"""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. """ 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 error(self, message): raise NotImplementedError( "subclasses of ParserBase must override error()") 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 (""). # 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] == "": # 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 self.error("unsupported '[' char in %s declaration" % decltype) else: self.error("unexpected '[' char in declaration") else: self.error( "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 content def parse_marked_section(self, i, report=1): rawdata= self.rawdata assert rawdata[i:i+3] == ' 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: self.error('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] != '