mirror of
https://gitflic.ru/project/openide/openide.git
synced 2026-09-27 10:03:11 +07:00
upgrade to Jython 2.5.0
This commit is contained in:
Dmitry Jemerov
@@ -1,10 +1,22 @@
|
||||
"""Shared support for scanning document type declarations in HTML and XHTML."""
|
||||
"""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
|
||||
import string
|
||||
|
||||
_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
|
||||
|
||||
@@ -38,10 +50,10 @@ class ParserBase:
|
||||
if i >= j:
|
||||
return j
|
||||
rawdata = self.rawdata
|
||||
nlines = string.count(rawdata, "\n", i, j)
|
||||
nlines = rawdata.count("\n", i, j)
|
||||
if nlines:
|
||||
self.lineno = self.lineno + nlines
|
||||
pos = string.rindex(rawdata, "\n", i, j) # Should not fail
|
||||
pos = rawdata.rindex("\n", i, j) # Should not fail
|
||||
self.offset = j-(pos+1)
|
||||
else:
|
||||
self.offset = self.offset + j-i
|
||||
@@ -54,16 +66,36 @@ 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"
|
||||
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
|
||||
# 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+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":
|
||||
@@ -88,17 +120,60 @@ 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:
|
||||
self.error(
|
||||
"unexpected %s char in declaration" % `rawdata[j]`)
|
||||
"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:
|
||||
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] != '<!--':
|
||||
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):
|
||||
@@ -114,8 +189,7 @@ class ParserBase:
|
||||
return -1
|
||||
if s != "<!":
|
||||
self.updatepos(declstartpos, j + 1)
|
||||
self.error("unexpected char in internal subset (in %s)"
|
||||
% `s`)
|
||||
self.error("unexpected char in internal subset (in %r)" % s)
|
||||
if (j + 2) == n:
|
||||
# end of buffer; incomplete
|
||||
return -1
|
||||
@@ -133,7 +207,7 @@ class ParserBase:
|
||||
if name not in ("attlist", "element", "entity", "notation"):
|
||||
self.updatepos(declstartpos, j + 2)
|
||||
self.error(
|
||||
"unknown declaration %s in internal subset" % `name`)
|
||||
"unknown declaration %r in internal subset" % name)
|
||||
# handle the individual names
|
||||
meth = getattr(self, "_parse_doctype_" + name)
|
||||
j = meth(j, declstartpos)
|
||||
@@ -151,7 +225,7 @@ class ParserBase:
|
||||
j = j + 1
|
||||
elif c == "]":
|
||||
j = j + 1
|
||||
while j < n and rawdata[j] in string.whitespace:
|
||||
while j < n and rawdata[j].isspace():
|
||||
j = j + 1
|
||||
if j < n:
|
||||
if rawdata[j] == ">":
|
||||
@@ -160,11 +234,11 @@ class ParserBase:
|
||||
self.error("unexpected char after internal subset")
|
||||
else:
|
||||
return -1
|
||||
elif c in string.whitespace:
|
||||
elif c.isspace():
|
||||
j = j + 1
|
||||
else:
|
||||
self.updatepos(declstartpos, j)
|
||||
self.error("unexpected char %s in internal subset" % `c`)
|
||||
self.error("unexpected char %r in internal subset" % c)
|
||||
# end of buffer reached
|
||||
return -1
|
||||
|
||||
@@ -176,7 +250,7 @@ class ParserBase:
|
||||
# style content model; just skip until '>'
|
||||
rawdata = self.rawdata
|
||||
if '>' in rawdata[j:]:
|
||||
return string.find(rawdata, ">", j) + 1
|
||||
return rawdata.find(">", j) + 1
|
||||
return -1
|
||||
|
||||
# Internal -- scan past <!ATTLIST declarations
|
||||
@@ -200,10 +274,10 @@ class ParserBase:
|
||||
if c == "(":
|
||||
# an enumerated type; look for ')'
|
||||
if ")" in rawdata[j:]:
|
||||
j = string.find(rawdata, ")", j) + 1
|
||||
j = rawdata.find(")", j) + 1
|
||||
else:
|
||||
return -1
|
||||
while rawdata[j:j+1] in string.whitespace:
|
||||
while rawdata[j:j+1].isspace():
|
||||
j = j + 1
|
||||
if not rawdata[j:]:
|
||||
# end of buffer, incomplete
|
||||
@@ -268,7 +342,7 @@ class ParserBase:
|
||||
c = rawdata[j:j+1]
|
||||
if not c:
|
||||
return -1
|
||||
if c in string.whitespace:
|
||||
if c.isspace():
|
||||
j = j + 1
|
||||
else:
|
||||
break
|
||||
@@ -307,10 +381,11 @@ class ParserBase:
|
||||
name = s.strip()
|
||||
if (i + len(s)) == n:
|
||||
return None, -1 # end of buffer
|
||||
return string.lower(name), m.end()
|
||||
return name.lower(), m.end()
|
||||
else:
|
||||
self.updatepos(declstartpos, i)
|
||||
self.error("expected name token")
|
||||
self.error("expected name token at %r"
|
||||
% rawdata[declstartpos:declstartpos+20])
|
||||
|
||||
# To be overridden -- handlers for unknown objects
|
||||
def unknown_decl(self, data):
|
||||
|
||||
Reference in New Issue
Block a user