test_htmlparser.py :  » Web-Frameworks » Zope » Zope-2.6.0 » lib » python » TAL » tests » Python Open Source

Home
Python Open Source
1.3.1.2 Python
2.Ajax
3.Aspect Oriented
4.Blog
5.Build
6.Business Application
7.Chart Report
8.Content Management Systems
9.Cryptographic
10.Database
11.Development
12.Editor
13.Email
14.ERP
15.Game 2D 3D
16.GIS
17.GUI
18.IDE
19.Installer
20.IRC
21.Issue Tracker
22.Language Interface
23.Log
24.Math
25.Media Sound Audio
26.Mobile
27.Network
28.Parser
29.PDF
30.Project Management
31.RSS
32.Search
33.Security
34.Template Engines
35.Test
36.UML
37.USB Serial
38.Web Frameworks
39.Web Server
40.Web Services
41.Web Unit
42.Wiki
43.Windows
44.XML
Python Open Source » Web Frameworks » Zope 
Zope » Zope 2.6.0 » lib » python » TAL » tests » test_htmlparser.py
#! /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)
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.