From nobody Tue Apr 7 16:20:27 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id C600137CD30; Thu, 12 Mar 2026 14:55:01 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773327301; cv=none; b=YZ1NfW3+5+Tx5J2iYA8etrs6g9AifUGgCjUPp5MiGwgW12/uIpvI/pEgJR3tk8MRyIjz02SmExVHL9v0ZVA/ifUf88jWgIt9EnLkP0qMJXX7eFhZROfb/7tz7lSXCmzYxc4X/etXVKoh0s8Lj+HR+gW6LLwi1izBLQthlj//bHI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773327301; c=relaxed/simple; bh=VTrfpIcoDJoiKg/0Gp5KrZ4qMcYV14/HT00S5tsu8cc=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=sUHLrkEOh3oYRAaFHa6KHtUK0VUAUWA+fpjhByI1zrud3827ogQLB33X4+1Ctq9bQcevvn9yR9KMvUlF7XgOxC/7Jism2IRBIIFCPF0+/JocZVicnpWQhzV8LGkOezdOCmzKltFuhQb/4cqODWmRoW4E+eSykov0UDXXs6vCLm8= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=oEToEVgC; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="oEToEVgC" Received: by smtp.kernel.org (Postfix) with ESMTPSA id AB882C4CEF7; Thu, 12 Mar 2026 14:55:01 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1773327301; bh=VTrfpIcoDJoiKg/0Gp5KrZ4qMcYV14/HT00S5tsu8cc=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=oEToEVgCfiFaJt6RWONliPJKP4rX+18J/CWNLJJy3BtXeeBLx0jB/IhGSjdZqglws ce12A/ffTP1RmfJ/u3tRVvLeLHSa1i/JK9x/WhbT4FCTJ6+1yNBbU/WVSOBWbO4T4Y lfeHAljHsqBmmrnwKjybgJLW9a9xNPMq4bFIv26NVV5dcBLOCtrHtNoRI3cQW23Kwo +5DQLM9HvE9RP1FmeyV+Rlqy+FpzStd1rh22Kamvsophc194nh/S9AHiLpuszI8mEr ubRGTGVTUHd1+VJOj99OG+AI/vIn/C0k08hdULcsAv6agL67jVdqtzIFInPozqLopW xFmKB4zoqrMpw== Received: from mchehab by mail.kernel.org with local (Exim 4.99.1) (envelope-from ) id 1w0hRD-00000008yE8-3g0O; Thu, 12 Mar 2026 15:54:59 +0100 From: Mauro Carvalho Chehab To: Jonathan Corbet , Linux Doc Mailing List Cc: Mauro Carvalho Chehab , linux-hardening@vger.kernel.org, linux-kernel@vger.kernel.org, Aleksandr Loktionov , Randy Dunlap Subject: [PATCH v2 23/28] docs: c_lex: setup a logger to report tokenizer issues Date: Thu, 12 Mar 2026 15:54:43 +0100 Message-ID: X-Mailer: git-send-email 2.52.0 In-Reply-To: References: Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Sender: Mauro Carvalho Chehab Report file that has issues detected via CMatch and CTokenizer. This is done by setting up a logger that will be overriden by kdoc_parser, when used on it. Signed-off-by: Mauro Carvalho Chehab --- tools/lib/python/kdoc/c_lex.py | 36 ++++++++++++++++++++++++---- tools/lib/python/kdoc/kdoc_parser.py | 3 +++ 2 files changed, 34 insertions(+), 5 deletions(-) diff --git a/tools/lib/python/kdoc/c_lex.py b/tools/lib/python/kdoc/c_lex.py index bc70b55f0dbe..596510bb4e95 100644 --- a/tools/lib/python/kdoc/c_lex.py +++ b/tools/lib/python/kdoc/c_lex.py @@ -6,14 +6,39 @@ Regular expression ancillary classes. =20 Those help caching regular expressions and do matching for kernel-doc. + +Please notice that the code here may rise exceptions to indicate bad +usage inside kdoc to indicate problems at the replace pattern. + +Other errors are logged via log instance. """ =20 +import logging import re =20 from copy import copy =20 from .kdoc_re import KernRe =20 +log =3D logging.getLogger(__name__) + +def tokenizer_set_log(logger, prefix =3D ""): + """ + Replace the module=E2=80=91level logger with a LoggerAdapter that + prepends *prefix* to every message. + """ + global log + + class PrefixAdapter(logging.LoggerAdapter): + """ + Ancillary class to set prefix on all message logs. + """ + def process(self, msg, kwargs): + return f"{prefix}{msg}", kwargs + + # Wrap the provided logger in our adapter + log =3D PrefixAdapter(logger, {"prefix": prefix}) + class CToken(): """ Data class to define a C token. @@ -169,7 +194,7 @@ class CTokenizer(): value =3D match.group() =20 if kind =3D=3D CToken.MISMATCH: - raise RuntimeError(f"Unexpected token '{value}' on {pos}:\= n\t{source}") + log.error(f"Unexpected token '{value}' on {pos}:\n\t{sourc= e}") elif kind =3D=3D CToken.BEGIN: if value =3D=3D '(': paren_level +=3D 1 @@ -189,7 +214,7 @@ class CTokenizer(): yield CToken(kind, value, pos, brace_level, paren_level, bracket_level) =20 - def __init__(self, source=3DNone): + def __init__(self, source=3DNone, log=3DNone): """ Create a regular expression to handle TOKEN_LIST. =20 @@ -349,7 +374,7 @@ class CTokenArgs: elif tok.value =3D=3D "(": delim =3D "," else: - raise ValueError(fr"Can't handle \1..\n on {sub_str}") + self.log.error(fr"Can't handle \1..\n on {sub_str}") =20 level =3D tok.level break @@ -383,7 +408,7 @@ class CTokenArgs: groups_list[pos].append(tok) =20 if pos < self.max_group: - raise ValueError(fr"{self.sub_str} groups are up to {pos} inst= ead of {self.max_group}") + log.error(fr"{self.sub_str} groups are up to {pos} instead of = {self.max_group}") =20 return level, groups_list =20 @@ -503,7 +528,8 @@ class CMatch: # picking an incomplete block. # if start and stack: - print("WARNING: can't find an end", file=3Dsys.stderr) + s =3D str(tokenizer) + log.warning(f"can't find a final end at {s}") yield start, len(tokenizer.tokens) =20 def search(self, source): diff --git a/tools/lib/python/kdoc/kdoc_parser.py b/tools/lib/python/kdoc/k= doc_parser.py index 0da95b090a34..3ff17b07c1c9 100644 --- a/tools/lib/python/kdoc/kdoc_parser.py +++ b/tools/lib/python/kdoc/kdoc_parser.py @@ -14,6 +14,7 @@ import re from pprint import pformat =20 from kdoc.kdoc_re import KernRe +from kdoc.c_lex import tokenizer_set_log from kdoc.c_lex import CTokenizer from kdoc.kdoc_item import KdocItem =20 @@ -253,6 +254,8 @@ class KernelDoc: self.config =3D config self.xforms =3D xforms =20 + tokenizer_set_log(self.config.log, f"{self.fname}: CMatch: ") + # Initial state for the state machines self.state =3D state.NORMAL =20 --=20 2.52.0