[PATCH 5/6] scripts/spdxcheck.py: keep track on what line SPDX header was found

[Mauro Carvalho Chehab]

According with Documentation/process/license-rules.rst, SPDX headers
can be found only at the first lines.

However, this script doesn't enforce it, and several files violate
that. It could be useful to be able to show a histogram with the
number of files that have the SPDX header on each line number.

This feature is optional, enabled with -H or --histogram.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@xxxxxxxxxx>
---
 scripts/spdxcheck.py | 37 ++++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py
index 6374e078a5f2..c969b050366f 100755
--- a/scripts/spdxcheck.py
+++ b/scripts/spdxcheck.py
@@ -189,7 +189,9 @@ class id_parser(object):
                 # Should we check for more SPDX ids in the same file and
                 # complain if there are any?
                 #
-                break
+                return self.curline - 1
+
+            return -1
 
         except ParserException as pe:
             if pe.tok:
@@ -200,7 +202,7 @@ class id_parser(object):
                 sys.stdout.write('%s: %d:0 %s\n' %(fname, self.curline, col, pe.txt))
             self.spdx_errors += 1
 
-def scan_git_tree(tree):
+def scan_git_tree(ln_count, tree):
     for el in tree.traverse():
         # Exclude stuff which would make pointless noise
         # FIXME: Put this somewhere more sensible
@@ -211,12 +213,15 @@ def scan_git_tree(tree):
         if not os.path.isfile(el.path):
             continue
         with open(el.path, 'rb') as fd:
-            parser.parse_lines(fd, args.maxlines, el.path)
+            ln = parser.parse_lines(fd, args.maxlines, el.path)
+            if ln >= 0:
+                ln_count[ln] += 1;
+    return ln_count
 
-def scan_git_subtree(tree, path):
+def scan_git_subtree(ln_count, tree, path):
     for p in path.strip('/').split('/'):
         tree = tree[p]
-    scan_git_tree(tree)
+    scan_git_tree(ln_count, tree)
 
 if __name__ == '__main__':
 
@@ -225,6 +230,7 @@ if __name__ == '__main__':
     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')
+    ap.add_argument('-H', '--histogram', action='store_true', help='Verbose histogram about SPDX header position')
     args = ap.parse_args()
 
     # Sanity check path arguments
@@ -255,23 +261,31 @@ if __name__ == '__main__':
         sys.stderr.write('%s\n' %traceback.format_exc())
         sys.exit(1)
 
+    ln_count= [0] * args.maxlines
+
     try:
         if len(args.path) and args.path[0] == '-':
             stdin = os.fdopen(sys.stdin.fileno(), 'rb')
-            parser.parse_lines(stdin, args.maxlines, '-')
+            ln = parser.parse_lines(stdin, args.maxlines, '-')
+            if ln >= 0:
+                ln_count[ln] += 1;
+
         else:
             if args.path:
                 for p in args.path:
                     if os.path.isfile(p):
-                        parser.parse_lines(open(p, 'rb'), args.maxlines, p)
+                        ln = parser.parse_lines(open(p, 'rb'), args.maxlines, p)
+                        if ln >= 0:
+                            ln_count[ln] += 1;
+
                     elif os.path.isdir(p):
-                        scan_git_subtree(repo.head.reference.commit.tree, p)
+                        scan_git_subtree(ln_count, repo.head.reference.commit.tree, p)
                     else:
                         sys.stderr.write('path %s does not exist\n' %p)
                         sys.exit(1)
             else:
                 # Full git tree scan
-                scan_git_tree(repo.head.commit.tree)
+                scan_git_tree(ln_count, repo.head.commit.tree)
 
             if args.verbose:
                 sys.stderr.write('\n')
@@ -284,6 +298,11 @@ if __name__ == '__main__':
                 sys.stderr.write('Lines checked:     %12d\n' %parser.lines_checked)
                 sys.stderr.write('Files with SPDX:   %12d\n' %parser.spdx_valid)
                 sys.stderr.write('Files with errors: %12d\n' %parser.spdx_errors)
+                sys.stderr.write('\n')
+            if args.histogram:
+                for i in range(0, len(ln_count)):
+                    if ln_count[i] > 0:
+                        sys.stderr.write('Files with SPDX at line #%-5d:   %12d\n' % (i + 1, ln_count[i]))
 
             sys.exit(0)
 
-- 
2.21.0