mirror of
https://gitlab.com/octtspacc/staticoso
synced 2025-06-05 22:09:23 +02:00
Cleaned code a bit, added HTML minification
This commit is contained in:
139
Source/Libs/htmlmin/python3html/__init__.py
Normal file
139
Source/Libs/htmlmin/python3html/__init__.py
Normal file
@ -0,0 +1,139 @@
|
||||
"""
|
||||
General functions for HTML manipulation.
|
||||
"""
|
||||
|
||||
import re as _re
|
||||
try:
|
||||
from html.entities import html5 as _html5
|
||||
unichr = chr
|
||||
except ImportError:
|
||||
import htmlentitydefs
|
||||
_html5 = {'apos;':u"'"}
|
||||
for k, v in htmlentitydefs.name2codepoint.iteritems():
|
||||
_html5[k + ';'] = unichr(v)
|
||||
|
||||
|
||||
__all__ = ['escape', 'unescape']
|
||||
|
||||
|
||||
def escape(s, quote=True):
|
||||
"""
|
||||
Replace special characters "&", "<" and ">" to HTML-safe sequences.
|
||||
If the optional flag quote is true (the default), the quotation mark
|
||||
characters, both double quote (") and single quote (') characters are also
|
||||
translated.
|
||||
"""
|
||||
s = s.replace("&", "&") # Must be done first!
|
||||
s = s.replace("<", "<")
|
||||
s = s.replace(">", ">")
|
||||
if quote:
|
||||
s = s.replace('"', """)
|
||||
s = s.replace('\'', "'")
|
||||
return s
|
||||
|
||||
|
||||
# see http://www.w3.org/TR/html5/syntax.html#tokenizing-character-references
|
||||
|
||||
_invalid_charrefs = {
|
||||
0x00: '\ufffd', # REPLACEMENT CHARACTER
|
||||
0x0d: '\r', # CARRIAGE RETURN
|
||||
0x80: '\u20ac', # EURO SIGN
|
||||
0x81: '\x81', # <control>
|
||||
0x82: '\u201a', # SINGLE LOW-9 QUOTATION MARK
|
||||
0x83: '\u0192', # LATIN SMALL LETTER F WITH HOOK
|
||||
0x84: '\u201e', # DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85: '\u2026', # HORIZONTAL ELLIPSIS
|
||||
0x86: '\u2020', # DAGGER
|
||||
0x87: '\u2021', # DOUBLE DAGGER
|
||||
0x88: '\u02c6', # MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0x89: '\u2030', # PER MILLE SIGN
|
||||
0x8a: '\u0160', # LATIN CAPITAL LETTER S WITH CARON
|
||||
0x8b: '\u2039', # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8c: '\u0152', # LATIN CAPITAL LIGATURE OE
|
||||
0x8d: '\x8d', # <control>
|
||||
0x8e: '\u017d', # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0x8f: '\x8f', # <control>
|
||||
0x90: '\x90', # <control>
|
||||
0x91: '\u2018', # LEFT SINGLE QUOTATION MARK
|
||||
0x92: '\u2019', # RIGHT SINGLE QUOTATION MARK
|
||||
0x93: '\u201c', # LEFT DOUBLE QUOTATION MARK
|
||||
0x94: '\u201d', # RIGHT DOUBLE QUOTATION MARK
|
||||
0x95: '\u2022', # BULLET
|
||||
0x96: '\u2013', # EN DASH
|
||||
0x97: '\u2014', # EM DASH
|
||||
0x98: '\u02dc', # SMALL TILDE
|
||||
0x99: '\u2122', # TRADE MARK SIGN
|
||||
0x9a: '\u0161', # LATIN SMALL LETTER S WITH CARON
|
||||
0x9b: '\u203a', # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9c: '\u0153', # LATIN SMALL LIGATURE OE
|
||||
0x9d: '\x9d', # <control>
|
||||
0x9e: '\u017e', # LATIN SMALL LETTER Z WITH CARON
|
||||
0x9f: '\u0178', # LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
}
|
||||
|
||||
_invalid_codepoints = {
|
||||
# 0x0001 to 0x0008
|
||||
0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8,
|
||||
# 0x000E to 0x001F
|
||||
0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19,
|
||||
0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
|
||||
# 0x007F to 0x009F
|
||||
0x7f, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8a,
|
||||
0x8b, 0x8c, 0x8d, 0x8e, 0x8f, 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
|
||||
0x97, 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
|
||||
# 0xFDD0 to 0xFDEF
|
||||
0xfdd0, 0xfdd1, 0xfdd2, 0xfdd3, 0xfdd4, 0xfdd5, 0xfdd6, 0xfdd7, 0xfdd8,
|
||||
0xfdd9, 0xfdda, 0xfddb, 0xfddc, 0xfddd, 0xfdde, 0xfddf, 0xfde0, 0xfde1,
|
||||
0xfde2, 0xfde3, 0xfde4, 0xfde5, 0xfde6, 0xfde7, 0xfde8, 0xfde9, 0xfdea,
|
||||
0xfdeb, 0xfdec, 0xfded, 0xfdee, 0xfdef,
|
||||
# others
|
||||
0xb, 0xfffe, 0xffff, 0x1fffe, 0x1ffff, 0x2fffe, 0x2ffff, 0x3fffe, 0x3ffff,
|
||||
0x4fffe, 0x4ffff, 0x5fffe, 0x5ffff, 0x6fffe, 0x6ffff, 0x7fffe, 0x7ffff,
|
||||
0x8fffe, 0x8ffff, 0x9fffe, 0x9ffff, 0xafffe, 0xaffff, 0xbfffe, 0xbffff,
|
||||
0xcfffe, 0xcffff, 0xdfffe, 0xdffff, 0xefffe, 0xeffff, 0xffffe, 0xfffff,
|
||||
0x10fffe, 0x10ffff
|
||||
}
|
||||
|
||||
|
||||
def _replace_charref(s):
|
||||
s = s.group(1)
|
||||
if s[0] == '#':
|
||||
# numeric charref
|
||||
if s[1] in 'xX':
|
||||
num = int(s[2:].rstrip(';'), 16)
|
||||
else:
|
||||
num = int(s[1:].rstrip(';'))
|
||||
if num in _invalid_charrefs:
|
||||
return _invalid_charrefs[num]
|
||||
if 0xD800 <= num <= 0xDFFF or num > 0x10FFFF:
|
||||
return '\uFFFD'
|
||||
if num in _invalid_codepoints:
|
||||
return ''
|
||||
return unichr(num)
|
||||
else:
|
||||
# named charref
|
||||
if s in _html5:
|
||||
return _html5[s]
|
||||
# find the longest matching name (as defined by the standard)
|
||||
for x in range(len(s)-1, 1, -1):
|
||||
if s[:x] in _html5:
|
||||
return _html5[s[:x]] + s[x:]
|
||||
else:
|
||||
return '&' + s
|
||||
|
||||
|
||||
_charref = _re.compile(r'&(#[0-9]+;?'
|
||||
r'|#[xX][0-9a-fA-F]+;?'
|
||||
r'|[^\t\n\f <&#;]{1,32};?)')
|
||||
|
||||
def unescape(s):
|
||||
"""
|
||||
Convert all named and numeric character references (e.g. >, >,
|
||||
&x3e;) in the string s to the corresponding unicode characters.
|
||||
This function uses the rules defined by the HTML 5 standard
|
||||
for both valid and invalid character references, and the list of
|
||||
HTML 5 named character references defined in html.entities.html5.
|
||||
"""
|
||||
if '&' not in s:
|
||||
return s
|
||||
return _charref.sub(_replace_charref, s)
|
||||
481
Source/Libs/htmlmin/python3html/parser.py
Normal file
481
Source/Libs/htmlmin/python3html/parser.py
Normal file
@ -0,0 +1,481 @@
|
||||
"""A parser for HTML and XHTML."""
|
||||
|
||||
########
|
||||
# This is copied from Python3 and the slightly modified to support needed
|
||||
# features. The original file can be found at:
|
||||
# https://github.com/python/cpython/blob/44b548dda872c0d4f30afd6b44fd74b053a55ad8/Lib/html/parser.py
|
||||
#
|
||||
# The largest difference is the reinstatment of the unescape method in
|
||||
# HTMLParser, which is needed for features in htmlmin. Changes are also
|
||||
# made to ensure Python2.7 compatability.
|
||||
########
|
||||
|
||||
|
||||
# This file is based on sgmllib.py, but the API is slightly different.
|
||||
|
||||
# XXX There should be a way to distinguish between PCDATA (parsed
|
||||
# character data -- the normal case), RCDATA (replaceable character
|
||||
# data -- only char and entity references and end tags are special)
|
||||
# and CDATA (character data -- only end tags are special).
|
||||
|
||||
|
||||
import re
|
||||
import warnings
|
||||
try:
|
||||
import _markupbase as markupbase
|
||||
except ImportError:
|
||||
import markupbase
|
||||
|
||||
from . import unescape
|
||||
|
||||
|
||||
__all__ = ['HTMLParser']
|
||||
|
||||
# Regular expressions used for parsing
|
||||
|
||||
interesting_normal = re.compile('[&<]')
|
||||
incomplete = re.compile('&[a-zA-Z#]')
|
||||
|
||||
entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
|
||||
charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
|
||||
|
||||
starttagopen = re.compile('<[a-zA-Z]')
|
||||
piclose = re.compile('>')
|
||||
commentclose = re.compile(r'--\s*>')
|
||||
# Note:
|
||||
# 1) if you change tagfind/attrfind remember to update locatestarttagend too;
|
||||
# 2) if you change tagfind/attrfind and/or locatestarttagend the parser will
|
||||
# explode, so don't do it.
|
||||
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
|
||||
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
|
||||
tagfind_tolerant = re.compile(r'([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
|
||||
attrfind_tolerant = re.compile(
|
||||
r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
|
||||
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
|
||||
locatestarttagend_tolerant = re.compile(r"""
|
||||
<[a-zA-Z][^\t\n\r\f />\x00]* # tag name
|
||||
(?:[\s/]* # optional whitespace before attribute name
|
||||
(?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name
|
||||
(?:\s*=+\s* # value indicator
|
||||
(?:'[^']*' # LITA-enclosed value
|
||||
|"[^"]*" # LIT-enclosed value
|
||||
|(?!['"])[^>\s]* # bare value
|
||||
)
|
||||
(?:\s*,)* # possibly followed by a comma
|
||||
)?(?:\s|/(?!>))*
|
||||
)*
|
||||
)?
|
||||
\s* # trailing whitespace
|
||||
""", re.VERBOSE)
|
||||
endendtag = re.compile('>')
|
||||
# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
|
||||
# </ and the tag name, so maybe this should be fixed
|
||||
endtagfind = re.compile(r'</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
|
||||
|
||||
|
||||
|
||||
class HTMLParser(markupbase.ParserBase):
|
||||
"""Find tags and other markup and call handler functions.
|
||||
|
||||
Usage:
|
||||
p = HTMLParser()
|
||||
p.feed(data)
|
||||
...
|
||||
p.close()
|
||||
|
||||
Start tags are handled by calling self.handle_starttag() or
|
||||
self.handle_startendtag(); end tags by self.handle_endtag(). The
|
||||
data between tags is passed from the parser to the derived class
|
||||
by calling self.handle_data() with the data as argument (the data
|
||||
may be split up in arbitrary chunks). If convert_charrefs is
|
||||
True the character references are converted automatically to the
|
||||
corresponding Unicode character (and self.handle_data() is no
|
||||
longer split in chunks), otherwise they are passed by calling
|
||||
self.handle_entityref() or self.handle_charref() with the string
|
||||
containing respectively the named or numeric reference as the
|
||||
argument.
|
||||
"""
|
||||
|
||||
CDATA_CONTENT_ELEMENTS = ("script", "style")
|
||||
|
||||
def __init__(self, convert_charrefs=True):
|
||||
"""Initialize and reset this instance.
|
||||
|
||||
If convert_charrefs is True (the default), all character references
|
||||
are automatically converted to the corresponding Unicode characters.
|
||||
"""
|
||||
self.convert_charrefs = convert_charrefs
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
"""Reset this instance. Loses all unprocessed data."""
|
||||
self.rawdata = ''
|
||||
self.lasttag = '???'
|
||||
self.interesting = interesting_normal
|
||||
self.cdata_elem = None
|
||||
markupbase.ParserBase.reset(self)
|
||||
|
||||
def feed(self, data):
|
||||
r"""Feed data to the parser.
|
||||
|
||||
Call this as often as you want, with as little or as much text
|
||||
as you want (may include '\n').
|
||||
"""
|
||||
self.rawdata = self.rawdata + data
|
||||
self.goahead(0)
|
||||
|
||||
def close(self):
|
||||
"""Handle any buffered data."""
|
||||
self.goahead(1)
|
||||
|
||||
__starttag_text = None
|
||||
|
||||
def get_starttag_text(self):
|
||||
"""Return full source of start tag: '<...>'."""
|
||||
return self.__starttag_text
|
||||
|
||||
def set_cdata_mode(self, elem):
|
||||
self.cdata_elem = elem.lower()
|
||||
self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
|
||||
|
||||
def clear_cdata_mode(self):
|
||||
self.interesting = interesting_normal
|
||||
self.cdata_elem = None
|
||||
|
||||
# Internal -- handle data as far as reasonable. May leave state
|
||||
# and data to be processed by a subsequent call. If 'end' is
|
||||
# true, force handling all data as if followed by EOF marker.
|
||||
def goahead(self, end):
|
||||
rawdata = self.rawdata
|
||||
i = 0
|
||||
n = len(rawdata)
|
||||
while i < n:
|
||||
if self.convert_charrefs and not self.cdata_elem:
|
||||
j = rawdata.find('<', i)
|
||||
if j < 0:
|
||||
# if we can't find the next <, either we are at the end
|
||||
# or there's more text incoming. If the latter is True,
|
||||
# we can't pass the text to handle_data in case we have
|
||||
# a charref cut in half at end. Try to determine if
|
||||
# this is the case before proceeding by looking for an
|
||||
# & near the end and see if it's followed by a space or ;.
|
||||
amppos = rawdata.rfind('&', max(i, n-34))
|
||||
if (amppos >= 0 and
|
||||
not re.compile(r'[\s;]').search(rawdata, amppos)):
|
||||
break # wait till we get all the text
|
||||
j = n
|
||||
else:
|
||||
match = self.interesting.search(rawdata, i) # < or &
|
||||
if match:
|
||||
j = match.start()
|
||||
else:
|
||||
if self.cdata_elem:
|
||||
break
|
||||
j = n
|
||||
if i < j:
|
||||
if self.convert_charrefs and not self.cdata_elem:
|
||||
self.handle_data(self.unescape(rawdata[i:j]))
|
||||
else:
|
||||
self.handle_data(rawdata[i:j])
|
||||
i = self.updatepos(i, j)
|
||||
if i == n: break
|
||||
startswith = rawdata.startswith
|
||||
if startswith('<', i):
|
||||
if starttagopen.match(rawdata, i): # < + letter
|
||||
k = self.parse_starttag(i)
|
||||
elif startswith("</", i):
|
||||
k = self.parse_endtag(i)
|
||||
elif startswith("<!--", i):
|
||||
k = self.parse_comment(i)
|
||||
elif startswith("<?", i):
|
||||
k = self.parse_pi(i)
|
||||
elif startswith("<!", i):
|
||||
k = self.parse_html_declaration(i)
|
||||
elif (i + 1) < n:
|
||||
self.handle_data("<")
|
||||
k = i + 1
|
||||
else:
|
||||
break
|
||||
if k < 0:
|
||||
if not end:
|
||||
break
|
||||
k = rawdata.find('>', i + 1)
|
||||
if k < 0:
|
||||
k = rawdata.find('<', i + 1)
|
||||
if k < 0:
|
||||
k = i + 1
|
||||
else:
|
||||
k += 1
|
||||
if self.convert_charrefs and not self.cdata_elem:
|
||||
self.handle_data(self.unescape(rawdata[i:k]))
|
||||
else:
|
||||
self.handle_data(rawdata[i:k])
|
||||
i = self.updatepos(i, k)
|
||||
elif startswith("&#", i):
|
||||
match = charref.match(rawdata, i)
|
||||
if match:
|
||||
name = match.group()[2:-1]
|
||||
self.handle_charref(name)
|
||||
k = match.end()
|
||||
if not startswith(';', k-1):
|
||||
k = k - 1
|
||||
i = self.updatepos(i, k)
|
||||
continue
|
||||
else:
|
||||
if ";" in rawdata[i:]: # bail by consuming &#
|
||||
self.handle_data(rawdata[i:i+2])
|
||||
i = self.updatepos(i, i+2)
|
||||
break
|
||||
elif startswith('&', i):
|
||||
match = entityref.match(rawdata, i)
|
||||
if match:
|
||||
name = match.group(1)
|
||||
self.handle_entityref(name)
|
||||
k = match.end()
|
||||
if not startswith(';', k-1):
|
||||
k = k - 1
|
||||
i = self.updatepos(i, k)
|
||||
continue
|
||||
match = incomplete.match(rawdata, i)
|
||||
if match:
|
||||
# match.group() will contain at least 2 chars
|
||||
if end and match.group() == rawdata[i:]:
|
||||
k = match.end()
|
||||
if k <= i:
|
||||
k = n
|
||||
i = self.updatepos(i, i + 1)
|
||||
# incomplete
|
||||
break
|
||||
elif (i + 1) < n:
|
||||
# not the end of the buffer, and can't be confused
|
||||
# with some other construct
|
||||
self.handle_data("&")
|
||||
i = self.updatepos(i, i + 1)
|
||||
else:
|
||||
break
|
||||
else:
|
||||
assert 0, "interesting.search() lied"
|
||||
# end while
|
||||
if end and i < n and not self.cdata_elem:
|
||||
if self.convert_charrefs and not self.cdata_elem:
|
||||
self.handle_data(self.unescape(rawdata[i:n]))
|
||||
else:
|
||||
self.handle_data(rawdata[i:n])
|
||||
i = self.updatepos(i, n)
|
||||
self.rawdata = rawdata[i:]
|
||||
|
||||
# Internal -- parse html declarations, return length or -1 if not terminated
|
||||
# See w3.org/TR/html5/tokenization.html#markup-declaration-open-state
|
||||
# See also parse_declaration in _markupbase
|
||||
def parse_html_declaration(self, i):
|
||||
rawdata = self.rawdata
|
||||
assert rawdata[i:i+2] == '<!', ('unexpected call to '
|
||||
'parse_html_declaration()')
|
||||
if rawdata[i:i+4] == '<!--':
|
||||
# this case is actually already handled in goahead()
|
||||
return self.parse_comment(i)
|
||||
elif rawdata[i:i+3] == '<![':
|
||||
return self.parse_marked_section(i)
|
||||
elif rawdata[i:i+9].lower() == '<!doctype':
|
||||
# find the closing >
|
||||
gtpos = rawdata.find('>', i+9)
|
||||
if gtpos == -1:
|
||||
return -1
|
||||
self.handle_decl(rawdata[i+2:gtpos])
|
||||
return gtpos+1
|
||||
else:
|
||||
return self.parse_bogus_comment(i)
|
||||
|
||||
# Internal -- parse bogus comment, return length or -1 if not terminated
|
||||
# see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
|
||||
def parse_bogus_comment(self, i, report=1):
|
||||
rawdata = self.rawdata
|
||||
assert rawdata[i:i+2] in ('<!', '</'), ('unexpected call to '
|
||||
'parse_comment()')
|
||||
pos = rawdata.find('>', i+2)
|
||||
if pos == -1:
|
||||
return -1
|
||||
if report:
|
||||
self.handle_comment(rawdata[i+2:pos])
|
||||
return pos + 1
|
||||
|
||||
# Internal -- parse processing instr, return end or -1 if not terminated
|
||||
def parse_pi(self, i):
|
||||
rawdata = self.rawdata
|
||||
assert rawdata[i:i+2] == '<?', 'unexpected call to parse_pi()'
|
||||
match = piclose.search(rawdata, i+2) # >
|
||||
if not match:
|
||||
return -1
|
||||
j = match.start()
|
||||
self.handle_pi(rawdata[i+2: j])
|
||||
j = match.end()
|
||||
return j
|
||||
|
||||
# Internal -- handle starttag, return end or -1 if not terminated
|
||||
def parse_starttag(self, i):
|
||||
self.__starttag_text = None
|
||||
endpos = self.check_for_whole_start_tag(i)
|
||||
if endpos < 0:
|
||||
return endpos
|
||||
rawdata = self.rawdata
|
||||
self.__starttag_text = rawdata[i:endpos]
|
||||
|
||||
# Now parse the data between i+1 and j into a tag and attrs
|
||||
attrs = []
|
||||
match = tagfind_tolerant.match(rawdata, i+1)
|
||||
assert match, 'unexpected call to parse_starttag()'
|
||||
k = match.end()
|
||||
self.lasttag = tag = match.group(1).lower()
|
||||
while k < endpos:
|
||||
m = attrfind_tolerant.match(rawdata, k)
|
||||
if not m:
|
||||
break
|
||||
attrname, rest, attrvalue = m.group(1, 2, 3)
|
||||
if not rest:
|
||||
attrvalue = None
|
||||
elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
|
||||
attrvalue[:1] == '"' == attrvalue[-1:]:
|
||||
attrvalue = attrvalue[1:-1]
|
||||
if attrvalue:
|
||||
attrvalue = self.unescape(attrvalue)
|
||||
attrs.append((attrname.lower(), attrvalue))
|
||||
k = m.end()
|
||||
|
||||
end = rawdata[k:endpos].strip()
|
||||
if end not in (">", "/>"):
|
||||
lineno, offset = self.getpos()
|
||||
if "\n" in self.__starttag_text:
|
||||
lineno = lineno + self.__starttag_text.count("\n")
|
||||
offset = len(self.__starttag_text) \
|
||||
- self.__starttag_text.rfind("\n")
|
||||
else:
|
||||
offset = offset + len(self.__starttag_text)
|
||||
self.handle_data(rawdata[i:endpos])
|
||||
return endpos
|
||||
if end.endswith('/>'):
|
||||
# XHTML-style empty tag: <span attr="value" />
|
||||
self.handle_startendtag(tag, attrs)
|
||||
else:
|
||||
self.handle_starttag(tag, attrs)
|
||||
if tag in self.CDATA_CONTENT_ELEMENTS:
|
||||
self.set_cdata_mode(tag)
|
||||
return endpos
|
||||
|
||||
# Internal -- check to see if we have a complete starttag; return end
|
||||
# or -1 if incomplete.
|
||||
def check_for_whole_start_tag(self, i):
|
||||
rawdata = self.rawdata
|
||||
m = locatestarttagend_tolerant.match(rawdata, i)
|
||||
if m:
|
||||
j = m.end()
|
||||
next = rawdata[j:j+1]
|
||||
if next == ">":
|
||||
return j + 1
|
||||
if next == "/":
|
||||
if rawdata.startswith("/>", j):
|
||||
return j + 2
|
||||
if rawdata.startswith("/", j):
|
||||
# buffer boundary
|
||||
return -1
|
||||
# else bogus input
|
||||
if j > i:
|
||||
return j
|
||||
else:
|
||||
return i + 1
|
||||
if next == "":
|
||||
# end of input
|
||||
return -1
|
||||
if next in ("abcdefghijklmnopqrstuvwxyz=/"
|
||||
"ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
|
||||
# end of input in or before attribute value, or we have the
|
||||
# '/' from a '/>' ending
|
||||
return -1
|
||||
if j > i:
|
||||
return j
|
||||
else:
|
||||
return i + 1
|
||||
raise AssertionError("we should not get here!")
|
||||
|
||||
# Internal -- parse endtag, return end or -1 if incomplete
|
||||
def parse_endtag(self, i):
|
||||
rawdata = self.rawdata
|
||||
assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
|
||||
match = endendtag.search(rawdata, i+1) # >
|
||||
if not match:
|
||||
return -1
|
||||
gtpos = match.end()
|
||||
match = endtagfind.match(rawdata, i) # </ + tag + >
|
||||
if not match:
|
||||
if self.cdata_elem is not None:
|
||||
self.handle_data(rawdata[i:gtpos])
|
||||
return gtpos
|
||||
# find the name: w3.org/TR/html5/tokenization.html#tag-name-state
|
||||
namematch = tagfind_tolerant.match(rawdata, i+2)
|
||||
if not namematch:
|
||||
# w3.org/TR/html5/tokenization.html#end-tag-open-state
|
||||
if rawdata[i:i+3] == '</>':
|
||||
return i+3
|
||||
else:
|
||||
return self.parse_bogus_comment(i)
|
||||
tagname = namematch.group(1).lower()
|
||||
# consume and ignore other stuff between the name and the >
|
||||
# Note: this is not 100% correct, since we might have things like
|
||||
# </tag attr=">">, but looking for > after tha name should cover
|
||||
# most of the cases and is much simpler
|
||||
gtpos = rawdata.find('>', namematch.end())
|
||||
self.handle_endtag(tagname)
|
||||
return gtpos+1
|
||||
|
||||
elem = match.group(1).lower() # script or style
|
||||
if self.cdata_elem is not None:
|
||||
if elem != self.cdata_elem:
|
||||
self.handle_data(rawdata[i:gtpos])
|
||||
return gtpos
|
||||
|
||||
self.handle_endtag(elem.lower())
|
||||
self.clear_cdata_mode()
|
||||
return gtpos
|
||||
|
||||
# Overridable -- finish processing of start+end tag: <tag.../>
|
||||
def handle_startendtag(self, tag, attrs):
|
||||
self.handle_starttag(tag, attrs)
|
||||
self.handle_endtag(tag)
|
||||
|
||||
# Overridable -- handle start tag
|
||||
def handle_starttag(self, tag, attrs):
|
||||
pass
|
||||
|
||||
# Overridable -- handle end tag
|
||||
def handle_endtag(self, tag):
|
||||
pass
|
||||
|
||||
# Overridable -- handle character reference
|
||||
def handle_charref(self, name):
|
||||
pass
|
||||
|
||||
# Overridable -- handle entity reference
|
||||
def handle_entityref(self, name):
|
||||
pass
|
||||
|
||||
# Overridable -- handle data
|
||||
def handle_data(self, data):
|
||||
pass
|
||||
|
||||
# Overridable -- handle comment
|
||||
def handle_comment(self, data):
|
||||
pass
|
||||
|
||||
# Overridable -- handle declaration
|
||||
def handle_decl(self, decl):
|
||||
pass
|
||||
|
||||
# Overridable -- handle processing instruction
|
||||
def handle_pi(self, data):
|
||||
pass
|
||||
|
||||
def unknown_decl(self, data):
|
||||
pass
|
||||
|
||||
# Internal -- helper to remove special character quoting
|
||||
def unescape(self, s):
|
||||
return unescape(s)
|
||||
Reference in New Issue
Block a user