goodwe-addon/goodwe_controller/tools/maint21_same_ast.py

#!/usr/bin/env python3
"""MAINT-21: prove that splitting app/main.py moved code and changed none.

    python3 goodwe_controller/tools/maint21_same_ast.py [BASE_REF] [--docstrings]

Every module-level def, class and assignment of app/main.py at BASE_REF
(default release/1.0), and every method of its `Controller`, is looked up by
qualified name in the working tree: app/main.py, app/rows.py and the mixin
classes of app/ctl_*.py (a mixin's methods count as `Controller.<name>`).
Each must be found exactly once with an identical `ast.dump()`, docstrings
removed unless --docstrings. Allowed extras: the `Controller` class header,
`_LOG = logging.getLogger("goodwe")` in a module that logs, and import lines.
Prints one line per file and `OK` or the differences. The diff against
BASE_REF may touch only goodwe_controller/app, DECISIONS, test_*.py and
tools. Run from the repository root on a clean checkout (untracked files are
read, but the diff check only sees tracked ones). Exit 1 on any difference.
"""
import ast
import collections
import glob
import os
import re
import subprocess
import sys

APP = "goodwe_controller/app"
MIXIN = re.compile(r"^[A-Z][A-Za-z]*Mixin$")


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


def bare(n, docstrings):
    if not docstrings:
        for x in ast.walk(n):
            if isinstance(x, (ast.FunctionDef, ast.AsyncFunctionDef,
                              ast.ClassDef)) and x.body:
                e = x.body[0]
                if (isinstance(e, ast.Expr) and isinstance(e.value, ast.Constant)
                        and isinstance(e.value.value, str)):
                    x.body = x.body[1:] or [ast.Pass()]
    return ast.dump(n)


def key_of(n):
    if isinstance(n, (ast.FunctionDef, ast.AsyncFunctionDef, ast.ClassDef)):
        return n.name
    if isinstance(n, ast.Assign):
        return "=" + ",".join(ast.unparse(t) for t in n.targets)
    if isinstance(n, ast.AnnAssign):
        return "=" + ast.unparse(n.target)
    return "?" + ast.unparse(n)[:60]


def units(src, docstrings, mixins):
    """{qualified name: [dump, ...]} for one file's text."""
    out = collections.defaultdict(list)
    tree = ast.parse(src)
    for n in tree.body:
        if isinstance(n, (ast.Import, ast.ImportFrom)):
            continue
        if (isinstance(n, ast.Expr) and isinstance(n.value, ast.Constant)
                and isinstance(n.value.value, str)):
            continue
        if isinstance(n, ast.ClassDef) and (
                n.name == "Controller" or (mixins and MIXIN.match(n.name))):
            for m in n.body:
                out["Controller." + key_of(m)].append(bare(m, docstrings))
            continue
        out[key_of(n)].append(bare(n, docstrings))
    return out


def main(argv):
    docstrings = "--docstrings" in argv
    argv = [a for a in argv if not a.startswith("--")]
    base = argv[0] if argv else "release/1.0"
    bad = 0
    print(f"base {base} = {git('rev-parse', base).strip()}")
    for f in git("diff", "--name-only", base).split():
        if not re.match(r"^goodwe_controller/(app/[^/]+|DECISIONS/[^/]+|"
                        r"test_[^/]+\.py|tools/[^/]+)$", f):
            print(f"FAIL: diff touches {f}")
            bad += 1
    old = units(git("show", f"{base}:{APP}/main.py"), docstrings, False)
    files = ["main.py", "rows.py"] + sorted(
        os.path.basename(p) for p in glob.glob(f"{APP}/ctl_*.py"))
    where = collections.defaultdict(list)       # key -> [(file, dump)]
    for fn in files:
        p = f"{APP}/{fn}"
        if not os.path.exists(p):
            continue
        for k, dumps in units(open(p, encoding="utf-8").read(), docstrings,
                              True).items():
            for d in dumps:
                where[k].append((fn, d))
    found = collections.Counter()
    problems = collections.defaultdict(list)
    for k, dumps in old.items():
        if k == "Controller":
            continue
        got = where.get(k, [])
        if k == "=_LOG":        # one per module that logs, all the same
            got = got[:1] * len(dumps) if all(
                d == dumps[0] for _, d in got) else []
        if len(got) != len(dumps):
            problems["?"].append(f"{k}: {len(dumps)} in base, "
                                 f"{len(got)} in head")
            continue
        for (fn, d), want in zip(got, dumps):
            if d != want:
                problems[fn].append(f"{k}: AST differs")
            else:
                found[fn] += 1
    for k, got in where.items():
        if k not in old and k != "=_LOG":
            for fn, _ in got:
                problems[fn].append(f"{k}: not in base")
    for fn in files:
        if not os.path.exists(f"{APP}/{fn}"):
            continue
        if problems.get(fn):
            print(f"DIFFERS  {fn}")
            for line in problems[fn]:
                print("   ", line)
            bad += len(problems[fn])
        else:
            print(f"OK       {fn}  {found[fn]} units identical")
    for line in problems.get("?", []):
        print("DIFFERS ", line)
        bad += 1
    total = sum(found.values())
    print(f"base units {sum(len(v) for k, v in old.items() if k != 'Controller')}"
          f", identical in head {total}")
    print("OK: code moved, none changed" if not bad else f"FAIL: {bad} problem(s)")
    return 1 if bad else 0


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