"""Shared support for scanning document type declarations in HTML and XHTML.
This module is used as a foundation for the HTMLParser and sgmllib
modules (indirectly, for htmllib as well). It has no documented
public API and should not be used directly.
_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*>')
"""Parser base class which provides some common support methods used
by the SGML/HTML and XHTML parsers."""
if self.__class__ is ParserBase:
"markupbase.ParserBase must be subclassed")
def error(self, message):
raise NotImplementedError(
"subclasses of ParserBase must override error()")
"""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):
nlines = rawdata.count("\n", i, j)
self.lineno = self.lineno + nlines
pos = rawdata.rindex("\n", i, j) # Should not fail
self.offset = self.offset + j-i
# 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:
# name in the following list: ENTITY, DOCTYPE, ELEMENT,
# ATTLIST, NOTATION, SHORTREF, USEMAP,
# LINKTYPE, LINK, IDLINK, USELINK, SYSTEM
assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
if rawdata[j:j+1] == ">":
if rawdata[j:j+1] in ("-", ""):
# Start of comment followed by buffer boundary,
# or just a buffer boundary.
# A simple, practical version could look like: ((name|stringlit) S*) + '>'
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 decltype == "doctype":
self._decl_otherchars = ''
# end of declaration syntax
if decltype == "doctype":
# 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.
m = _declstringlit_match(rawdata, j)
elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ":
name, j = self._scan_name(j, i)
elif c in self._decl_otherchars:
# 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
self.error("unsupported '[' char in %s declaration" % decltype)
self.error("unexpected '[' char in declaration")
"unexpected %r char in declaration" % rawdata[j])
# 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):
assert rawdata[i:i+3] == '<![', "unexpected call to parse_marked_section()"
sectName, j = self._scan_name( i+3, i )
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)
self.error('unknown status keyword %r in marked section' % rawdata[i+3:j])
self.unknown_decl(rawdata[i+3: j])
# Internal -- parse comment, return length or -1 if not terminated
def parse_comment(self, i, report=1):
if rawdata[i:i+4] != '<!--':
self.error('unexpected call to parse_comment()')
match = _commentclose.search(rawdata, i+4)
self.handle_comment(rawdata[i+4: j])
# 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):
# end of buffer; incomplete
self.updatepos(declstartpos, j + 1)
self.error("unexpected char in internal subset (in %r)" % s)
# end of buffer; incomplete
# end of buffer; incomplete
if rawdata[j:j+4] == "<!--":
j = self.parse_comment(j, report=0)
name, j = self._scan_name(j + 2, declstartpos)
if name not in ("attlist", "element", "entity", "notation"):
self.updatepos(declstartpos, j + 2)
"unknown declaration %r in internal subset" % name)
# handle the individual names
meth = getattr(self, "_parse_doctype_" + name)
j = meth(j, declstartpos)
# parameter entity reference
# end of buffer; incomplete
s, j = self._scan_name(j + 1, declstartpos)
while j < n and rawdata[j].isspace():
self.updatepos(declstartpos, j)
self.error("unexpected char after internal subset")
self.updatepos(declstartpos, j)
self.error("unexpected char %r in internal subset" % c)
# Internal -- scan past <!ELEMENT declarations
def _parse_doctype_element(self, i, declstartpos):
name, j = self._scan_name(i, declstartpos)
# style content model; just skip until '>'
return rawdata.find(">", j) + 1
# Internal -- scan past <!ATTLIST declarations
def _parse_doctype_attlist(self, i, declstartpos):
name, j = self._scan_name(i, declstartpos)
# scan a series of attribute descriptions; simplified:
# name type [value] [#constraint]
name, j = self._scan_name(j, declstartpos)
# an enumerated type; look for ')'
j = rawdata.find(")", j) + 1
while rawdata[j:j+1].isspace():
# end of buffer, incomplete
name, j = self._scan_name(j, declstartpos)
m = _declstringlit_match(rawdata, j)
name, j = self._scan_name(j + 1, declstartpos)
# Internal -- scan past <!NOTATION declarations
def _parse_doctype_notation(self, i, declstartpos):
name, j = self._scan_name(i, declstartpos)
# end of buffer; incomplete
m = _declstringlit_match(rawdata, j)
name, j = self._scan_name(j, declstartpos)
# Internal -- scan past <!ENTITY declarations
def _parse_doctype_entity(self, i, declstartpos):
if rawdata[i:i+1] == "%":
name, j = self._scan_name(j, declstartpos)
m = _declstringlit_match(rawdata, j)
name, j = self._scan_name(j, declstartpos)
# 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):
m = _declname_match(rawdata, i)
return None, -1 # end of buffer
return name.lower(), m.end()
self.updatepos(declstartpos, i)
self.error("expected name token at %r"
% rawdata[declstartpos:declstartpos+20])
# To be overridden -- handlers for unknown objects
def unknown_decl(self, data):
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
