[PATCH] tools/docs/checktransupdate.py: use metadata to lookup origin path

[Haoyang LIU]

The get_origin_path() function assumes that translation files have the
same relative path as their origin files, just with "translations/{locale}"
inserted after "Documentation/". However, this assumption is incorrect
for several translation files where the origin path differs. For example:
translations/zh_CN/dev-tools/gdb-kernel-debugging.rst
-> process/debugging/gdb-kernel-debugging.rst


The correct origin path is specified in each translation file's
:Original: metadata field, which can appear in several formats:
1. Plain path: :Original: Documentation/path/to/file.rst
2. With :ref: :Original: :ref:`Documentation/path/to/file.rst <label>`
3. With :doc: :Original: :doc:`../../../path/to/file`


Add get_origin_path_from_metadata() to parse the :Original: metadata
from translation files and extract the actual origin path. Update
check_per_file() to use metadata-based lookup first, falling back to
the path manipulation heuristic only when no metadata is found.

Signed-off-by: Haoyang LIU <tttturtleruss@xxxxxxxxx>
---
 tools/docs/checktransupdate.py | 63 ++++++++++++++++++++++++++++++++--
 1 file changed, 61 insertions(+), 2 deletions(-)

diff --git a/tools/docs/checktransupdate.py b/tools/docs/checktransupdate.py
index cc07cda667fc..b3c695fa0f7a 100755
--- a/tools/docs/checktransupdate.py
+++ b/tools/docs/checktransupdate.py
@@ -32,7 +32,7 @@ from datetime import datetime
 
 
 def get_origin_path(file_path):
-    """Get the origin path from the translation path"""
+    """Get the origin path from the translation path by path manipulation (fallback)"""
     paths = file_path.split("/")
     tidx = paths.index("translations")
     opaths = paths[:tidx]
@@ -40,6 +40,62 @@ def get_origin_path(file_path):
     return "/".join(opaths)
 
 
+def get_origin_path_from_metadata(file_path):
+    """Get the origin path from the :Original: metadata in the translation file.
+
+    The :Original: metadata can have several formats:
+    1. Plain path: :Original: Documentation/path/to/file.rst
+    2. With :ref: directive: :Original: :ref:`Documentation/path/to/file.rst <label>`
+    3. With :doc: directive: :Original: :doc:`../../../path/to/file`
+
+    Returns the origin path if found, None otherwise.
+    """
+    # Pattern to match :Original: line
+    original_re = re.compile(r'^:Original:\s*(.+?)\s*$', re.IGNORECASE)
+    # Pattern to extract path from :ref:`path <label>` or :ref:`path`
+    ref_re = re.compile(r':ref:`([^`<]+?)(?:\s*<[^>]+>)?`')
+    # Pattern to extract path from :doc:`path`
+    doc_re = re.compile(r':doc:`([^`]+)`')
+
+    try:
+        with open(file_path, 'r', encoding='utf-8') as f:
+            # Only check the first 20 lines for metadata
+            for _ in range(20):
+                line = f.readline()
+                if not line:
+                    break
+                match = original_re.match(line.strip())
+                if match:
+                    original_value = match.group(1).strip()
+
+                    # Try to extract from :ref:`...`
+                    ref_match = ref_re.search(original_value)
+                    if ref_match:
+                        return ref_match.group(1).strip()
+
+                    # Try to extract from :doc:`...`
+                    doc_match = doc_re.search(original_value)
+                    if doc_match:
+                        doc_path = doc_match.group(1).strip()
+                        # Handle relative paths - resolve relative to translation file
+                        if doc_path.startswith('../'):
+                            trans_dir = os.path.dirname(file_path)
+                            resolved = os.path.normpath(os.path.join(trans_dir, doc_path))
+                            # Add .rst extension if not present
+                            if not resolved.endswith('.rst'):
+                                resolved += '.rst'
+                            return resolved
+
+                    # Plain path (no directive wrapper)
+                    if original_value.startswith('Documentation/'):
+                        return original_value
+
+    except (IOError, OSError) as e:
+        logging.debug("Could not read file %s: %s", file_path, e)
+
+    return None
+
+
 def get_latest_commit_from(file_path, commit):
     """Get the latest commit from the specified commit for the specified file"""
     command = f"git log --pretty=format:%H%n%aD%n%cD%n%n%B {commit} -1 -- {file_path}"
@@ -128,7 +184,10 @@ def valid_commit(commit):
 
 def check_per_file(file_path):
     """Check the translation status for the specified file"""
-    opath = get_origin_path(file_path)
+    opath = get_origin_path_from_metadata(file_path)
+    if opath is None:
+        opath = get_origin_path(file_path)
+        logging.debug("No :Original: metadata found, using path-based fallback for %s", file_path)
 
     if not os.path.isfile(opath):
         logging.error("Cannot find the origin path for %s", file_path)
-- 
2.53.0