tor

commit 43f163de80864a4918b1566c3fbc0b73aac6a327
parent f93057fc0ae7308c85a888599643d2dc369444de
Author: Nick Mathewson <nickm@torproject.org>
Date:   Wed, 17 Jul 2019 14:30:12 +0200

Practracker: improve exclude-directory logic

Instead of excluding directories at the last minute if they happen
to appear in our filenames, we exclude them early, before recursing
into all their subdirectories.

Part of 29746.

Diffstat:
M
scripts/maint/practracker/util.py
 | 
14
++++++++++----

1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/scripts/maint/practracker/util.py b/scripts/maint/practracker/util.py
@@ -2,15 +2,24 @@ import os
 
 # We don't want to run metrics for unittests, automatically-generated C files,
 # external libraries or git leftovers.
-EXCLUDE_SOURCE_DIRS = {"/src/test/", "/src/trunnel/", "/src/ext/", "/.git/"}
+EXCLUDE_SOURCE_DIRS = {"src/test/", "src/trunnel/", "src/rust/",
+                       "src/ext/", ".git/"}
+
+def _norm(p):
+    return os.path.normcase(os.path.normpath(p))
 
 def get_tor_c_files(tor_topdir):
     """
     Return a list with the .c filenames we want to get metrics of.
     """
     files_list = []
+    exclude_dirs = { _norm(os.path.join(tor_topdir, p)) for p in EXCLUDE_SOURCE_DIRS }
+
 
     for root, directories, filenames in os.walk(tor_topdir):
+        # Remove all the directories that are excluded.
+        directories[:] = [ d for d in directories
+                           if _norm(os.path.join(root,d)) not in exclude_dirs ]
         directories.sort()
         filenames.sort()
         for filename in filenames:
@@ -18,10 +27,7 @@ def get_tor_c_files(tor_topdir):
             if not filename.endswith(".c"):
                 continue
 
-            # Exclude the excluded paths
             full_path = os.path.join(root,filename)
-            if any(os.path.normcase(exclude_dir) in full_path for exclude_dir in EXCLUDE_SOURCE_DIRS):
-                continue
 
             files_list.append(full_path)