From 4d836989720523cd0363927e3e066f56b9dc445c Mon Sep 17 00:00:00 2001 From: yum Date: Sat, 17 Dec 2022 17:26:16 -0800 Subject: Check in `future` package I hit some issues installing Whisper and had to embed this package. I haven't taken the time to deeply understand what's going on. I think that embedded Python follows different rules about resolving module paths than regular system Python. Basically, `future`'s setup.py has a line like `import src`, where `src` is a module inside future (like `future/src/__init__.py`). This doesn't work unless we put that directory on the search path. --- .../tests/test_future/test_htmlparser.py | 764 +++++++++++++++++++++ 1 file changed, 764 insertions(+) create mode 100644 Python/Dependencies/future-0.18.2/tests/test_future/test_htmlparser.py (limited to 'Python/Dependencies/future-0.18.2/tests/test_future/test_htmlparser.py') diff --git a/Python/Dependencies/future-0.18.2/tests/test_future/test_htmlparser.py b/Python/Dependencies/future-0.18.2/tests/test_future/test_htmlparser.py new file mode 100644 index 0000000..7a745ac --- /dev/null +++ b/Python/Dependencies/future-0.18.2/tests/test_future/test_htmlparser.py @@ -0,0 +1,764 @@ +# -*- coding: utf-8 -*- +""" +Tests for the html.parser functions. + +Adapted for the python-future module from the Python 3.3 standard library +tests. +""" + +from __future__ import (absolute_import, print_function, unicode_literals) +from future import standard_library, utils +from future.builtins import * + +from future.backports.test import support +import future.backports.html.parser as html_parser + +import pprint +from future.tests.base import unittest +import sys + +# print(html_parser.__doc__, file=sys.stderr) + + +class EventCollector(html_parser.HTMLParser): + + def __init__(self, *args, **kw): + self.events = [] + self.append = self.events.append + html_parser.HTMLParser.__init__(self, *args, **kw) + + 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): + + def get_collector(self): + raise NotImplementedError + + 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\n" + "Expected:\n" + pprint.pformat(expected_events) + + "\nReceived:\n" + pprint.pformat(events)) + + def _run_check_extra(self, source, events): + self._run_check(source, events, EventCollectorExtra()) + + def _parse_error(self, source): + def parse(source=source): + parser = self.get_collector() + parser.feed(source) + parser.close() + self.assertRaises(html_parser.HTMLParseError, parse) + + +class HTMLParserStrictTestCase(TestCaseBase): + + def get_collector(self): + with support.check_warnings(("", DeprecationWarning), quiet=False): + return EventCollector(strict=True) + + 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"), + ]) + + def test_unclosed_entityref(self): + self._run_check("&entityref foo", [ + ("entityref", "entityref"), + ("data", " foo"), + ]) + + def test_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("", [ + ("starttag", "a", []), + ("starttag", "b", []), + ("endtag", "a"), + ("endtag", "b"), + ]) + + def test_bare_ampersands(self): + self._run_check("this text & contains & ampersands &", [ + ("data", "this text & contains & ampersands &"), + ]) + + def test_bare_pointy_brackets(self): + self._run_check("this < text > contains < bare>pointy< brackets", [ + ("data", "this < text > contains < bare>pointy< brackets"), + ]) + + def test_illegal_declarations(self): + self._parse_error('') + + def test_starttag_end_boundary(self): + self._run_check("""""", [("starttag", "a", [("b", "<")])]) + self._run_check("""""", [("starttag", "a", [("b", ">")])]) + + def test_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) + + output = [("comment", "abc")] + self._run_check(["", ""], output) + self._run_check(["<", "!--abc-->"], output) + self._run_check([""], output) + 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 test_starttag_junk_chars(self): + self._parse_error("") + self._parse_error("") + self._parse_error("") + self._parse_error("") + self._parse_error("'") + self._parse_error("" % dtd, + [('decl', 'DOCTYPE ' + dtd)]) + + def test_declaration_junk_chars(self): + self._parse_error("") + + def test_startendtag(self): + self._run_check("

", [ + ("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)]) + + def test_cdata_content(self): + contents = [ + ' ¬-an-entity-ref;', + "", + '

', + 'foo = "";', + 'foo = "";', + 'foo = <\n/script> ', + '', + ('\n//<\\/s\'+\'cript>\');\n//]]>'), + '\n\n', + 'foo = "";', + '', + # these two should be invalid according to the HTML 5 spec, + # section 8.1.2.2 + #'foo = ', + #'foo = ', + ] + elements = ['script', 'style', 'SCRIPT', 'STYLE', 'Script', 'Style'] + for content in contents: + for element in elements: + element_lower = element.lower() + s = '<{element}>{content}'.format(element=element, + content=content) + self._run_check(s, [("starttag", element_lower, []), + ("data", content), + ("endtag", element_lower)]) + + def test_cdata_with_closing_tags(self): + # see issue #13358 + # make sure that HTMLParser calls handle_data only once for each CDATA. + # The normal event collector normalizes the events in get_events, + # so we override it to return the original list of events. + class Collector(EventCollector): + def get_events(self): + return self.events + + content = """ ¬-an-entity-ref; +

+ ''""" + for element in [' script', 'script ', ' script ', + '\nscript', 'script\n', '\nscript\n']: + element_lower = element.lower().strip() + s = '