[PATCH v2 06/20] docs: kdoc: use tokenizer to handle comments on structs

[Mauro Carvalho Chehab <mchehab+huawei@kernel.org>]

Better handle comments inside structs. After those changes,
all unittests now pass:

  test_private:
    TestPublicPrivate:
        test balanced_inner_private:                                 OK
        test balanced_non_greddy_private:                            OK
        test balanced_private:                                       OK
        test no private:                                             OK
        test unbalanced_inner_private:                               OK
        test unbalanced_private:                                     OK
        test unbalanced_struct_group_tagged_with_private:            OK
        test unbalanced_two_struct_group_tagged_first_with_private:  OK
        test unbalanced_without_end_of_line:                         OK

  Ran 9 tests

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Message-ID: <f83ee9e8c38407eaab6ad10d4ccf155fb36683cc.1773074166.git.mchehab+huawei@kernel.org>
---
 tools/lib/python/kdoc/kdoc_parser.py | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/tools/lib/python/kdoc/kdoc_parser.py b/tools/lib/python/kdoc/kdoc_parser.py
index 4b3c555e6c8e..6b181ead3175 100644
--- a/tools/lib/python/kdoc/kdoc_parser.py
+++ b/tools/lib/python/kdoc/kdoc_parser.py
@@ -13,7 +13,7 @@ import sys
 import re
 from pprint import pformat
 
-from kdoc.kdoc_re import NestedMatch, KernRe
+from kdoc.kdoc_re import NestedMatch, KernRe, CTokenizer
 from kdoc.kdoc_item import KdocItem
 
 #
@@ -84,15 +84,9 @@ def trim_private_members(text):
     """
     Remove ``struct``/``enum`` members that have been marked "private".
     """
-    # First look for a "public:" block that ends a private region, then
-    # handle the "private until the end" case.
-    #
-    text = KernRe(r'/\*\s*private:.*?/\*\s*public:.*?\*/', flags=re.S).sub('', text)
-    text = KernRe(r'/\*\s*private:.*', flags=re.S).sub('', text)
-    #
-    # We needed the comments to do the above, but now we can take them out.
-    #
-    return KernRe(r'\s*/\*.*?\*/\s*', flags=re.S).sub('', text).strip()
+
+    tokens = CTokenizer(text)
+    return str(tokens)
 
 class state:
     """
-- 
2.53.0