# -*- coding: utf-8 -*-
"""
勘察未完成分类的真实数模（定位销/勾销缸/翻转缸/夹爪缸/电缸）
用法: PYTHONUTF8=1 python scan-pending-series.py
"""
import os, re, collections, sys

BASE = r'X:/新开发产品-Research and Development/1_产品3D数模(发客户仿真)'

# 各分类的数据源目录
ROOTS = {
    'PIN': ['2-伸缩销', '2019 Math Data 铁臂', '2019-NEW product', '2020UNICLAMP数模汇总'],
    'HOK': ['3-勾销缸'],
    'ROT': ['4-翻转缸'],
    'GRP': ['5-夹臂', 'GR8_REV02'],
    'ELEC': ['1-夹紧缸/电缸'],
}

# 关注的系列前缀（新码 UL* / US* / UAGP / UGP / LAE）
FOCUS = re.compile(r'^(UL[A-Z]|US[A-Z]?|UAGP|UGP|LAE|LAGP|UAG)')


def scan(dirs):
    found = collections.defaultdict(list)
    for d in dirs:
        root = os.path.join(BASE, d)
        if not os.path.isdir(root):
            continue
        for dirpath, _, files in os.walk(root):
            for f in files:
                if f.lower().endswith(('.stp', '.step')):
                    found[f].append(os.path.join(dirpath, f))
    return found


def main():
    for cat, dirs in ROOTS.items():
        print(f'\n{"="*70}\n### {cat}  (源: {", ".join(dirs)})\n{"="*70}')
        files = scan(dirs)
        buckets = collections.defaultdict(set)
        for fname in files:
            stem = os.path.splitext(fname)[0].upper().strip()
            m = FOCUS.match(stem)
            if not m:
                continue
            pfx = m.group(1)
            buckets[pfx].add(stem)
        for pfx in sorted(buckets):
            names = sorted(buckets[pfx])
            print(f'\n  -- {pfx}  ({len(names)} 个)')
            for n in names[:200]:
                print(f'     {n}')
            if len(names) > 200:
                print(f'     ... 还有 {len(names)-200} 个')


if __name__ == '__main__':
    main()