Initial upload of python program file

trylex2po.py

@@ -0,0 +1,218 @@
+import os
+import polib
+from pathlib import Path
+import re
+import shutil
+
+# Define paths
+SOURCE_LOCALE_DIR = Path("/home/brianr/Documents/smeserver-manager-locale/root/usr/share/smanager/lib/SrvMngr/I18N/Modules")
+SOURCE_MANAGER_DIR = Path("/home/brianr/Documents/smeserver-manager/root/usr/share/smanager/lib/SrvMngr/I18N/Modules")
+
+def extract_language_from_filename(filename):
+    match = re.search(r'[_-]([a-z]{2}(?:-[a-z]{2})?)\.lex', filename, re.IGNORECASE)
+    if match:
+        return match.group(1).replace("-", "_").lower()
+    return None
+
+def parse_lex_file(lex_file):
+	entries = {}
+	with open(lex_file, 'r', encoding='utf-8') as file:
+		content = file.read()
+		# Use regex to find all key-value pairs, handling quotes around keys optionally
+		matches = re.finditer(r"""
+			(['"]?)       # Optional opening quote for the key
+			([^'" \t]+?)  # The key itself (excluding quotes and whitespace)
+			\1            # Optional closing quote matching the opening quote
+			\s*=>\s*      # The delimiter
+			'             # Opening quote for the value
+			(.*?)         # The value (non-greedy to capture minimal text)
+			'             # Closing quote for the value
+			\s*,\s*       # Trailing comma and optional whitespace
+			""", content, re.DOTALL | re.VERBOSE)
+		#matches = re.findall(r"['\"]?([^'\"]+)['\"]?\s*=>\s*['\"](.*?)['\"]\s*,", content, re.DOTALL)
+		for match in matches:
+			key, value = match.group(2).strip(), match.group(3).strip()
+			entries[key] = value.replace("\\n", "\n")
+	return entries
+
+def save_lex_file(entries, lex_file):
+    with open(lex_file, 'w', encoding='utf-8') as file:
+        for key, value in entries.items():
+            escaped_value = value.replace("'", "\\'")  # Escape single quotes
+            file.write(f"'{key}' => '{escaped_value}',\n")
+
+def infer_prefix(entries, filename):
+	"""
+	Infer the <abc> prefix from entries that contain it, fallback to the first 3 characters of the filename.
+	"""
+	for key in entries.keys():
+		match = re.match(r"(.*?_)?.*", key)
+		if match:
+			prefix = match.group(1)
+			if prefix:
+				print(f"Found prefix:{prefix} {filename}")
+				return prefix
+	# If no prefix is found, return the first 3 characters of the filename
+	return filename.stem[:3].lower() + "_"
+	
+def extract_module_name(file_path):
+    # Convert the file path to a Path object
+    path = Path(file_path)
+    # Extract the module directory name
+    module_name = path.parts[-2]  # Get the second-to-last part in the path
+    # Capitalize the first letter
+    return module_name.capitalize()
+
+def ensure_prefix(entries, prefix,file_path):
+	"""
+	Ensure each msgctxt within the entries has the given prefix.
+	"""
+	updated_entries = {}
+	module_name = extract_module_name(file_path)
+	for key, value in entries.items():
+		if not key.startswith(prefix):
+			updated_key = f"{prefix}{key}"
+			print(f"Adding prefix: {key} -> {updated_key} ({module_name})")
+			updated_entries[updated_key] = value
+		else:
+			updated_entries[key] = value
+	return updated_entries
+
+def convert_lex_to_po(lex_file, po_file, en_entries, general_en_entries):
+	translated_entries = parse_lex_file(lex_file)
+	language_code = extract_language_from_filename(po_file.name)
+
+	# Infer prefix from original en_entries and ensure all entries have this prefix
+	prefix = infer_prefix(en_entries, Path(lex_file))
+	en_entries = ensure_prefix(en_entries, prefix,lex_file)
+	translated_entries = ensure_prefix(translated_entries, prefix,lex_file)
+
+	po = polib.POFile()
+	po.metadata = {
+		'Project-Id-Version': '1.0',
+		'Language': language_code,
+		'Content-Type': 'text/plain; charset=utf-8',
+	}
+
+	new_entries = []
+
+	for msgctxt, msgstr in translated_entries.items():
+		msgid = en_entries.get(msgctxt, "")  # Find the original text using msgctxt (Msg ID)
+		if not msgid:
+			print(f"Warning: Could not find original text for Msg ID '{msgctxt}'")
+			# See if in General 
+			msgid = general_en_entries.get(msgctxt, "")
+			if not msgid:
+				msgid = "Placeholder for missing original text"
+				new_entries.append((msgctxt, msgid))   
+			else:
+				print(f"Found {msgctxt} => {msgid} in general")   
+		entry = polib.POEntry(
+			msgctxt=msgctxt,
+			msgid=msgid,
+			msgstr=msgstr
+		)
+		po.append(entry)
+
+	# Update en_entries with new entries
+	for msgctxt, msgid in new_entries:
+		en_entries[msgctxt] = msgid
+
+	po.save(po_file)
+
+def process_directory_with_en_mapping(source_directory, master_directory):
+	# First pick up the general ones that may come in any of the files
+	print("loading General directory")
+	# Load it up and use it to check for ones without prefix
+	general_en_file = master_directory /"General/general_en.lex"
+	general_en_entries = parse_lex_file(general_en_file)
+	if  len(general_en_entries)>0:
+		print(f"Found {len(general_en_entries)} entries in General lex file")
+	else:
+		quit()
+	for subdir, _, files in os.walk(source_directory):
+		subdir_path = Path(subdir)
+		print(subdir_path)
+
+		# Skip if subdir_path is exactly the source_directory or contains 'pofiles'
+		if subdir_path == source_directory or 'pofiles' in subdir_path.parts:
+			continue
+
+		# Extract the subservient directory name and ensure it's capitalized
+		try:
+			subservient_dir_name = subdir_path.relative_to(source_directory).parts[0].capitalize()
+		except IndexError:
+			print(f"Skipping directory {subdir_path} as it has no subservient directory.")
+			continue
+
+
+		# Apply it to find the corresponding en directory
+		corresponding_en_dir = master_directory / subservient_dir_name
+
+		#Skip the General directory as it has not prefix's
+		if subservient_dir_name == "General":
+			# and skip to next
+			continue
+
+		# Find corresponding `*`_en.lex` files
+		en_entries = {}
+		en_file = corresponding_en_dir / f"{subservient_dir_name.lower()}_en.lex"
+		if en_file.is_file():
+			en_entries = parse_lex_file(en_file)
+		else:
+			print(f"Warning: No *_en.lex file found in {corresponding_en_dir}")
+
+		pofiles_dir = subdir_path / "pofiles"
+		if not pofiles_dir.exists():
+			pofiles_dir.mkdir(parents=True, exist_ok=True)
+
+		for file in files:
+			if file.endswith('.lex') and not file.endswith('_en.lex'):
+				lex_file = subdir_path / file
+				po_file = pofiles_dir / lex_file.with_suffix('.po').name
+				#po_file = po_file.lower().replace("-", "_")
+
+				print(f"Converting {lex_file} to {po_file}")
+				convert_lex_to_po(lex_file, po_file, en_entries,general_en_entries)
+
+		# Save the updated en_entries to the en.lex file in the locale directory
+		if en_entries:
+			locale_en_file = subdir_path / f"{subservient_dir_name.lower()}_en.lex"
+			if en_file.exists():
+				shutil.copy(en_file, locale_en_file)  # Backup the original en.lex file to the locale path
+
+			save_lex_file(en_entries, locale_en_file)
+			print(f"Updated and saved {locale_en_file}")
+
+			# Create and save the po file in the pofiles directory
+			updated_po_file = pofiles_dir / f"{subservient_dir_name.lower()}_en.po"
+			create_po_from_en_entries(en_entries, updated_po_file)
+
+def create_po_from_en_entries(entries, po_file):
+    po = polib.POFile()
+    po.metadata = {
+        'Project-Id-Version': '1.0',
+        'Language': 'en',
+        'Content-Type': 'text/plain; charset=utf-8',
+    }
+
+    for msgctxt, msgid in entries.items():
+        entry = polib.POEntry(
+            msgctxt=msgctxt,
+            msgid=msgid,
+            msgstr=""
+        )
+        po.append(entry)
+
+    po.save(po_file)
+    print(f"Created {po_file}")
+
+def main():
+    # Convert all .lex files under smeserver-manager-locale into respective pofiles directories using en-mapping
+    print("Processing locale directory...")
+    process_directory_with_en_mapping(SOURCE_LOCALE_DIR, SOURCE_MANAGER_DIR)
+
+    print("Conversion complete.")
+
+if __name__ == "__main__":
+    main()