cpython-lru_cache-weakref: Lib/HTMLParser.py annotate

annotate Lib/HTMLParser.py @ 61885:ebda6803f8d5 legacy-trunk

Issue #6662: Fix parsing of malformatted charref (&#bad;)

author	Victor Stinner <victor.stinner@haypocalc.com>
date	Mon, 24 May 2010 21:33:24 +0000
parents	454d38c1f47e
children	05cccd4257a2

rev	line source
47177 454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	1 """A parser for HTML and XHTML."""
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	2
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	3 # This file is based on sgmllib.py, but the API is slightly different.
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	4
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	5 # XXX There should be a way to distinguish between PCDATA (parsed
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	6 # character data -- the normal case), RCDATA (replaceable character
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	7 # data -- only char and entity references and end tags are special)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	8 # and CDATA (character data -- only end tags are special).
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	9
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	10
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	11 import markupbase
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	12 import re
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	13
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	14 # Regular expressions used for parsing
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	15
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	16 interesting_normal = re.compile('[&<]')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	17 interesting_cdata = re.compile(r'<(/\|\Z)')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	18 incomplete = re.compile('&[a-zA-Z#]')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	19
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	20 entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	21 charref = re.compile('&#(?:[0-9]+\|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	22
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	23 starttagopen = re.compile('<[a-zA-Z]')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	24 piclose = re.compile('>')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	25 commentclose = re.compile(r'--\s*>')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	26 tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	27 attrfind = re.compile(
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	28 r'\s([a-zA-Z_][-.:a-zA-Z_0-9])(\s=\s'
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	29 r'(\'[^\']\'\|"[^"]"\|[-a-zA-Z0-9./,:;+%?!&$_#=~@]))?')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	30
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	31 locatestarttagend = re.compile(r"""
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	32 <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	33 (?:\s+ # whitespace before attribute name
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	34 (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	35 (?:\s=\s # value indicator
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	36 (?:'[^']*' # LITA-enclosed value
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	37 \|\"[^\"]*\" # LIT-enclosed value
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	38 \|[^'\">\s]+ # bare value
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	39 )
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	40 )?
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	41 )
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	42 )*
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	43 \s* # trailing whitespace
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	44 """, re.VERBOSE)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	45 endendtag = re.compile('>')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	46 endtagfind = re.compile('</\s([a-zA-Z][-.a-zA-Z0-9:_])\s*>')
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	47
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	48
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	49 class HTMLParseError(Exception):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	50 """Exception raised for all parse errors."""
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	51
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	52 def __init__(self, msg, position=(None, None)):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	53 assert msg
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	54 self.msg = msg
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	55 self.lineno = position[0]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	56 self.offset = position[1]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	57
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	58 def __str__(self):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	59 result = self.msg
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	60 if self.lineno is not None:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	61 result = result + ", at line %d" % self.lineno
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	62 if self.offset is not None:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	63 result = result + ", column %d" % (self.offset + 1)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	64 return result
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	65
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	66
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	67 class HTMLParser(markupbase.ParserBase):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	68 """Find tags and other markup and call handler functions.
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	69
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	70 Usage:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	71 p = HTMLParser()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	72 p.feed(data)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	73 ...
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	74 p.close()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	75
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	76 Start tags are handled by calling self.handle_starttag() or
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	77 self.handle_startendtag(); end tags by self.handle_endtag(). The
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	78 data between tags is passed from the parser to the derived class
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	79 by calling self.handle_data() with the data as argument (the data
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	80 may be split up in arbitrary chunks). Entity references are
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	81 passed by calling self.handle_entityref() with the entity
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	82 reference as the argument. Numeric character references are
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	83 passed to self.handle_charref() with the string containing the
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	84 reference as the argument.
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	85 """
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	86
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	87 CDATA_CONTENT_ELEMENTS = ("script", "style")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	88
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	89
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	90 def __init__(self):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	91 """Initialize and reset this instance."""
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	92 self.reset()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	93
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	94 def reset(self):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	95 """Reset this instance. Loses all unprocessed data."""
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	96 self.rawdata = ''
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	97 self.lasttag = '???'
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	98 self.interesting = interesting_normal
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	99 markupbase.ParserBase.reset(self)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	100
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	101 def feed(self, data):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	102 """Feed data to the parser.
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	103
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	104 Call this as often as you want, with as little or as much text
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	105 as you want (may include '\n').
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	106 """
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	107 self.rawdata = self.rawdata + data
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	108 self.goahead(0)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	109
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	110 def close(self):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	111 """Handle any buffered data."""
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	112 self.goahead(1)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	113
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	114 def error(self, message):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	115 raise HTMLParseError(message, self.getpos())
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	116
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	117 __starttag_text = None
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	118
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	119 def get_starttag_text(self):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	120 """Return full source of start tag: '<...>'."""
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	121 return self.__starttag_text
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	122
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	123 def set_cdata_mode(self):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	124 self.interesting = interesting_cdata
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	125
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	126 def clear_cdata_mode(self):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	127 self.interesting = interesting_normal
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	128
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	129 # Internal -- handle data as far as reasonable. May leave state
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	130 # and data to be processed by a subsequent call. If 'end' is
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	131 # true, force handling all data as if followed by EOF marker.
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	132 def goahead(self, end):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	133 rawdata = self.rawdata
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	134 i = 0
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	135 n = len(rawdata)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	136 while i < n:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	137 match = self.interesting.search(rawdata, i) # < or &
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	138 if match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	139 j = match.start()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	140 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	141 j = n
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	142 if i < j: self.handle_data(rawdata[i:j])
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	143 i = self.updatepos(i, j)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	144 if i == n: break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	145 startswith = rawdata.startswith
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	146 if startswith('<', i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	147 if starttagopen.match(rawdata, i): # < + letter
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	148 k = self.parse_starttag(i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	149 elif startswith("</", i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	150 k = self.parse_endtag(i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	151 elif startswith("<!--", i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	152 k = self.parse_comment(i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	153 elif startswith("<?", i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	154 k = self.parse_pi(i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	155 elif startswith("<!", i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	156 k = self.parse_declaration(i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	157 elif (i + 1) < n:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	158 self.handle_data("<")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	159 k = i + 1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	160 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	161 break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	162 if k < 0:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	163 if end:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	164 self.error("EOF in middle of construct")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	165 break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	166 i = self.updatepos(i, k)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	167 elif startswith("&#", i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	168 match = charref.match(rawdata, i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	169 if match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	170 name = match.group()[2:-1]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	171 self.handle_charref(name)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	172 k = match.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	173 if not startswith(';', k-1):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	174 k = k - 1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	175 i = self.updatepos(i, k)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	176 continue
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	177 else:
61885 ebda6803f8d5 Issue #6662: Fix parsing of malformatted charref (&#bad;) Victor Stinner <victor.stinner@haypocalc.com> parents: 47177 diff changeset	178 if ";" in rawdata[i:]: #bail by consuming &#
ebda6803f8d5 Issue #6662: Fix parsing of malformatted charref (&#bad;) Victor Stinner <victor.stinner@haypocalc.com> parents: 47177 diff changeset	179 self.handle_data(rawdata[0:2])
ebda6803f8d5 Issue #6662: Fix parsing of malformatted charref (&#bad;) Victor Stinner <victor.stinner@haypocalc.com> parents: 47177 diff changeset	180 i = self.updatepos(i, 2)
47177 454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	181 break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	182 elif startswith('&', i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	183 match = entityref.match(rawdata, i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	184 if match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	185 name = match.group(1)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	186 self.handle_entityref(name)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	187 k = match.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	188 if not startswith(';', k-1):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	189 k = k - 1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	190 i = self.updatepos(i, k)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	191 continue
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	192 match = incomplete.match(rawdata, i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	193 if match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	194 # match.group() will contain at least 2 chars
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	195 if end and match.group() == rawdata[i:]:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	196 self.error("EOF in middle of entity or char ref")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	197 # incomplete
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	198 break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	199 elif (i + 1) < n:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	200 # not the end of the buffer, and can't be confused
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	201 # with some other construct
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	202 self.handle_data("&")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	203 i = self.updatepos(i, i + 1)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	204 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	205 break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	206 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	207 assert 0, "interesting.search() lied"
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	208 # end while
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	209 if end and i < n:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	210 self.handle_data(rawdata[i:n])
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	211 i = self.updatepos(i, n)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	212 self.rawdata = rawdata[i:]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	213
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	214 # Internal -- parse processing instr, return end or -1 if not terminated
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	215 def parse_pi(self, i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	216 rawdata = self.rawdata
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	217 assert rawdata[i:i+2] == '<?', 'unexpected call to parse_pi()'
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	218 match = piclose.search(rawdata, i+2) # >
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	219 if not match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	220 return -1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	221 j = match.start()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	222 self.handle_pi(rawdata[i+2: j])
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	223 j = match.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	224 return j
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	225
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	226 # Internal -- handle starttag, return end or -1 if not terminated
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	227 def parse_starttag(self, i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	228 self.__starttag_text = None
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	229 endpos = self.check_for_whole_start_tag(i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	230 if endpos < 0:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	231 return endpos
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	232 rawdata = self.rawdata
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	233 self.__starttag_text = rawdata[i:endpos]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	234
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	235 # Now parse the data between i+1 and j into a tag and attrs
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	236 attrs = []
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	237 match = tagfind.match(rawdata, i+1)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	238 assert match, 'unexpected call to parse_starttag()'
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	239 k = match.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	240 self.lasttag = tag = rawdata[i+1:k].lower()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	241
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	242 while k < endpos:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	243 m = attrfind.match(rawdata, k)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	244 if not m:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	245 break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	246 attrname, rest, attrvalue = m.group(1, 2, 3)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	247 if not rest:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	248 attrvalue = None
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	249 elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	250 attrvalue[:1] == '"' == attrvalue[-1:]:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	251 attrvalue = attrvalue[1:-1]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	252 attrvalue = self.unescape(attrvalue)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	253 attrs.append((attrname.lower(), attrvalue))
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	254 k = m.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	255
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	256 end = rawdata[k:endpos].strip()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	257 if end not in (">", "/>"):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	258 lineno, offset = self.getpos()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	259 if "\n" in self.__starttag_text:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	260 lineno = lineno + self.__starttag_text.count("\n")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	261 offset = len(self.__starttag_text) \
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	262 - self.__starttag_text.rfind("\n")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	263 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	264 offset = offset + len(self.__starttag_text)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	265 self.error("junk characters in start tag: %r"
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	266 % (rawdata[k:endpos][:20],))
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	267 if end.endswith('/>'):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	268 # XHTML-style empty tag: <span attr="value" />
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	269 self.handle_startendtag(tag, attrs)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	270 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	271 self.handle_starttag(tag, attrs)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	272 if tag in self.CDATA_CONTENT_ELEMENTS:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	273 self.set_cdata_mode()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	274 return endpos
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	275
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	276 # Internal -- check to see if we have a complete starttag; return end
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	277 # or -1 if incomplete.
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	278 def check_for_whole_start_tag(self, i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	279 rawdata = self.rawdata
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	280 m = locatestarttagend.match(rawdata, i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	281 if m:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	282 j = m.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	283 next = rawdata[j:j+1]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	284 if next == ">":
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	285 return j + 1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	286 if next == "/":
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	287 if rawdata.startswith("/>", j):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	288 return j + 2
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	289 if rawdata.startswith("/", j):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	290 # buffer boundary
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	291 return -1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	292 # else bogus input
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	293 self.updatepos(i, j + 1)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	294 self.error("malformed empty start tag")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	295 if next == "":
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	296 # end of input
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	297 return -1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	298 if next in ("abcdefghijklmnopqrstuvwxyz=/"
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	299 "ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	300 # end of input in or before attribute value, or we have the
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	301 # '/' from a '/>' ending
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	302 return -1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	303 self.updatepos(i, j)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	304 self.error("malformed start tag")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	305 raise AssertionError("we should not get here!")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	306
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	307 # Internal -- parse endtag, return end or -1 if incomplete
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	308 def parse_endtag(self, i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	309 rawdata = self.rawdata
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	310 assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	311 match = endendtag.search(rawdata, i+1) # >
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	312 if not match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	313 return -1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	314 j = match.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	315 match = endtagfind.match(rawdata, i) # </ + tag + >
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	316 if not match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	317 self.error("bad end tag: %r" % (rawdata[i:j],))
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	318 tag = match.group(1)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	319 self.handle_endtag(tag.lower())
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	320 self.clear_cdata_mode()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	321 return j
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	322
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	323 # Overridable -- finish processing of start+end tag: <tag.../>
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	324 def handle_startendtag(self, tag, attrs):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	325 self.handle_starttag(tag, attrs)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	326 self.handle_endtag(tag)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	327
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	328 # Overridable -- handle start tag
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	329 def handle_starttag(self, tag, attrs):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	330 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	331
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	332 # Overridable -- handle end tag
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	333 def handle_endtag(self, tag):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	334 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	335
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	336 # Overridable -- handle character reference
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	337 def handle_charref(self, name):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	338 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	339
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	340 # Overridable -- handle entity reference
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	341 def handle_entityref(self, name):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	342 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	343
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	344 # Overridable -- handle data
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	345 def handle_data(self, data):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	346 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	347
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	348 # Overridable -- handle comment
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	349 def handle_comment(self, data):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	350 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	351
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	352 # Overridable -- handle declaration
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	353 def handle_decl(self, decl):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	354 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	355
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	356 # Overridable -- handle processing instruction
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	357 def handle_pi(self, data):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	358 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	359
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	360 def unknown_decl(self, data):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	361 self.error("unknown declaration: %r" % (data,))
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	362
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	363 # Internal -- helper to remove special character quoting
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	364 entitydefs = None
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	365 def unescape(self, s):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	366 if '&' not in s:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	367 return s
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	368 def replaceEntities(s):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	369 s = s.groups()[0]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	370 if s[0] == "#":
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	371 s = s[1:]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	372 if s[0] in ['x','X']:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	373 c = int(s[1:], 16)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	374 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	375 c = int(s)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	376 return unichr(c)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	377 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	378 # Cannot use name2codepoint directly, because HTMLParser supports apos,
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	379 # which is not part of HTML 4
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	380 import htmlentitydefs
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	381 if HTMLParser.entitydefs is None:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	382 entitydefs = HTMLParser.entitydefs = {'apos':u"'"}
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	383 for k, v in htmlentitydefs.name2codepoint.iteritems():
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	384 entitydefs[k] = unichr(v)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	385 try:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	386 return self.entitydefs[s]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	387 except KeyError:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	388 return '&'+s+';'
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	389
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	390 return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+\|\w{1,8}));", replaceEntities, s)

Mercurial > cpython-lru_cache-weakref

annotate Lib/HTMLParser.py @ 61885:ebda6803f8d5 legacy-trunk