#!/usr/bin/env python3
"""Scan tools/*.py for DRY smells: repeated sum(1 for ...)/list-comprehension patterns,
duplicated function bodies, and other refactor candidates."""
import ast, os, hashlib, collections, sys

REPO = "/root/troupe-standup"
TOOLS = os.path.join(REPO, "tools")

def scan_file(path):
    src = open(path, encoding="utf-8").read()
    lines = src.splitlines()
    info = collections.Counter()

    # sum(1 for ... patterns - potential DRY
    info["sum_gen"] = sum(1 for l in lines if "sum(1 for" in l)
    # len([...]) vs len([...])  patterns
    info["len_listcomp"] = sum(1 for l in lines if "len([" in l or "len([" in l)
    # list comprehensions that filter
    info["listcomp_filter"] = sum(1 for l in lines if "if r[" in l)
    # count() calls on lists
    info["count_method"] = sum(1 for l in lines if ".count(" in l)
    # manual counting loops
    info["manual_count"] = sum(1 for l in lines if "+= 1" in l)

    # Find repeated string literals / patterns
    # Look for duplicated .strip() calls, split() calls etc.

    # Check for duplicate function bodies using AST
    try:
        tree = ast.parse(src)
        funcs = [(node.name, node.body) for node in ast.walk(tree) if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef))]
        # hash each function body
        body_hashes = {}
        for name, body in funcs:
            h = hashlib.sha256(ast.unparse(body).encode()).hexdigest()[:12]
            body_hashes.setdefault(h, []).append(name)
        dup_funcs = {h: names for h, names in body_hashes.items() if len(names) > 1}
    except Exception as e:
        dup_funcs = {}
        funcs = []

    # Find repeated string patterns (lines that appear 3+ times)
    line_counts = collections.Counter(l.strip() for l in lines if l.strip())
    repeated_lines = [(l, c) for l, c in line_counts.items() if c >= 3 and len(l) > 15]

    return info, dup_funcs, repeated_lines, len(lines), funcs

for f in sorted(os.listdir(TOOLS)):
    if not f.endswith(".py") or f.startswith("_"):
        continue
    path = os.path.join(TOOLS, f)
    info, dup_funcs, repeated, nlines, funcs = scan_file(path)
    if info["sum_gen"] >= 2 or dup_funcs or repeated:
        print(f"\n=== {f} ({nlines} lines, {len(funcs)} funcs) ===")
        if info["sum_gen"]:
            print(f"  sum(1 for ...) x{info['sum_gen']}")
        if info["len_listcomp"]:
            print(f"  len([...]) x{info['len_listcomp']}")
        if info["listcomp_filter"]:
            print(f"  listcomp with if-filter x{info['listcomp_filter']}")
        if info["count_method"]:
            print(f"  .count() calls x{info['count_method']}")
        if info["manual_count"]:
            print(f"  manual +=1 count x{info['manual_count']}")
        if dup_funcs:
            print(f"  DUPLICATE function bodies: {dup_funcs}")
        for l, c in repeated[:5]:
            print(f"  repeated x{c}: {l[:90]}")