PATH: //proc/thread-self/root/proc/self/root/opt/alt/python311/lib64/python3.11/test
FILE_BARU
CREATE
FOLDER_BARU
MKDIR
UPLOAD_FILE
GO
[ .. KEMBALI ]
📄 Sine-1000Hz-300ms.aif
↓
X
📄 __init__.py
↓
X
📄 __main__.py
↓
X
📁 __pycache__/
X
📄 _test_atexit.py
↓
X
📄 _test_eintr.py
↓
X
📄 _test_embed_set_config.py
↓
X
📄 _test_embed_structseq.py
↓
X
📄 _test_multiprocessing.py
↓
X
📄 _test_venv_multiprocessing.py
↓
X
📄 archiver_tests.py
↓
X
📁 audiodata/
X
📄 audiotest.au
↓
X
📄 audiotests.py
↓
X
📄 audit-tests.py
↓
X
📄 autotest.py
↓
X
📄 bisect_cmd.py
↓
X
📁 certdata/
X
📁 cjkencodings/
X
📄 clinic.test.c
↓
X
📄 cmath_testcases.txt
↓
X
📁 configdata/
X
📁 crashers/
X
📄 curses_tests.py
↓
X
📁 data/
X
📄 datetimetester.py
↓
X
📁 decimaltestdata/
X
📄 dis_module.py
↓
X
📁 dtracedata/
X
📄 empty.vbs
↓
X
📁 encoded_modules/
X
📄 exception_hierarchy.txt
↓
X
📄 floating_points.txt
↓
X
📄 fork_wait.py
↓
X
📄 formatfloat_testcases.txt
↓
X
📄 ieee754.txt
↓
X
📁 imghdrdata/
X
📄 imp_dummy.py
↓
X
📁 leakers/
X
📁 libregrtest/
X
📄 list_tests.py
↓
X
📄 lock_tests.py
↓
X
📄 mailcap.txt
↓
X
📄 mapping_tests.py
↓
X
📄 math_testcases.txt
↓
X
📄 memory_watchdog.py
↓
X
📄 mime.types
↓
X
📄 mock_socket.py
↓
X
📄 mp_fork_bomb.py
↓
X
📄 mp_preload.py
↓
X
📄 multibytecodec_support.py
↓
X
📄 pickletester.py
↓
X
📄 profilee.py
↓
X
📄 pstats.pck
↓
X
📄 pyclbr_input.py
↓
X
📄 pythoninfo.py
↓
X
📄 randv2_32.pck
↓
X
📄 randv2_64.pck
↓
X
📄 randv3.pck
↓
X
📄 re_tests.py
↓
X
📄 recursion.tar
↓
X
📄 regrtest.py
↓
X
📁 regrtestdata/
X
📄 relimport.py
↓
X
📄 reperf.py
↓
X
📄 seq_tests.py
↓
X
📄 signalinterproctester.py
↓
X
📁 sndhdrdata/
X
📄 ssl_servers.py
↓
X
📄 ssltests.py
↓
X
📄 string_tests.py
↓
X
📁 subprocessdata/
X
📁 support/
X
📄 test___all__.py
↓
X
📄 test__locale.py
↓
X
📄 test__opcode.py
↓
X
📄 test__osx_support.py
↓
X
📄 test__xxsubinterpreters.py
↓
X
📄 test_abc.py
↓
X
📄 test_abstract_numbers.py
↓
X
📄 test_aifc.py
↓
X
📄 test_argparse.py
↓
X
📄 test_array.py
↓
X
📄 test_asdl_parser.py
↓
X
📄 test_ast.py
↓
X
📄 test_asyncgen.py
↓
X
📄 test_asynchat.py
↓
X
📁 test_asyncio/
X
📄 test_asyncore.py
↓
X
📄 test_atexit.py
↓
X
📄 test_audioop.py
↓
X
📄 test_audit.py
↓
X
📄 test_augassign.py
↓
X
📄 test_base64.py
↓
X
📄 test_baseexception.py
↓
X
📄 test_bdb.py
↓
X
📄 test_bigaddrspace.py
↓
X
📄 test_bigmem.py
↓
X
📄 test_binascii.py
↓
X
📄 test_binop.py
↓
X
📄 test_bisect.py
↓
X
📄 test_bool.py
↓
X
📄 test_buffer.py
↓
X
📄 test_bufio.py
↓
X
📄 test_builtin.py
↓
X
📄 test_bytes.py
↓
X
📄 test_bz2.py
↓
X
📄 test_c_locale_coercion.py
↓
X
📄 test_calendar.py
↓
X
📄 test_call.py
↓
X
📁 test_capi/
X
📄 test_cgi.py
↓
X
📄 test_cgitb.py
↓
X
📄 test_charmapcodec.py
↓
X
📄 test_check_c_globals.py
↓
X
📄 test_class.py
↓
X
📄 test_clinic.py
↓
X
📄 test_cmath.py
↓
X
📄 test_cmd.py
↓
X
📄 test_cmd_line.py
↓
X
📄 test_cmd_line_script.py
↓
X
📄 test_code.py
↓
X
📄 test_code_module.py
↓
X
📄 test_codeccallbacks.py
↓
X
📄 test_codecencodings_cn.py
↓
X
📄 test_codecencodings_hk.py
↓
X
📄 test_codecencodings_iso2022.py
↓
X
📄 test_codecencodings_jp.py
↓
X
📄 test_codecencodings_kr.py
↓
X
📄 test_codecencodings_tw.py
↓
X
📄 test_codecmaps_cn.py
↓
X
📄 test_codecmaps_hk.py
↓
X
📄 test_codecmaps_jp.py
↓
X
📄 test_codecmaps_kr.py
↓
X
📄 test_codecmaps_tw.py
↓
X
📄 test_codecs.py
↓
X
📄 test_codeop.py
↓
X
📄 test_collections.py
↓
X
📄 test_colorsys.py
↓
X
📄 test_compare.py
↓
X
📄 test_compile.py
↓
X
📄 test_compileall.py
↓
X
📄 test_complex.py
↓
X
📁 test_concurrent_futures/
X
📄 test_configparser.py
↓
X
📄 test_contains.py
↓
X
📄 test_context.py
↓
X
📄 test_contextlib.py
↓
X
📄 test_contextlib_async.py
↓
X
📄 test_copy.py
↓
X
📄 test_copyreg.py
↓
X
📄 test_coroutines.py
↓
X
📁 test_cppext/
X
📄 test_cprofile.py
↓
X
📄 test_crashers.py
↓
X
📄 test_crypt.py
↓
X
📄 test_csv.py
↓
X
📄 test_ctypes.py
↓
X
📄 test_curses.py
↓
X
📁 test_dataclasses/
X
📄 test_datetime.py
↓
X
📄 test_dbm.py
↓
X
📄 test_dbm_dumb.py
↓
X
📄 test_dbm_gnu.py
↓
X
📄 test_dbm_ndbm.py
↓
X
📄 test_decimal.py
↓
X
📄 test_decorators.py
↓
X
📄 test_defaultdict.py
↓
X
📄 test_deque.py
↓
X
📄 test_descr.py
↓
X
📄 test_descrtut.py
↓
X
📄 test_devpoll.py
↓
X
📄 test_dict.py
↓
X
📄 test_dict_version.py
↓
X
📄 test_dictcomps.py
↓
X
📄 test_dictviews.py
↓
X
📄 test_difflib.py
↓
X
📄 test_difflib_expect.html
↓
X
📄 test_dis.py
↓
X
📄 test_distutils.py
↓
X
📁 test_doctest/
X
📄 test_docxmlrpc.py
↓
X
📄 test_dtrace.py
↓
X
📄 test_dynamic.py
↓
X
📄 test_dynamicclassattribute.py
↓
X
📄 test_eintr.py
↓
X
📁 test_email/
X
📄 test_embed.py
↓
X
📄 test_ensurepip.py
↓
X
📄 test_enum.py
↓
X
📄 test_enumerate.py
↓
X
📄 test_eof.py
↓
X
📄 test_epoll.py
↓
X
📄 test_errno.py
↓
X
📄 test_except_star.py
↓
X
📄 test_exception_group.py
↓
X
📄 test_exception_hierarchy.py
↓
X
📄 test_exception_variations.py
↓
X
📄 test_exceptions.py
↓
X
📄 test_extcall.py
↓
X
📄 test_faulthandler.py
↓
X
📄 test_fcntl.py
↓
X
📄 test_file.py
↓
X
📄 test_file_eintr.py
↓
X
📄 test_filecmp.py
↓
X
📄 test_fileinput.py
↓
X
📄 test_fileio.py
↓
X
📄 test_fileutils.py
↓
X
📄 test_finalization.py
↓
X
📄 test_float.py
↓
X
📄 test_flufl.py
↓
X
📄 test_fnmatch.py
↓
X
📄 test_fork1.py
↓
X
📄 test_format.py
↓
X
📄 test_fractions.py
↓
X
📄 test_frame.py
↓
X
📄 test_frozen.py
↓
X
📄 test_fstring.py
↓
X
📄 test_ftplib.py
↓
X
📄 test_funcattrs.py
↓
X
📄 test_functools.py
↓
X
📁 test_future_stmt/
X
📄 test_gc.py
↓
X
📁 test_gdb/
X
📄 test_generator_stop.py
↓
X
📄 test_generators.py
↓
X
📄 test_genericalias.py
↓
X
📄 test_genericclass.py
↓
X
📄 test_genericpath.py
↓
X
📄 test_genexps.py
↓
X
📄 test_getopt.py
↓
X
📄 test_getpass.py
↓
X
📄 test_getpath.py
↓
X
📄 test_gettext.py
↓
X
📄 test_glob.py
↓
X
📄 test_global.py
↓
X
📄 test_grammar.py
↓
X
📄 test_graphlib.py
↓
X
📄 test_grp.py
↓
X
📄 test_gzip.py
↓
X
📄 test_hash.py
↓
X
📄 test_hashlib.py
↓
X
📄 test_heapq.py
↓
X
📄 test_hmac.py
↓
X
📄 test_html.py
↓
X
📄 test_htmlparser.py
↓
X
📄 test_http_cookiejar.py
↓
X
📄 test_http_cookies.py
↓
X
📄 test_httplib.py
↓
X
📄 test_httpservers.py
↓
X
📄 test_idle.py
↓
X
📄 test_imaplib.py
↓
X
📄 test_imghdr.py
↓
X
📄 test_imp.py
↓
X
📁 test_import/
X
📁 test_importlib/
X
📄 test_index.py
↓
X
📁 test_inspect/
X
📄 test_int.py
↓
X
📄 test_int_literal.py
↓
X
📄 test_interpreters.py
↓
X
📄 test_io.py
↓
X
📄 test_ioctl.py
↓
X
📄 test_ipaddress.py
↓
X
📄 test_isinstance.py
↓
X
📄 test_iter.py
↓
X
📄 test_iterlen.py
↓
X
📄 test_itertools.py
↓
X
📁 test_json/
X
📄 test_keyword.py
↓
X
📄 test_keywordonlyarg.py
↓
X
📄 test_kqueue.py
↓
X
📄 test_largefile.py
↓
X
📄 test_launcher.py
↓
X
📄 test_lib2to3.py
↓
X
📄 test_linecache.py
↓
X
📄 test_list.py
↓
X
📄 test_listcomps.py
↓
X
📄 test_lltrace.py
↓
X
📄 test_locale.py
↓
X
📄 test_logging.py
↓
X
📄 test_long.py
↓
X
📄 test_longexp.py
↓
X
📄 test_lzma.py
↓
X
📄 test_mailbox.py
↓
X
📄 test_mailcap.py
↓
X
📄 test_marshal.py
↓
X
📄 test_math.py
↓
X
📄 test_memoryio.py
↓
X
📄 test_memoryview.py
↓
X
📄 test_metaclass.py
↓
X
📄 test_mimetypes.py
↓
X
📄 test_minidom.py
↓
X
📄 test_mmap.py
↓
X
📁 test_module/
X
📄 test_modulefinder.py
↓
X
📄 test_msilib.py
↓
X
📄 test_multibytecodec.py
↓
X
📁 test_multiprocessing_fork/
X
📁 test_multiprocessing_forkserver/
X
📄 test_multiprocessing_main_handling.py
↓
X
📁 test_multiprocessing_spawn/
X
📄 test_named_expressions.py
↓
X
📄 test_netrc.py
↓
X
📄 test_nis.py
↓
X
📄 test_nntplib.py
↓
X
📄 test_ntpath.py
↓
X
📄 test_numeric_tower.py
↓
X
📄 test_opcache.py
↓
X
📄 test_opcodes.py
↓
X
📄 test_openpty.py
↓
X
📄 test_operator.py
↓
X
📄 test_optparse.py
↓
X
📄 test_ordered_dict.py
↓
X
📄 test_os.py
↓
X
📄 test_ossaudiodev.py
↓
X
📄 test_osx_env.py
↓
X
📄 test_pathlib.py
↓
X
📄 test_patma.py
↓
X
📄 test_pdb.py
↓
X
📄 test_peepholer.py
↓
X
📁 test_peg_generator/
X
📄 test_pep646_syntax.py
↓
X
📄 test_pickle.py
↓
X
📄 test_picklebuffer.py
↓
X
📄 test_pickletools.py
↓
X
📄 test_pipes.py
↓
X
📄 test_pkg.py
↓
X
📄 test_pkgutil.py
↓
X
📄 test_platform.py
↓
X
📄 test_plistlib.py
↓
X
📄 test_poll.py
↓
X
📄 test_popen.py
↓
X
📄 test_poplib.py
↓
X
📄 test_positional_only_arg.py
↓
X
📄 test_posix.py
↓
X
📄 test_posixpath.py
↓
X
📄 test_pow.py
↓
X
📄 test_pprint.py
↓
X
📄 test_print.py
↓
X
📄 test_profile.py
↓
X
📄 test_property.py
↓
X
📄 test_pstats.py
↓
X
📄 test_pty.py
↓
X
📄 test_pulldom.py
↓
X
📄 test_pwd.py
↓
X
📄 test_py_compile.py
↓
X
📄 test_pyclbr.py
↓
X
📁 test_pydoc/
X
📄 test_pyexpat.py
↓
X
📄 test_queue.py
↓
X
📄 test_quopri.py
↓
X
📄 test_raise.py
↓
X
📄 test_random.py
↓
X
📄 test_range.py
↓
X
📄 test_re.py
↓
X
📄 test_readline.py
↓
X
📄 test_regrtest.py
↓
X
📄 test_repl.py
↓
X
📄 test_reprlib.py
↓
X
📄 test_resource.py
↓
X
📄 test_richcmp.py
↓
X
📄 test_rlcompleter.py
↓
X
📄 test_robotparser.py
↓
X
📄 test_runpy.py
↓
X
📄 test_sax.py
↓
X
📄 test_sched.py
↓
X
📄 test_scope.py
↓
X
📄 test_script_helper.py
↓
X
📄 test_secrets.py
↓
X
📄 test_select.py
↓
X
📄 test_selectors.py
↓
X
📄 test_set.py
↓
X
📄 test_setcomps.py
↓
X
📄 test_shelve.py
↓
X
📄 test_shlex.py
↓
X
📄 test_shutil.py
↓
X
📄 test_signal.py
↓
X
📄 test_site.py
↓
X
📄 test_slice.py
↓
X
📄 test_smtpd.py
↓
X
📄 test_smtplib.py
↓
X
📄 test_smtpnet.py
↓
X
📄 test_sndhdr.py
↓
X
📄 test_socket.py
↓
X
📄 test_socketserver.py
↓
X
📄 test_sort.py
↓
X
📄 test_source_encoding.py
↓
X
📄 test_spwd.py
↓
X
📁 test_sqlite3/
X
📄 test_ssl.py
↓
X
📄 test_stable_abi_ctypes.py
↓
X
📄 test_startfile.py
↓
X
📄 test_stat.py
↓
X
📄 test_statistics.py
↓
X
📄 test_strftime.py
↓
X
📄 test_string.py
↓
X
📄 test_string_literals.py
↓
X
📄 test_stringprep.py
↓
X
📄 test_strptime.py
↓
X
📄 test_strtod.py
↓
X
📄 test_struct.py
↓
X
📄 test_structseq.py
↓
X
📄 test_subclassinit.py
↓
X
📄 test_subprocess.py
↓
X
📄 test_sunau.py
↓
X
📄 test_sundry.py
↓
X
📄 test_super.py
↓
X
📄 test_support.py
↓
X
📄 test_symtable.py
↓
X
📄 test_syntax.py
↓
X
📄 test_sys.py
↓
X
📄 test_sys_setprofile.py
↓
X
📄 test_sys_settrace.py
↓
X
📄 test_sysconfig.py
↓
X
📄 test_syslog.py
↓
X
📄 test_tabnanny.py
↓
X
📄 test_tarfile.py
↓
X
📄 test_tcl.py
↓
X
📄 test_telnetlib.py
↓
X
📄 test_tempfile.py
↓
X
📄 test_termios.py
↓
X
📄 test_textwrap.py
↓
X
📄 test_thread.py
↓
X
📄 test_threadedtempfile.py
↓
X
📄 test_threading.py
↓
X
📄 test_threading_local.py
↓
X
📄 test_threadsignals.py
↓
X
📄 test_time.py
↓
X
📄 test_timeit.py
↓
X
📄 test_timeout.py
↓
X
📄 test_tix.py
↓
X
📄 test_tk.py
↓
X
📄 test_tokenize.py
↓
X
📁 test_tomllib/
X
📁 test_tools/
X
📄 test_trace.py
↓
X
📄 test_traceback.py
↓
X
📄 test_tracemalloc.py
↓
X
📄 test_ttk_guionly.py
↓
X
📄 test_ttk_textonly.py
↓
X
📄 test_tty.py
↓
X
📄 test_tuple.py
↓
X
📄 test_turtle.py
↓
X
📄 test_type_annotations.py
↓
X
📄 test_type_cache.py
↓
X
📄 test_type_comments.py
↓
X
📄 test_typechecks.py
↓
X
📄 test_types.py
↓
X
📄 test_typing.py
↓
X
📄 test_ucn.py
↓
X
📄 test_unary.py
↓
X
📄 test_unicode.py
↓
X
📄 test_unicode_file.py
↓
X
📄 test_unicode_file_functions.py
↓
X
📄 test_unicode_identifiers.py
↓
X
📄 test_unicodedata.py
↓
X
📄 test_unittest.py
↓
X
📄 test_univnewlines.py
↓
X
📄 test_unpack.py
↓
X
📄 test_unpack_ex.py
↓
X
📄 test_unparse.py
↓
X
📄 test_urllib.py
↓
X
📄 test_urllib2.py
↓
X
📄 test_urllib2_localnet.py
↓
X
📄 test_urllib2net.py
↓
X
📄 test_urllib_response.py
↓
X
📄 test_urllibnet.py
↓
X
📄 test_urlparse.py
↓
X
📄 test_userdict.py
↓
X
📄 test_userlist.py
↓
X
📄 test_userstring.py
↓
X
📄 test_utf8_mode.py
↓
X
📄 test_utf8source.py
↓
X
📄 test_uu.py
↓
X
📄 test_uuid.py
↓
X
📄 test_venv.py
↓
X
📄 test_wait3.py
↓
X
📄 test_wait4.py
↓
X
📁 test_warnings/
X
📄 test_wave.py
↓
X
📄 test_weakref.py
↓
X
📄 test_weakset.py
↓
X
📄 test_webbrowser.py
↓
X
📄 test_winconsoleio.py
↓
X
📄 test_winreg.py
↓
X
📄 test_winsound.py
↓
X
📄 test_with.py
↓
X
📄 test_wsgiref.py
↓
X
📄 test_xdrlib.py
↓
X
📄 test_xml_dom_minicompat.py
↓
X
📄 test_xml_etree.py
↓
X
📄 test_xml_etree_c.py
↓
X
📄 test_xmlrpc.py
↓
X
📄 test_xmlrpc_net.py
↓
X
📄 test_xxlimited.py
↓
X
📄 test_xxtestfuzz.py
↓
X
📄 test_yield_from.py
↓
X
📄 test_zipapp.py
↓
X
📄 test_zipfile.py
↓
X
📄 test_zipfile64.py
↓
X
📄 test_zipimport.py
↓
X
📄 test_zipimport_support.py
↓
X
📄 test_zlib.py
↓
X
📁 test_zoneinfo/
X
📄 testcodec.py
↓
X
📄 testtar.tar
↓
X
📄 testtar.tar.xz
↓
X
📄 tf_inherit_check.py
↓
X
📄 time_hashlib.py
↓
X
📁 tokenizedata/
X
📁 tracedmodules/
X
📁 typinganndata/
X
📄 win_console_handler.py
↓
X
📁 xmltestdata/
X
📄 xmltests.py
↓
X
📄 zip_cp437_header.zip
↓
X
📄 zipdir.zip
↓
X
📄 zipdir_backslash.zip
↓
X
📁 ziptestdata/
X
SAVING...
BERHASIL DIUBAH!
EDITING: test_htmlparser.py
"""Tests for HTMLParser.py.""" import html.parser import pprint import unittest 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 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') 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("<?processing instruction>", [ ("pi", "processing instruction"), ]) self._run_check("<?processing instruction ?>", [ ("pi", "processing instruction ?"), ]) def test_simple_html(self): self._run_check(""" <!DOCTYPE html PUBLIC 'foo'> <HTML>&entity;  <!--comment1a -></foo><bar><<?pi?></foo<bar comment1b--> <Img sRc='Bar' isMAP>sample text “ <!--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><<?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 test_malformatted_charref(self): self._run_check("<p>&#bad;</p>", [ ("starttag", "p", []), ("data", "&#bad;"), ("endtag", "p"), ]) # add the [] as a workaround to avoid buffering (see #20288) self._run_check(["<div>&#bad;</div>"], [ ("starttag", "div", []), ("data", "&#bad;"), ("endtag", "div"), ]) 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("<a><b></a></b>", [ ("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_starttag_end_boundary(self): self._run_check("""<a b='<'>""", [("starttag", "a", [("b", "<")])]) self._run_check("""<a b='>'>""", [("starttag", "a", [("b", ">")])]) def test_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) output = [("comment", "abc")] self._run_check(["", "<!--abc-->"], output) self._run_check(["<", "!--abc-->"], output) self._run_check(["<!", "--abc-->"], output) self._run_check(["<!-", "-abc-->"], output) self._run_check(["<!--", "abc-->"], output) self._run_check(["<!--a", "bc-->"], output) self._run_check(["<!--ab", "c-->"], output) self._run_check(["<!--abc", "-->"], output) self._run_check(["<!--abc-", "->"], output) self._run_check(["<!--abc--", ">"], output) self._run_check(["<!--abc-->", ""], output) def test_valid_doctypes(self): # from http://www.w3.org/QA/2002/04/valid-dtd-list.html dtds = ['HTML', # HTML5 doctype ('HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" ' '"http://www.w3.org/TR/html4/strict.dtd"'), ('HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" ' '"http://www.w3.org/TR/html4/loose.dtd"'), ('html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" ' '"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"'), ('html PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN" ' '"http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd"'), ('math PUBLIC "-//W3C//DTD MathML 2.0//EN" ' '"http://www.w3.org/Math/DTD/mathml2/mathml2.dtd"'), ('html PUBLIC "-//W3C//DTD ' 'XHTML 1.1 plus MathML 2.0 plus SVG 1.1//EN" ' '"http://www.w3.org/2002/04/xhtml-math-svg/xhtml-math-svg.dtd"'), ('svg PUBLIC "-//W3C//DTD SVG 1.1//EN" ' '"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"'), 'html PUBLIC "-//IETF//DTD HTML 2.0//EN"', 'html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"'] for dtd in dtds: self._run_check("<!DOCTYPE %s>" % dtd, [('decl', 'DOCTYPE ' + dtd)]) def test_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 test_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 test_cdata_content(self): contents = [ '<!-- not a comment --> ¬-an-entity-ref;', "<not a='start tag'>", '<a href="" /> <p> <span></span>', 'foo = "</scr" + "ipt>";', 'foo = "</SCRIPT" + ">";', 'foo = <\n/script> ', '<!-- document.write("</scr" + "ipt>"); -->', ('\n//<![CDATA[\n' 'document.write(\'<s\'+\'cript type="text/javascript" ' 'src="http://www.example.org/r=\'+new ' 'Date().getTime()+\'"><\\/s\'+\'cript>\');\n//]]>'), '\n<!-- //\nvar foo = 3.14;\n// -->\n', 'foo = "</sty" + "le>";', '<!-- \u2603 -->', # these two should be invalid according to the HTML 5 spec, # section 8.1.2.2 #'foo = </\nscript>', #'foo = </ script>', ] elements = ['script', 'style', 'SCRIPT', 'STYLE', 'Script', 'Style'] for content in contents: for element in elements: element_lower = element.lower() s = '<{element}>{content}</{element}>'.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 = """<!-- not a comment --> ¬-an-entity-ref; <a href="" /> </p><p> <span></span></style> '</script' + '>'""" for element in [' script', 'script ', ' script ', '\nscript', 'script\n', '\nscript\n']: element_lower = element.lower().strip() s = '<script>{content}</{element}>'.format(element=element, content=content) self._run_check(s, [("starttag", element_lower, []), ("data", content), ("endtag", element_lower)], collector=Collector(convert_charrefs=False)) def test_comments(self): html = ("<!-- I'm a valid comment -->" '<!--me too!-->' '<!------>' '<!---->' '<!----I have many hyphens---->' '<!-- I have a > in the middle -->' '<!-- and I have -- in the middle! -->') expected = [('comment', " I'm a valid comment "), ('comment', 'me too!'), ('comment', '--'), ('comment', ''), ('comment', '--I have many hyphens--'), ('comment', ' I have a > in the middle '), ('comment', ' and I have -- in the middle! ')] self._run_check(html, expected) def test_condcoms(self): html = ('<!--[if IE & !(lte IE 8)]>aren\'t<![endif]-->' '<!--[if IE 8]>condcoms<![endif]-->' '<!--[if lte IE 7]>pretty?<![endif]-->') expected = [('comment', "[if IE & !(lte IE 8)]>aren't<![endif]"), ('comment', '[if IE 8]>condcoms<![endif]'), ('comment', '[if lte IE 7]>pretty?<![endif]')] self._run_check(html, expected) def test_convert_charrefs(self): # default value for convert_charrefs is now True collector = lambda: EventCollectorCharrefs() self.assertTrue(collector().convert_charrefs) charrefs = ['"', '"', '"', '"', '"', '"'] # check charrefs in the middle of the text/attributes expected = [('starttag', 'a', [('href', 'foo"zar')]), ('data', 'a"z'), ('endtag', 'a')] for charref in charrefs: self._run_check('<a href="foo{0}zar">a{0}z</a>'.format(charref), expected, collector=collector()) # check charrefs at the beginning/end of the text/attributes expected = [('data', '"'), ('starttag', 'a', [('x', '"'), ('y', '"X'), ('z', 'X"')]), ('data', '"'), ('endtag', 'a'), ('data', '"')] for charref in charrefs: self._run_check('{0}<a x="{0}" y="{0}X" z="X{0}">' '{0}</a>{0}'.format(charref), expected, collector=collector()) # check charrefs in <script>/<style> elements for charref in charrefs: text = 'X'.join([charref]*3) expected = [('data', '"'), ('starttag', 'script', []), ('data', text), ('endtag', 'script'), ('data', '"'), ('starttag', 'style', []), ('data', text), ('endtag', 'style'), ('data', '"')] self._run_check('{1}<script>{0}</script>{1}' '<style>{0}</style>{1}'.format(text, charref), expected, collector=collector()) # check truncated charrefs at the end of the file html = '&quo &# &#x' for x in range(1, len(html)): self._run_check(html[:x], [('data', html[:x])], collector=collector()) # check a string with no charrefs self._run_check('no charrefs here', [('data', 'no charrefs here')], collector=collector()) # the remaining tests were for the "tolerant" parser (which is now # the default), and check various kind of broken markup def test_tolerant_parsing(self): self._run_check('<html <html>te>>xt&a<<bc</a></html>\n' '<img src="URL><//img></html</html>', [ ('starttag', 'html', [('<html', None)]), ('data', 'te>>xt'), ('entityref', 'a'), ('data', '<'), ('starttag', 'bc<', [('a', None)]), ('endtag', 'html'), ('data', '\n<img src="URL>'), ('comment', '/img'), ('endtag', 'html<')]) def test_starttag_junk_chars(self): self._run_check("</>", []) self._run_check("</$>", [('comment', '$')]) self._run_check("</", [('data', '</')]) self._run_check("</a", [('data', '</a')]) self._run_check("<a<a>", [('starttag', 'a<a', [])]) self._run_check("</a<a>", [('endtag', 'a<a')]) self._run_check("<!", [('data', '<!')]) self._run_check("<a", [('data', '<a')]) self._run_check("<a foo='bar'", [('data', "<a foo='bar'")]) self._run_check("<a foo='bar", [('data', "<a foo='bar")]) self._run_check("<a foo='>'", [('data', "<a foo='>'")]) self._run_check("<a foo='>", [('data', "<a foo='>")]) self._run_check("<a$>", [('starttag', 'a$', [])]) self._run_check("<a$b>", [('starttag', 'a$b', [])]) self._run_check("<a$b/>", [('startendtag', 'a$b', [])]) self._run_check("<a$b >", [('starttag', 'a$b', [])]) self._run_check("<a$b />", [('startendtag', 'a$b', [])]) def test_slashes_in_starttag(self): self._run_check('<a foo="var"/>', [('startendtag', 'a', [('foo', 'var')])]) html = ('<img width=902 height=250px ' 'src="/sites/default/files/images/homepage/foo.jpg" ' '/*what am I doing here*/ />') expected = [( 'startendtag', 'img', [('width', '902'), ('height', '250px'), ('src', '/sites/default/files/images/homepage/foo.jpg'), ('*what', None), ('am', None), ('i', None), ('doing', None), ('here*', None)] )] self._run_check(html, expected) html = ('<a / /foo/ / /=/ / /bar/ / />' '<a / /foo/ / /=/ / /bar/ / >') expected = [ ('startendtag', 'a', [('foo', None), ('=', None), ('bar', None)]), ('starttag', 'a', [('foo', None), ('=', None), ('bar', None)]) ] self._run_check(html, expected) #see issue #14538 html = ('<meta><meta / ><meta // ><meta / / >' '<meta/><meta /><meta //><meta//>') expected = [ ('starttag', 'meta', []), ('starttag', 'meta', []), ('starttag', 'meta', []), ('starttag', 'meta', []), ('startendtag', 'meta', []), ('startendtag', 'meta', []), ('startendtag', 'meta', []), ('startendtag', 'meta', []), ] self._run_check(html, expected) def test_declaration_junk_chars(self): self._run_check("<!DOCTYPE foo $ >", [('decl', 'DOCTYPE foo $ ')]) def test_illegal_declarations(self): self._run_check('<!spacer type="block" height="25">', [('comment', 'spacer type="block" height="25"')]) def test_invalid_end_tags(self): # A collection of broken end tags. <br> is used as separator. # see http://www.w3.org/TR/html5/tokenization.html#end-tag-open-state # and #13993 html = ('<br></label</p><br></div end tmAd-leaderBoard><br></<h4><br>' '</li class="unit"><br></li\r\n\t\t\t\t\t\t</ul><br></><br>') expected = [('starttag', 'br', []), # < is part of the name, / is discarded, p is an attribute ('endtag', 'label<'), ('starttag', 'br', []), # text and attributes are discarded ('endtag', 'div'), ('starttag', 'br', []), # comment because the first char after </ is not a-zA-Z ('comment', '<h4'), ('starttag', 'br', []), # attributes are discarded ('endtag', 'li'), ('starttag', 'br', []), # everything till ul (included) is discarded ('endtag', 'li'), ('starttag', 'br', []), # </> is ignored ('starttag', 'br', [])] self._run_check(html, expected) def test_broken_invalid_end_tag(self): # This is technically wrong (the "> shouldn't be included in the 'data') # but is probably not worth fixing it (in addition to all the cases of # the previous test, it would require a full attribute parsing). # see #13993 html = '<b>This</b attr=">"> confuses the parser' expected = [('starttag', 'b', []), ('data', 'This'), ('endtag', 'b'), ('data', '"> confuses the parser')] self._run_check(html, expected) def test_correct_detection_of_start_tags(self): # see #13273 html = ('<div style="" ><b>The <a href="some_url">rain</a> ' '<br /> in <span>Spain</span></b></div>') expected = [ ('starttag', 'div', [('style', '')]), ('starttag', 'b', []), ('data', 'The '), ('starttag', 'a', [('href', 'some_url')]), ('data', 'rain'), ('endtag', 'a'), ('data', ' '), ('startendtag', 'br', []), ('data', ' in '), ('starttag', 'span', []), ('data', 'Spain'), ('endtag', 'span'), ('endtag', 'b'), ('endtag', 'div') ] self._run_check(html, expected) html = '<div style="", foo = "bar" ><b>The <a href="some_url">rain</a>' expected = [ ('starttag', 'div', [('style', ''), (',', None), ('foo', 'bar')]), ('starttag', 'b', []), ('data', 'The '), ('starttag', 'a', [('href', 'some_url')]), ('data', 'rain'), ('endtag', 'a'), ] self._run_check(html, expected) def test_EOF_in_charref(self): # see #17802 # This test checks that the UnboundLocalError reported in the issue # is not raised, however I'm not sure the returned values are correct. # Maybe HTMLParser should use self.unescape for these data = [ ('a&', [('data', 'a&')]), ('a&b', [('data', 'ab')]), ('a&b ', [('data', 'a'), ('entityref', 'b'), ('data', ' ')]), ('a&b;', [('data', 'a'), ('entityref', 'b')]), ] for html, expected in data: self._run_check(html, expected) def test_broken_comments(self): html = ('<! not really a comment >' '<! not a comment either -->' '<! -- close enough -->' '<!><!<-- this was an empty comment>' '<!!! another bogus comment !!!>') expected = [ ('comment', ' not really a comment '), ('comment', ' not a comment either --'), ('comment', ' -- close enough --'), ('comment', ''), ('comment', '<-- this was an empty comment'), ('comment', '!! another bogus comment !!!'), ] self._run_check(html, expected) def test_broken_condcoms(self): # these condcoms are missing the '--' after '<!' and before the '>' html = ('<![if !(IE)]>broken condcom<![endif]>' '<![if ! IE]><link href="favicon.tiff"/><![endif]>' '<![if !IE 6]><img src="firefox.png" /><![endif]>' '<![if !ie 6]><b>foo</b><![endif]>' '<![if (!IE)|(lt IE 9)]><img src="mammoth.bmp" /><![endif]>') # According to the HTML5 specs sections "8.2.4.44 Bogus comment state" # and "8.2.4.45 Markup declaration open state", comment tokens should # be emitted instead of 'unknown decl', but calling unknown_decl # provides more flexibility. # See also Lib/_markupbase.py:parse_declaration expected = [ ('unknown decl', 'if !(IE)'), ('data', 'broken condcom'), ('unknown decl', 'endif'), ('unknown decl', 'if ! IE'), ('startendtag', 'link', [('href', 'favicon.tiff')]), ('unknown decl', 'endif'), ('unknown decl', 'if !IE 6'), ('startendtag', 'img', [('src', 'firefox.png')]), ('unknown decl', 'endif'), ('unknown decl', 'if !ie 6'), ('starttag', 'b', []), ('data', 'foo'), ('endtag', 'b'), ('unknown decl', 'endif'), ('unknown decl', 'if (!IE)|(lt IE 9)'), ('startendtag', 'img', [('src', 'mammoth.bmp')]), ('unknown decl', 'endif') ] self._run_check(html, expected) def test_convert_charrefs_dropped_text(self): # #23144: make sure that all the events are triggered when # convert_charrefs is True, even if we don't call .close() parser = EventCollector(convert_charrefs=True) # before the fix, bar & baz was missing parser.feed("foo <a>link</a> bar & baz") self.assertEqual( parser.get_events(), [('data', 'foo '), ('starttag', 'a', []), ('data', 'link'), ('endtag', 'a'), ('data', ' bar & baz')] ) class AttributesTestCase(TestCaseBase): def test_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 test_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", "")])]) # Regression test for SF patch #669683. self._run_check("<e a=rgb(1,2,3)>", [("starttag", "e", [("a", "rgb(1,2,3)")])]) # Regression test for SF bug #921657. self._run_check( "<a href=mailto:xyz@example.com>", [("starttag", "a", [("href", "mailto:xyz@example.com")])]) def test_attr_nonascii(self): # see issue 7311 self._run_check( "<img src=/foo/bar.png alt=\u4e2d\u6587>", [("starttag", "img", [("src", "/foo/bar.png"), ("alt", "\u4e2d\u6587")])]) self._run_check( "<a title='\u30c6\u30b9\u30c8' href='\u30c6\u30b9\u30c8.html'>", [("starttag", "a", [("title", "\u30c6\u30b9\u30c8"), ("href", "\u30c6\u30b9\u30c8.html")])]) self._run_check( '<a title="\u30c6\u30b9\u30c8" href="\u30c6\u30b9\u30c8.html">', [("starttag", "a", [("title", "\u30c6\u30b9\u30c8"), ("href", "\u30c6\u30b9\u30c8.html")])]) def test_attr_entity_replacement(self): self._run_check( "<a b='&><"''>", [("starttag", "a", [("b", "&><\"'")])]) def test_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 test_entityrefs_in_attributes(self): self._run_check( "<html foo='€&aa&unsupported;'>", [("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])]) def test_attr_funky_names2(self): self._run_check( r"<a $><b $=%><c \=/>", [("starttag", "a", [("$", None)]), ("starttag", "b", [("$", "%")]), ("starttag", "c", [("\\", "/")])]) def test_entities_in_attribute_value(self): # see #1200313 for entity in ['&', '&', '&', '&']: self._run_check('<a href="%s">' % entity, [("starttag", "a", [("href", "&")])]) self._run_check("<a href='%s'>" % entity, [("starttag", "a", [("href", "&")])]) self._run_check("<a href=%s>" % entity, [("starttag", "a", [("href", "&")])]) def test_malformed_attributes(self): # see #13357 html = ( "<a href=test'style='color:red;bad1'>test - bad1</a>" "<a href=test'+style='color:red;ba2'>test - bad2</a>" "<a href=test' style='color:red;bad3'>test - bad3</a>" "<a href = test' style='color:red;bad4' >test - bad4</a>" ) expected = [ ('starttag', 'a', [('href', "test'style='color:red;bad1'")]), ('data', 'test - bad1'), ('endtag', 'a'), ('starttag', 'a', [('href', "test'+style='color:red;ba2'")]), ('data', 'test - bad2'), ('endtag', 'a'), ('starttag', 'a', [('href', "test'\xa0style='color:red;bad3'")]), ('data', 'test - bad3'), ('endtag', 'a'), ('starttag', 'a', [('href', "test'\xa0style='color:red;bad4'")]), ('data', 'test - bad4'), ('endtag', 'a') ] self._run_check(html, expected) def test_malformed_adjacent_attributes(self): # see #12629 self._run_check('<x><y z=""o"" /></x>', [('starttag', 'x', []), ('startendtag', 'y', [('z', ''), ('o""', None)]), ('endtag', 'x')]) self._run_check('<x><y z="""" /></x>', [('starttag', 'x', []), ('startendtag', 'y', [('z', ''), ('""', None)]), ('endtag', 'x')]) # see #755670 for the following 3 tests def test_adjacent_attributes(self): self._run_check('<a width="100%"cellspacing=0>', [("starttag", "a", [("width", "100%"), ("cellspacing","0")])]) self._run_check('<a id="foo"class="bar">', [("starttag", "a", [("id", "foo"), ("class","bar")])]) def test_missing_attribute_value(self): self._run_check('<a v=>', [("starttag", "a", [("v", "")])]) def test_javascript_attribute_value(self): self._run_check("<a href=javascript:popup('/popup/help.html')>", [("starttag", "a", [("href", "javascript:popup('/popup/help.html')")])]) def test_end_tag_in_attribute_value(self): # see #1745761 self._run_check("<a href='http://www.example.org/\">;'>spam</a>", [("starttag", "a", [("href", "http://www.example.org/\">;")]), ("data", "spam"), ("endtag", "a")]) def test_with_unquoted_attributes(self): # see #12008 html = ("<html><body bgcolor=d0ca90 text='181008'>" "<table cellspacing=0 cellpadding=1 width=100% ><tr>" "<td align=left><font size=-1>" "- <a href=/rabota/><span class=en> software-and-i</span></a>" "- <a href='/1/'><span class=en> library</span></a></table>") expected = [ ('starttag', 'html', []), ('starttag', 'body', [('bgcolor', 'd0ca90'), ('text', '181008')]), ('starttag', 'table', [('cellspacing', '0'), ('cellpadding', '1'), ('width', '100%')]), ('starttag', 'tr', []), ('starttag', 'td', [('align', 'left')]), ('starttag', 'font', [('size', '-1')]), ('data', '- '), ('starttag', 'a', [('href', '/rabota/')]), ('starttag', 'span', [('class', 'en')]), ('data', ' software-and-i'), ('endtag', 'span'), ('endtag', 'a'), ('data', '- '), ('starttag', 'a', [('href', '/1/')]), ('starttag', 'span', [('class', 'en')]), ('data', ' library'), ('endtag', 'span'), ('endtag', 'a'), ('endtag', 'table') ] self._run_check(html, expected) def test_comma_between_attributes(self): # see bpo 41478 # HTMLParser preserves duplicate attributes, leaving the task of # removing duplicate attributes to a conformant html tree builder html = ('<div class=bar,baz=asd>' # between attrs (unquoted) '<div class="bar",baz="asd">' # between attrs (quoted) '<div class=bar, baz=asd,>' # after values (unquoted) '<div class="bar", baz="asd",>' # after values (quoted) '<div class="bar",>' # one comma values (quoted) '<div class=,bar baz=,asd>' # before values (unquoted) '<div class=,"bar" baz=,"asd">' # before values (quoted) '<div ,class=bar ,baz=asd>' # before names '<div class,="bar" baz,="asd">' # after names ) expected = [ ('starttag', 'div', [('class', 'bar,baz=asd'),]), ('starttag', 'div', [('class', 'bar'), (',baz', 'asd')]), ('starttag', 'div', [('class', 'bar,'), ('baz', 'asd,')]), ('starttag', 'div', [('class', 'bar'), (',', None), ('baz', 'asd'), (',', None)]), ('starttag', 'div', [('class', 'bar'), (',', None)]), ('starttag', 'div', [('class', ',bar'), ('baz', ',asd')]), ('starttag', 'div', [('class', ',"bar"'), ('baz', ',"asd"')]), ('starttag', 'div', [(',class', 'bar'), (',baz', 'asd')]), ('starttag', 'div', [('class,', 'bar'), ('baz,', 'asd')]), ] self._run_check(html, expected) def test_weird_chars_in_unquoted_attribute_values(self): self._run_check('<form action=bogus|&#()value>', [ ('starttag', 'form', [('action', 'bogus|&#()value')])]) if __name__ == "__main__": unittest.main()
SIMPAN PERUBAHAN