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

annotate Lib/HTMLParser.py @ 49955:878d40468c4e legacy-trunk

Issue #4384: Added logging integration with warnings module using captureWarnings(). This change includes a NullHandler which does nothing; it will be of use to library developers who want to avoid the "No handlers could be found for logger XXX" message which can appear if the library user doesn't configure logging.

author	Vinay Sajip <vinay_sajip@yahoo.co.uk>
date	Wed, 03 Dec 2008 23:22:58 +0000
parents	454d38c1f47e
children	ebda6803f8d5

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:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	178 break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	179 elif startswith('&', i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	180 match = entityref.match(rawdata, i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	181 if match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	182 name = match.group(1)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	183 self.handle_entityref(name)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	184 k = match.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	185 if not startswith(';', k-1):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	186 k = k - 1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	187 i = self.updatepos(i, k)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	188 continue
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	189 match = incomplete.match(rawdata, i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	190 if match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	191 # 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	192 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	193 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	194 # incomplete
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	195 break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	196 elif (i + 1) < n:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	197 # 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	198 # with some other construct
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	199 self.handle_data("&")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	200 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	201 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	202 break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	203 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	204 assert 0, "interesting.search() lied"
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	205 # end while
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	206 if end and i < n:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	207 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	208 i = self.updatepos(i, n)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	209 self.rawdata = rawdata[i:]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	210
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	211 # 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	212 def parse_pi(self, i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	213 rawdata = self.rawdata
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	214 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	215 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	216 if not match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	217 return -1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	218 j = match.start()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	219 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	220 j = match.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	221 return j
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	222
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	223 # 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	224 def parse_starttag(self, i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	225 self.__starttag_text = None
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	226 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	227 if endpos < 0:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	228 return endpos
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	229 rawdata = self.rawdata
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	230 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	231
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	232 # 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	233 attrs = []
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	234 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	235 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	236 k = match.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	237 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	238
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	239 while k < endpos:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	240 m = attrfind.match(rawdata, k)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	241 if not m:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	242 break
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	243 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	244 if not rest:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	245 attrvalue = None
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	246 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	247 attrvalue[:1] == '"' == attrvalue[-1:]:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	248 attrvalue = attrvalue[1:-1]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	249 attrvalue = self.unescape(attrvalue)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	250 attrs.append((attrname.lower(), attrvalue))
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	251 k = m.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	252
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	253 end = rawdata[k:endpos].strip()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	254 if end not in (">", "/>"):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	255 lineno, offset = self.getpos()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	256 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	257 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	258 offset = len(self.__starttag_text) \
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	259 - self.__starttag_text.rfind("\n")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	260 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	261 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	262 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	263 % (rawdata[k:endpos][:20],))
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	264 if end.endswith('/>'):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	265 # 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	266 self.handle_startendtag(tag, attrs)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	267 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	268 self.handle_starttag(tag, attrs)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	269 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	270 self.set_cdata_mode()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	271 return endpos
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	272
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	273 # 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	274 # or -1 if incomplete.
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	275 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	276 rawdata = self.rawdata
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	277 m = locatestarttagend.match(rawdata, i)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	278 if m:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	279 j = m.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	280 next = rawdata[j:j+1]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	281 if next == ">":
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	282 return j + 1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	283 if next == "/":
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	284 if rawdata.startswith("/>", j):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	285 return j + 2
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	286 if rawdata.startswith("/", j):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	287 # buffer boundary
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	288 return -1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	289 # else bogus input
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	290 self.updatepos(i, j + 1)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	291 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	292 if next == "":
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	293 # end of input
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	294 return -1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	295 if next in ("abcdefghijklmnopqrstuvwxyz=/"
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	296 "ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	297 # 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	298 # '/' from a '/>' ending
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	299 return -1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	300 self.updatepos(i, j)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	301 self.error("malformed start tag")
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	302 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	303
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	304 # 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	305 def parse_endtag(self, i):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	306 rawdata = self.rawdata
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	307 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	308 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	309 if not match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	310 return -1
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	311 j = match.end()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	312 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	313 if not match:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	314 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	315 tag = match.group(1)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	316 self.handle_endtag(tag.lower())
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	317 self.clear_cdata_mode()
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	318 return j
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	319
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	320 # 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	321 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	322 self.handle_starttag(tag, attrs)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	323 self.handle_endtag(tag)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	324
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	325 # Overridable -- handle start tag
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	326 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	327 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	328
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	329 # Overridable -- handle end tag
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	330 def handle_endtag(self, tag):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	331 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	332
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	333 # Overridable -- handle character reference
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	334 def handle_charref(self, name):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	335 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	336
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	337 # Overridable -- handle entity reference
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	338 def handle_entityref(self, name):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	339 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	340
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	341 # Overridable -- handle data
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	342 def handle_data(self, data):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	343 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	344
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	345 # Overridable -- handle comment
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	346 def handle_comment(self, data):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	347 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	348
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	349 # Overridable -- handle declaration
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	350 def handle_decl(self, decl):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	351 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	352
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	353 # Overridable -- handle processing instruction
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	354 def handle_pi(self, data):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	355 pass
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	356
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	357 def unknown_decl(self, data):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	358 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	359
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	360 # 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	361 entitydefs = None
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	362 def unescape(self, s):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	363 if '&' not in s:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	364 return s
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	365 def replaceEntities(s):
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	366 s = s.groups()[0]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	367 if s[0] == "#":
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	368 s = s[1:]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	369 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	370 c = int(s[1:], 16)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	371 else:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	372 c = int(s)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	373 return unichr(c)
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 # 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	376 # 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	377 import htmlentitydefs
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	378 if HTMLParser.entitydefs is None:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	379 entitydefs = HTMLParser.entitydefs = {'apos':u"'"}
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	380 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	381 entitydefs[k] = unichr(v)
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	382 try:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	383 return self.entitydefs[s]
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	384 except KeyError:
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	385 return '&'+s+';'
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	386
454d38c1f47e revert creation of the html.entities and html.parser modules Fred Drake <fdrake@acm.org> parents: diff changeset	387 return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+\|\w{1,8}));", replaceEntities, s)

Mercurial > cpython-lru_cache-weakref

annotate Lib/HTMLParser.py @ 49955:878d40468c4e legacy-trunk