Commit cb265a49 authored by John Koleszar's avatar John Koleszar
Browse files

FTFY: an automated style corrector

This is a utility for applying a limited amount of style correction on
a change-by-change basis. Rather than a big-bang reformatting, this
tool attempts to only correct the style in diff hunks that you touch.
This should make the cosmetic changes small enough that we can mix them
with functional changes without destroying the diffs, and there's an
escape hatch for separating the reformatting to a second commit for
purists and cases where it hurts readability.

At this time, the script requires a clean working tree, so run it after
you've commited your changes. Run without arguments, the style
corrections will be applied and left unstaged in your working copy. It
also supports the --amend option, which will automatically amend your
HEAD with the corrected style, and --commit, which will create a new
change dependent on your HEAD that contains only the whitespace changes.

There are a number of ways this could be applied in an automated manner
if this proves to be useful, either on a project-wide or per-user
basis. This doesn't buy anything in terms of real code quality, the
intent here would be to keep formatting nits out of review comments in
favor of more meaningful ones and help people whose habitual style
doesn't match the baseline.

Requires astyle[1] 1.24 or newer.

Change-Id: I2fb3434de8479655e9811f094029bb90e5d757e1
parent e9cacfd6
usage() {
cat <<EOF >&2
Usage: $self [option]
This script applies a whitespace transformation to the commit at HEAD. If no
options are given, then the modified files are left in the working tree.
-n, --dry-run Shows a diff of the changes to be made.
--amend Squashes the changes into the commit at HEAD
--commit Creates a new commit containing only the whitespace changes
rm -f ${CLEAN_FILES}
exit 1
log() {
echo "${self##*/}: $@" >&2
vpx_style() {
astyle --style=bsd --min-conditional-indent=0 --break-blocks \
--pad-oper --pad-header --unpad-paren \
--align-pointer=name \
--indent-preprocessor --convert-tabs --indent-labels \
--suffix=none --quiet "$@"
sed -i 's/[[:space:]]\{1,\},/,/g' "$@"
apply() {
patch -p1 < "$1"
commit() {
LAST_CHANGEID=$(git show | awk '/Change-Id:/{print $2}')
if [ -z "$LAST_CHANGEID" ]; then
log "HEAD doesn't have a Change-Id, unable to generate a new commit"
exit 1
# Build a deterministic Change-Id from the parent's
NEW_CHANGEID=I$(echo $NEW_CHANGEID | git hash-object --stdin)
# Commit, preserving authorship from the parent commit.
git commit -a -C HEAD > /dev/null
git commit --amend -F- << EOF
Cosmetic: Fix whitespace in change ${LAST_CHANGEID:0:9}
Change-Id: ${NEW_CHANGEID}
amend() {
git commit -a --amend -C HEAD
# Temporary files
# Preconditions
[ $# -lt 2 ] || usage
if ! git diff --quiet HEAD; then
log "Working tree is dirty, commit your changes first"
exit 1
# Need to be in the root
cd "$(git rev-parse --show-toplevel)"
# Collect the original diff
git show > "${ORIG_DIFF}"
# Apply the style guide on the modified files and collect its diff
for f in $(git diff HEAD^ --name-only | grep '\.[ch]$'); do
case "$f" in
third_party/*) continue;;
nestegg/*) continue;;
vpx_style "$f"
git diff --no-color --no-ext-diff > "${MODIFIED_DIFF}"
# Intersect the two diffs
$(dirname ${self})/ \
git reset --hard >/dev/null
if [ $INTERSECT_RESULT -eq 0 ]; then
# Handle options
if [ -n "$1" ]; then
case "$1" in
-h|--help) usage;;
-n|--dry-run) cat "${FINAL_DIFF}";;
--commit) apply "${FINAL_DIFF}"; commit;;
--amend) apply "${FINAL_DIFF}"; amend;;
*) usage;;
apply "${FINAL_DIFF}"
if ! git diff --quiet; then
log "Formatting changes applied, verify and commit."
log "See also:"
git diff --stat
rm -f ${CLEAN_FILES}
#!/usr/bin/env python
## Copyright (c) 2012 The WebM project authors. All Rights Reserved.
## Use of this source code is governed by a BSD-style license
## that can be found in the LICENSE file in the root of the source
## tree. An additional intellectual property rights grant can be found
## in the file PATENTS. All contributing project authors may
## be found in the AUTHORS file in the root of the source tree.
"""Calculates the "intersection" of two unified diffs.
Given two diffs, A and B, it finds all hunks in B that had non-context lines
in A and prints them to stdout. This is useful to determine the hunks in B that
are relevant to A. The resulting file can be applied with patch(1) on top of A.
__author__ = ""
import re
import sys
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] == " ":
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
def FormatDiffHunks(hunks):
"""Re-serialize a list of DiffHunks."""
r = []
last_header = None
for hunk in hunks:
this_header = hunk.header[0:2]
if last_header != this_header:
last_header = this_header
return "".join(r)
def ZipHunks(rhs_hunks, lhs_hunks):
"""Join two hunk lists on filename."""
for rhs_hunk in rhs_hunks:
rhs_file = rhs_hunk.right.filename.split("/")[1:]
for lhs_hunk in lhs_hunks:
lhs_file = lhs_hunk.left.filename.split("/")[1:]
if lhs_file != rhs_file:
yield (rhs_hunk, lhs_hunk)
def main():
old_hunks = [x for x in ParseDiffHunks(open(sys.argv[1], "r"))]
new_hunks = [x for x in ParseDiffHunks(open(sys.argv[2], "r"))]
out_hunks = []
# Join the right hand side of the older diff with the left hand side of the
# newer diff.
for old_hunk, new_hunk in ZipHunks(old_hunks, new_hunks):
if new_hunk in out_hunks:
old_lines = old_hunk.right
new_lines = new_hunk.left
# Determine if this hunk overlaps any non-context line from the other
for i in old_lines.delta_line_nums:
if i in new_lines:
if out_hunks:
print FormatDiffHunks(out_hunks)
if __name__ == "__main__":
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment