Add ability to get the GitHub URL for any repo to generate xliff files from markdown

readme.md

@@ -18,6 +18,8 @@ If you want to use a different Crowdin project, store the project and file IDs i
   - Required: `xliffPath` — path to the source XLIFF file; `mdPath` — path for the resulting Markdown file.
   - Optional: `-u`/`--untranslated` — produce the untranslated version of the Markdown file.
 
+- `md2xliff` - Convert a Markdown file to XLIFF.
+  - Required: `mdPath` — path to the Markdown file; `xliffPath` — path for the resulting XLIFF file.
 - `md2html` - Convert a Markdown file to HTML.
   - Required: `mdPath` — path to the Markdown file; `htmlPath` — path for the resulting HTML file.
   - Optional: `-l`/`--lang` — language code (default: `en`); `-t`/`--docType` — document type, one of `userGuide`, `developerGuide`, `changes`, `keyCommands`.

source/l10nUtil.py

@@ -888,6 +888,9 @@ def main():
 	)
 	command_xliff2md.add_argument("xliffPath", help="Path to the xliff file")
 	command_xliff2md.add_argument("mdPath", help="Path to the resulting markdown file")
+	command_md2xliff = commands.add_parser("md2xliff", help="Convert markdown to xliff")
+	command_md2xliff.add_argument("mdPath", help="Path to the markdown file")
+	command_md2xliff.add_argument("xliffPath", help="Path to the resulting xliff file")
 	command_md2html = commands.add_parser("md2html", help="Convert markdown to html")
 	command_md2html.add_argument(
 		"-l",
@@ -1058,6 +1061,11 @@ def main():
 				outputPath=args.mdPath,
 				translated=not args.untranslated,
 			)
+		case "md2xliff":
+			markdownTranslate.generateXliff(
+				mdPath=args.mdPath,
+				outputPath=args.xliffPath,
+			)
 		case "md2html":
 			md2html.main(
 				source=args.mdPath,

source/markdownTranslate.py

@@ -18,7 +18,6 @@
 from dataclasses import dataclass
 import subprocess
 
-RAW_GITHUB_REPO_URL = "https://raw.githubusercontent.com/nvaccess/nvda"
 re_kcTitle = re.compile(r"^(<!--\s+KC:title:\s*)(.+?)(\s*-->)$")
 re_kcSettingsSection = re.compile(r"^(<!--\s+KC:settingsSection:\s*)(.+?)(\s*-->)$")
 # Comments that span a single line in their entirety
@@ -90,11 +89,34 @@ def getGitDir() -> str:
 
 
 def getRawGithubURLForPath(filePath: str) -> str:
+	rawGithubRepoURL = getGithubRepoURL()
 	gitDirPath = getGitDir()
 	commitID = getLastCommitID(filePath)
 	relativePath = os.path.relpath(os.path.abspath(filePath), gitDirPath)
 	relativePath = relativePath.replace("\\", "/")
-	return f"{RAW_GITHUB_REPO_URL}/{commitID}/{relativePath}"
+	return f"{rawGithubRepoURL}/{commitID}/{relativePath}"
+
+
+def getGithubRepoURL() -> str:
+	"""
+	Get the GitHub repository URL from git remote origin.
+	return: The raw GitHub URL for the repository.
+	"""
+	result = subprocess.run(
+		["git", "remote", "get-url", "origin"],
+		capture_output=True,
+		text=True,
+		check=True,
+	)
+	remote_url = result.stdout.strip()
+	# Convert SSH or HTTPS URL to raw GitHub URL format
+	if match := re.match(r"git@github\.com:(.+?)(?:\.git)?$", remote_url):
+		repo_path = match.group(1)
+	elif match := re.match(r"https://github\.com/(.+?)(?:\.git)?$", remote_url):
+		repo_path = match.group(1)
+	else:
+		raise ValueError(f"Cannot parse GitHub URL from git remote: {remote_url}")
+	return f"https://raw.githubusercontent.com/{repo_path}"
 
 
 def preprocessMarkdownLines(mdLines: Iterable[str]) -> Iterable[str]:
@@ -611,9 +633,9 @@ def ensureMarkdownFilesMatch(path1: str, path2: str, allowBadAnchors: bool = Fal
 					line1 = m1.group(1) + m1.group(2)
 					line2 = m2.group(1) + m2.group(2)
 			if line1 != line2:
-				raise ValueError(
-					f"Files do not match at line {lineNo}: {line1=} {line2=}",
-				)
+			raise ValueError(
+				f"Files do not match at line {lineNo}: {line1=} {line2=}",
+			)
 		print("Files match")