Skip to content

Commit 924cd08

Browse files
authored
utils: Translation Utility Script (#1831)
* feature: Translation helper script A small python scritp that helps to translate between EN to a target language. It loads the target translation file and compares with the EN base file, showing which keys are missing and asking to translate. * feature: Added code comments to translation utility script * feature: Insert new keys in alphabetical order when translating * feature: README for the translate_helper.py * feature: Move translate helper script to root folder * feature: Added traslation utility script documentation to README file * feature: removed old docs for translation script
1 parent 08c796c commit 924cd08

File tree

2 files changed

+232
-0
lines changed

2 files changed

+232
-0
lines changed

README.md

Lines changed: 17 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -68,6 +68,23 @@
6868

6969
You can find the current translation status in [TRANSLATION.md](https://github.com/sourcegit-scm/sourcegit/blob/develop/TRANSLATION.md)
7070

71+
### Translate Utility Script
72+
73+
A script that assists with translations by reading the target language, comparing it with the base language, and going through missing keys one by one, so the translator can provide the translations interactively without needing to check each key manually.
74+
75+
#### Usage
76+
77+
Check for a given language (e.g., `pt_BR`) and optionally check for missing translations:
78+
79+
```bash
80+
python translate_helper.py pt_BR [--check]
81+
```
82+
83+
- `pt_BR` is the target language code (change as needed), it should correspond to a file named `pt_BR.axaml` in the `src/Resources/Locales/` directory, so you can replace it with any other language code you want to translate, e.g., `de_DE`, `es_ES`, etc.
84+
- `--check` is an optional flag used to only check for missing keys without prompting for translations, useful for getting a list of missing translations.
85+
86+
The script will read the base language file (`en_US.axaml`) and the target language file (e.g., `pt_BR.axaml`), identify missing keys, and prompt you to provide translations for those keys. If the `--check` flag is used, it will only list the missing keys without prompting for translations.
87+
7188
## How to Use
7289

7390
**To use this tool, you need to install Git(>=2.25.1) first.**

translate_helper.py

Lines changed: 215 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,215 @@
1+
import sys
2+
import io
3+
import os
4+
import xml.etree.ElementTree as ET
5+
import re
6+
7+
# Define namespaces URIs
8+
XAML_NS = 'https://github.com/avaloniaui'
9+
X_NS = 'http://schemas.microsoft.com/winfx/2006/xaml'
10+
11+
def register_namespaces():
12+
"""Registers namespaces for ElementTree to use when writing the XML file."""
13+
ET.register_namespace('', XAML_NS)
14+
ET.register_namespace('x', X_NS)
15+
16+
def get_locale_dir():
17+
"""Constructs the absolute path for the locales files"""
18+
try:
19+
script_dir = os.path.dirname(os.path.realpath(__file__))
20+
project_root = os.path.abspath(os.path.join(script_dir, '.'))
21+
locales_dir = os.path.join(project_root, 'src', 'Resources', 'Locales')
22+
except NameError:
23+
project_root = os.path.abspath(os.getcwd())
24+
locales_dir = os.path.join(project_root, 'src', 'Resources', 'Locales')
25+
26+
return locales_dir
27+
28+
def get_locale_files(lang_id):
29+
"""Constructs the absolute paths for the target and reference locale files."""
30+
31+
# get the locales dir
32+
locales_dir = get_locale_dir()
33+
34+
# get the target file absolute path
35+
target_file = os.path.join(locales_dir, f"{lang_id}.axaml")
36+
37+
if not os.path.exists(target_file):
38+
print(f"Error: Target language file not found at {target_file}")
39+
sys.exit(1)
40+
41+
try:
42+
tree = ET.parse(target_file)
43+
root = tree.getroot()
44+
merged_dict = root.find(f"{{{XAML_NS}}}ResourceDictionary.MergedDictionaries")
45+
if merged_dict is None:
46+
raise ValueError("Could not find MergedDictionaries tag.")
47+
48+
resource_include = merged_dict.find(f"{{{XAML_NS}}}ResourceInclude")
49+
if resource_include is None:
50+
raise ValueError("Could not find ResourceInclude tag.")
51+
52+
include_source = resource_include.get('Source')
53+
ref_filename_match = re.search(r'([a-zA-Z]{2}_[a-zA-Z]{2}).axaml', include_source)
54+
if not ref_filename_match:
55+
raise ValueError("Could not parse reference filename from Source attribute.")
56+
57+
ref_filename = f"{ref_filename_match.group(1)}.axaml"
58+
ref_file = os.path.join(locales_dir, ref_filename)
59+
except Exception as e:
60+
print(f"Error parsing {target_file} to find reference file: {e}")
61+
sys.exit(1)
62+
63+
if not os.path.exists(ref_file):
64+
print(f"Error: Reference language file '{ref_file}' not found.")
65+
sys.exit(1)
66+
67+
return target_file, ref_file
68+
69+
def get_strings(root):
70+
"""Extracts all translation keys and their text values from an XML root."""
71+
strings = {}
72+
for string_tag in root.findall(f"{{{X_NS}}}String"):
73+
key = string_tag.get(f"{{{X_NS}}}Key")
74+
if key:
75+
strings[key] = string_tag.text if string_tag.text is not None else ""
76+
return strings
77+
78+
def add_new_string_tag(root, key, value):
79+
"""Adds a new <x:String> tag to the XML root, maintaining some formatting."""
80+
81+
# create a new tag with Key<>Value
82+
new_tag = ET.Element(f"{{{X_NS}}}String")
83+
new_tag.set(f"{{{X_NS}}}Key", key)
84+
new_tag.set("xml:space", "preserve")
85+
new_tag.text = value
86+
87+
# try to find the last tag in the
88+
last_element_index = -1
89+
children = list(root)
90+
91+
start = 0
92+
end = len(children) - 1
93+
middle = -1
94+
95+
# find the first String tag
96+
while (children[start].tag != f"{{{X_NS}}}String"):
97+
start = start + 1
98+
99+
# find where the insert the new tag
100+
# so it always keeps the alphabetical order
101+
while (end - start) > 1:
102+
middle = int((start + end) / 2)
103+
104+
if (children[middle].tag == f"{{{X_NS}}}String"):
105+
middle_key = children[middle].get(f"{{{X_NS}}}Key")
106+
107+
if key.lower() < middle_key.lower():
108+
end = middle
109+
else:
110+
start = middle
111+
112+
# insert after the middle or at the end
113+
if middle != -1:
114+
new_tag.tail = root[middle].tail
115+
root.insert(middle + 1, new_tag)
116+
else:
117+
new_tag.tail = "\n "
118+
root.append(new_tag)
119+
120+
def save_translations(tree, file_path):
121+
"""Saves the XML tree to the file, attempting to preserve formatting."""
122+
try:
123+
ET.indent(tree, space=" ")
124+
except AttributeError:
125+
print("Warning: ET.indent not available. Output formatting may not be ideal.")
126+
127+
tree.write(file_path, encoding='utf-8', xml_declaration=False)
128+
print(f"\nSaved changes to {file_path}")
129+
130+
def main():
131+
"""Main function to run the translation helper script."""
132+
if len(sys.argv) < 2:
133+
print("Usage: python utils/translate_helper.py <lang_id> [--check]")
134+
sys.exit(1)
135+
136+
# Force sys.stdin to use UTF-8 decoding
137+
if sys.stdin.encoding.lower() != 'utf-8':
138+
print("Changin input encoding to UTF-8")
139+
sys.stdin = io.TextIOWrapper(sys.stdin.buffer, encoding='utf-8')
140+
141+
# get arguments
142+
lang_id = sys.argv[1]
143+
is_check_mode = len(sys.argv) > 2 and sys.argv[2] == '--check'
144+
145+
# setup XML parser
146+
register_namespaces()
147+
148+
# try to find XML files
149+
target_file_path, ref_file_path = get_locale_files(lang_id)
150+
151+
# parse files
152+
parser = ET.XMLParser(target=ET.TreeBuilder(insert_comments=True))
153+
target_tree = ET.parse(target_file_path, parser)
154+
target_root = target_tree.getroot()
155+
156+
ref_tree = ET.parse(ref_file_path)
157+
ref_root = ref_tree.getroot()
158+
159+
# get all translation keys
160+
target_strings = get_strings(target_root)
161+
ref_strings = get_strings(ref_root)
162+
163+
# compute the missing keys between the target and reference files
164+
missing_keys = sorted([key for key in ref_strings.keys() if key not in target_strings])
165+
166+
if not missing_keys:
167+
print("All keys are translated. Nothing to do.")
168+
return
169+
170+
print(f"Found {len(missing_keys)} missing keys for language '{lang_id}'.")
171+
172+
# running in check mode will only display the missing keys
173+
if is_check_mode:
174+
print("Missing keys:")
175+
for key in missing_keys:
176+
print(f" - {key}")
177+
return
178+
179+
# running in normal mode will trigger the translation process
180+
print("Starting interactive translation...\n")
181+
changes_made = False
182+
try:
183+
# for each missing key
184+
for i, key in enumerate(missing_keys):
185+
186+
# show the original text
187+
original_text = ref_strings.get(key, "")
188+
print("-" * 40)
189+
print(f"({i+1}/{len(missing_keys)}) Key: '{key}'")
190+
print(f"Original: '{original_text}'")
191+
192+
# asks for a translated version
193+
user_input = input("Enter translation (or press Enter to skip, 'q' to save and quit): ")
194+
195+
# if 'q' quit and save
196+
if user_input.lower() == 'q':
197+
print("\nQuitting and saving changes...")
198+
break
199+
# if valid input, save
200+
elif user_input:
201+
add_new_string_tag(target_root, key, user_input)
202+
changes_made = True
203+
print(f"Added translation for '{key}'")
204+
205+
except (KeyboardInterrupt, EOFError):
206+
print("\n\nProcess interrupted. Saving changes...")
207+
finally:
208+
# if there was any changes, save back to the target file
209+
if changes_made:
210+
save_translations(target_tree, target_file_path)
211+
else:
212+
print("\nNo changes were made.")
213+
214+
if __name__ == "__main__":
215+
main()

0 commit comments

Comments
 (0)