"""Draft business labels for public company profiles, never financial verification.

Input is a directory of JSON records with a `company` object containing
one_liner and tags, as retained by the official-profile research snapshot.
Output is for review; unmatched records remain C00 rather than being forced.
This tool does not fetch sources, modify the site database or run a build.
"""
import argparse
import json
import re
from pathlib import Path

def match(pattern,text):return bool(re.search(pattern,text,re.I))
def classify(c):
 short=c.get('one_liner') or '';tags=' '.join(c.get('tags') or [])
 rules=[
 ('C10',r'\brobot(?:s|ics|ic)?\b|embodied|physical intelligence|autonomous (?:driving|vehicle)|drones?|manufacturing hardware'),
 ('C02',r'context compression|compression middleware|RNA intelligence|audio data for AI|synthetic data|data quality|\bGPU\b|\bGPUs\b|\bchips?\b|semiconductor|data centers?|datacenters?|inference|compute|training data|data labeling|data labelling|RL environments|reinforcement learning|model training'),
 ('C07',r'precision medicine|ambulance|clinic|biology|manufacturers|distributors|fabrication|people-intelligence|deskless workers|health|medical|clinical|dental|physician|hospital|veterinar|therap|radiolog|pharma|legal|law firm|lawyer|litigation|accountant|accounting|audit\b|insurance|underwrit|financ|hedge funds?|bank|wealth|investment|investing|real estate|property|properties|construction|building (?:plan|code)|engineering projects|\bCAD\b|\bEDA\b|chip design|architecture|architects|logistics|supply chain|freight|global trade|compliance|government|govtech|lobby|energy|utilities|\bfleets?\b|education|edtech|\btutor|schools?|exam prep|tax\b|recruit|hiring|human resources|procurement|retail|e-commerce|ecommerce|merchants?|industrial'),
 ('C03',r'AI evaluations|AI governance|voice agents|chat AI agents|harnesses|agent.{0,25}(?:infrastructure|tools|identity|identities|memory|evaluation|eval|observability|browser|payment|communication)|(?:infrastructure|tools|identity|identities|evaluation|eval|observability|browsers?|payments?).{0,25}agents?|\bMCP\b|agentmail|API.{0,20}agents?|developer.{0,15}agents?'),
 ('C04',r'firmware|internal apps|coding|software engineer|code\b|codebase|developer|programming|app(?:lication)? (?:builder|creation|generation)|(?:build|building|make|create|generat).{0,25}(?:apps|applications|software)|\bDevOps\b|product docs|documentation engineer|\bIDE\b|logs and fix|testing|debug'),
 ('C06',r'\bsales\b|marketing|customer support|customer service|call center|call centre|\bGTM\b|\bCRM\b|\bSEO\b|\bGEO\b|\bAEO\b|growth engine|outbound|telemarketing|advertis|\bads\b|contact center|customer success'),
 ('C08',r'\bvideo\b|\bimage\b|\bphoto\b|\bfilm\b|\bdesign\b|animation|creative|creators?|content creation|\bmusic\b|media|audio edit|voiceover'),
 ('C01',r'foundation models?|frontier models?|large language models?|\bLLMs?\b|voice model|speech model|world model'),
 ('C09',r'consumer|personal|companions?|\bstor(?:y|ies)\b|entertainment|\bgam(?:e|es|ing)\b|social network|\bphone\b|smartphone|keyboard|your digital life'),
 ('C05',r'\bB2B\b|enterprise|workflow|workspace|productivity|operations|\bSaaS\b|\bSOP\b|Word editor|spreadsheet|knowledge|company OS|company brain|work\b|teams?|business|employee|meeting|security|cyber|search'),
 ]
 for label,text in [('主营简介',short),('目录标签',tags)]:
  for cat,pattern in rules:
   if match(pattern,text):return cat,label+'的规则初分'
 return 'C00','简介不足以确定主业务，待复核'


def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--input", required=True, type=Path)
    parser.add_argument("--output", required=True, type=Path)
    args = parser.parse_args()
    result = []
    for path in sorted(args.input.glob("*.json")):
        record = json.loads(path.read_text())
        company = record["company"]
        category, basis = classify(company)
        result.append({"ycId": company["id"], "category": category,
                       "basis": basis, "status": "provisional"})
    args.output.write_text(json.dumps(result, ensure_ascii=False, indent=2) + "\n")


if __name__ == "__main__":
    main()