Commit 35293ebb authored by Zhiyu Zhang's avatar Zhiyu Zhang Committed by Jonathan Corbet
Browse files

scripts: add origin commit identification based on specific patterns 



This patch adds the functionability to smartly identify origin commit
of the translation by matching the following patterns in commit log:
1) update to commit HASH
2) Update the translation through commit HASH
If no such pattern is found, script will obey the original workflow.

Signed-off-by: default avatarZhiyu Zhang <zhiyuzhang999@gmail.com>
Reviewed-by: default avatarDongliang Mu <dzm91@hust.edu.cn>
Signed-off-by: default avatarJonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20250713163418.1459-1-zhiyuzhang999@gmail.com
parent 2b16b71a

scripts/checktransupdate.py

+37 −1
Original line number Diff line number Diff line
@@ -24,6 +24,7 @@ commit 42fb9cfd5b18 ("Documentation: dev-tools: Add link to RV docs") 
"""



import os

import re

import time

import logging

from argparse import ArgumentParser, ArgumentTypeError, BooleanOptionalAction
@@ -69,6 +70,38 @@ def get_origin_from_trans(origin_path, t_from_head): 
    return o_from_t





def get_origin_from_trans_smartly(origin_path, t_from_head):

    """Get the latest origin commit from the formatted translation commit:

    (1) update to commit HASH (TITLE)

    (2) Update the translation through commit HASH (TITLE)

    """

    # catch flag for 12-bit commit hash

    HASH = r'([0-9a-f]{12})'

    # pattern 1: contains "update to commit HASH"

    pat_update_to = re.compile(rf'update to commit {HASH}')

    # pattern 2: contains "Update the translation through commit HASH"

    pat_update_translation = re.compile(rf'Update the translation through commit {HASH}')



    origin_commit_hash = None

    for line in t_from_head["message"]:

        # check if the line matches the first pattern

        match = pat_update_to.search(line)

        if match:

            origin_commit_hash = match.group(1)

            break

        # check if the line matches the second pattern

        match = pat_update_translation.search(line)

        if match:

            origin_commit_hash = match.group(1)

            break

    if origin_commit_hash is None:

        return None

    o_from_t = get_latest_commit_from(origin_path, origin_commit_hash)

    if o_from_t is not None:

        logging.debug("tracked origin commit id: %s", o_from_t["hash"])

    return o_from_t





def get_commits_count_between(opath, commit1, commit2):

    """Get the commits count between two commits for the specified file"""

    command = f"git log --pretty=format:%H {commit1}...{commit2} -- {opath}"
@@ -108,6 +141,9 @@ def check_per_file(file_path): 
        logging.error("Cannot find the latest commit for %s", file_path)

        return



    o_from_t = get_origin_from_trans_smartly(opath, t_from_head)

    # notice, o_from_t from get_*_smartly() is always more accurate than from get_*()

    if o_from_t is None:

        o_from_t = get_origin_from_trans(opath, t_from_head)



    if o_from_t is None: