#!/usr/bin/env -S uv run
# /// script
# requires-python = ">=3.11"
# dependencies = ["gremlinpython", "python-dotenv"]
# ///
import os
from pathlib import Path
from dotenv import load_dotenv
load_dotenv(Path(__file__).parent.parent / ".env.gremlin")
from gremlin_python.driver import client as gc, serializer

c = gc.Client(os.environ["GREMLIN_ENDPOINT"], "g",
    username=os.environ["GREMLIN_USERNAME"],
    password=os.environ["GREMLIN_PASSWORD"],
    message_serializer=serializer.GraphSONSerializersV2d0())

def q(query, b=None):
    return c.submitAsync(query, b or {}).result().all().result()

print("═"*60)
print("Q1: Braid modules with sorries")
print("─"*60)
r = q("g.V().hasLabel('module').has('math_kind','braid').has('sorry_count',gt(0))"
      ".project('module','sorries','theorems')"
      ".by('id').by('sorry_count').by('theorem_count')")
for row in r:
    print(f"  {row['module'].split('.')[-1]:40s}  sorry={row['sorries']}  thm={row['theorems']}")

print()
print("═"*60)
print("Q2: Number_theory modules imported by quantum modules")
print("─"*60)
r = q("g.V().hasLabel('module').has('math_kind','quantum')"
      ".out('imports').has('math_kind','number_theory').dedup()"
      ".project('module','sorries','theorems')"
      ".by('id').by('sorry_count').by('theorem_count')")
for row in r:
    print(f"  {row['module'].split('.')[-1]:40s}  sorry={row.get('sorries','?')}  thm={row.get('theorems','?')}")

print()
print("═"*60)
print("Q3: Top theorem-producing modules per math_kind")
print("─"*60)
for kind in ["braid","number_theory","quantum","geometry","algebra"]:
    r = q("g.V().hasLabel('module').has('math_kind',mk)"
          ".order().by('theorem_count',decr).limit(3)"
          ".project('m','t').by('id').by('theorem_count')",
          {"mk": kind})
    tops = ", ".join(f"{x['m'].split('.')[-1]}({x['t']})" for x in r)
    print(f"  {kind:15s}: {tops}")

print()
print("═"*60)
print("Q4: Modules with both high theorem count AND sorries")
print("─"*60)
r = q("g.V().hasLabel('module').has('theorem_count',gt(5)).has('sorry_count',gt(0))"
      ".order().by('sorry_count',decr)"
      ".project('m','s','t','k')"
      ".by('id').by('sorry_count').by('theorem_count').by('math_kind')")
for row in r:
    print(f"  {row['m'].split('.')[-1]:40s}  sorry={row['s']}  thm={row['t']}  [{row['k']}]")

c.close()