From bd3090d4d659951ed38d1da0f44c3e59ec830bea Mon Sep 17 00:00:00 2001 From: Fred Drake Date: Fri, 18 May 2001 15:32:59 +0000 Subject: [PATCH] Added test suite for the new HTMLParser module, originally from the TAL/PageTemplate package for Zope. This only needed a little boilerplate change; the tests themselves are unchanged. --- Lib/test/output/test_htmlparser | 1 + Lib/test/test_htmlparser.py | 254 ++++++++++++++++++++++++++++++++ 2 files changed, 255 insertions(+) create mode 100644 Lib/test/output/test_htmlparser create mode 100755 Lib/test/test_htmlparser.py diff --git a/Lib/test/output/test_htmlparser b/Lib/test/output/test_htmlparser new file mode 100644 index 00000000000..a6953e5baa5 --- /dev/null +++ b/Lib/test/output/test_htmlparser @@ -0,0 +1 @@ +test_htmlparser diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py new file mode 100755 index 00000000000..e331ac8bcfe --- /dev/null +++ b/Lib/test/test_htmlparser.py @@ -0,0 +1,254 @@ +"""Tests for HTMLParser.py.""" + +import HTMLParser +import sys +import test_support +import unittest + + +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)) + + +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("", [ + ("pi", "processing instruction"), + ]) + + def check_simple_html(self): + self._run_check(""" + +&entity; + +sample +text + + +""", [ + ("data", "\n"), + ("decl", "DOCTYPE html PUBLIC 'foo'"), + ("data", "\n"), + ("starttag", "html", []), + ("entityref", "entity"), + ("charref", "32"), + ("data", "\n"), + ("comment", "comment1a\n-><", [ + ("starttag", "a", []), + ("starttag", "b", []), + ("endtag", "a"), + ("endtag", "b"), + ]) + + def check_attr_syntax(self): + output = [ + ("starttag", "a", [("b", "v"), ("c", "v"), ("d", "v"), ("e", None)]) + ] + self._run_check("""""", output) + self._run_check("""""", output) + self._run_check("""""", output) + self._run_check("""""", output) + + def check_attr_values(self): + self._run_check("""""", + [("starttag", "a", [("b", "xxx\n\txxx"), + ("c", "yyy\t\nyyy"), + ("d", "\txyz\n")]) + ]) + self._run_check("""""", [ + ("starttag", "a", [("b", ""), ("c", "")]), + ]) + + def check_attr_entity_replacement(self): + self._run_check("""""", [ + ("starttag", "a", [("b", "&><\"'")]), + ]) + + def check_attr_funky_names(self): + self._run_check("""""", [ + ("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")]), + ]) + + def check_starttag_end_boundary(self): + self._run_check("""""", [("starttag", "a", [("b", "<")])]) + self._run_check("""""", [("starttag", "a", [("b", ">")])]) + + def check_buffer_artefacts(self): + output = [("starttag", "a", [("b", "<")])] + self._run_check([""], output) + self._run_check([""], output) + self._run_check([""], output) + self._run_check([""], output) + self._run_check([""], output) + self._run_check([""], output) + + output = [("starttag", "a", [("b", ">")])] + self._run_check([""], output) + self._run_check([""], output) + self._run_check([""], output) + self._run_check(["'>"], output) + self._run_check([""], output) + self._run_check([""], output) + + def check_starttag_junk_chars(self): + self._parse_error("<") + self._parse_error("<>") + self._parse_error("") + self._parse_error("") + self._parse_error("") + self._parse_error("") + self._parse_error("<$") + self._parse_error("<$>") + self._parse_error("") + self._parse_error("'") + self._parse_error("

", [ + ("starttag", "p", []), + ("startendtag", "img", [("src", "foo")]), + ("endtag", "p"), + ]) + + def check_get_starttag_text(self): + s = """""" + self._run_check_extra(s, [ + ("starttag", "foo:bar", [("one", "1"), ("two", "2")]), + ("starttag_text", s)]) + + def check_cdata_content(self): + s = """""" + self._run_check(s, [ + ("starttag", "script", []), + ("data", " ¬-an-entity-ref; "), + ("endtag", "script"), + ]) + s = """""" + self._run_check(s, [ + ("starttag", "script", []), + ("data", " "), + ("endtag", "script"), + ]) + + +test_support.run_unittest(HTMLParserTestCase)