blob: bac6aabdc07875a8e57fb71a98eda5fe3a8b8237 [file] [log] [blame]
#!/usr/bin/env python
## Copyright (c) 2016, Alliance for Open Media. All rights reserved
## This source code is subject to the terms of the BSD 2 Clause License and
## the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License
## was not distributed with this source code in the LICENSE file, you can
## obtain it at If the Alliance for Open
## Media Patent License 1.0 was not distributed with this source code in the
## PATENTS file, you can obtain it at
"""Classes for representing diff pieces."""
__author__ = ""
import re
class DiffLines(object):
"""A container for one half of a diff."""
def __init__(self, filename, offset, length):
self.filename = filename
self.offset = offset
self.length = length
self.lines = []
self.delta_line_nums = []
def Append(self, line):
l = len(self.lines)
if line[0] != " ":
self.delta_line_nums.append(self.offset + l)
assert l+1 <= self.length
def Complete(self):
return len(self.lines) == self.length
def __contains__(self, item):
return item >= self.offset and item <= self.offset + self.length - 1
class DiffHunk(object):
"""A container for one diff hunk, consisting of two DiffLines."""
def __init__(self, header, file_a, file_b, start_a, len_a, start_b, len_b):
self.header = header
self.left = DiffLines(file_a, start_a, len_a)
self.right = DiffLines(file_b, start_b, len_b)
self.lines = []
def Append(self, line):
"""Adds a line to the DiffHunk and its DiffLines children."""
if line[0] == "-":
elif line[0] == "+":
elif line[0] == " ":
elif line[0] == "\\":
# Ignore newline messages from git diff.
assert False, ("Unrecognized character at start of diff line "
"%r" % line[0])
def Complete(self):
return self.left.Complete() and self.right.Complete()
def __repr__(self):
return "DiffHunk(%s, %s, len %d)" % (
self.left.filename, self.right.filename,
max(self.left.length, self.right.length))
def ParseDiffHunks(stream):
"""Walk a file-like object, yielding DiffHunks as they're parsed."""
file_regex = re.compile(r"(\+\+\+|---) (\S+)")
range_regex = re.compile(r"@@ -(\d+)(,(\d+))? \+(\d+)(,(\d+))?")
hunk = None
while True:
line = stream.readline()
if not line:
if hunk is None:
# Parse file names
diff_file = file_regex.match(line)
if diff_file:
if line.startswith("---"):
a_line = line
a =
if line.startswith("+++"):
b_line = line
b =
# Parse offset/lengths
diffrange = range_regex.match(line)
if diffrange:
start_a = int(
len_a = int(
start_a = 1
len_a = int(
start_b = int(
len_b = int(
start_b = 1
len_b = int(
header = [a_line, b_line, line]
hunk = DiffHunk(header, a, b, start_a, len_a, start_b, len_b)
# Add the current line to the hunk
# See if the whole hunk has been parsed. If so, yield it and prepare
# for the next hunk.
if hunk.Complete():
yield hunk
hunk = None
# Partial hunks are a parse error
assert hunk is None