2005-08-23 04:06:46 +00:00
|
|
|
"""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.
|
|
|
|
|
|
|
|
|
|
"""
|
2001-09-24 20:01:28 +00:00
|
|
|
|
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match
|
|
|
|
|
_declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match
|
2003-03-30 14:25:40 +00:00
|
|
|
_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*>')
|
2001-09-24 20:01:28 +00:00
|
|
|
|
|
|
|
|
del re
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class ParserBase:
|
|
|
|
|
"""Parser base class which provides some common support methods used
|
|
|
|
|
by the SGML/HTML and XHTML parsers."""
|
|
|
|
|
|
2001-10-26 18:02:28 +00:00
|
|
|
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()")
|
|
|
|
|
|
2001-09-24 20:01:28 +00:00
|
|
|
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
|
2002-05-31 14:13:04 +00:00
|
|
|
nlines = rawdata.count("\n", i, j)
|
2001-09-24 20:01:28 +00:00
|
|
|
if nlines:
|
|
|
|
|
self.lineno = self.lineno + nlines
|
2002-05-31 14:13:04 +00:00
|
|
|
pos = rawdata.rindex("\n", i, j) # Should not fail
|
2001-09-24 20:01:28 +00:00
|
|
|
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...>").
|
2003-04-24 16:02:54 +00:00
|
|
|
# ISO 8879:1986, however, has more complex
|
2003-03-30 14:25:40 +00:00
|
|
|
# declaration syntax for elements in <!...>, including:
|
|
|
|
|
# --comment--
|
|
|
|
|
# [marked section]
|
2003-04-24 16:02:54 +00:00
|
|
|
# name in the following list: ENTITY, DOCTYPE, ELEMENT,
|
|
|
|
|
# ATTLIST, NOTATION, SHORTREF, USEMAP,
|
2003-03-30 14:25:40 +00:00
|
|
|
# LINKTYPE, LINK, IDLINK, USELINK, SYSTEM
|
2001-09-24 20:01:28 +00:00
|
|
|
rawdata = self.rawdata
|
|
|
|
|
j = i + 2
|
|
|
|
|
assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
|
2006-03-09 13:27:14 +00:00
|
|
|
if rawdata[j:j+1] == ">":
|
|
|
|
|
# the empty comment <!>
|
|
|
|
|
return j + 1
|
2001-09-24 20:01:28 +00:00
|
|
|
if rawdata[j:j+1] in ("-", ""):
|
|
|
|
|
# Start of comment followed by buffer boundary,
|
|
|
|
|
# or just a buffer boundary.
|
|
|
|
|
return -1
|
2003-03-30 14:25:40 +00:00
|
|
|
# A simple, practical version could look like: ((name|stringlit) S*) + '>'
|
2001-09-24 20:01:28 +00:00
|
|
|
n = len(rawdata)
|
2006-03-09 13:27:14 +00:00
|
|
|
if rawdata[j:j+2] == '--': #comment
|
2003-03-30 14:25:40 +00:00
|
|
|
# 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)
|
2001-09-24 20:01:28 +00:00
|
|
|
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:
|
|
|
|
|
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 == "[":
|
2003-03-30 14:25:40 +00:00
|
|
|
# this could be handled in a separate doctype parser
|
2001-09-24 20:01:28 +00:00
|
|
|
if decltype == "doctype":
|
|
|
|
|
j = self._parse_doctype_subset(j + 1, i)
|
2003-03-30 14:25:40 +00:00
|
|
|
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)
|
2001-09-24 20:01:28 +00:00
|
|
|
else:
|
|
|
|
|
self.error("unexpected '[' char in declaration")
|
|
|
|
|
else:
|
|
|
|
|
self.error(
|
2004-02-12 17:35:32 +00:00
|
|
|
"unexpected %r char in declaration" % rawdata[j])
|
2001-09-24 20:01:28 +00:00
|
|
|
if j < 0:
|
|
|
|
|
return j
|
|
|
|
|
return -1 # incomplete
|
|
|
|
|
|
2003-03-30 14:25:40 +00:00
|
|
|
# Internal -- parse a marked section
|
|
|
|
|
# Override this to handle MS-word extension syntax <![if word]>content<![endif]>
|
2006-06-06 12:46:55 +00:00
|
|
|
def parse_marked_section(self, i, report=1):
|
2003-03-30 14:25:40 +00:00
|
|
|
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:
|
2004-02-12 17:35:32 +00:00
|
|
|
self.error('unknown status keyword %r in marked section' % rawdata[i+3:j])
|
2003-03-30 14:25:40 +00:00
|
|
|
if not match:
|
|
|
|
|
return -1
|
|
|
|
|
if report:
|
|
|
|
|
j = match.start(0)
|
|
|
|
|
self.unknown_decl(rawdata[i+3: j])
|
|
|
|
|
return match.end(0)
|
2003-04-24 16:02:54 +00:00
|
|
|
|
2003-03-30 14:25:40 +00:00
|
|
|
# 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)
|
|
|
|
|
|
2001-09-24 20:01:28 +00:00
|
|
|
# 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)
|
2004-02-12 17:35:32 +00:00
|
|
|
self.error("unexpected char in internal subset (in %r)" % s)
|
2001-09-24 20:01:28 +00:00
|
|
|
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)
|
|
|
|
|
self.error(
|
2004-02-12 17:35:32 +00:00
|
|
|
"unknown declaration %r in internal subset" % name)
|
2001-09-24 20:01:28 +00:00
|
|
|
# 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
|
Remove uses of the string and types modules:
x in string.whitespace => x.isspace()
type(x) in types.StringTypes => isinstance(x, basestring)
isinstance(x, types.StringTypes) => isinstance(x, basestring)
type(x) is types.StringType => isinstance(x, str)
type(x) == types.StringType => isinstance(x, str)
string.split(x, ...) => x.split(...)
string.join(x, y) => y.join(x)
string.zfill(x, ...) => x.zfill(...)
string.count(x, ...) => x.count(...)
hasattr(types, "UnicodeType") => try: unicode except NameError:
type(x) != types.TupleTuple => not isinstance(x, tuple)
isinstance(x, types.TupleType) => isinstance(x, tuple)
type(x) is types.IntType => isinstance(x, int)
Do not mention the string module in the rlcompleter docstring.
This partially applies SF patch http://www.python.org/sf/562373
(with basestring instead of string). (It excludes the changes to
unittest.py and does not change the os.stat stuff.)
2002-06-03 15:58:32 +00:00
|
|
|
while j < n and rawdata[j].isspace():
|
2001-09-24 20:01:28 +00:00
|
|
|
j = j + 1
|
|
|
|
|
if j < n:
|
|
|
|
|
if rawdata[j] == ">":
|
|
|
|
|
return j
|
|
|
|
|
self.updatepos(declstartpos, j)
|
|
|
|
|
self.error("unexpected char after internal subset")
|
|
|
|
|
else:
|
|
|
|
|
return -1
|
Remove uses of the string and types modules:
x in string.whitespace => x.isspace()
type(x) in types.StringTypes => isinstance(x, basestring)
isinstance(x, types.StringTypes) => isinstance(x, basestring)
type(x) is types.StringType => isinstance(x, str)
type(x) == types.StringType => isinstance(x, str)
string.split(x, ...) => x.split(...)
string.join(x, y) => y.join(x)
string.zfill(x, ...) => x.zfill(...)
string.count(x, ...) => x.count(...)
hasattr(types, "UnicodeType") => try: unicode except NameError:
type(x) != types.TupleTuple => not isinstance(x, tuple)
isinstance(x, types.TupleType) => isinstance(x, tuple)
type(x) is types.IntType => isinstance(x, int)
Do not mention the string module in the rlcompleter docstring.
This partially applies SF patch http://www.python.org/sf/562373
(with basestring instead of string). (It excludes the changes to
unittest.py and does not change the os.stat stuff.)
2002-06-03 15:58:32 +00:00
|
|
|
elif c.isspace():
|
2001-09-24 20:01:28 +00:00
|
|
|
j = j + 1
|
|
|
|
|
else:
|
|
|
|
|
self.updatepos(declstartpos, j)
|
2004-02-12 17:35:32 +00:00
|
|
|
self.error("unexpected char %r in internal subset" % c)
|
2001-09-24 20:01:28 +00:00
|
|
|
# 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 '>'
|
2001-10-26 18:02:28 +00:00
|
|
|
rawdata = self.rawdata
|
2001-09-24 20:01:28 +00:00
|
|
|
if '>' in rawdata[j:]:
|
2002-05-31 14:13:04 +00:00
|
|
|
return rawdata.find(">", j) + 1
|
2001-09-24 20:01:28 +00:00
|
|
|
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:]:
|
2002-05-31 14:13:04 +00:00
|
|
|
j = rawdata.find(")", j) + 1
|
2001-09-24 20:01:28 +00:00
|
|
|
else:
|
|
|
|
|
return -1
|
Remove uses of the string and types modules:
x in string.whitespace => x.isspace()
type(x) in types.StringTypes => isinstance(x, basestring)
isinstance(x, types.StringTypes) => isinstance(x, basestring)
type(x) is types.StringType => isinstance(x, str)
type(x) == types.StringType => isinstance(x, str)
string.split(x, ...) => x.split(...)
string.join(x, y) => y.join(x)
string.zfill(x, ...) => x.zfill(...)
string.count(x, ...) => x.count(...)
hasattr(types, "UnicodeType") => try: unicode except NameError:
type(x) != types.TupleTuple => not isinstance(x, tuple)
isinstance(x, types.TupleType) => isinstance(x, tuple)
type(x) is types.IntType => isinstance(x, int)
Do not mention the string module in the rlcompleter docstring.
This partially applies SF patch http://www.python.org/sf/562373
(with basestring instead of string). (It excludes the changes to
unittest.py and does not change the os.stat stuff.)
2002-06-03 15:58:32 +00:00
|
|
|
while rawdata[j:j+1].isspace():
|
2001-09-24 20:01:28 +00:00
|
|
|
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
|
Remove uses of the string and types modules:
x in string.whitespace => x.isspace()
type(x) in types.StringTypes => isinstance(x, basestring)
isinstance(x, types.StringTypes) => isinstance(x, basestring)
type(x) is types.StringType => isinstance(x, str)
type(x) == types.StringType => isinstance(x, str)
string.split(x, ...) => x.split(...)
string.join(x, y) => y.join(x)
string.zfill(x, ...) => x.zfill(...)
string.count(x, ...) => x.count(...)
hasattr(types, "UnicodeType") => try: unicode except NameError:
type(x) != types.TupleTuple => not isinstance(x, tuple)
isinstance(x, types.TupleType) => isinstance(x, tuple)
type(x) is types.IntType => isinstance(x, int)
Do not mention the string module in the rlcompleter docstring.
This partially applies SF patch http://www.python.org/sf/562373
(with basestring instead of string). (It excludes the changes to
unittest.py and does not change the os.stat stuff.)
2002-06-03 15:58:32 +00:00
|
|
|
if c.isspace():
|
2001-09-24 20:01:28 +00:00
|
|
|
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
|
2002-05-31 14:13:04 +00:00
|
|
|
return name.lower(), m.end()
|
2001-09-24 20:01:28 +00:00
|
|
|
else:
|
|
|
|
|
self.updatepos(declstartpos, i)
|
2004-07-10 21:49:45 +00:00
|
|
|
self.error("expected name token at %r"
|
|
|
|
|
% rawdata[declstartpos:declstartpos+20])
|
2001-10-26 18:02:28 +00:00
|
|
|
|
|
|
|
|
# To be overridden -- handlers for unknown objects
|
|
|
|
|
def unknown_decl(self, data):
|
|
|
|
|
pass
|
