def _apply_pygments(self, data, filename):
"""Apply Pygments syntax-highlighting to a file's contents.
This will only apply syntax highlighting if a lexer is available and
the file extension is not blacklisted.
Args:
data (unicode):
The data to syntax highlight.
filename (unicode):
The name of the file. This is used to help determine a
suitable lexer.
Returns:
list of unicode:
A list of lines, all syntax-highlighted, if a lexer is found.
If no lexer is available, this will return ``None``.
"""
if filename.endswith(self.STYLED_EXT_BLACKLIST):
return None
try:
lexer = guess_lexer_for_filename(filename,
data,
stripnl=False,
encoding='utf-8')
except pygments.util.ClassNotFound:
return None
lexer.add_filter('codetagify')
return split_line_endings(
highlight(data, lexer, NoWrapperHtmlFormatter()))
def __init__(self, data):
from reviewboard.diffviewer.diffutils import split_line_endings
self.base_commit_id = None
self.new_commit_id = None
self.data = data
self.lines = split_line_endings(data)
def __init__(self, data):
from reviewboard.diffviewer.diffutils import split_line_endings
self.base_commit_id = None
self.new_commit_id = None
self.data = data
self.lines = split_line_endings(data)
def _apply_pygments(self, data, filename):
"""Applies Pygments syntax-highlighting to a file's contents.
The resulting HTML will be returned as a list of lines.
"""
lexer = get_lexer_for_filename(filename, stripnl=False, encoding="utf-8")
lexer.add_filter("codetagify")
return split_line_endings(highlight(data, lexer, NoWrapperHtmlFormatter()))
def _apply_pygments(self, data, filename):
"""Applies Pygments syntax-highlighting to a file's contents.
The resulting HTML will be returned as a list of lines.
"""
lexer = get_lexer_for_filename(filename,
stripnl=False,
encoding='utf-8')
lexer.add_filter('codetagify')
return split_line_endings(
highlight(data, lexer, NoWrapperHtmlFormatter()))
def _find_range_info_v1(diff):
lines = split_line_endings(diff)
process_changes = False
process_trailing_context = False
ranges = []
for range_info in get_diff_data_chunks_info(diff):
orig_info = range_info['orig']
modified_info = range_info['modified']
orig_pre_lines_of_context = orig_info['pre_lines_of_context']
orig_post_lines_of_context = orig_info['post_lines_of_context']
modified_pre_lines_of_context = \
modified_info['pre_lines_of_context']
modified_post_lines_of_context = \
modified_info['post_lines_of_context']
if modified_pre_lines_of_context and orig_pre_lines_of_context:
pre_lines_of_context = min(orig_pre_lines_of_context,
modified_pre_lines_of_context)
else:
pre_lines_of_context = (modified_pre_lines_of_context
or orig_pre_lines_of_context)
if modified_post_lines_of_context and orig_post_lines_of_context:
post_lines_of_context = min(orig_post_lines_of_context,
modified_post_lines_of_context)
else:
post_lines_of_context = (modified_post_lines_of_context
or orig_post_lines_of_context)
start = modified_info['chunk_start'] + pre_lines_of_context
if pre_lines_of_context > 0:
start -= 1
length = (modified_info['chunk_len'] - pre_lines_of_context -
post_lines_of_context)
ranges.append((start, start + length))
return ranges
def _apply_pygments(self, data, filename):
"""Applies Pygments syntax-highlighting to a file's contents.
Syntax highlight obeys a explicitly provided list of preferences by
extension or it is derived from the contents of the file.
The resulting HTML will be returned as a list of lines.
"""
lexer = self._get_preferred_lexer(
filename, stripln=False, encoding='utf-8')
logger.debug('preferred lexer for %s: %s' % (filename, lexer))
if not lexer:
lexer = guess_lexer_for_filename(
filename, data, stripnl=False,
encoding='utf-8')
lexer.add_filter('codetagify')
return split_line_endings(highlight(data, lexer,
NoWrapperHtmlFormatter()))
def _find_range_info(diff):
lines = split_line_endings(diff)
process_changes = False
ranges = []
chunk_start = None
chunk_len = 0
lines_of_context = 0
# Look through the chunks of the diff, trying to find the amount
# of context shown at the beginning of each chunk. Though this
# will usually be 3 lines, it may be fewer or more, depending
# on file length and diff generation settings.
for line in lines:
if process_changes:
if line.startswith((b'-', b'+')):
# We've found the first change in the chunk. We now
# know how many lines of context we have.
#
# We reduce the indexes by 1 because the chunk ranges
# in diffs start at 1, and we want a 0-based index.
start = chunk_start - 1 + lines_of_context
ranges.append((start, start + chunk_len))
process_changes = False
continue
else:
lines_of_context += 1
# This was not a change within a chunk, or we weren't processing,
# so check to see if this is a chunk header instead.
m = CHUNK_RANGE_RE.match(line)
if m:
# It is a chunk header. Reset the state for the next range,
# and pull the line number and length from the header.
chunk_start = int(m.group('new_start'))
chunk_len = int(m.group('new_len') or '1')
process_changes = True
lines_of_context = 0
return ranges
def __init__(self, data):
"""Initialize the parser.
Args:
data (bytes):
The diff content to parse.
Raises:
TypeError:
The provided ``data`` argument was not a ``bytes`` type.
"""
from reviewboard.diffviewer.diffutils import split_line_endings
if not isinstance(data, bytes):
raise TypeError(
_('%s expects bytes values for "data", not %s') %
(type(self).__name__, type(data)))
self.base_commit_id = None
self.new_commit_id = None
self.data = data
self.lines = split_line_endings(data)
def _apply_pygments(self, data, filename):
"""Applies Pygments syntax-highlighting to a file's contents.
Syntax highlight obeys a explicitly provided list of preferences by
extension or it is derived from the contents of the file.
The resulting HTML will be returned as a list of lines.
"""
lexer = self._get_preferred_lexer(filename,
stripln=False,
encoding='utf-8')
logger.debug('preferred lexer for %s: %s' % (filename, lexer))
if not lexer:
lexer = guess_lexer_for_filename(filename,
data,
stripnl=False,
encoding='utf-8')
lexer.add_filter('codetagify')
return split_line_endings(
highlight(data, lexer, NoWrapperHtmlFormatter()))
def _find_range_info(diff):
lines = split_line_endings(diff)
process_changes = False
process_trailing_context = False
ranges = []
chunk_start = None
chunk_len = 0
lines_of_context = 0
# Look through the chunks of the diff, trying to find the amount
# of context shown at the beginning of each chunk. Though this
# will usually be 3 lines, it may be fewer or more, depending
# on file length and diff generation settings.
for line in lines:
if process_changes:
if line.startswith((b'-', b'+')):
# We've found the first change in the chunk. We now
# know how many lines of context we have.
#
# We reduce the indexes by 1 because the chunk ranges
# in diffs start at 1, and we want a 0-based index.
start = chunk_start - 1 + lines_of_context
chunk_len -= lines_of_context
# We then reduce by 1 again, compensating for the
# additional line of context, if any. We must do this
# because the first line after a "@@" section is being
# counted in lines_of_context, but is also the line
# referred to in chunk_start.
if lines_of_context > 0:
start -= 1
ranges.append((start, start + chunk_len))
process_changes = False
process_trailing_context = True
lines_of_context = 0
continue
else:
lines_of_context += 1
elif process_trailing_context:
if line.startswith(b' '):
# This may be a line of context after the modifications
# in this chunk. Bump up the counter.
lines_of_context += 1
continue
else:
# Reset the lines of trailing context, since we hit
# something other than an equal line.
lines_of_context = 0
# This was not a change within a chunk, or we weren't processing,
# so check to see if this is a chunk header instead.
m = CHUNK_RANGE_RE.match(line)
if m:
# It is a chunk header. Start by updating the previous range
# to factor in the lines of trailing context.
if process_trailing_context and lines_of_context > 0:
last_range = ranges[-1]
ranges[-1] = (last_range[0],
last_range[1] - lines_of_context)
# Next, reset the state for the next range, and pull the line
# number and length from the header.
chunk_start = int(m.group('new_start'))
chunk_len = int(m.group('new_len') or '1')
process_changes = True
process_trailing_context = False
lines_of_context = 0
# We need to adjust the last range, if we're still processing
# trailing context.
if process_trailing_context and lines_of_context > 0:
last_range = ranges[-1]
ranges[-1] = (last_range[0],
last_range[1] - lines_of_context)
return ranges
def _find_range_info(diff):
lines = split_line_endings(diff)
process_changes = False
process_trailing_context = False
ranges = []
chunk_start = None
chunk_len = 0
lines_of_context = 0
# Look through the chunks of the diff, trying to find the amount
# of context shown at the beginning of each chunk. Though this
# will usually be 3 lines, it may be fewer or more, depending
# on file length and diff generation settings.
for line in lines:
if process_changes:
if line.startswith((b'-', b'+')):
# We've found the first change in the chunk. We now
# know how many lines of context we have.
#
# We reduce the indexes by 1 because the chunk ranges
# in diffs start at 1, and we want a 0-based index.
start = chunk_start - 1 + lines_of_context
chunk_len -= lines_of_context
# We then reduce by 1 again, compensating for the
# additional line of context, if any. We must do this
# because the first line after a "@@" section is being
# counted in lines_of_context, but is also the line
# referred to in chunk_start.
if lines_of_context > 0:
start -= 1
ranges.append((start, start + chunk_len))
process_changes = False
process_trailing_context = True
lines_of_context = 0
continue
else:
lines_of_context += 1
elif process_trailing_context:
if line.startswith(b' '):
# This may be a line of context after the modifications
# in this chunk. Bump up the counter.
lines_of_context += 1
continue
else:
# Reset the lines of trailing context, since we hit
# something other than an equal line.
lines_of_context = 0
# This was not a change within a chunk, or we weren't processing,
# so check to see if this is a chunk header instead.
m = CHUNK_RANGE_RE.match(line)
if m:
# It is a chunk header. Start by updating the previous range
# to factor in the lines of trailing context.
if process_trailing_context and lines_of_context > 0:
last_range = ranges[-1]
ranges[-1] = (last_range[0],
last_range[1] - lines_of_context)
# Next, reset the state for the next range, and pull the line
# number and length from the header.
chunk_start = int(m.group('new_start'))
chunk_len = int(m.group('new_len') or '1')
process_changes = True
process_trailing_context = False
lines_of_context = 0
# We need to adjust the last range, if we're still processing
# trailing context.
if process_trailing_context and lines_of_context > 0:
last_range = ranges[-1]
ranges[-1] = (last_range[0], last_range[1] - lines_of_context)
return ranges