Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <20220516102615.651153597@linutronix.de>
From:   Thomas Gleixner <tglx@linutronix.de>
To:     LKML <linux-kernel@vger.kernel.org>
Cc:     linux-spdx@vger.kernel.org,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Christoph Hellwig <hch@lst.de>
Subject: [patch 4/9] scripts/spdxcheck: Add option to display files without SPDX
References: <20220516101901.475557433@linutronix.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Date:   Mon, 16 May 2022 12:27:27 +0200 (CEST)
Precedence: bulk

Makes life easier when chasing the missing ones. Is activated with '-f'
on the command line.

# scripts/spdxcheck.py -f kernel/
Files without SPDX:
    ./kernel/cpu.c
    ./kernel/kmod.c
    ./kernel/relay.c
    ./kernel/bpf/offload.c
    ./kernel/bpf/preload/.gitignore
    ./kernel/bpf/preload/iterators/README
    ./kernel/bpf/ringbuf.c
    ./kernel/cgroup/cgroup.c
    ./kernel/cgroup/cpuset.c
    ./kernel/cgroup/legacy_freezer.c
    ./kernel/debug/debug_core.h
    ./kernel/debug/kdb/Makefile
    ./kernel/debug/kdb/kdb_bp.c
    ./kernel/debug/kdb/kdb_bt.c
    ./kernel/debug/kdb/kdb_cmds
    ./kernel/debug/kdb/kdb_debugger.c
    ./kernel/debug/kdb/kdb_io.c
    ./kernel/debug/kdb/kdb_keyboard.c
    ./kernel/debug/kdb/kdb_main.c
    ./kernel/debug/kdb/kdb_private.h
    ./kernel/debug/kdb/kdb_support.c
    ./kernel/locking/lockdep_states.h
    ./kernel/locking/mutex-debug.c
    ./kernel/locking/spinlock_debug.c
    ./kernel/sched/pelt.h

With the optional -D parameter the directory depth can be limited:

# scripts/spdxcheck.py -f -D 0 kernel/
Files without SPDX:
    ./kernel/cpu.c
    ./kernel/kmod.c
    ./kernel/relay.c

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 scripts/spdxcheck.py |   21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

--- a/scripts/spdxcheck.py
+++ b/scripts/spdxcheck.py
@@ -32,10 +32,16 @@ import os
     def __init__(self):
         self.missing = 0
         self.total = 0
+        self.files = []
 
-    def update(self, miss):
+    def update(self, fname, basedir, miss):
         self.total += 1
         self.missing += miss
+        if miss:
+            fname = './' + fname
+            bdir = os.path.dirname(fname)
+            if bdir == basedir.rstrip('/'):
+                self.files.append(fname)
 
 # Read the spdx data from the LICENSES directory
 def read_spdxdata(repo):
@@ -245,7 +251,7 @@ import os
         base += '/'
 
         di = self.spdx_dirs.get(base, dirinfo())
-        di.update(fail)
+        di.update(fname, base, fail)
         self.spdx_dirs[base] = di
 
 def scan_git_tree(tree, basedir, dirdepth):
@@ -275,6 +281,8 @@ import os
                     help='Show [sub]directory statistics.')
     ap.add_argument('-D', '--depth', type=int, default=-1,
                     help='Directory depth for -d statistics. Default: unlimited')
+    ap.add_argument('-f', '--files', action='store_true',
+                    help='Show files without SPDX.')
     ap.add_argument('-m', '--maxlines', type=int, default=15,
                     help='Maximum number of lines to scan in a file. Default 15')
     ap.add_argument('-v', '--verbose', action='store_true', help='Verbose statistics output')
@@ -364,6 +372,15 @@ import os
                         pc = int(100 * valid / di.total)
                         sys.stderr.write('    %-80s: %5d of %5d  %3d%%\n' %(f, valid, di.total, pc))
 
+            if ndirs and ndirs != dirsok and args.files:
+                if args.verbose or args.dirs:
+                    sys.stderr.write('\n')
+                sys.stderr.write('Files without SPDX:\n')
+                for f in sorted(parser.spdx_dirs.keys()):
+                    di = parser.spdx_dirs[f]
+                    for f in sorted(di.files):
+                        sys.stderr.write('    %s\n' %f)
+
             sys.exit(0)
 
     except Exception as ex: