[PATCH 17/18] docs: kdoc_re: make NestedMatch use KernRe

From: Mauro Carvalho Chehab

Date: Mon Mar 02 2026 - 11:59:56 EST


Instead of using re_compile, let's create the class with the
regex and use KernRe to keep it cached.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@xxxxxxxxxx>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@xxxxxxxxx>
---
tools/lib/python/kdoc/kdoc_parser.py | 25 ++++++++++++-------------
tools/lib/python/kdoc/kdoc_re.py | 24 +++++++++++++++++-------
2 files changed, 29 insertions(+), 20 deletions(-)

diff --git a/tools/lib/python/kdoc/kdoc_parser.py b/tools/lib/python/kdoc/kdoc_parser.py
index 0f90c16cb51a..cd9857906a2b 100644
--- a/tools/lib/python/kdoc/kdoc_parser.py
+++ b/tools/lib/python/kdoc/kdoc_parser.py
@@ -75,17 +75,17 @@ doc_begin_func = KernRe(str(doc_com) + # initial " * '
# is allowed.
#
struct_nested_prefixes = [
- (re.compile(r"__cond_acquires\s*\("), ""),
- (re.compile(r"__cond_releases\s*\("), ""),
- (re.compile(r"__acquires\s*\("), ""),
- (re.compile(r"__releases\s*\("), ""),
- (re.compile(r"__must_hold\s*\("), ""),
- (re.compile(r"__must_not_hold\s*\("), ""),
- (re.compile(r"__must_hold_shared\s*\("), ""),
- (re.compile(r"__cond_acquires_shared\s*\("), ""),
- (re.compile(r"__acquires_shared\s*\("), ""),
- (re.compile(r"__releases_shared\s*\("), ""),
- (re.compile(r'\bSTRUCT_GROUP\('), r'\0'),
+ (NestedMatch(r"__cond_acquires\s*\("), ""),
+ (NestedMatch(r"__cond_releases\s*\("), ""),
+ (NestedMatch(r"__acquires\s*\("), ""),
+ (NestedMatch(r"__releases\s*\("), ""),
+ (NestedMatch(r"__must_hold\s*\("), ""),
+ (NestedMatch(r"__must_not_hold\s*\("), ""),
+ (NestedMatch(r"__must_hold_shared\s*\("), ""),
+ (NestedMatch(r"__cond_acquires_shared\s*\("), ""),
+ (NestedMatch(r"__acquires_shared\s*\("), ""),
+ (NestedMatch(r"__releases_shared\s*\("), ""),
+ (NestedMatch(r'\bSTRUCT_GROUP\('), r'\0'),
]

#
@@ -761,9 +761,8 @@ class KernelDoc:
members = trim_private_members(members)
members = self.xforms.apply("struct", members)

- nested = NestedMatch()
for search, sub in struct_nested_prefixes:
- members = nested.sub(search, sub, members)
+ members = search.sub(search, sub, members)
#
# Deal with embedded struct and union members, and drop enums entirely.
#
diff --git a/tools/lib/python/kdoc/kdoc_re.py b/tools/lib/python/kdoc/kdoc_re.py
index ea4f6f3d9e42..085b89a4547c 100644
--- a/tools/lib/python/kdoc/kdoc_re.py
+++ b/tools/lib/python/kdoc/kdoc_re.py
@@ -200,7 +200,10 @@ class NestedMatch:
#
# FOO(arg1, arg2, arg3)

- def _search(self, regex, line):
+ def __init__(self, regex):
+ self.regex = KernRe(regex)
+
+ def _search(self, line):
"""
Finds paired blocks for a regex that ends with a delimiter.

@@ -222,7 +225,7 @@ class NestedMatch:

stack = []

- for match_re in regex.finditer(line):
+ for match_re in self.regex.finditer(line):
start = match_re.start()
offset = match_re.end()
string_char = None
@@ -270,7 +273,7 @@ class NestedMatch:
yield start, offset, pos + 1
break

- def search(self, regex, line):
+ def search(self, line):
"""
This is similar to re.search:

@@ -278,12 +281,12 @@ class NestedMatch:
returning occurrences only if all delimiters are paired.
"""

- for t in self._search(regex, line):
+ for t in self._search(line):

yield line[t[0]:t[2]]

- def sub(self, regex, sub, line, count=0):
- r"""
+ def sub(self, sub, line, count=0):
+ """
This is similar to re.sub:

It matches a regex that it is followed by a delimiter,
@@ -304,7 +307,7 @@ class NestedMatch:
cur_pos = 0
n = 0

- for start, end, pos in self._search(regex, line):
+ for start, end, pos in self._search(line):
out += line[cur_pos:start]

# Value, ignoring start/end delimiters
@@ -331,3 +334,10 @@ class NestedMatch:
out += line[cur_pos:l]

return out
+
+ def __repr__(self):
+ """
+ Returns a displayable version of the class init.
+ """
+
+ return f'NestedMatch("{self.regex.regex.pattern}")'
--
2.52.0