diff options
author | Martin v. Löwis <martin@v.loewis.de> | 2003-03-30 14:25:40 (GMT) |
---|---|---|
committer | Martin v. Löwis <martin@v.loewis.de> | 2003-03-30 14:25:40 (GMT) |
commit | 3163a3b4b2a820ef38e6c7282033fe2db9d43ebe (patch) | |
tree | e83e06cbe049f06610d6c5e025e813e644fc9b01 /Lib/markupbase.py | |
parent | a965649386dbd385a92b2b93934abaff80c94198 (diff) | |
download | cpython-3163a3b4b2a820ef38e6c7282033fe2db9d43ebe.zip cpython-3163a3b4b2a820ef38e6c7282033fe2db9d43ebe.tar.gz cpython-3163a3b4b2a820ef38e6c7282033fe2db9d43ebe.tar.bz2 |
Patch #545300: Support marked sections.
Diffstat (limited to 'Lib/markupbase.py')
-rw-r--r-- | Lib/markupbase.py | 71 |
1 files changed, 69 insertions, 2 deletions
diff --git a/Lib/markupbase.py b/Lib/markupbase.py index acd0726..f97cf10 100644 --- a/Lib/markupbase.py +++ b/Lib/markupbase.py @@ -4,6 +4,13 @@ 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 @@ -53,6 +60,13 @@ class ParserBase: # 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" @@ -60,9 +74,19 @@ class ParserBase: # Start of comment followed by buffer boundary, # or just a buffer boundary. return -1 - # in practice, this should look like: ((name|stringlit) S*)+ '>' + # A simple, practical version could look like: ((name|stringlit) S*) + '>' n = len(rawdata) - decltype, j = self._scan_name(j, i) + if rawdata[j:j+1] == '--': #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": @@ -87,8 +111,15 @@ class ParserBase: 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: @@ -98,6 +129,42 @@ class ParserBase: 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: + self.error('unknown status keyword %s 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] != '<!--': + self.error('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): |