src/third_party/blink/Tools/Scripts/webkitpy/w3c/test_converter.py - cobalt - Git at Google

 # Copyright (C) 2013 Adobe Systems Incorporated. All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions
 # are met:
 #
 # 1. Redistributions of source code must retain the above
 #    copyright notice, this list of conditions and the following
 #    disclaimer.
 # 2. Redistributions in binary form must reproduce the above
 #    copyright notice, this list of conditions and the following
 #    disclaimer in the documentation and/or other materials
 #    provided with the distribution.
 #
 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER "AS IS" AND ANY
 # EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 # IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 # PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER BE
 # LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY,
 # OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
 # PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
 # TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF
 # THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 # SUCH DAMAGE.

 import logging
 import re

 from webkitpy.common.host import Host
 from webkitpy.common.webkit_finder import WebKitFinder
 from HTMLParser import HTMLParser


 _log = logging.getLogger(__name__)


 def convert_for_webkit(new_path, filename, reference_support_info, host=Host()):
     """Converts a file's contents so the Blink layout test runner can run it.

     Args:
         new_path: Absolute path where file will be copied to in the Chromium repo.
         filename: Absolute path to where the file is.
         reference_support_info: Dict of information about a related reference HTML, if any.

     Returns:
         A pair of (list of modified CSS properties, modified text).
     """
     # Conversion is not necessary for any tests in wpt now; see http://crbug.com/654081.
     contents = host.filesystem.read_binary_file(filename)
     try:
         contents = contents.decode('utf-8')
     except UnicodeDecodeError:
         contents = contents.decode('utf-16')

     converter = _W3CTestConverter(new_path, filename, reference_support_info, host)
     if filename.endswith('.css'):
         return converter.add_webkit_prefix_to_unprefixed_properties(contents)
     converter.feed(contents)
     converter.close()
     return converter.output()


 class _W3CTestConverter(HTMLParser):
     """A HTMLParser subclass which converts a HTML file as it is parsed.

     After the feed() method is called, the converted document will be stored
     in converted_data, and can be retrieved with the output() method.
     """

     def __init__(self, new_path, filename, reference_support_info, host=Host()):
         HTMLParser.__init__(self)

         self._host = host
         self._filesystem = self._host.filesystem
         self._webkit_root = WebKitFinder(self._filesystem).webkit_base()

         self.converted_data = []
         self.converted_properties = []
         self.in_style_tag = False
         self.style_data = []
         self.filename = filename
         self.reference_support_info = reference_support_info
         resources_path = self.path_from_webkit_root('LayoutTests', 'resources')
         resources_relpath = self._filesystem.relpath(resources_path, new_path)
         self.resources_relpath = resources_relpath

         # These settings might vary between WebKit and Blink.
         # Only -webkit-text-emphasis is currently needed. See:
         # https://bugs.chromium.org/p/chromium/issues/detail?id=614955#c1
         self.prefixed_properties = [
             '-webkit-text-emphasis',
             '-webkit-text-emphasis-color',
             '-webkit-text-emphasis-position',
             '-webkit-text-emphasis-style',
         ]
         prop_regex = r'([\s{]|^)(' + '|'.join(
             prop.replace('-webkit-', '') for prop in self.prefixed_properties) + r')(\s+:|:)'
         self.prop_re = re.compile(prop_regex)

     def output(self):
         return (self.converted_properties, ''.join(self.converted_data))

     def path_from_webkit_root(self, *comps):
         return self._filesystem.abspath(self._filesystem.join(self._webkit_root, *comps))

     def add_webkit_prefix_to_unprefixed_properties(self, text):
         """Searches |text| for instances of properties requiring the -webkit- prefix and adds the prefix to them.

         Returns the list of converted properties and the modified text.
         """
         converted_properties = set()
         text_chunks = []
         cur_pos = 0
         for match in self.prop_re.finditer(text):
             text_chunks.extend([
                 text[cur_pos:match.start()],
                 match.group(1), '-webkit-',
                 match.group(2),
                 match.group(3)
             ])
             converted_properties.add(match.group(2))
             cur_pos = match.end()
         text_chunks.append(text[cur_pos:])

         for prop in converted_properties:
             _log.info('  converting %s', prop)

         # FIXME: Handle the JS versions of these properties and GetComputedStyle, too.
         return (converted_properties, ''.join(text_chunks))

     def convert_reference_relpaths(self, text):
         """Converts reference file paths found in the given text.

         Searches |text| for instances of files in |self.reference_support_info| and
         updates the relative path to be correct for the new ref file location.
         """
         converted = text
         for path in self.reference_support_info['files']:
             if path in text:
                 # FIXME: This doesn't handle an edge case where simply removing the relative path doesn't work.
                 # See crbug.com/421584 for details.
                 new_path = re.sub(self.reference_support_info['reference_relpath'], '', path, 1)
                 converted = re.sub(path, new_path, text)

         return converted

     def convert_style_data(self, data):
         converted = self.add_webkit_prefix_to_unprefixed_properties(data)
         if converted[0]:
             self.converted_properties.extend(list(converted[0]))

         if self.reference_support_info is None or self.reference_support_info == {}:
             return converted[1]

         return self.convert_reference_relpaths(converted[1])

     def convert_attributes_if_needed(self, tag, attrs):
         """Converts attributes in a start tag in HTML.

         The converted tag text is appended to |self.converted_data|.
         """
         converted = self.get_starttag_text()
         for attr_name, attr_value in attrs:
             if attr_name == 'style':
                 new_style = self.convert_style_data(attr_value)
                 converted = re.sub(re.escape(attr_value), new_style, converted)

         src_tags = ('script', 'img', 'style', 'frame', 'iframe', 'input', 'layer', 'textarea', 'video', 'audio')
         if tag in src_tags and self.reference_support_info is not None and self.reference_support_info != {}:
             for attr_name, attr_value in attrs:
                 if attr_name == 'src':
                     new_path = self.convert_reference_relpaths(attr_value)
                     converted = re.sub(re.escape(attr_value), new_path, converted)

         self.converted_data.append(converted)

     def parse_endtag(self, i):
         # parse_endtag is being overridden here instead of handle_endtag
         # so we can get the original end tag text with the original
         # capitalization
         endpos = HTMLParser.parse_endtag(self, i)
         self.converted_data.extend([self.rawdata[i:endpos]])
         return endpos

     def handle_starttag(self, tag, attrs):
         if tag == 'style':
             self.in_style_tag = True
         self.convert_attributes_if_needed(tag, attrs)

     def handle_endtag(self, tag):
         if tag == 'style':
             self.converted_data.append(self.convert_style_data(''.join(self.style_data)))
             self.in_style_tag = False
             self.style_data = []

     def handle_startendtag(self, tag, attrs):
         self.convert_attributes_if_needed(tag, attrs)

     def handle_data(self, data):
         if self.in_style_tag:
             self.style_data.append(data)
         else:
             self.converted_data.append(data)

     def handle_entityref(self, name):
         self.converted_data.extend(['&', name, ';'])

     def handle_charref(self, name):
         self.converted_data.extend(['&#', name, ';'])

     def handle_comment(self, data):
         self.converted_data.extend(['<!--', data, '-->'])

     def handle_decl(self, decl):
         self.converted_data.extend(['<!', decl, '>'])

     def handle_pi(self, data):
         self.converted_data.extend(['<?', data, '>'])
	# Copyright (C) 2013 Adobe Systems Incorporated. All rights reserved.
	#
	# Redistribution and use in source and binary forms, with or without
	# modification, are permitted provided that the following conditions
	# are met:
	#
	# 1. Redistributions of source code must retain the above
	# copyright notice, this list of conditions and the following
	# disclaimer.
	# 2. Redistributions in binary form must reproduce the above
	# copyright notice, this list of conditions and the following
	# disclaimer in the documentation and/or other materials
	# provided with the distribution.
	#
	# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER "AS IS" AND ANY
	# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
	# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
	# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER BE
	# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY,
	# OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
	# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
	# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
	# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
	# TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF
	# THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
	# SUCH DAMAGE.

	import logging
	import re

	from webkitpy.common.host import Host
	from webkitpy.common.webkit_finder import WebKitFinder
	from HTMLParser import HTMLParser


	_log = logging.getLogger(__name__)


	def convert_for_webkit(new_path, filename, reference_support_info, host=Host()):
	"""Converts a file's contents so the Blink layout test runner can run it.

	Args:
	new_path: Absolute path where file will be copied to in the Chromium repo.
	filename: Absolute path to where the file is.
	reference_support_info: Dict of information about a related reference HTML, if any.

	Returns:
	A pair of (list of modified CSS properties, modified text).
	"""
	# Conversion is not necessary for any tests in wpt now; see http://crbug.com/654081.
	contents = host.filesystem.read_binary_file(filename)
	try:
	contents = contents.decode('utf-8')
	except UnicodeDecodeError:
	contents = contents.decode('utf-16')

	converter = _W3CTestConverter(new_path, filename, reference_support_info, host)
	if filename.endswith('.css'):
	return converter.add_webkit_prefix_to_unprefixed_properties(contents)
	converter.feed(contents)
	converter.close()
	return converter.output()


	class _W3CTestConverter(HTMLParser):
	"""A HTMLParser subclass which converts a HTML file as it is parsed.

	After the feed() method is called, the converted document will be stored
	in converted_data, and can be retrieved with the output() method.
	"""

	def __init__(self, new_path, filename, reference_support_info, host=Host()):
	HTMLParser.__init__(self)

	self._host = host
	self._filesystem = self._host.filesystem
	self._webkit_root = WebKitFinder(self._filesystem).webkit_base()

	self.converted_data = []
	self.converted_properties = []
	self.in_style_tag = False
	self.style_data = []
	self.filename = filename
	self.reference_support_info = reference_support_info
	resources_path = self.path_from_webkit_root('LayoutTests', 'resources')
	resources_relpath = self._filesystem.relpath(resources_path, new_path)
	self.resources_relpath = resources_relpath

	# These settings might vary between WebKit and Blink.
	# Only -webkit-text-emphasis is currently needed. See:
	# https://bugs.chromium.org/p/chromium/issues/detail?id=614955#c1
	self.prefixed_properties = [
	'-webkit-text-emphasis',
	'-webkit-text-emphasis-color',
	'-webkit-text-emphasis-position',
	'-webkit-text-emphasis-style',
	]
	prop_regex = r'([\s{]\|^)(' + '\|'.join(
	prop.replace('-webkit-', '') for prop in self.prefixed_properties) + r')(\s+:\|:)'
	self.prop_re = re.compile(prop_regex)

	def output(self):
	return (self.converted_properties, ''.join(self.converted_data))

	def path_from_webkit_root(self, *comps):
	return self._filesystem.abspath(self._filesystem.join(self._webkit_root, *comps))

	def add_webkit_prefix_to_unprefixed_properties(self, text):
	"""Searches \|text\| for instances of properties requiring the -webkit- prefix and adds the prefix to them.

	Returns the list of converted properties and the modified text.
	"""
	converted_properties = set()
	text_chunks = []
	cur_pos = 0
	for match in self.prop_re.finditer(text):
	text_chunks.extend([
	text[cur_pos:match.start()],
	match.group(1), '-webkit-',
	match.group(2),
	match.group(3)
	])
	converted_properties.add(match.group(2))
	cur_pos = match.end()
	text_chunks.append(text[cur_pos:])

	for prop in converted_properties:
	_log.info(' converting %s', prop)

	# FIXME: Handle the JS versions of these properties and GetComputedStyle, too.
	return (converted_properties, ''.join(text_chunks))

	def convert_reference_relpaths(self, text):
	"""Converts reference file paths found in the given text.

	Searches \|text\| for instances of files in \|self.reference_support_info\| and
	updates the relative path to be correct for the new ref file location.
	"""
	converted = text
	for path in self.reference_support_info['files']:
	if path in text:
	# FIXME: This doesn't handle an edge case where simply removing the relative path doesn't work.
	# See crbug.com/421584 for details.
	new_path = re.sub(self.reference_support_info['reference_relpath'], '', path, 1)
	converted = re.sub(path, new_path, text)

	return converted

	def convert_style_data(self, data):
	converted = self.add_webkit_prefix_to_unprefixed_properties(data)
	if converted[0]:
	self.converted_properties.extend(list(converted[0]))

	if self.reference_support_info is None or self.reference_support_info == {}:
	return converted[1]

	return self.convert_reference_relpaths(converted[1])

	def convert_attributes_if_needed(self, tag, attrs):
	"""Converts attributes in a start tag in HTML.

	The converted tag text is appended to \|self.converted_data\|.
	"""
	converted = self.get_starttag_text()
	for attr_name, attr_value in attrs:
	if attr_name == 'style':
	new_style = self.convert_style_data(attr_value)
	converted = re.sub(re.escape(attr_value), new_style, converted)

	src_tags = ('script', 'img', 'style', 'frame', 'iframe', 'input', 'layer', 'textarea', 'video', 'audio')
	if tag in src_tags and self.reference_support_info is not None and self.reference_support_info != {}:
	for attr_name, attr_value in attrs:
	if attr_name == 'src':
	new_path = self.convert_reference_relpaths(attr_value)
	converted = re.sub(re.escape(attr_value), new_path, converted)

	self.converted_data.append(converted)

	def parse_endtag(self, i):
	# parse_endtag is being overridden here instead of handle_endtag
	# so we can get the original end tag text with the original
	# capitalization
	endpos = HTMLParser.parse_endtag(self, i)
	self.converted_data.extend([self.rawdata[i:endpos]])
	return endpos

	def handle_starttag(self, tag, attrs):
	if tag == 'style':
	self.in_style_tag = True
	self.convert_attributes_if_needed(tag, attrs)

	def handle_endtag(self, tag):
	if tag == 'style':
	self.converted_data.append(self.convert_style_data(''.join(self.style_data)))
	self.in_style_tag = False
	self.style_data = []

	def handle_startendtag(self, tag, attrs):
	self.convert_attributes_if_needed(tag, attrs)

	def handle_data(self, data):
	if self.in_style_tag:
	self.style_data.append(data)
	else:
	self.converted_data.append(data)

	def handle_entityref(self, name):
	self.converted_data.extend(['&', name, ';'])

	def handle_charref(self, name):
	self.converted_data.extend(['&#', name, ';'])

	def handle_comment(self, data):
	self.converted_data.extend(['<!--', data, '-->'])

	def handle_decl(self, decl):
	self.converted_data.extend(['<!', decl, '>'])

	def handle_pi(self, data):
	self.converted_data.extend(['<?', data, '>'])