Merge pull request #2948 from Wurschdhaud/new-extras-translation-helper

New helper script for translations

Author: jmcouffin

extras/bundle_translations/apply_translations.py

@@ -0,0 +1,119 @@
+"""Apply translations from CSV back to pyRevit bundle YAML files.
+
+This script reads a CSV file containing translations (generated by 
+extract_translations.py) and applies them to the corresponding bundle.yaml
+files, updating or creating multilingual field dictionaries.
+
+Configuration:
+    TRANSLATION_CSV: Path to the CSV file containing translations
+    LANGUAGE_KEY: Translation language key to apply (e.g., 'chinese_s')
+    SOURCE_LANG: Source language key (default: 'en_us')
+"""
+import csv
+from pathlib import Path
+from ruamel.yaml import YAML  # pip install ruamel.yaml
+
+# -------- CONFIG --------
+TRANSLATION_CSV = r"C:\temp\translations.csv"  # same path as in other script
+LANGUAGE_KEY = "chinese_s"  # same as in other script
+SOURCE_LANG = "en_us"  # same as in other script
+# ------------------------
+
+yaml = YAML()
+
+
+def build_lookup(csv_path):
+    """Build dictionary: {yaml_file: {key_type: {"en_us":..., "translation":...}}}"""
+    lookup = {}
+
+    with open(csv_path, encoding="utf-8") as f:
+        reader = csv.DictReader(f)
+
+        for row in reader:
+            file = row["yaml_file"]
+            key = row["key_type"]
+
+            en = row[SOURCE_LANG]
+            tr = row[LANGUAGE_KEY]
+
+            lookup.setdefault(file, {}).setdefault(key, {})
+            lookup[file][key] = {"en": en, "tr": tr}
+
+    return lookup
+
+
+def insert_translation(data, key_type, trans, node_path=""):
+    """Insert translation from CSV.
+       Rule: write ONLY if CSV provides a non-empty translation; always overwrite."""
+    if not isinstance(data, dict):
+        return
+
+    translation = trans["tr"].strip()
+
+    if key_type in data:
+        value = data[key_type]
+
+        # CASE A: scalar -> convert to dict
+        if isinstance(value, str):
+            print(f"[Scalar detected during import] {node_path}/{key_type} | Converting to multilingual")
+            new_dict = {SOURCE_LANG: value}
+
+            if translation:
+                new_dict[LANGUAGE_KEY] = translation
+                print(f"[Write] {node_path}/{key_type} | {LANGUAGE_KEY} = '{translation}'")
+            else:
+                print(f"[Skip] CSV translation empty for {node_path}/{key_type}")
+
+            data[key_type] = new_dict
+            return
+
+        # CASE B: dict
+        elif isinstance(value, dict):
+            # ensure en_us exists
+            if SOURCE_LANG not in value:
+                if len(value):
+                    first_key = next(iter(value.keys()))
+                    value[SOURCE_LANG] = value[first_key]
+                    print(f"[Promotion] No {SOURCE_LANG} → using '{first_key}' value")
+
+            # write only if CSV translation provided
+            if translation:
+                value[LANGUAGE_KEY] = translation
+                print(f"[Write] {node_path}/{key_type} | Overwriting {LANGUAGE_KEY} = '{translation}'")
+            else:
+                print(f"[Skip] CSV translation empty for {node_path}/{key_type}")
+
+    # recurse deeper
+    for k, v in data.items():
+        child_path = f"{node_path}/{k}" if node_path else k
+        insert_translation(v, key_type, trans, child_path)
+
+
+def main():
+    lookup = build_lookup(TRANSLATION_CSV)
+
+    for yaml_file, fields in lookup.items():
+        yaml_file = Path(yaml_file)
+
+        if not yaml_file.exists():
+            print(f"[Missing] {yaml_file}")
+            continue
+
+        try:
+            with open(yaml_file, "r", encoding="utf-8") as f:
+                data = yaml.load(f)
+
+            for key_type, trans in fields.items():
+                insert_translation(data, key_type, trans)
+
+            with open(yaml_file, "w", encoding="utf-8") as f:
+                yaml.dump(data, f)
+
+            print(f"[Processing] {yaml_file}")
+
+        except Exception as e:
+            print(f"[ERROR] writing {yaml_file}: {e}")
+
+
+if __name__ == "__main__":
+    main()

extras/bundle_translations/extract_translations.py

@@ -0,0 +1,102 @@
+"""Extract translation strings from pyRevit bundle YAML files.
+
+This script scans bundle.yaml files for title and tooltip fields,
+extracting English source text and any existing translations to a CSV file
+for easier translation workflow.
+
+Configuration:
+    BASE_DIR: Root directory containing bundle YAML files
+    OUTPUT_CSV: Path where the CSV file will be written
+    LANGUAGE_KEY: Translation language key (e.g., 'chinese_s')
+    SOURCE_LANG: Source language key (default: 'en_us')
+"""
+import os
+from pathlib import Path
+from ruamel.yaml import YAML  # pip install ruamel.yaml
+import csv
+
+# -------- CONFIG --------
+BASE_DIR = r"C:\Program Files\pyRevit-Master\extensions\pyRevitTools.extension"  # adjust for custom installation 
+OUTPUT_CSV = r"C:\temp\translations.csv"  # same path as in other script
+LANGUAGE_KEY = "chinese_s"  # translation key to extract/merge
+SOURCE_LANG = "en_us"  # main source language
+# ------------------------
+
+yaml = YAML()
+
+
+def find_yaml_files(base_dir):
+    for root, _, files in os.walk(base_dir):
+        for f in files:
+            if f.endswith(".yaml"):
+                yield Path(root) / f
+
+
+def extract_field(path, field_name, value, results):
+    """Extracts English + existing translated value from dict or scalar."""
+    # CASE 1: multilingual dict
+    if isinstance(value, dict):
+        # English (preferred)
+        en = value.get(SOURCE_LANG)
+
+        # fallback to first language if no en_us exists
+        if not en and len(value):
+            first_key = next(iter(value.keys()))
+            en = value[first_key]
+
+        # Existing translation to preserve
+        tr = value.get(LANGUAGE_KEY, "")
+
+        if en:
+            results.append([path, field_name, en, tr])
+        return
+
+    # CASE 2: scalar string
+    if isinstance(value, str):
+        print(
+            f"[Scalar detected] File: {path} | Field: {field_name} | Value: '{value}'"
+        )
+        results.append([path, field_name, value, ""])
+        return
+
+
+def extract_values(data, path, results):
+    """Recursively walk through structure and extract fields."""
+    if not isinstance(data, dict):
+        return
+
+    for field_name in ("title", "tooltip"):
+        if field_name in data:
+            extract_field(path, field_name, data[field_name], results)
+
+    # recurse into children
+    for k, v in data.items():
+        child_path = f"{path}/{k}"
+        extract_values(v, child_path, results)
+
+
+def main():
+    results = []
+
+    for yaml_file in find_yaml_files(BASE_DIR):
+        try:
+            with open(yaml_file, "r", encoding="utf-8") as f:
+                data = yaml.load(f)
+
+            extract_values(data, str(yaml_file), results)
+
+        except Exception as e:
+            print(f"ERROR reading {yaml_file}: {e}")
+
+    # write CSV
+    with open(OUTPUT_CSV, "w", newline="", encoding="utf-8") as f:
+        writer = csv.writer(f)
+        writer.writerow(["yaml_file", "key_type", SOURCE_LANG, LANGUAGE_KEY])
+        for row in results:
+            writer.writerow(row)
+
+    print(f"\nExtracted {len(results)} records to {OUTPUT_CSV}")
+
+
+if __name__ == "__main__":
+    main()