linux/scripts/checkkconfigsymbols.py
Valentin Rothberg b1a3f24348 checkkconfigsymbols.py: make it Git aware
The script now supports to check a specified commit or a specified range
of commits (i.e., commit1..commit2).  Developers and maintainers are
encouraged to use this functionality before sending or merging patches
to avoid potential bugs and to keep the code, documentation, etc. clean.

This patch adds the following options to the script:

 -c COMMIT, --commit=COMMIT
                  Check if the specified commit (hash) introduces
                  undefined Kconfig symbols.

 -d DIFF, --diff=DIFF
                  Diff undefined symbols between two commits.  The input
                  format bases on Git log's 'commmit1..commit2'.

  --force         Reset current Git tree even when it's dirty.

Note that the first two options require to 'git reset --hard' the user's
Git tree.  This hard reset is necessary to keep the script fast, but it
can lead to the loss of uncommitted data.  Hence, the script aborts in
case it is executed in a dirty tree.  It won't abort if '--force' is
passed.

If neither -c nor -d is specified, the script defaults to check the
entire local tree (i.e., the previous behavior).

Signed-off-by: Valentin Rothberg <valentinrothberg@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-03-16 21:10:28 +01:00

267 lines
9.1 KiB
Python
Executable File

#!/usr/bin/env python
"""Find Kconfig symbols that are referenced but not defined."""
# (c) 2014-2015 Valentin Rothberg <Valentin.Rothberg@lip6.fr>
# (c) 2014 Stefan Hengelein <stefan.hengelein@fau.de>
#
# Licensed under the terms of the GNU GPL License version 2
import os
import re
import sys
from subprocess import Popen, PIPE, STDOUT
from optparse import OptionParser
# regex expressions
OPERATORS = r"&|\(|\)|\||\!"
FEATURE = r"(?:\w*[A-Z0-9]\w*){2,}"
DEF = r"^\s*(?:menu){,1}config\s+(" + FEATURE + r")\s*"
EXPR = r"(?:" + OPERATORS + r"|\s|" + FEATURE + r")+"
STMT = r"^\s*(?:if|select|depends\s+on)\s+" + EXPR
SOURCE_FEATURE = r"(?:\W|\b)+[D]{,1}CONFIG_(" + FEATURE + r")"
# regex objects
REGEX_FILE_KCONFIG = re.compile(r".*Kconfig[\.\w+\-]*$")
REGEX_FEATURE = re.compile(r"(" + FEATURE + r")")
REGEX_SOURCE_FEATURE = re.compile(SOURCE_FEATURE)
REGEX_KCONFIG_DEF = re.compile(DEF)
REGEX_KCONFIG_EXPR = re.compile(EXPR)
REGEX_KCONFIG_STMT = re.compile(STMT)
REGEX_KCONFIG_HELP = re.compile(r"^\s+(help|---help---)\s*$")
REGEX_FILTER_FEATURES = re.compile(r"[A-Za-z0-9]$")
def parse_options():
"""The user interface of this module."""
usage = "%prog [options]\n\n" \
"Run this tool to detect Kconfig symbols that are referenced but " \
"not defined in\nKconfig. The output of this tool has the " \
"format \'Undefined symbol\\tFile list\'\n\n" \
"If no option is specified, %prog will default to check your\n" \
"current tree. Please note that specifying commits will " \
"\'git reset --hard\'\nyour current tree! You may save " \
"uncommitted changes to avoid losing data."
parser = OptionParser(usage=usage)
parser.add_option('-c', '--commit', dest='commit', action='store',
default="",
help="Check if the specified commit (hash) introduces "
"undefined Kconfig symbols.")
parser.add_option('-d', '--diff', dest='diff', action='store',
default="",
help="Diff undefined symbols between two commits. The "
"input format bases on Git log's "
"\'commmit1..commit2\'.")
parser.add_option('', '--force', dest='force', action='store_true',
default=False,
help="Reset current Git tree even when it's dirty.")
(opts, _) = parser.parse_args()
if opts.commit and opts.diff:
sys.exit("Please specify only one option at once.")
if opts.diff and not re.match(r"^[\w\-\.]+\.\.[\w\-\.]+$", opts.diff):
sys.exit("Please specify valid input in the following format: "
"\'commmit1..commit2\'")
if opts.commit or opts.diff:
if not opts.force and tree_is_dirty():
sys.exit("The current Git tree is dirty (see 'git status'). "
"Running this script may\ndelete important data since it "
"calls 'git reset --hard' for some performance\nreasons. "
" Please run this script in a clean Git tree or pass "
"'--force' if you\nwant to ignore this warning and "
"continue.")
return opts
def main():
"""Main function of this module."""
opts = parse_options()
if opts.commit or opts.diff:
head = get_head()
# get commit range
commit_a = None
commit_b = None
if opts.commit:
commit_a = opts.commit + "~"
commit_b = opts.commit
elif opts.diff:
split = opts.diff.split("..")
commit_a = split[0]
commit_b = split[1]
undefined_a = {}
undefined_b = {}
# get undefined items before the commit
execute("git reset --hard %s" % commit_a)
undefined_a = check_symbols()
# get undefined items for the commit
execute("git reset --hard %s" % commit_b)
undefined_b = check_symbols()
# report cases that are present for the commit but not before
for feature in undefined_b:
# feature has not been undefined before
if not feature in undefined_a:
files = undefined_b.get(feature)
print "%s\t%s" % (feature, ", ".join(files))
# check if there are new files that reference the undefined feature
else:
files = undefined_b.get(feature) - undefined_a.get(feature)
if files:
print "%s\t%s" % (feature, ", ".join(files))
# reset to head
execute("git reset --hard %s" % head)
# default to check the entire tree
else:
undefined = check_symbols()
for feature in undefined:
files = undefined.get(feature)
def execute(cmd):
"""Execute %cmd and return stdout. Exit in case of error."""
pop = Popen(cmd, stdout=PIPE, stderr=STDOUT, shell=True)
(stdout, _) = pop.communicate() # wait until finished
if pop.returncode != 0:
sys.exit(stdout)
return stdout
def tree_is_dirty():
"""Return true if the current working tree is dirty (i.e., if any file has
been added, deleted, modified, renamed or copied but not committed)."""
stdout = execute("git status --porcelain")
for line in stdout:
if re.findall(r"[URMADC]{1}", line[:2]):
return True
return False
def get_head():
"""Return commit hash of current HEAD."""
stdout = execute("git rev-parse HEAD")
return stdout.strip('\n')
def check_symbols():
"""Find undefined Kconfig symbols and return a dict with the symbol as key
and a list of referencing files as value."""
source_files = []
kconfig_files = []
defined_features = set()
referenced_features = dict() # {feature: [files]}
# use 'git ls-files' to get the worklist
stdout = execute("git ls-files")
if len(stdout) > 0 and stdout[-1] == "\n":
stdout = stdout[:-1]
for gitfile in stdout.rsplit("\n"):
if ".git" in gitfile or "ChangeLog" in gitfile or \
".log" in gitfile or os.path.isdir(gitfile) or \
gitfile.startswith("tools/"):
continue
if REGEX_FILE_KCONFIG.match(gitfile):
kconfig_files.append(gitfile)
else:
# all non-Kconfig files are checked for consistency
source_files.append(gitfile)
for sfile in source_files:
parse_source_file(sfile, referenced_features)
for kfile in kconfig_files:
parse_kconfig_file(kfile, defined_features, referenced_features)
undefined = {} # {feature: [files]}
for feature in sorted(referenced_features):
# filter some false positives
if feature == "FOO" or feature == "BAR" or \
feature == "FOO_BAR" or feature == "XXX":
continue
if feature not in defined_features:
if feature.endswith("_MODULE"):
# avoid false positives for kernel modules
if feature[:-len("_MODULE")] in defined_features:
continue
undefined[feature] = referenced_features.get(feature)
return undefined
def parse_source_file(sfile, referenced_features):
"""Parse @sfile for referenced Kconfig features."""
lines = []
with open(sfile, "r") as stream:
lines = stream.readlines()
for line in lines:
if not "CONFIG_" in line:
continue
features = REGEX_SOURCE_FEATURE.findall(line)
for feature in features:
if not REGEX_FILTER_FEATURES.search(feature):
continue
sfiles = referenced_features.get(feature, set())
sfiles.add(sfile)
referenced_features[feature] = sfiles
def get_features_in_line(line):
"""Return mentioned Kconfig features in @line."""
return REGEX_FEATURE.findall(line)
def parse_kconfig_file(kfile, defined_features, referenced_features):
"""Parse @kfile and update feature definitions and references."""
lines = []
skip = False
with open(kfile, "r") as stream:
lines = stream.readlines()
for i in range(len(lines)):
line = lines[i]
line = line.strip('\n')
line = line.split("#")[0] # ignore comments
if REGEX_KCONFIG_DEF.match(line):
feature_def = REGEX_KCONFIG_DEF.findall(line)
defined_features.add(feature_def[0])
skip = False
elif REGEX_KCONFIG_HELP.match(line):
skip = True
elif skip:
# ignore content of help messages
pass
elif REGEX_KCONFIG_STMT.match(line):
features = get_features_in_line(line)
# multi-line statements
while line.endswith("\\"):
i += 1
line = lines[i]
line = line.strip('\n')
features.extend(get_features_in_line(line))
for feature in set(features):
paths = referenced_features.get(feature, set())
paths.add(kfile)
referenced_features[feature] = paths
if __name__ == "__main__":
main()