[PATCH v3] checkkconfigsymbols.py: make it Git aware

[Valentin Rothberg]

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@xxxxxxxxx>
---
Changelog for v2:
* To avoid losing data with 'git reset --hard' the script aborts in dirty
  trees.
* Added option --force to force hard resets and ignore aborts in dirty trees.
* Reset to initial HEAD in the end.
* Some minor code refactoring.

Changelog for v3:
* I accidentally sent the wrong state for v2.  Now the patch corresponds to the
  changelog for v2.  Thanks for catching, Stefan!
---
 scripts/checkkconfigsymbols.py | 138 +++++++++++++++++++++++++++++++++++++++--
 1 file changed, 132 insertions(+), 6 deletions(-)

diff --git a/scripts/checkkconfigsymbols.py b/scripts/checkkconfigsymbols.py
index 6445693df669..ce9ca60808b8 100755
--- a/scripts/checkkconfigsymbols.py
+++ b/scripts/checkkconfigsymbols.py
@@ -1,6 +1,6 @@
 #!/usr/bin/env python
 
-"""Find Kconfig identifiers that are referenced but not defined."""
+"""Find Kconfig symbols that are referenced but not defined."""
 
 # (c) 2014-2015 Valentin Rothberg <Valentin.Rothberg@xxxxxxx>
 # (c) 2014 Stefan Hengelein <stefan.hengelein@xxxxxx>
@@ -10,7 +10,9 @@
 
 import os
 import re
+import sys
 from subprocess import Popen, PIPE, STDOUT
+from optparse import OptionParser
 
 
 # regex expressions
@@ -32,16 +34,140 @@ 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
-    pop = Popen("git ls-files", stdout=PIPE, stderr=STDOUT, shell=True)
-    (stdout, _) = pop.communicate()  # wait until finished
+    stdout = execute("git ls-files")
     if len(stdout) > 0 and stdout[-1] == "\n":
         stdout = stdout[:-1]
 
@@ -62,7 +188,7 @@ def main():
     for kfile in kconfig_files:
         parse_kconfig_file(kfile, defined_features, referenced_features)
 
-    print "Undefined symbol used\tFile list"
+    undefined = {}  # {feature: [files]}
     for feature in sorted(referenced_features):
         # filter some false positives
         if feature == "FOO" or feature == "BAR" or \
@@ -73,8 +199,8 @@ def main():
                 # avoid false positives for kernel modules
                 if feature[:-len("_MODULE")] in defined_features:
                     continue
-            files = referenced_features.get(feature)
-            print "%s\t%s" % (feature, ", ".join(files))
+            undefined[feature] = referenced_features.get(feature)
+    return undefined
 
 
 def parse_source_file(sfile, referenced_features):
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/