checkkconfigsymbols.sh: reimplementation in python

#!/usr/bin/env python

"""Find Kconfig identifieres that are referenced but not defined."""

# Copyright (C) 2014 Valentin Rothberg <valentinrothberg@gmail.com>

# Copyright (C) 2014 Stefan Hengelein <stefan.hengelein@fau.de>

#

# This program is free software; you can redistribute it and/or modify it

# under the terms and conditions of the GNU General Public License,

# version 2, as published by the Free Software Foundation.

#

# This program is distributed in the hope it will be useful, but WITHOUT

# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for

# more details.

import os

import re

from subprocess import Popen, PIPE, STDOUT

# REGEX EXPRESSIONS

OPERATORS = r"&|\(|\)|\||\!"

FEATURE = r"\w*[A-Z]{1}\w*"

CONFIG_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

# REGEX OBJECTS

REGEX_FILE_KCONFIG = re.compile(r".*Kconfig[\.\w+\-]*$")

REGEX_FEATURE = re.compile(r"(" + FEATURE + r")")

REGEX_SOURCE_FEATURE = re.compile(r"(?:D|\W|\b)+CONFIG_(" + FEATURE + r")")

REGEX_KCONFIG_DEF = re.compile(CONFIG_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 main():

    """Main function of this module."""

    source_files = []

    kconfig_files = []

    defined_features = set()

    referenced_features = dict()

    # use 'git ls-files' to get the worklist

    pop = Popen("git ls-files", stdout=PIPE, stderr=STDOUT, shell=True)

    (stdout, _) = pop.communicate()  # wait until finished

    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 \

                os.path.isdir(gitfile):

            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)

    print "Undefined symbol used\tFile list"

    for feature in sorted(referenced_features):

        if feature not in defined_features:

            if feature.endswith("_MODULE"):

                # Avoid false positives for kernel modules

                if feature[:-len("_MODULE")] in defined_features:

                    continue

            if "FOO" in feature or "BAR" in feature:

                continue

            files = referenced_features.get(feature)

            print "%s:\t%s" % (feature, ", ".join(files))

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

            paths = referenced_features.get(feature, set())

            paths.add(sfile)

            referenced_features[feature] = paths

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 Kconfig 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()

#!/bin/sh

# Find Kconfig variables used in source code but never defined in Kconfig

# Copyright (C) 2007, Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>

# Tested with dash.

paths="$@"

[ -z "$paths" ] && paths=.

# Doing this once at the beginning saves a lot of time, on a cache-hot tree.

Kconfigs="`find . -name 'Kconfig' -o -name 'Kconfig*[^~]'`"

printf "File list \tundefined symbol used\n"

find $paths -name '*.[chS]' -o -name 'Makefile' -o -name 'Makefile*[^~]'| while read i

do

	# Output the bare Kconfig variable and the filename; the _MODULE part at

	# the end is not removed here (would need perl an not-hungry regexp for that).

	sed -ne 's!^.*\<\(UML_\)\?CONFIG_\([0-9A-Za-z_]\+\).*!\2 '$i'!p' < $i

done | \

# Smart "sort|uniq" implemented in awk and tuned to collect the names of all

# files which use a given symbol

awk '{map[$1, count[$1]++] = $2; }

END {

	for (combIdx in map) {

		split(combIdx, separate, SUBSEP);

		# The value may have been removed.

		if (! ( (separate[1], separate[2]) in map ) )

			continue;

		symb=separate[1];

		printf "%s ", symb;

		#Use gawk extension to delete the names vector

		delete names;

		#Portably delete the names vector

		#split("", names);

		for (i=0; i < count[symb]; i++) {

			names[map[symb, i]] = 1;

			# Unfortunately, we may still encounter symb, i in the

			# outside iteration.

			delete map[symb, i];

		}

		i=0;

		for (name in names) {

			if (i > 0)

				printf ", %s", name;

			else

				printf "%s", name;

			i++;

		}

		printf "\n";

	}

}' |

while read symb files; do

	# Remove the _MODULE suffix when checking the variable name. This should

	# be done only on tristate symbols, actually, but Kconfig parsing is

	# beyond the purpose of this script.

	symb_bare=`echo $symb | sed -e 's/_MODULE//'`

	if ! grep -q "\<$symb_bare\>" $Kconfigs; then

		printf "$files: \t$symb\n"

	fi

done|sort