tt-India-2026/scripts/extract_i18n.py

# -*- coding: utf-8 -*-
import re
import os
from collections import defaultdict

ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))

proc_calls = re.compile(r'(?:getProcedureData|execProduceData)\("([^"]+)"')
java_throw_rt = re.compile(r'throw new RuntimeException\("([^"]+)"')
java_throw_cr = re.compile(r'throw new CustomerRuntimeException\(\d+,\s*"([^"]+)"')
java_put_msg = re.compile(r'put\("(?:errorMsg|resultMsg|message|msg)"\s*,\s*"([^"]+)"')

menus = []
labels_print = []
frontend = defaultdict(set)
backend_msgs = defaultdict(set)
proc_list = set()
proc_handlers = set()

# master.ftl
master_path = os.path.join(ROOT, 'src/main/resources/templates/master.ftl')
with open(master_path, encoding='utf-8') as f:
    content = f.read()
    for m in re.finditer(r'<a[^>]*>([^<]+)</a>', content):
        text = m.group(1).strip()
        if text:
            menus.append(text)
    for m in re.finditer(r'label="([^"]+)"', content):
        frontend['表单标签'].add(f'master.ftl: {m.group(1)}')
    for m in re.finditer(r"dialog\('setTitle',\s*'([^']+)'", content):
        frontend['弹窗标题'].add(m.group(1))
    for m in re.finditer(r"layer\.alert\('([^']+)'", content):
        frontend['layer提示'].add(m.group(1))
    for m in re.finditer(r"messager\.alert\('[^']*','([^']+)'", content):
        frontend['messager提示'].add(m.group(1))
    for m in re.finditer(r"messager\.confirm\('[^']*','([^']+)'", content):
        frontend['确认框'].add(m.group(1))

# Java
for dirpath, _, files in os.walk(os.path.join(ROOT, 'src/main/java')):
    for fn in files:
        if not fn.endswith('.java'):
            continue
        path = os.path.join(dirpath, fn)
        rel = os.path.relpath(path, ROOT).replace('\\', '/')
        with open(path, encoding='utf-8', errors='ignore') as f:
            text = f.read()
        for m in proc_calls.finditer(text):
            proc_list.add(m.group(1))
        if 'result_msg' in text or 'result_code' in text:
            proc_handlers.add(rel)
        for m in java_throw_rt.finditer(text):
            backend_msgs[m.group(1)].add(rel)
        for m in java_throw_cr.finditer(text):
            backend_msgs[m.group(1)].add(rel)
        for m in java_put_msg.finditer(text):
            backend_msgs[m.group(1)].add(rel)

# Templates
for dirpath, _, files in os.walk(os.path.join(ROOT, 'src/main/resources/templates')):
    for fn in files:
        if not fn.endswith('.ftl'):
            continue
        path = os.path.join(dirpath, fn)
        rel = os.path.relpath(path, ROOT).replace('\\', '/')
        with open(path, encoding='utf-8', errors='ignore') as f:
            text = f.read()

        if '/print/' in rel.replace('\\', '/'):
            for m in re.finditer(r'ADD_PRINT_TEXT\([^,]+,[^,]+,[^,]+,[^,]+,"([^"]+)"', text):
                s = m.group(1)
                if '${' not in s and not s.startswith('+'):
                    labels_print.append((rel, s))
            for m in re.finditer(r'"([\u4e00-\u9fff]+)"', text):
                labels_print.append((rel, m.group(1)))

        for m in re.finditer(r'field:[^>]+>([^<]+)</th>', text):
            col = m.group(1).strip()
            if col:
                frontend['表格列名'].add(f'{rel}: {col}')
        for m in re.finditer(r'label="([^"]*)"', text):
            if re.search(r'[\u4e00-\u9fff]', m.group(1)):
                frontend['表单标签'].add(f'{rel}: {m.group(1)}')
        for m in re.finditer(r"title:\s*'([^']+)'", text):
            if re.search(r'[\u4e00-\u9fff]', m.group(1)) or m.group(1) in ('提示', 'Error', 'Confirm', 'Info'):
                frontend['弹窗标题'].add(f'{rel}: {m.group(1)}')
        for m in re.finditer(r"layer\.(?:alert|msg)\('([^']+)'", text):
            frontend['layer提示'].add(f'{rel}: {m.group(1)}')
        for m in re.finditer(r"messager\.(?:alert|confirm)\('[^']*',\s*'([^']+)'", text):
            frontend['messager提示'].add(f'{rel}: {m.group(1)}')
        for m in re.finditer(r'<h[1-4][^>]*>([^<]+)</h[1-4]>', text):
            t = m.group(1).strip()
            if re.search(r'[\u4e00-\u9fff]', t):
                frontend['页面标题'].add(f'{rel}: {t}')
        for m in re.finditer(r'<button[^>]*>([^<]+)</button>', text):
            t = m.group(1).strip()
            if re.search(r'[\u4e00-\u9fff]', t):
                frontend['按钮'].add(f'{rel}: {t}')

# Output summary
out = []
out.append(f'Menus: {len(menus)}')
out.append(f'Procedures: {len(proc_list)}')
out.append(f'Backend messages: {len(backend_msgs)}')
out.append(f'Print labels: {len(labels_print)}')
for k, v in sorted(frontend.items()):
    out.append(f'Frontend {k}: {len(v)}')

print('\n'.join(out))
print('\n=== PROCEDURES ===')
for p in sorted(proc_list):
    print(p)
print('\n=== PROC HANDLERS ===')
for p in sorted(proc_handlers):
    print(p)

# Write JSON for doc generation
import json
data = {
    'menus': menus,
    'procedures': sorted(proc_list),
    'procedure_handlers': sorted(proc_handlers),
    'backend_messages': {k: sorted(v) for k, v in sorted(backend_msgs.items())},
    'frontend': {k: sorted(v) for k, v in sorted(frontend.items())},
    'print_labels': labels_print,
}
with open(os.path.join(ROOT, 'scripts', 'i18n_extract.json'), 'w', encoding='utf-8') as f:
    json.dump(data, f, ensure_ascii=False, indent=2)
print('\nWrote scripts/i18n_extract.json')