#!/usr/bin/env python3
"""Inspect gwshop catalog shape: Space Marines chapters, AoS, dedupe stats."""
import json
import pathlib
from collections import Counter

cat = json.loads(pathlib.Path("data/gwshop_catalog.json").read_text(encoding="utf-8"))
entries = cat["entries"]

def show(pred, label, n=6):
    print(f"--- {label}")
    shown = 0
    for e in entries:
        if pred(e):
            p = " > ".join(x for x in (e["system"], e["group"], e["faction"], e["subfaction"], e["class"]) if x)
            print(f"  {e['name'][:60]!r}  ->  {p}")
            shown += 1
            if shown >= n:
                break

show(lambda e: e["group"] == "Space Marines", "Space Marines group samples")
show(lambda e: e["group"] == "Armies of the Imperium" and e["subfaction"], "Imperium with subfaction")
show(lambda e: e["system"] == "Age of Sigmar", "Age of Sigmar samples", 5)
show(lambda e: e["system"] == "The Old World", "Old World samples", 5)
show(lambda e: e["system"] == "Other Games", "Other Games samples", 5)
show(lambda e: e["group"] == "Unit Type", "Unit Type branch", 6)

names = Counter(e["name"].casefold() for e in entries)
dups = {n: c for n, c in names.items() if c > 1}
print("duplicate names:", len(dups), "example:", list(dups.items())[:3])

# faction-level value census for 40k
print("--- 40k factions census")
print(Counter(e["faction"] for e in entries if e["system"] == "Warhammer 40,000").most_common(40))