78 lines
2.7 KiB
Python
78 lines
2.7 KiB
Python
# -*- encoding=utf8 -*-
|
|
import re
|
|
import json
|
|
import logging
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
def parse_utg_js(js_path, target_package=None):
|
|
"""
|
|
解析 utg.js 文件，提取 UTG 统计信息
|
|
|
|
Args:
|
|
js_path: utg.js 文件路径
|
|
target_package: 目标包名（用于过滤节点）
|
|
|
|
Returns:
|
|
dict: {
|
|
'num_nodes': int,
|
|
'num_reached_activities': int,
|
|
'app_num_total_activities': int
|
|
}
|
|
"""
|
|
result = {
|
|
'num_nodes': 0,
|
|
'num_reached_activities': 0,
|
|
'app_num_total_activities': 0
|
|
}
|
|
|
|
try:
|
|
with open(js_path, 'r', encoding='utf-8') as f:
|
|
content = f.read()
|
|
|
|
json_match = re.search(r'var\s+utg\s*=\s*(\{.*\})\s*;?\s*$', content, re.DOTALL)
|
|
if json_match:
|
|
try:
|
|
utg_data = json.loads(json_match.group(1))
|
|
|
|
app_package = utg_data.get('app_package', '')
|
|
filter_package = target_package if target_package else app_package
|
|
|
|
nodes = utg_data.get('nodes', [])
|
|
if filter_package:
|
|
filtered_count = sum(1 for node in nodes if node.get('package') == filter_package)
|
|
result['num_nodes'] = filtered_count
|
|
else:
|
|
result['num_nodes'] = len(nodes)
|
|
|
|
num_reached = utg_data.get('num_reached_activities', 0)
|
|
result['num_reached_activities'] = num_reached if isinstance(num_reached, int) else 0
|
|
|
|
app_total = utg_data.get('app_num_total_activities', 0)
|
|
result['app_num_total_activities'] = app_total if isinstance(app_total, int) else 0
|
|
|
|
except json.JSONDecodeError as e:
|
|
logger.warning(f"解析 UTG JSON 时出错: {e}")
|
|
_fallback_parse(content, result)
|
|
else:
|
|
_fallback_parse(content, result)
|
|
|
|
except Exception as e:
|
|
logger.error(f"解析 UTG 文件 {js_path} 时出错: {e}")
|
|
|
|
return result
|
|
|
|
def _fallback_parse(content, result):
|
|
"""正则表达式后备解析"""
|
|
num_nodes_match = re.search(r'"num_nodes"\s*:\s*(\d+)', content)
|
|
if num_nodes_match:
|
|
result['num_nodes'] = int(num_nodes_match.group(1))
|
|
|
|
num_reached_match = re.search(r'"num_reached_activities"\s*:\s*(\d+)', content)
|
|
if num_reached_match:
|
|
result['num_reached_activities'] = int(num_reached_match.group(1))
|
|
|
|
app_total_match = re.search(r'"app_num_total_activities"\s*:\s*(\d+)', content)
|
|
if app_total_match:
|
|
result['app_num_total_activities'] = int(app_total_match.group(1))
|