20]
)
# To be overridden -- handlers for unknown objects
def unknown_decl(self, data):
pass