inkwell/android/tools/check-strings.py

#!/usr/bin/env python3
"""Check every R.string / R.plurals reference against strings.xml.

Three ways a resource reference compiles and then fails, none of which ktlint,
detekt or the Kotlin compiler will catch:

  1. the name does not exist  -> resource-not-found at runtime
  2. `stringResource` on a plural (or the reverse) -> wrong overload, wrong text
  3. the format string takes more arguments than the call passes -> the format
     silently renders `%2$s` as literal text, or throws

    python3 android/tools/check-strings.py

Exits non-zero on any problem.
"""

import glob
import os
import re
import sys
import xml.etree.ElementTree as ET

BASE = (
    sys.argv[1]
    if len(sys.argv) > 1
    else os.path.join(os.path.dirname(os.path.abspath(__file__)), "..")
)
STRINGS = os.path.join(BASE, "app", "src", "main", "res", "values", "strings.xml")
SOURCES = os.path.join(BASE, "app", "src", "main", "java", "**", "*.kt")

CALL = re.compile(
    r"(stringResource|pluralStringResource)\(\s*R\.(string|plurals)\.(\w+)"
    r"((?:[^()]|\([^()]*\))*)\)"
)


def arity(text):
    """How many distinct arguments a format string consumes."""
    numbered = set(re.findall(r"%(\d)\$", text))
    return len(numbered) if numbered else len(re.findall(r"%[sd]", text))


def supplied_args(rest):
    """Count top-level commas in an argument tail.

    Kotlin permits a TRAILING comma before the closing paren, which is not an
    argument; counting it would inflate every multi-line call by one. Braces count
    toward depth as well as parens, or a comma inside a lambda would be read as
    another argument.
    """
    rest = rest.rstrip()
    if rest.endswith(","):
        rest = rest[:-1]
    depth = 0
    count = 0
    for ch in rest:
        if ch in "([{":
            depth += 1
        elif ch in ")]}":
            depth -= 1
        elif ch == "," and depth == 0:
            count += 1
    return count


def main():
    root = ET.parse(STRINGS).getroot()
    strings = {e.get("name"): "".join(e.itertext()) for e in root.findall("string")}
    plurals = {
        e.get("name"): max(
            (arity("".join(i.itertext())) for i in e.findall("item")), default=0
        )
        for e in root.findall("plurals")
    }

    problems = 0
    for path in glob.glob(SOURCES, recursive=True):
        with open(path, encoding="utf-8") as fh:
            src = fh.read()
        for match in CALL.finditer(src):
            fn, kind, name, rest = match.groups()
            line = src[: match.start()].count("\n") + 1
            where = f"{os.path.basename(path)}:{line} {name}"

            if kind == "string" and name not in strings:
                print(f"MISSING  {where}: no such string")
                problems += 1
                continue
            if kind == "plurals" and name not in plurals:
                print(f"MISSING  {where}: no such plural")
                problems += 1
                continue
            if (fn == "pluralStringResource") != (kind == "plurals"):
                print(f"KIND     {where}: {fn} used on R.{kind}")
                problems += 1
                continue

            passed = supplied_args(rest)
            # A plural call passes the count first, then the format arguments.
            wanted = arity(strings[name]) if kind == "string" else plurals[name] + 1
            if passed != wanted:
                print(f"ARITY    {where}: wants {wanted}, call passes {passed}")
                problems += 1

    print(f"\n{len(strings)} strings, {len(plurals)} plurals, {problems} problems")
    return 1 if problems else 0


if __name__ == "__main__":
    sys.exit(main())