Skip to content

Z
Zope
Commit 7b4ae31a authored by Fred Drake's avatar Fred Drake
Browse files
Options

remove local version of the HTMLParser module; this is now part of Python

parent 3c86de13
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 715 deletions
lib/python/TAL/HTMLParser.py deleted 100644 → 0
View file @ 3c86de13
"""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
# 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 = rawdata[i+1:k].lower()
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((attrname.lower(), attrvalue))
k = m.end()
end = rawdata[k:endpos].strip()
if end not in (">", "/>"):
lineno, offset = self.getpos()
if "\n" in self.__starttag_text:
lineno = lineno + self.__starttag_text.count("\n")
offset = len(self.__starttag_text) \
- self.__starttag_text.rfind("\n")
else:
offset = offset + len(self.__starttag_text)
self.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 = match.group(1).lower()
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 = s.replace("&lt;", "<")
s = s.replace("&gt;", ">")
s = s.replace("&apos;", "'")
s = s.replace("&quot;", '"')
s = s.replace("&amp;", "&") # Must be last
return s
lib/python/TAL/tests/test_htmlparser.py deleted 100755 → 0
View file @ 3c86de13
#! /usr/bin/env python1.5
"""Tests for HTMLParser.py."""
import sys
from TAL.tests import utils
import unittest
from TAL import HTMLParser
class EventCollector(HTMLParser.HTMLParser):
def __init__(self):
self.events = []
self.append = self.events.append
HTMLParser.HTMLParser.__init__(self)
def get_events(self):
# Normalize the list of events so that buffer artefacts don't
# separate runs of contiguous characters.
L = []
prevtype = None
for event in self.events:
type = event[0]
if type == prevtype == "data":
L[-1] = ("data", L[-1][1] + event[1])
else:
L.append(event)
prevtype = type
self.events = L
return L
# structure markup
def handle_starttag(self, tag, attrs):
self.append(("starttag", tag, attrs))
def handle_startendtag(self, tag, attrs):
self.append(("startendtag", tag, attrs))
def handle_endtag(self, tag):
self.append(("endtag", tag))
# all other markup
def handle_comment(self, data):
self.append(("comment", data))
def handle_charref(self, data):
self.append(("charref", data))
def handle_data(self, data):
self.append(("data", data))
def handle_decl(self, data):
self.append(("decl", data))
def handle_entityref(self, data):
self.append(("entityref", data))
def handle_pi(self, data):
self.append(("pi", data))
def unknown_decl(self, decl):
self.append(("unknown decl", decl))
class EventCollectorExtra(EventCollector):
def handle_starttag(self, tag, attrs):
EventCollector.handle_starttag(self, tag, attrs)
self.append(("starttag_text", self.get_starttag_text()))
class TestCaseBase(unittest.TestCase):
# Constant pieces of source and events
prologue = ""
epilogue = ""
initial_events = []
final_events = []
def _run_check(self, source, events, collector=EventCollector):
parser = collector()
parser.feed(self.prologue)
for s in source:
parser.feed(s)
for c in self.epilogue:
parser.feed(c)
parser.close()
self.assert_(parser.get_events() ==
self.initial_events + events + self.final_events,
parser.get_events())
def _run_check_extra(self, source, events):
self._run_check(source, events, EventCollectorExtra)
def _parse_error(self, source):
def parse(source=source):
parser = HTMLParser.HTMLParser()
parser.feed(source)
parser.close()
self.assertRaises(HTMLParser.HTMLParseError, parse)
class HTMLParserTestCase(TestCaseBase):
def check_processing_instruction_only(self):
self._run_check("<?processing instruction>", [
("pi", "processing instruction"),
])
def check_simple_html(self):
self._run_check("""
<!DOCTYPE html PUBLIC 'foo'>
<HTML>&entity;&#32;
<!--comment1a
-></foo><bar>&lt;<?pi?></foo<bar
comment1b-->
<Img sRc='Bar' isMAP>sample
text
&#x201C;
<!--comment2a-- --comment2b-->
</Html>
""", [
("data", "\n"),
("decl", "DOCTYPE html PUBLIC 'foo'"),
("data", "\n"),
("starttag", "html", []),
("entityref", "entity"),
("charref", "32"),
("data", "\n"),
("comment", "comment1a\n-></foo><bar>&lt;<?pi?></foo<bar\ncomment1b"),
("data", "\n"),
("starttag", "img", [("src", "Bar"), ("ismap", None)]),
("data", "sample\ntext\n"),
("charref", "x201C"),
("data", "\n"),
("comment", "comment2a-- --comment2b"),
("data", "\n"),
("endtag", "html"),
("data", "\n"),
])
def check_unclosed_entityref(self):
self._run_check("&entityref foo", [
("entityref", "entityref"),
("data", " foo"),
])
def check_doctype_decl(self):
inside = """\
DOCTYPE html [
<!ELEMENT html - O EMPTY>
<!ATTLIST html
version CDATA #IMPLIED
profile CDATA 'DublinCore'>
<!NOTATION datatype SYSTEM 'http://xml.python.org/notations/python-module'>
<!ENTITY myEntity 'internal parsed entity'>
<!ENTITY anEntity SYSTEM 'http://xml.python.org/entities/something.xml'>
<!ENTITY % paramEntity 'name|name|name'>
%paramEntity;
<!-- comment -->
]"""
self._run_check("<!%s>" % inside, [
("decl", inside),
])
def check_bad_nesting(self):
# Strangely, this *is* supposed to test that overlapping
# elements are allowed. HTMLParser is more geared toward
# lexing the input that parsing the structure.
self._run_check("<a><b></a></b>", [
("starttag", "a", []),
("starttag", "b", []),
("endtag", "a"),
("endtag", "b"),
])
def check_bare_ampersands(self):
self._run_check("this text & contains & ampersands &", [
("data", "this text & contains & ampersands &"),
])
def check_bare_pointy_brackets(self):
self._run_check("this < text > contains < bare>pointy< brackets", [
("data", "this < text > contains < bare>pointy< brackets"),
])
def check_attr_syntax(self):
output = [
("starttag", "a", [("b", "v"), ("c", "v"), ("d", "v"), ("e", None)])
]
self._run_check("""<a b='v' c="v" d=v e>""", output)
self._run_check("""<a b = 'v' c = "v" d = v e>""", output)
self._run_check("""<a\nb\n=\n'v'\nc\n=\n"v"\nd\n=\nv\ne>""", output)
self._run_check("""<a\tb\t=\t'v'\tc\t=\t"v"\td\t=\tv\te>""", output)
def check_attr_values(self):
self._run_check("""<a b='xxx\n\txxx' c="yyy\t\nyyy" d='\txyz\n'>""",
[("starttag", "a", [("b", "xxx\n\txxx"),
("c", "yyy\t\nyyy"),
("d", "\txyz\n")])
])
self._run_check("""<a b='' c="">""", [
("starttag", "a", [("b", ""), ("c", "")]),
])
def check_attr_entity_replacement(self):
self._run_check("""<a b='&amp;&gt;&lt;&quot;&apos;'>""", [
("starttag", "a", [("b", "&><\"'")]),
])
def check_attr_funky_names(self):
self._run_check("""<a a.b='v' c:d=v e-f=v>""", [
("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")]),
])
def check_illegal_declarations(self):
self._parse_error('<!spacer type="block" height="25">')
def check_starttag_end_boundary(self):
self._run_check("""<a b='<'>""", [("starttag", "a", [("b", "<")])])
self._run_check("""<a b='>'>""", [("starttag", "a", [("b", ">")])])
def check_buffer_artefacts(self):
output = [("starttag", "a", [("b", "<")])]
self._run_check(["<a b='<'>"], output)
self._run_check(["<a ", "b='<'>"], output)
self._run_check(["<a b", "='<'>"], output)
self._run_check(["<a b=", "'<'>"], output)
self._run_check(["<a b='<", "'>"], output)
self._run_check(["<a b='<'", ">"], output)
output = [("starttag", "a", [("b", ">")])]
self._run_check(["<a b='>'>"], output)
self._run_check(["<a ", "b='>'>"], output)
self._run_check(["<a b", "='>'>"], output)
self._run_check(["<a b=", "'>'>"], output)
self._run_check(["<a b='>", "'>"], output)
self._run_check(["<a b='>'", ">"], output)
def check_starttag_junk_chars(self):
self._parse_error("</>")
self._parse_error("</$>")
self._parse_error("</")
self._parse_error("</a")
self._parse_error("<a<a>")
self._parse_error("</a<a>")
self._parse_error("<!")
self._parse_error("<a $>")
self._parse_error("<a")
self._parse_error("<a foo='bar'")
self._parse_error("<a foo='bar")
self._parse_error("<a foo='>'")
self._parse_error("<a foo='>")
self._parse_error("<a foo=>")
def check_declaration_junk_chars(self):
self._parse_error("<!DOCTYPE foo $ >")
def check_startendtag(self):
self._run_check("<p/>", [
("startendtag", "p", []),
])
self._run_check("<p></p>", [
("starttag", "p", []),
("endtag", "p"),
])
self._run_check("<p><img src='foo' /></p>", [
("starttag", "p", []),
("startendtag", "img", [("src", "foo")]),
("endtag", "p"),
])
def check_get_starttag_text(self):
s = """<foo:bar \n one="1"\ttwo=2 >"""
self._run_check_extra(s, [
("starttag", "foo:bar", [("one", "1"), ("two", "2")]),
("starttag_text", s)])
def check_cdata_content(self):
s = """<script> <!-- not a comment --> &not-an-entity-ref; </script>"""
self._run_check(s, [
("starttag", "script", []),
("data", " <!-- not a comment --> &not-an-entity-ref; "),
("endtag", "script"),
])
s = """<script> <not a='start tag'> </script>"""
self._run_check(s, [
("starttag", "script", []),
("data", " <not a='start tag'> "),
("endtag", "script"),
])
def check_enumerated_attr_type(self):
s = "<!DOCTYPE doc [<!ATTLIST doc attr (a | b) >]>"
self._run_check(s, [
('decl', 'DOCTYPE doc [<!ATTLIST doc attr (a | b) >]'),
])
# Support for the Zope regression test framework:
def test_suite():
suite = unittest.TestSuite()
suite.addTest(unittest.makeSuite(HTMLParserTestCase, "check_"))
return suite
if __name__ == "__main__":
errs = utils.run_suite(test_suite())
sys.exit(errs and 1 or 0)
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7