def _process_replace_chunk(self, chunk1, chunk2):
"""Process a replace chunk type and return the sub-chunks.
The text is encoded in UTF-32 before to be passed to the Patience algorithm in order to have
fixed character boundaries.
"""
sub_chunks = []
text1, text2 = [
str(chunk).encode('utf_32-BE') for chunk in (chunk1, chunk2)
]
line_sequence_matcher = PatienceSequenceMatcher(None, text1, text2)
opcodes = line_sequence_matcher.get_opcodes()
for tag, start_1, stop_1, start_2, stop_2 in opcodes:
slice1 = FlatSlice(start_1, stop_1) // 4 # 4-byte encoding
slice2 = FlatSlice(start_2, stop_2) // 4
sub_chunk1 = chunk1[slice1]
sub_chunk2 = chunk2[slice2]
if tag == 'equal':
sub_chunk_diff = TwoWayChunkEqual(sub_chunk1, sub_chunk2)
elif tag == 'delete':
sub_chunk_diff = TwoWayChunkDelete(sub_chunk1, sub_chunk2)
elif tag == 'insert':
sub_chunk_diff = TwoWayChunkInsert(sub_chunk1, sub_chunk2)
elif tag == 'replace':
sub_chunk_diff = TwoWayChunkReplace(sub_chunk1, sub_chunk2)
sub_chunks.append(sub_chunk_diff)
return sub_chunks
def _process_replace_chunk(self, chunk1, chunk2):
"""Process a replace chunk type and return the sub-chunks.
The text is encoded in UTF-32 before to be passed to the Patience algorithm in order to have
fixed character boundaries.
"""
sub_chunks = []
text1, text2 = [str(chunk).encode('utf_32-BE') for chunk in (chunk1, chunk2)]
line_sequence_matcher = PatienceSequenceMatcher(None, text1, text2)
opcodes = line_sequence_matcher.get_opcodes()
for tag, start_1, stop_1, start_2, stop_2 in opcodes:
slice1 = FlatSlice(start_1, stop_1) //4 # 4-byte encoding
slice2 = FlatSlice(start_2, stop_2) //4
sub_chunk1 = chunk1[slice1]
sub_chunk2 = chunk2[slice2]
if tag == 'equal':
sub_chunk_diff = TwoWayChunkEqual(sub_chunk1, sub_chunk2)
elif tag == 'delete':
sub_chunk_diff = TwoWayChunkDelete(sub_chunk1, sub_chunk2)
elif tag == 'insert':
sub_chunk_diff = TwoWayChunkInsert(sub_chunk1, sub_chunk2)
elif tag == 'replace':
sub_chunk_diff = TwoWayChunkReplace(sub_chunk1, sub_chunk2)
sub_chunks.append(sub_chunk_diff)
return sub_chunks
def process(self, document1, document2, number_of_lines_of_context=3):
"""Compute the difference between two :class:`RawTextDocument` documents using the Patience
algorithm and return a :class:`TwoWayFileDiff` instance. The parameter
*number_of_lines_of_context* provides the number of lines of context for the diff algorithm.
"""
file_diff = TwoWayFileDiff(document1, document2)
sequence_matcher = PatienceSequenceMatcher(None, document1.lines(), document2.lines())
sequence_matcher_groups = sequence_matcher.get_grouped_opcodes(number_of_lines_of_context)
for opcodes in sequence_matcher_groups:
self._process_group(file_diff, opcodes)
return file_diff
def process(self, document1, document2, number_of_lines_of_context=3):
"""Compute the difference between two :class:`RawTextDocument` documents using the Patience
algorithm and return a :class:`TwoWayFileDiff` instance. The parameter
*number_of_lines_of_context* provides the number of lines of context for the diff algorithm.
"""
file_diff = TwoWayFileDiff(document1, document2)
sequence_matcher = PatienceSequenceMatcher(None, document1.lines(), document2.lines())
sequence_matcher_groups = sequence_matcher.get_grouped_opcodes(number_of_lines_of_context)
for opcodes in sequence_matcher_groups:
self._process_group(file_diff, opcodes)
return file_diff