"""Tests for HTMLParser.py.""" import html.parser import pprint import unittest from unittest.mock import patch from test import support SAMPLE_RCDATA = ( '' "" '' '' '' '\u2603' ) SAMPLE_RAWTEXT = SAMPLE_RCDATA + '&☺' class EventCollector(html.parser.HTMLParser): def __init__(self, *args, autocdata=False, **kw): self.autocdata = autocdata self.events = [] self.append = self.events.append html.parser.HTMLParser.__init__(self, *args, **kw) if autocdata: self._set_support_cdata(False) 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)) if self.autocdata and tag == 'svg': self._set_support_cdata(True) def handle_startendtag(self, tag, attrs): self.append(("startendtag", tag, attrs)) def handle_endtag(self, tag): self.append(("endtag", tag)) if self.autocdata and tag == 'svg': self._set_support_cdata(False) # 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 EventCollectorCharrefs(EventCollector): def handle_charref(self, data): self.fail('This should never be called with convert_charrefs=True') def handle_entityref(self, data): self.fail('This should never be called with convert_charrefs=True') # The normal event collector normalizes the events in get_events, # so we override it to return the original list of events. class EventCollectorNoNormalize(EventCollector): def get_events(self): return self.events class TestCaseBase(unittest.TestCase): def get_collector(self): return EventCollector(convert_charrefs=False) def _run_check(self, source, expected_events, collector=None): if collector is None: collector = self.get_collector() parser = collector for s in source: parser.feed(s) parser.close() events = parser.get_events() if events != expected_events: self.fail("received events did not match expected events" + "\nSource:\n" + repr(source) + "\nExpected:\n" + pprint.pformat(expected_events) + "\nReceived:\n" + pprint.pformat(events)) def _run_check_extra(self, source, events): self._run_check(source, events, EventCollectorExtra(convert_charrefs=False)) class HTMLParserTestCase(TestCaseBase): def test_processing_instruction_only(self): self._run_check("", [ ("pi", "processing instruction"), ]) self._run_check("", [ ("pi", "processing instruction ?"), ]) def test_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-><&#bad;

", [ ("starttag", "p", []), ("data", "&#bad;"), ("endtag", "p"), ]) # add the [] as a workaround to avoid buffering (see #20288) self._run_check(["

&#bad;

", [ ("startendtag", "p", []), ]) self._run_check("

", [ ("starttag", "p", []), ("endtag", "p"), ]) self._run_check("

", [ ("starttag", "p", []), ("startendtag", "img", [("src", "foo")]), ("endtag", "p"), ]) def test_get_starttag_text(self): s = """""" self._run_check_extra(s, [ ("starttag", "foo:bar", [("one", "1"), ("two", "2")]), ("starttag_text", s)]) @support.subTests('content', [ ' ¬-an-entity-ref;', "", '

', 'foo = "";', 'foo = "";', 'foo = <\n/script> ', '', ('\n//<\\/s\'+\'cript>\');\n//]]>'), '\n\n', '', ]) def test_script_content(self, content): s = f'' self._run_check(s, [ ("starttag", "script", []), ("data", content), ("endtag", "script"), ]) @support.subTests('content', [ 'a::before { content: ""; }', 'a::before { content: "¬-an-entity-ref;"; }', 'a::before { content: ""; }', 'a::before { content: "\u2603"; }', ]) def test_style_content(self, content): s = f'' self._run_check(s, [("starttag", "style", []), ("data", content), ("endtag", "style")]) @support.subTests('tag', ['title', 'textarea']) def test_rcdata_content(self, tag): source = f"<{tag}>{SAMPLE_RCDATA}" self._run_check(source, [ ("starttag", tag, []), ("data", SAMPLE_RCDATA), ("endtag", tag), ]) source = f"<{tag}>&" self._run_check(source, [ ("starttag", tag, []), ('entityref', 'amp'), ("endtag", tag), ]) @support.subTests('tag', ['style', 'xmp', 'iframe', 'noembed', 'noframes', 'script']) def test_rawtext_content(self, tag): source = f"<{tag}>{SAMPLE_RAWTEXT}" self._run_check(source, [ ("starttag", tag, []), ("data", SAMPLE_RAWTEXT), ("endtag", tag), ]) def test_noscript_content(self): source = f"" # scripting=False -- normal mode self._run_check(source, [ ('starttag', 'noscript', []), ('comment', ' not a comment '), ('starttag', 'not', [('a', 'start tag')]), ('unknown decl', 'CDATA[not a cdata'), ('comment', 'not a bogus comment'), ('endtag', 'not'), ('data', '☃'), ('entityref', 'amp'), ('charref', '9786'), ('endtag', 'noscript'), ]) # scripting=True -- RAWTEXT mode self._run_check(source, [ ("starttag", "noscript", []), ("data", SAMPLE_RAWTEXT), ("endtag", "noscript"), ], collector=EventCollector(scripting=True)) def test_plaintext_content(self): content = SAMPLE_RAWTEXT + '' # not closing source = f"