Received-SPF: pass (google.com: domain of linux-kernel+bounces-152812-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
From: Cheng Ziqiu <chengziqiu@hust.edu.cn>
To: Alex Shi <alexs@kernel.org>,
	Yanteng Si <siyanteng@loongson.cn>,
	Jonathan Corbet <corbet@lwn.net>
Cc: Dongliang Mu <dzm91@hust.edu.cn>,
	linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	hust-os-kernel-patches@googlegroups.com,
	Cheng Ziqiu <chengziqiu@hust.edu.cn>
Subject: [PATCH] scripts: add `check-trans-update.py`
Date: Mon, 22 Apr 2024 14:58:22 +0800
Message-Id: <20240422065822.1441611-1-chengziqiu@hust.edu.cn>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

The `check-trans-update.py` scripts check whether a translated version
of a documentation is up-to-date with the english version.

The scripts use `git log` commit to find the latest english commit from
the translation commit (order by author date) and the latest english
commits from HEAD. If differences occurs, report the file and commits
need to be updated.

Signed-off-by: Cheng Ziqiu <chengziqiu@hust.edu.cn>
---
 scripts/check-trans-update.py | 176 ++++++++++++++++++++++++++++++++++
 1 file changed, 176 insertions(+)
 create mode 100755 scripts/check-trans-update.py

diff --git a/scripts/check-trans-update.py b/scripts/check-trans-update.py
new file mode 100755
index 000000000000..0f913c5c4555
--- /dev/null
+++ b/scripts/check-trans-update.py
@@ -0,0 +1,176 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import os
+from argparse import ArgumentParser, BooleanOptionalAction
+from datetime import datetime
+
+flag_p_c = False
+flag_p_uf = False
+flag_debug = False
+
+
+def dprint(*args, **kwargs):
+    if flag_debug:
+        print("[DEBUG] ", end="")
+        print(*args, **kwargs)
+
+
+def get_origin_path(file_path):
+    paths = file_path.split("/")
+    tidx = paths.index("translations")
+    opaths = paths[:tidx]
+    opaths += paths[tidx + 2 :]
+    return "/".join(opaths)
+
+
+def get_latest_commit_from(file_path, commit):
+    command = "git log --pretty=format:%H%n%aD%n%cD%n%n%B {} -1 -- {}".format(
+        commit, file_path
+    )
+    dprint(command)
+    pipe = os.popen(command)
+    result = pipe.read()
+    result = result.split("\n")
+    if len(result) <= 1:
+        return None
+
+    dprint("Result: {}".format(result[0]))
+
+    return {
+        "hash": result[0],
+        "author_date": datetime.strptime(result[1], "%a, %d %b %Y %H:%M:%S %z"),
+        "commit_date": datetime.strptime(result[2], "%a, %d %b %Y %H:%M:%S %z"),
+        "message": result[4:],
+    }
+
+
+def get_origin_from_trans(origin_path, t_from_head):
+    o_from_t = get_latest_commit_from(origin_path, t_from_head["hash"])
+    while o_from_t is not None and o_from_t["author_date"] > t_from_head["author_date"]:
+        o_from_t = get_latest_commit_from(origin_path, o_from_t["hash"] + "^")
+    if o_from_t is not None:
+        dprint("tracked origin commit id: {}".format(o_from_t["hash"]))
+    return o_from_t
+
+
+def get_commits_count_between(opath, commit1, commit2):
+    command = "git log --pretty=format:%H {}...{} -- {}".format(commit1, commit2, opath)
+    dprint(command)
+    pipe = os.popen(command)
+    result = pipe.read().split("\n")
+    # filter out empty lines
+    result = list(filter(lambda x: x != "", result))
+    return result
+
+
+def check_per_file(file_path):
+    opath = get_origin_path(file_path)
+
+    if not os.path.isfile(opath):
+        dprint("Error: Cannot find the origin path for {}".format(file_path))
+        return
+
+    o_from_head = get_latest_commit_from(opath, "HEAD")
+    t_from_head = get_latest_commit_from(file_path, "HEAD")
+
+    if o_from_head is None or t_from_head is None:
+        print("Error: Cannot find the latest commit for {}".format(file_path))
+        return
+
+    o_from_t = get_origin_from_trans(opath, t_from_head)
+
+    if o_from_t is None:
+        print("Error: Cannot find the latest origin commit for {}".format(file_path))
+        return
+
+    if o_from_head["hash"] == o_from_t["hash"]:
+        if flag_p_uf:
+            print("No update needed for {}".format(file_path))
+        return
+    else:
+        print("{}".format(file_path), end="\t")
+        commits = get_commits_count_between(
+            opath, o_from_t["hash"], o_from_head["hash"]
+        )
+        print("({} commits)".format(len(commits)))
+        if flag_p_c:
+            print("\t", end="")
+            print("\n\t".join(commits))
+
+
+def main():
+    script_path = os.path.dirname(os.path.abspath(__file__))
+    linux_path = os.path.join(script_path, "..")
+
+    parser = ArgumentParser(description="Check the translation update")
+    parser.add_argument(
+        "-l",
+        "--locale",
+        help="Locale to check when file is not specified",
+    )
+    parser.add_argument(
+        "--print-commits",
+        action=BooleanOptionalAction,
+        default=True,
+        help="Print commits between origin and translation",
+    )
+
+    parser.add_argument(
+        "--print-updated-files",
+        action=BooleanOptionalAction,
+        default=False,
+        help="Print files no need to be updated",
+    )
+
+    parser.add_argument(
+        "--debug",
+        action=BooleanOptionalAction,
+        help="Print debug information",
+        default=False,
+    )
+
+    parser.add_argument(
+        "files", nargs="*", help="File to check, if not specified, check all"
+    )
+    args = parser.parse_args()
+
+    global flag_p_c, flag_p_uf, flag_debug
+    flag_p_c = args.print_commits
+    flag_p_uf = args.print_updated_files
+    flag_debug = args.debug
+
+    # get files related to linux path
+    files = args.files
+    if len(files) == 0:
+        if args.locale is not None:
+            files = (
+                os.popen(
+                    "find {}/Documentation/translations/{} -type f".format(
+                        linux_path, args.locale
+                    )
+                )
+                .read()
+                .split("\n")
+            )
+        else:
+            files = (
+                os.popen(
+                    "find {}/Documentation/translations -type f".format(linux_path)
+                )
+                .read()
+                .split("\n")
+            )
+
+    files = list(filter(lambda x: x != "", files))
+    files = list(map(lambda x: os.path.relpath(os.path.abspath(x), linux_path), files))
+
+    # cd to linux root directory
+    os.chdir(linux_path)
+
+    for file in files:
+        check_per_file(file)
+
+
+if __name__ == "__main__":
+    main()
-- 
2.34.1