#!/usr/bin/env python3
"""MAINT-20: prove a comment/docstring cut changed no code, and show the ratio.

    python3 goodwe_controller/tools/maint20_same_code.py [BASE_REF] [FILE ...]

For each FILE (default: every goodwe_controller/app/*.py that differs from
BASE_REF, default release/1.0) the ast.dump() of the tree with docstrings
removed must be identical at BASE_REF and in the working tree. Also prints
code lines vs comment-only + docstring lines (whole lines, via tokenize) before
and after. Run from the repository root. Exit 1 on any code difference.
"""
import ast
import io
import subprocess
import sys
import tokenize

SCOPES = (ast.Module, ast.FunctionDef, ast.AsyncFunctionDef, ast.ClassDef)


def docstring(n):
    if isinstance(n, SCOPES) and n.body:
        e = n.body[0]
        if (isinstance(e, ast.Expr) and isinstance(e.value, ast.Constant)
                and isinstance(e.value.value, str)):
            return e
    return None


def dump(src):
    tree = ast.parse(src)
    for n in ast.walk(tree):
        if docstring(n) is not None:
            n.body = n.body[1:] or [ast.Pass()]
    return ast.dump(tree)


def counts(src):
    doc = set()
    for n in ast.walk(ast.parse(src)):
        e = docstring(n)
        if e is not None:
            doc.update(range(e.lineno, e.end_lineno + 1))
    skip = (tokenize.NL, tokenize.NEWLINE, tokenize.INDENT, tokenize.DEDENT,
            tokenize.ENDMARKER, tokenize.COMMENT)
    code, com = set(), set()
    for tk in tokenize.generate_tokens(io.StringIO(src).readline):
        if tk.type == tokenize.COMMENT:
            com.add(tk.start[0])
        elif tk.type not in skip:
            code.update(range(tk.start[0], tk.end[0] + 1))
    code -= doc
    return len(code), len(doc) + len(com - code - doc)


def git(*a):
    return subprocess.run(["git", *a], check=True, capture_output=True,
                          text=True).stdout


def main(argv):
    base = argv[0] if argv else "release/1.0"
    files = argv[1:] or [
        f for f in git("diff", "--name-only", base, "--",
                       "goodwe_controller/app").split()
        if f.endswith(".py")]
    bad = 0
    print(f"base {base} = {git('rev-parse', base).strip()}")
    for f in files:
        old = git("show", f"{base}:{f}")
        new = open(f, encoding="utf-8").read()
        same = dump(old) == dump(new)
        (c0, m0), (c1, m1) = counts(old), counts(new)
        print(f"{'SAME CODE' if same else 'CODE DIFFERS'}  {f}  "
              f"code {c0}->{c1}  comment+doc {m0}->{m1}  "
              f"ratio {m0 / c0:.2f}->{m1 / c1:.2f}")
        bad += not same
    print("OK: no code change" if not bad else f"FAIL: {bad} file(s) differ")
    return 1 if bad else 0


if __name__ == "__main__":
    sys.exit(main(sys.argv[1:]))