Mercurial Repository: p/roundup/code: TAL/HTMLParser.py comparison

comparison TAL/HTMLParser.py @ 982:bfd348432420

Adding TAL to the dist

author	Richard Jones <richard@users.sourceforge.net>
date	Fri, 30 Aug 2002 08:23:53 +0000
parents
children

comparison

equal deleted inserted replaced

-:f36ffa50374f
+:bfd348432420
+"""A parser for HTML and XHTML."""
+# This file is based on sgmllib.py, but the API is slightly different.
+# XXX There should be a way to distinguish between PCDATA (parsed
+# character data -- the normal case), RCDATA (replaceable character
+# data -- only char and entity references and end tags are special)
+# and CDATA (character data -- only end tags are special).
+import markupbase
+import re
+import string
+# Regular expressions used for parsing
+interesting_normal = re.compile('[&<]')
+interesting_cdata = re.compile(r'<(/|\Z)')
+incomplete = re.compile('&[a-zA-Z#]')
+entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
+charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
+starttagopen = re.compile('<[a-zA-Z]')
+piclose = re.compile('>')
+endtagopen = re.compile('</')
+commentclose = re.compile(r'--\s*>')
+tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
+attrfind = re.compile(
+r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
+r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./:;+*%?!&$\(\)_#=~]*))?')
+locatestarttagend = re.compile(r"""
+<[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
+(?:\s+                             # whitespace before attribute name
+(?:[a-zA-Z_][-.:a-zA-Z0-9_]*     # attribute name
+(?:\s*=\s*                     # value indicator
+(?:'[^']*'                   # LITA-enclosed value
+|\"[^\"]*\"                # LIT-enclosed value
+|[^'\">\s]+                # bare value
+)
+)?
+)
+)*
+\s*                                # trailing whitespace
+""", re.VERBOSE)
+endendtag = re.compile('>')
+endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
+class HTMLParseError(Exception):
+"""Exception raised for all parse errors."""
+def __init__(self, msg, position=(None, None)):
+assert msg
+self.msg = msg
+self.lineno = position[0]
+self.offset = position[1]
+def __str__(self):
+result = self.msg
+if self.lineno is not None:
+result = result + ", at line %d" % self.lineno
+if self.offset is not None:
+result = result + ", column %d" % (self.offset + 1)
+return result
+def _contains_at(s, sub, pos):
+return s[pos:pos+len(sub)] == sub
+class HTMLParser(markupbase.ParserBase):
+"""Find tags and other markup and call handler functions.
+Usage:
+p = HTMLParser()
+p.feed(data)
+...
+p.close()
+Start tags are handled by calling self.handle_starttag() or
+self.handle_startendtag(); end tags by self.handle_endtag().  The
+data between tags is passed from the parser to the derived class
+by calling self.handle_data() with the data as argument (the data
+may be split up in arbitrary chunks).  Entity references are
+passed by calling self.handle_entityref() with the entity
+reference as the argument.  Numeric character references are
+passed to self.handle_charref() with the string containing the
+reference as the argument.
+"""
+CDATA_CONTENT_ELEMENTS = ("script", "style")
+def __init__(self):
+"""Initialize and reset this instance."""
+self.reset()
+def reset(self):
+"""Reset this instance.  Loses all unprocessed data."""
+self.rawdata = ''
+self.stack = []
+self.lasttag = '???'
+self.interesting = interesting_normal
+markupbase.ParserBase.reset(self)
+def feed(self, data):
+"""Feed data to the parser.
+Call this as often as you want, with as little or as much text
+as you want (may include '\n').
+"""
+self.rawdata = self.rawdata + data
+self.goahead(0)
+def close(self):
+"""Handle any buffered data."""
+self.goahead(1)
+def error(self, message):
+raise HTMLParseError(message, self.getpos())
+__starttag_text = None
+def get_starttag_text(self):
+"""Return full source of start tag: '<...>'."""
+return self.__starttag_text
+cdata_endtag = None
+def set_cdata_mode(self, endtag=None):
+self.cdata_endtag = endtag
+self.interesting = interesting_cdata
+def clear_cdata_mode(self):
+self.cdata_endtag = None
+self.interesting = interesting_normal
+# Internal -- handle data as far as reasonable.  May leave state
+# and data to be processed by a subsequent call.  If 'end' is
+# true, force handling all data as if followed by EOF marker.
+def goahead(self, end):
+rawdata = self.rawdata
+i = 0
+n = len(rawdata)
+while i < n:
+match = self.interesting.search(rawdata, i) # < or &
+if match:
+j = match.start()
+else:
+j = n
+if i < j: self.handle_data(rawdata[i:j])
+i = self.updatepos(i, j)
+if i == n: break
+if rawdata[i] == '<':
+if starttagopen.match(rawdata, i): # < + letter
+k = self.parse_starttag(i)
+elif endtagopen.match(rawdata, i): # </
+k = self.parse_endtag(i)
+elif _contains_at(rawdata, "<!--", i): # <!--
+k = self.parse_comment(i)
+elif _contains_at(rawdata, "<!", i): # <!
+k = self.parse_declaration(i)
+elif _contains_at(rawdata, "<?", i): # <?
+k = self.parse_pi(i)
+elif _contains_at(rawdata, "<?", i): # <!
+k = self.parse_declaration(i)
+elif (i + 1) < n:
+self.handle_data("<")
+k = i + 1
+else:
+break
+if k < 0:
+if end:
+self.error("EOF in middle of construct")
+break
+i = self.updatepos(i, k)
+elif rawdata[i:i+2] == "&#":
+match = charref.match(rawdata, i)
+if match:
+name = match.group()[2:-1]
+self.handle_charref(name)
+k = match.end()
+if rawdata[k-1] != ';':
+k = k - 1
+i = self.updatepos(i, k)
+continue
+else:
+break
+elif rawdata[i] == '&':
+match = entityref.match(rawdata, i)
+if match:
+name = match.group(1)
+self.handle_entityref(name)
+k = match.end()
+if rawdata[k-1] != ';':
+k = k - 1
+i = self.updatepos(i, k)
+continue
+match = incomplete.match(rawdata, i)
+if match:
+# match.group() will contain at least 2 chars
+rest = rawdata[i:]
+if end and match.group() == rest:
+self.error("EOF in middle of entity or char ref")
+# incomplete
+break
+elif (i + 1) < n:
+# not the end of the buffer, and can't be confused
+# with some other construct
+self.handle_data("&")
+i = self.updatepos(i, i + 1)
+else:
+break
+else:
+assert 0, "interesting.search() lied"
+# end while
+if end and i < n:
+self.handle_data(rawdata[i:n])
+i = self.updatepos(i, n)
+self.rawdata = rawdata[i:]
+# Internal -- parse comment, return end or -1 if not terminated
+def parse_comment(self, i, report=1):
+rawdata = self.rawdata
+assert rawdata[i:i+4] == '<!--', 'unexpected call to parse_comment()'
+match = commentclose.search(rawdata, i+4)
+if not match:
+return -1
+if report:
+j = match.start()
+self.handle_comment(rawdata[i+4: j])
+j = match.end()
+return j
+# Internal -- parse processing instr, return end or -1 if not terminated
+def parse_pi(self, i):
+rawdata = self.rawdata
+assert rawdata[i:i+2] == '<?', 'unexpected call to parse_pi()'
+match = piclose.search(rawdata, i+2) # >
+if not match:
+return -1
+j = match.start()
+self.handle_pi(rawdata[i+2: j])
+j = match.end()
+return j
+# Internal -- handle starttag, return end or -1 if not terminated
+def parse_starttag(self, i):
+self.__starttag_text = None
+endpos = self.check_for_whole_start_tag(i)
+if endpos < 0:
+return endpos
+rawdata = self.rawdata
+self.__starttag_text = rawdata[i:endpos]
+# Now parse the data between i+1 and j into a tag and attrs
+attrs = []
+match = tagfind.match(rawdata, i+1)
+assert match, 'unexpected call to parse_starttag()'
+k = match.end()
+self.lasttag = tag = string.lower(rawdata[i+1:k])
+while k < endpos:
+m = attrfind.match(rawdata, k)
+if not m:
+break
+attrname, rest, attrvalue = m.group(1, 2, 3)
+if not rest:
+attrvalue = None
+elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
+attrvalue[:1] == '"' == attrvalue[-1:]:
+attrvalue = attrvalue[1:-1]
+attrvalue = self.unescape(attrvalue)
+attrs.append((string.lower(attrname), attrvalue))
+k = m.end()
+end = string.strip(rawdata[k:endpos])
+if end not in (">", "/>"):
+lineno, offset = self.getpos()
+if "\n" in self.__starttag_text:
+lineno = lineno + string.count(self.__starttag_text, "\n")
+offset = len(self.__starttag_text) \
+- string.rfind(self.__starttag_text, "\n")
+else:
+offset = offset + len(self.__starttag_text)
+self.error("junk characters in start tag: %s"
+% `rawdata[k:endpos][:20]`)
+if end[-2:] == '/>':
+# XHTML-style empty tag: <span attr="value" />
+self.handle_startendtag(tag, attrs)
+else:
+self.handle_starttag(tag, attrs)
+if tag in self.CDATA_CONTENT_ELEMENTS:
+self.set_cdata_mode(tag)
+return endpos
+# Internal -- check to see if we have a complete starttag; return end
+# or -1 if incomplete.
+def check_for_whole_start_tag(self, i):
+rawdata = self.rawdata
+m = locatestarttagend.match(rawdata, i)
+if m:
+j = m.end()
+next = rawdata[j:j+1]
+if next == ">":
+return j + 1
+if next == "/":
+s = rawdata[j:j+2]
+if s == "/>":
+return j + 2
+if s == "/":
+# buffer boundary
+return -1
+# else bogus input
+self.updatepos(i, j + 1)
+self.error("malformed empty start tag")
+if next == "":
+# end of input
+return -1
+if next in ("abcdefghijklmnopqrstuvwxyz=/"
+"ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
+# end of input in or before attribute value, or we have the
+# '/' from a '/>' ending
+return -1
+self.updatepos(i, j)
+self.error("malformed start tag")
+raise AssertionError("we should not get here!")
+# Internal -- parse endtag, return end or -1 if incomplete
+def parse_endtag(self, i):
+rawdata = self.rawdata
+assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
+match = endendtag.search(rawdata, i+1) # >
+if not match:
+return -1
+j = match.end()
+match = endtagfind.match(rawdata, i) # </ + tag + >
+if not match:
+self.error("bad end tag: %s" % `rawdata[i:j]`)
+tag = string.lower(match.group(1))
+if (  self.cdata_endtag is not None
+and tag != self.cdata_endtag):
+# Should be a mismatched end tag, but we'll treat it
+# as text anyway, since most HTML authors aren't
+# interested in the finer points of syntax.
+self.handle_data(match.group(0))
+else:
+self.handle_endtag(tag)
+self.clear_cdata_mode()
+return j
+# Overridable -- finish processing of start+end tag: <tag.../>
+def handle_startendtag(self, tag, attrs):
+self.handle_starttag(tag, attrs)
+self.handle_endtag(tag)
+# Overridable -- handle start tag
+def handle_starttag(self, tag, attrs):
+pass
+# Overridable -- handle end tag
+def handle_endtag(self, tag):
+pass
+# Overridable -- handle character reference
+def handle_charref(self, name):
+pass
+# Overridable -- handle entity reference
+def handle_entityref(self, name):
+pass
+# Overridable -- handle data
+def handle_data(self, data):
+pass
+# Overridable -- handle comment
+def handle_comment(self, data):
+pass
+# Overridable -- handle declaration
+def handle_decl(self, decl):
+pass
+# Overridable -- handle processing instruction
+def handle_pi(self, data):
+pass
+def unknown_decl(self, data):
+self.error("unknown declaration: " + `data`)
+# Internal -- helper to remove special character quoting
+def unescape(self, s):
+if '&' not in s:
+return s
+s = string.replace(s, "&lt;", "<")
+s = string.replace(s, "&gt;", ">")
+s = string.replace(s, "&apos;", "'")
+s = string.replace(s, "&quot;", '"')
+s = string.replace(s, "&amp;", "&") # Must be last
+return s

Mercurial > p > roundup > code

comparison TAL/HTMLParser.py @ 982:bfd348432420