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

annotate Lib/HTMLParser.py @ 19687:3731ad1d9033 legacy-trunk

HTMLParser is allowed to be more strict than sgmllib, so let's not change their basic behavior: When parsing something that cannot possibly be valid in either HTML or XHTML, raise an exception.

author	Fred Drake <fdrake@acm.org>
date	Tue, 04 Sep 2001 16:26:03 +0000
parents	8dfb13a4e175
children	0f9df563b65d

rev	line source
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	1 """A parser for HTML and XHTML."""
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	2
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	3 # This file is based on sgmllib.py, but the API is slightly different.
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	4
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	5 # XXX There should be a way to distinguish between PCDATA (parsed
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	6 # character data -- the normal case), RCDATA (replaceable character
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	7 # data -- only char and entity references and end tags are special)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	8 # and CDATA (character data -- only end tags are special).
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	9
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	10
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	11 import re
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	12 import string
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	13
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	14 # Regular expressions used for parsing
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	15
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	16 interesting_normal = re.compile('[&<]')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	17 interesting_cdata = re.compile(r'<(/\|\Z)')
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	18 incomplete = re.compile('&[a-zA-Z#]')
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	19
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	20 entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	21 charref = re.compile('&#(?:[0-9]+\|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	22
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	23 starttagopen = re.compile('<[a-zA-Z]')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	24 piopen = re.compile(r'<\?')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	25 piclose = re.compile('>')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	26 endtagopen = re.compile('</')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	27 declopen = re.compile('<!')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	28 special = re.compile('<![^<>]*>')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	29 commentopen = re.compile('<!--')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	30 commentclose = re.compile(r'--\s*>')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	31 tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	32 attrfind = re.compile(
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	33 r'\s([a-zA-Z_][-.:a-zA-Z_0-9])(\s=\s'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	34 r'(\'[^\']\'\|"[^"]"\|[-a-zA-Z0-9./:;+%?!&$_#=~]))?')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	35
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	36 locatestarttagend = re.compile(r"""
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	37 <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	38 (?:\s+ # whitespace before attribute name
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	39 (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	40 (?:\s=\s # value indicator
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	41 (?:'[^']*' # LITA-enclosed value
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	42 \|\"[^\"]*\" # LIT-enclosed value
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	43 \|[^'\">\s]+ # bare value
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	44 )
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	45 )?
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	46 )
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	47 )*
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	48 \s* # trailing whitespace
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	49 """, re.VERBOSE)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	50 endstarttag = re.compile(r"\s*/?>")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	51 endendtag = re.compile('>')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	52 endtagfind = re.compile('</\s([a-zA-Z][-.a-zA-Z0-9:_])\s*>')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	53
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	54 declname = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]\s')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	55 declstringlit = re.compile(r'(\'[^\']\'\|"[^"]")\s*')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	56
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	57
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	58 class HTMLParseError(Exception):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	59 """Exception raised for all parse errors."""
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	60
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	61 def __init__(self, msg, position=(None, None)):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	62 assert msg
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	63 self.msg = msg
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	64 self.lineno = position[0]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	65 self.offset = position[1]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	66
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	67 def __str__(self):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	68 result = self.msg
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	69 if self.lineno is not None:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	70 result = result + ", at line %d" % self.lineno
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	71 if self.offset is not None:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	72 result = result + ", column %d" % (self.offset + 1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	73 return result
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	74
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	75
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	76 class HTMLParser:
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	77 """Find tags and other markup and call handler functions.
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	78
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	79 Usage:
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	80 p = HTMLParser()
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	81 p.feed(data)
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	82 ...
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	83 p.close()
17932 ce7f0e380830 Removed incorrect comment left over from sgmllib.py. Guido van Rossum <guido@python.org> parents: 17853 diff changeset	84
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	85 Start tags are handled by calling self.handle_starttag() or
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	86 self.handle_startendtag(); end tags by self.handle_endtag(). The
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	87 data between tags is passed from the parser to the derived class
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	88 by calling self.handle_data() with the data as argument (the data
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	89 may be split up in arbitrary chunks). Entity references are
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	90 passed by calling self.handle_entityref() with the entity
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	91 reference as the argument. Numeric character references are
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	92 passed to self.handle_charref() with the string containing the
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	93 reference as the argument.
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	94 """
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	95
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	96 CDATA_CONTENT_ELEMENTS = ("script", "style")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	97
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	98
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	99 def __init__(self):
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	100 """Initialize and reset this instance."""
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	101 self.reset()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	102
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	103 def reset(self):
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	104 """Reset this instance. Loses all unprocessed data."""
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	105 self.rawdata = ''
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	106 self.stack = []
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	107 self.lasttag = '???'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	108 self.lineno = 1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	109 self.offset = 0
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	110 self.interesting = interesting_normal
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	111
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	112 def feed(self, data):
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	113 """Feed data to the parser.
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	114
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	115 Call this as often as you want, with as little or as much text
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	116 as you want (may include '\n').
00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	117 """
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	118 self.rawdata = self.rawdata + data
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	119 self.goahead(0)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	120
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	121 def close(self):
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	122 """Handle any buffered data."""
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	123 self.goahead(1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	124
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	125 # Internal -- update line number and offset. This should be
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	126 # called for each piece of data exactly once, in order -- in other
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	127 # words the concatenation of all the input strings to this
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	128 # function should be exactly the entire input.
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	129 def updatepos(self, i, j):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	130 if i >= j:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	131 return j
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	132 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	133 nlines = string.count(rawdata, "\n", i, j)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	134 if nlines:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	135 self.lineno = self.lineno + nlines
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	136 pos = string.rindex(rawdata, "\n", i, j) # Should not fail
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	137 self.offset = j-(pos+1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	138 else:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	139 self.offset = self.offset + j-i
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	140 return j
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	141
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	142 def getpos(self):
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	143 """Return current line number and offset."""
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	144 return self.lineno, self.offset
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	145
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	146 __starttag_text = None
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	147
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	148 def get_starttag_text(self):
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	149 """Return full source of start tag: '<...>'."""
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	150 return self.__starttag_text
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	151
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	152 def set_cdata_mode(self):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	153 self.interesting = interesting_cdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	154
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	155 def clear_cdata_mode(self):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	156 self.interesting = interesting_normal
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	157
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	158 # Internal -- handle data as far as reasonable. May leave state
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	159 # and data to be processed by a subsequent call. If 'end' is
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	160 # true, force handling all data as if followed by EOF marker.
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	161 def goahead(self, end):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	162 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	163 i = 0
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	164 n = len(rawdata)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	165 while i < n:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	166 match = self.interesting.search(rawdata, i) # < or &
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	167 if match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	168 j = match.start()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	169 else:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	170 j = n
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	171 if i < j: self.handle_data(rawdata[i:j])
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	172 i = self.updatepos(i, j)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	173 if i == n: break
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	174 if rawdata[i] == '<':
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	175 if starttagopen.match(rawdata, i): # < + letter
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	176 k = self.parse_starttag(i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	177 elif endtagopen.match(rawdata, i): # </
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	178 k = self.parse_endtag(i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	179 if k >= 0:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	180 self.clear_cdata_mode()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	181 elif commentopen.match(rawdata, i): # <!--
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	182 k = self.parse_comment(i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	183 elif piopen.match(rawdata, i): # <?
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	184 k = self.parse_pi(i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	185 elif declopen.match(rawdata, i): # <!
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	186 k = self.parse_declaration(i)
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	187 elif (i + 1) < n:
19410 c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18984 diff changeset	188 self.handle_data("<")
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18984 diff changeset	189 k = i + 1
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	190 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	191 break
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	192 if k < 0:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	193 if end:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	194 raise HTMLParseError("EOF in middle of construct",
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	195 self.getpos())
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	196 break
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	197 i = self.updatepos(i, k)
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	198 elif rawdata[i:i+2] == "&#":
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	199 match = charref.match(rawdata, i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	200 if match:
18984 00935031b373 Change some comments into docstrings. Fred Drake <fdrake@acm.org> parents: 17934 diff changeset	201 name = match.group()[2:-1]
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	202 self.handle_charref(name)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	203 k = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	204 if rawdata[k-1] != ';':
19410 c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18984 diff changeset	205 k = k - 1
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	206 i = self.updatepos(i, k)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	207 continue
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	208 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	209 break
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	210 elif rawdata[i] == '&':
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	211 match = entityref.match(rawdata, i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	212 if match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	213 name = match.group(1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	214 self.handle_entityref(name)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	215 k = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	216 if rawdata[k-1] != ';':
19410 c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18984 diff changeset	217 k = k - 1
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	218 i = self.updatepos(i, k)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	219 continue
19410 c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18984 diff changeset	220 match = incomplete.match(rawdata, i)
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18984 diff changeset	221 if match:
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	222 # match.group() will contain at least 2 chars
19410 c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this Fred Drake <fdrake@acm.org> parents: 18984 diff changeset	223 rest = rawdata[i:]
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	224 if end and match.group() == rest:
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	225 raise HTMLParseError(
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	226 "EOF in middle of entity or char ref",
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	227 self.getpos())
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	228 # incomplete
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	229 break
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	230 elif (i + 1) < n:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	231 # not the end of the buffer, and can't be confused
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	232 # with some other construct
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	233 self.handle_data("&")
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	234 i = self.updatepos(i, i + 1)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	235 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	236 break
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	237 else:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	238 assert 0, "interesting.search() lied"
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	239 # end while
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	240 if end and i < n:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	241 self.handle_data(rawdata[i:n])
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	242 i = self.updatepos(i, n)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	243 self.rawdata = rawdata[i:]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	244
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	245 # Internal -- parse comment, return end or -1 if not terminated
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	246 def parse_comment(self, i, report=1):
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	247 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	248 assert rawdata[i:i+4] == '<!--', 'unexpected call to parse_comment()'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	249 match = commentclose.search(rawdata, i+4)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	250 if not match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	251 return -1
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	252 if report:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	253 j = match.start()
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	254 self.handle_comment(rawdata[i+4: j])
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	255 j = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	256 return j
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	257
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	258 # Internal -- parse declaration.
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	259 def parse_declaration(self, i):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	260 # This is some sort of declaration; in "HTML as
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	261 # deployed," this should only be the document type
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	262 # declaration ("<!DOCTYPE html...>").
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	263 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	264 j = i + 2
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	265 assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	266 if rawdata[j:j+1] in ("-", ""):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	267 # Start of comment followed by buffer boundary,
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	268 # or just a buffer boundary.
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	269 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	270 # in practice, this should look like: ((name\|stringlit) S*)+ '>'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	271 n = len(rawdata)
19687 3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	272 decltype, j = self.scan_name(j, i)
3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	273 if j < 0:
3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	274 return j
3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	275 if decltype.lower() != "doctype":
3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	276 raise HTMLParseError("unknown declaration: '%s'" % decltype,
3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	277 self.getpos())
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	278 while j < n:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	279 c = rawdata[j]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	280 if c == ">":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	281 # end of declaration syntax
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	282 data = rawdata[i+2:j]
19687 3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	283 self.handle_decl(data)
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	284 return j + 1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	285 if c in "\"'":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	286 m = declstringlit.match(rawdata, j)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	287 if not m:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	288 return -1 # incomplete
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	289 j = m.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	290 elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ":
19687 3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	291 name, j = self.scan_name(j, i)
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	292 elif c == "[" and decltype == "doctype":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	293 j = self.parse_doctype_subset(j + 1, i)
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	294 else:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	295 raise HTMLParseError(
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	296 "unexpected char in declaration: %s" % `rawdata[j]`,
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	297 self.getpos())
19687 3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	298 if j < 0:
3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	299 return j
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	300 return -1 # incomplete
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	301
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	302 # Internal -- scan past the internal subset in a <!DOCTYPE declaration,
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	303 # returning the index just past any whitespace following the trailing ']'.
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	304 def parse_doctype_subset(self, i, declstartpos):
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	305 rawdata = self.rawdata
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	306 n = len(rawdata)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	307 j = i
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	308 while j < n:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	309 c = rawdata[j]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	310 if c == "<":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	311 s = rawdata[j:j+2]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	312 if s == "<":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	313 # end of buffer; incomplete
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	314 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	315 if s != "<!":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	316 self.updatepos(declstartpos, j + 1)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	317 raise HTMLParseError("unexpect char in internal subset",
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	318 self.getpos())
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	319 if (j + 2) == n:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	320 # end of buffer; incomplete
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	321 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	322 if (j + 4) > n:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	323 # end of buffer; incomplete
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	324 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	325 if rawdata[j:j+4] == "<!--":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	326 j = self.parse_comment(j, report=0)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	327 if j < 0:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	328 return j
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	329 continue
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	330 name, j = self.scan_name(j + 2, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	331 if j == -1:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	332 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	333 if name not in ("attlist", "element", "entity", "notation"):
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	334 self.updatepos(declstartpos, j + 2)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	335 raise HTMLParseError(
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	336 "unknown declaration %s in internal subset" % `name`,
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	337 self.getpos())
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	338 # handle the individual names
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	339 meth = getattr(self, "parse_doctype_" + name)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	340 j = meth(j, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	341 if j < 0:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	342 return j
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	343 elif c == "%":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	344 # parameter entity reference
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	345 if (j + 1) == n:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	346 # end of buffer; incomplete
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	347 return -1
19687 3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	348 s, j = self.scan_name(j + 1, declstartpos)
3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	349 if j < 0:
3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	350 return j
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	351 if rawdata[j] == ";":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	352 j = j + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	353 elif c == "]":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	354 j = j + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	355 while j < n and rawdata[j] in string.whitespace:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	356 j = j + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	357 if j < n:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	358 if rawdata[j] == ">":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	359 return j
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	360 self.updatepos(declstartpos, j)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	361 raise HTMLParseError(
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	362 "unexpected char after internal subset",
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	363 self.getpos())
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	364 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	365 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	366 elif c in string.whitespace:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	367 j = j + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	368 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	369 self.updatepos(declstartpos, j)
19687 3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	370 raise HTMLParseError(
3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	371 "unexpected char %s in internal subset" % `c`,
3731ad1d9033 HTMLParser is allowed to be more strict than sgmllib, so let's not Fred Drake <fdrake@acm.org> parents: 19682 diff changeset	372 self.getpos())
19682 8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	373 # end of buffer reached
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	374 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	375
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	376 def parse_doctype_element(self, i, declstartpos):
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	377 rawdata = self.rawdata
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	378 n = len(rawdata)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	379 name, j = self.scan_name(i, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	380 if j == -1:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	381 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	382 # style content model; just skip until '>'
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	383 if '>' in rawdata[j:]:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	384 return string.find(rawdata, ">", j) + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	385 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	386
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	387 def parse_doctype_attlist(self, i, declstartpos):
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	388 rawdata = self.rawdata
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	389 name, j = self.scan_name(i, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	390 c = rawdata[j:j+1]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	391 if c == "":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	392 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	393 if c == ">":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	394 return j + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	395 while 1:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	396 # scan a series of attribute descriptions; simplified:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	397 # name type [value] [#constraint]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	398 name, j = self.scan_name(j, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	399 if j < 0:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	400 return j
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	401 c = rawdata[j:j+1]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	402 if c == "":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	403 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	404 if c == "(":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	405 # an enumerated type; look for ')'
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	406 if ")" in rawdata[j:]:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	407 j = string.find(rawdata, ")", j) + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	408 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	409 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	410 while rawdata[j:j+1] in string.whitespace:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	411 j = j + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	412 if not rawdata[j:]:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	413 # end of buffer, incomplete
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	414 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	415 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	416 name, j = self.scan_name(j, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	417 c = rawdata[j:j+1]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	418 if not c:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	419 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	420 if c in "'\"":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	421 m = declstringlit.match(rawdata, j)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	422 if m:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	423 j = m.end()
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	424 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	425 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	426 c = rawdata[j:j+1]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	427 if not c:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	428 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	429 if c == "#":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	430 if rawdata[j:] == "#":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	431 # end of buffer
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	432 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	433 name, j = self.scan_name(j + 1, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	434 if j < 0:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	435 return j
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	436 c = rawdata[j:j+1]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	437 if not c:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	438 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	439 if c == '>':
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	440 # all done
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	441 return j + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	442
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	443 def parse_doctype_notation(self, i, declstartpos):
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	444 name, j = self.scan_name(i, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	445 if j < 0:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	446 return j
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	447 rawdata = self.rawdata
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	448 while 1:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	449 c = rawdata[j:j+1]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	450 if not c:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	451 # end of buffer; incomplete
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	452 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	453 if c == '>':
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	454 return j + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	455 if c in "'\"":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	456 m = declstringlit.match(rawdata, j)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	457 if not m:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	458 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	459 j = m.end()
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	460 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	461 name, j = self.scan_name(j, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	462 if j < 0:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	463 return j
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	464
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	465 def parse_doctype_entity(self, i, declstartpos):
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	466 rawdata = self.rawdata
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	467 if rawdata[i:i+1] == "%":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	468 j = i + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	469 while 1:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	470 c = rawdata[j:j+1]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	471 if not c:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	472 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	473 if c in string.whitespace:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	474 j = j + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	475 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	476 break
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	477 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	478 j = i
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	479 name, j = self.scan_name(j, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	480 if j < 0:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	481 return j
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	482 while 1:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	483 c = self.rawdata[j:j+1]
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	484 if not c:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	485 return -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	486 if c in "'\"":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	487 m = declstringlit.match(rawdata, j)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	488 if m:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	489 j = m.end()
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	490 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	491 return -1 # incomplete
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	492 elif c == ">":
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	493 return j + 1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	494 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	495 name, j = self.scan_name(j, declstartpos)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	496 if j < 0:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	497 return j
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	498
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	499 def scan_name(self, i, declstartpos):
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	500 rawdata = self.rawdata
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	501 n = len(rawdata)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	502 if i == n:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	503 return None, -1
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	504 m = declname.match(rawdata, i)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	505 if m:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	506 s = m.group()
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	507 name = s.strip()
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	508 if (i + len(s)) == n:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	509 return None, -1 # end of buffer
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	510 return name.lower(), m.end()
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	511 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	512 self.updatepos(declstartpos, i)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	513 raise HTMLParseError("expected name token", self.getpos())
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases Fred Drake <fdrake@acm.org> parents: 19410 diff changeset	514
17853 055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	515 # Internal -- parse processing instr, return end or -1 if not terminated
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	516 def parse_pi(self, i):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	517 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	518 assert rawdata[i:i+2] == '<?', 'unexpected call to parse_pi()'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	519 match = piclose.search(rawdata, i+2) # >
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	520 if not match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	521 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	522 j = match.start()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	523 self.handle_pi(rawdata[i+2: j])
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	524 j = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	525 return j
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	526
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	527 # Internal -- handle starttag, return end or -1 if not terminated
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	528 def parse_starttag(self, i):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	529 self.__starttag_text = None
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	530 endpos = self.check_for_whole_start_tag(i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	531 if endpos < 0:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	532 return endpos
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	533 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	534 self.__starttag_text = rawdata[i:endpos]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	535
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	536 # Now parse the data between i+1 and j into a tag and attrs
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	537 attrs = []
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	538 match = tagfind.match(rawdata, i+1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	539 assert match, 'unexpected call to parse_starttag()'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	540 k = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	541 self.lasttag = tag = string.lower(rawdata[i+1:k])
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	542
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	543 while k < endpos:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	544 m = attrfind.match(rawdata, k)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	545 if not m:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	546 break
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	547 attrname, rest, attrvalue = m.group(1, 2, 3)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	548 if not rest:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	549 attrvalue = None
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	550 elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	551 attrvalue[:1] == '"' == attrvalue[-1:]:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	552 attrvalue = attrvalue[1:-1]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	553 attrvalue = self.unescape(attrvalue)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	554 attrs.append((string.lower(attrname), attrvalue))
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	555 k = m.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	556
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	557 end = string.strip(rawdata[k:endpos])
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	558 if end not in (">", "/>"):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	559 lineno, offset = self.getpos()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	560 if "\n" in self.__starttag_text:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	561 lineno = lineno + string.count(self.__starttag_text, "\n")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	562 offset = len(self.__starttag_text) \
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	563 - string.rfind(self.__starttag_text, "\n")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	564 else:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	565 offset = offset + len(self.__starttag_text)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	566 raise HTMLParseError("junk characters in start tag: %s"
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	567 % `rawdata[k:endpos][:20]`,
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	568 (lineno, offset))
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	569 if end[-2:] == '/>':
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	570 # XHTML-style empty tag: <span attr="value" />
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	571 self.handle_startendtag(tag, attrs)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	572 else:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	573 self.handle_starttag(tag, attrs)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	574 if tag in self.CDATA_CONTENT_ELEMENTS:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	575 self.set_cdata_mode()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	576 return endpos
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	577
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	578 # Internal -- check to see if we have a complete starttag; return end
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	579 # or -1 if incomplete.
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	580 def check_for_whole_start_tag(self, i):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	581 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	582 m = locatestarttagend.match(rawdata, i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	583 if m:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	584 j = m.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	585 next = rawdata[j:j+1]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	586 if next == ">":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	587 return j + 1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	588 if next == "/":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	589 s = rawdata[j:j+2]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	590 if s == "/>":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	591 return j + 2
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	592 if s == "/":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	593 # buffer boundary
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	594 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	595 # else bogus input
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	596 self.updatepos(i, j + 1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	597 raise HTMLParseError("malformed empty start tag",
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	598 self.getpos())
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	599 if next == "":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	600 # end of input
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	601 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	602 if next in ("abcdefghijklmnopqrstuvwxyz=/"
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	603 "ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	604 # end of input in or before attribute value, or we have the
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	605 # '/' from a '/>' ending
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	606 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	607 self.updatepos(i, j)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	608 raise HTMLParseError("malformed start tag", self.getpos())
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	609 raise AssertionError("we should not gt here!")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	610
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	611 # Internal -- parse endtag, return end or -1 if incomplete
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	612 def parse_endtag(self, i):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	613 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	614 assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	615 match = endendtag.search(rawdata, i+1) # >
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	616 if not match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	617 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	618 j = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	619 match = endtagfind.match(rawdata, i) # </ + tag + >
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	620 if not match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	621 raise HTMLParseError("bad end tag: %s" % `rawdata[i:j]`,
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	622 self.getpos())
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	623 tag = match.group(1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	624 self.handle_endtag(string.lower(tag))
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	625 return j
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	626
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	627 # Overridable -- finish processing of start+end tag: <tag.../>
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	628 def handle_startendtag(self, tag, attrs):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	629 self.handle_starttag(tag, attrs)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	630 self.handle_endtag(tag)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	631
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	632 # Overridable -- handle start tag
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	633 def handle_starttag(self, tag, attrs):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	634 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	635
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	636 # Overridable -- handle end tag
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	637 def handle_endtag(self, tag):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	638 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	639
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	640 # Overridable -- handle character reference
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	641 def handle_charref(self, name):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	642 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	643
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	644 # Overridable -- handle entity reference
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	645 def handle_entityref(self, name):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	646 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	647
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	648 # Overridable -- handle data
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	649 def handle_data(self, data):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	650 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	651
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	652 # Overridable -- handle comment
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	653 def handle_comment(self, data):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	654 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	655
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	656 # Overridable -- handle declaration
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	657 def handle_decl(self, decl):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	658 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	659
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	660 # Overridable -- handle processing instruction
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	661 def handle_pi(self, data):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	662 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	663
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	664 # Internal -- helper to remove special character quoting
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	665 def unescape(self, s):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	666 if '&' not in s:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	667 return s
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	668 s = string.replace(s, "<", "<")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	669 s = string.replace(s, ">", ">")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	670 s = string.replace(s, "'", "'")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	671 s = string.replace(s, """, '"')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	672 s = string.replace(s, "&", "&") # Must be last
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is Guido van Rossum <guido@python.org> parents: diff changeset	673 return s

Mercurial > cpython-lru_cache-weakref

annotate Lib/HTMLParser.py @ 19687:3731ad1d9033 legacy-trunk