# Generate rules for all 31 industries from real reports
python scripts/generate_rules_from_real_reports.py --max-concurrent 5

# Single industry
python scripts/generate_rules_from_real_reports.py --industry 801120

# Run industry-specific sections only
python scripts/generate_rules_from_real_reports.py --industry 801780 --llm-only

# CLI
python scripts/industry_rules_dashboard.py
# or
fd-cn-report

# MCP tool
open_industry_rules_dashboard(port=8888)

# 1. Resolve company → 2. find latest annual → 3. pull MD&A → 4. LLM-extract revenue table

co = get_company("600519")
# {"stock_code": "600519", "name": "贵州茅台", "org_id": "gssh0600519", "exchange": "sse", ...}

filings = list_filings("600519", form="年度报告", year=2023, limit=3)
# [{"announcement_id": "1219730876", "pdf_url": "http://static.cninfo.com.cn/.../*.PDF", ...}]

sec = get_section("600519", year=2023, section="管理层讨论与分析")
# {"text": "<full MD&A body>", "pdf_url": "...", "outline_entry": {...}, ...}

records = ai_extract(
    text=sec["text"],
    schema={"type": "object", "properties": {
        "segment": {"type": "string"},
        "revenue_2023": {"type": "string"},
    }, "required": ["segment", "revenue_2023"]},
)
# {"records": [{"segment": "茅台酒", "revenue_2023": "139,989,000,000"}, ...]}

catalog = list_report_types()
# {"groups": [{"name": "定期报告", "categories": [...]}, {"name": "融资", ...}, ...], "count": 26}

list_report_types(group="融资")
# {"group": "融资", "categories": [{name: "首发", code: "category_sf_szsh", ...}, ...], "count": 6}

filings = list_filings("600519", category="首发", limit=3)

sec = get_special_report("600519", category="首发", section="募集资金运用")

stmts = get_financial_statements("600519", year=2023)
# {
#   "stock_code": "600519", "company_name": "贵州茅台", "year": 2023,
#   "form": "年度报告", "pdf_url": "...", "cached": False,
#   "statements": {
#     "income_statement": {"title": "2、 合并利润表", "outline_entry": {...}, "char_count": 4521, "text": "..."},
#     "balance_sheet":    {"title": "1、 合并资产负债表", ...},
#     "cashflow":         {"title": "3、 合并现金流量表", ...},
#   },
#   "missing": [],
# }

list_cache()
# {"cache_dir": ".../.cache/reports", "count": 2, "entries": [...]}

clear_cache()                              # evict everything
clear_cache(stock_code="600519")           # evict one company
clear_cache(stock_code="600519", year=2023) # evict one company + year

# Preview → pull one → pull all → CSV
list_indicators(company="工商银行")           # rules applicable to 工商银行
get_indicator("资本充足率", "工商银行", 2023)  # one value
extract_indicators("工商银行", 2023)           # all applicable, one PDF fetch
extract_indicators("工商银行", 2023,
                   indicators=["资本充足率","不良率"])  # subset
extract_indicators("工商银行", 2023, extractor_mode="python")  # LLM-free
extract_indicators_by_position("工商银行", 2023)  # CSV-driven

extract_indicators_by_position("工商银行", 2023, form="第一季度报告")
extract_indicators("贵州茅台", 2023, form="半年度报告")

extract_indicators("工商银行", 2023, concurrency=4)  # explicit cap
extract_indicators("工商银行", 2023, concurrency=1)  # sequential

# Batch: multi-company concurrent extraction
extract_indicators_batch([("601398", 2023), ("600519", 2023)],
                         concurrency=2, extract_concurrency=4)
# → {"results": {"601398_2023": {...}, ...}, "failures": [...], "concurrency": 2}

# Full engine extraction
python scripts/extract_indicators.py 601398 --year 2023 \
    [--rules indicator_rules.json] [--extractor auto|llm|python] \
    [--indicators 资本充足率,不良率] [--out-dir ./out]

# CSV-driven extraction
python scripts/extract_indicators_by_position.py 601398 --year 2023 \
    [--csv docs/indicators_position.csv] [--extractor auto|llm|python] \
    [--form 年度报告|半年度报告|第一季度报告|第三季度报告]

# Multi-year extraction
python scripts/extract_indicators_multiyear.py 601398 2023 2024

# Industry rules dashboard
python scripts/industry_rules_dashboard.py [port]
# or: fd-cn-report

# Generate industry rules from real reports
python scripts/generate_rules_from_real_reports.py

# Check industry coverage
python scripts/check_industry_coverage.py

# Seed industry rules
python scripts/seed_industry_rules.py

get_hk_company("00700")                    # → 腾讯控股
list_hk_filings("00700", year=2023)        # → HKEX filings
get_hk_financials("00700")                 # → financial statements
get_hk_section("00700", year=2023, section="管理层讨论与分析")

# SSE (上交所) - 600/601/603/605/688/900 codes
get_sse_company("600519")
list_sse_filings("600519", year=2023)                         # -> sse.com.cn disclosures
get_sse_section("600519", year=2023, section="管理层讨论与分析")
get_sse_interaction("600519")                                  # -> 上证e互动 Q&A

# SZSE (深交所) - 000/001/002/003/300/301 codes
get_szse_company("000001")
list_szse_filings("000001", year=2023)                        # -> szse.cn disclosures
get_szse_section("000001", year=2023, section="管理层讨论与分析")
get_szse_interaction("000001")                                 # -> 互动易 Q&A (irm.cninfo.com.cn)

# BSE (北交所) - 430xxx / 83xxxx / 87xxxx / 88xxxx / 920xxx codes
get_bse_company("835185")
list_bse_filings("835185", year=2023)                         # -> BSE-native, else CNINFO fallback
get_bse_section("835185", year=2023, section="管理层讨论与分析")  # result carries `source`

list_csrc_filings(begin_date="2024-01-01")              # -> regulatory announcements
get_csrc_ipo_review("贵州茅台")                          # -> IPO review status row
get_csrc_merger_review("某科技股份公司")                 # -> M&A review status row
list_csrc_enforcement()                                 # -> administrative-penalty actions

list_ministries()                       # -> [{id, label, en, transport, base}, ...]
get_nbs_stat("A0201")                   # -> NBS GDP series {period: value}  (dbcode="hgnd" annual)
get_ministry_stat("gacc")               # -> GACC trade page parsed into HTML tables
get_ministry_stat("pboc", limit=20)     # -> PBoC monetary tables
# Supported ids: nbs mof pboc safe gacc nfra

uv sync                    # installs akshare, pypdf, fastmcp, ...
uv run python server.py    # FastMCP over stdio

uv run python selfcheck.py           # DB + outline + company API + special reports
uv run python selfcheck_cache.py     # report cache + three-statements extraction

uv run --with pytest python -m pytest test_cnreport.py -v -p no:logfire

fd-cn-report/
├── server.py                      # FastMCP server (@app.tool registrations)
├── cninfo_client.py               # CNINFO API (keyless lookup + query)
├── hk_stock_client.py             # HK stock API (akshare + HKEX)
├── financials_client.py           # akshare financial statements (lazy)
├── cnreport_tools.py              # Pure helpers (outline, extract, LLM, ES)
├── report_cache.py                # On-disk PDF + text + outline cache
├── llm_section_cache.py           # LLM response section cache
│
├── indicators_client.py           # Rules engine (load, profile, route, extract)
├── indicators_extractors.py       # Pluggable Python extractors
├── indicators_models.py           # Pydantic extraction models
├── indicators_csv_migration.py    # CSV → JSON rule migration
├── report_section_map.py          # Section alias expansion + matching
│
├── rules_db.py                    # Rules database (SQLite via SQLAlchemy)
├── rules_models.py                # Pydantic rule models
├── rules_skills.py                # LLM rule generation + validation
├── cnreport_models.py             # ORM models (LlmRule, ScriptRule)
├── cnreport_database.py           # Database connection management
│
├── industry_taxonomy.py           # 申万 L1 industry taxonomy
├── industry_coverage.py           # Coverage checks for industry rules
│
├── docs/
│   ├── industry_taxonomy.json     # 31 industry taxonomy
│   ├── industry_indicator_baseline.json  # Baseline indicators per industry
│   ├── indicators_position.csv    # Indicator catalog (CSV source)
│   └── indicators-methodology.md  # Rendered methodology
│
├── scripts/
│   ├── industry_rules_dashboard.py          # Web dashboard (CLI + MCP)
│   ├── generate_rules_from_real_reports.py  # Per-industry rule generation
│   ├── generate_all_industry_rules.py       # LLM rule generation
│   ├── seed_industry_rules.py               # Universal rule seeding
│   ├── seed_missing_industry_rules.py       # Industry-specific seeding
│   ├── extract_indicators.py                # Standalone extraction CLI
│   ├── extract_indicators_by_position.py    # CSV-driven extraction CLI
│   ├── extract_indicators_multiyear.py      # Multi-year batch extraction
│   ├── check_industry_coverage.py           # Coverage validation
│   ├── migrate_indicators_csv.py            # CSV → DB migration
│   └── rules_dashboard.py                   # indicator_rules.json editor
│
└── .cache/reports/                # Downloaded PDFs + extracted text + outlines