Remove the boost test runner

[rustaceanrob]

Replaces the boost test runner with a simple header-only variant. Simplifies the macros to the following:

• CHECK, valid with any comparison operator (e.g. ==, !=), optional message
• REQUIRE, valid with any comparison operator, optional message
• CHECK_EQUAL_RANGES, better debugging for vectors
• THROW_*, macros for checking throwing conditions
• Info and warn messages

This framework has 4 log levels, offers test filtering, and also includes suites and fixtures. The runner executes in approximately the same time as boost, and should compile faster as well.

A list of a few advantages over boost in addition to macro simplification:

• Compilation fails when attempting to compare integers with different sign types
• Types that implement ToString are printed when CHECK or REQUIRE fails
• Flexible to additions (ABORT or ASSERT macros that fail-fast)

To try it out:

./build/bin/test_bitcoin -l=info

./build/bin/test_bitcoin -t=versionbits_tests

On commit 1 and commit 2, these are given by guidance of Catch2. && conditions are unrolled into two separate checks.

Replace all boost macros (third commit)

import argparse
import re
import sys
from pathlib import Path


# ---------------------------------------------------------------------------
# Parser primitives
# ---------------------------------------------------------------------------

_DIGIT_SEP_PREV = set("0123456789abcdefABCDEF'")


def _is_char_literal_open(text: str, i: int) -> bool:
    """A `'` at position i is a char-literal opener unless the previous
    character is a digit, hex letter, or another digit separator (C++14
    digit-separator usage like 1'000'000 or 0xFF'FF)."""
    return i == 0 or text[i - 1] not in _DIGIT_SEP_PREV


def find_matching_paren(text: str, open_idx: int) -> int | None:
    """Return index of ')' that matches '(' at open_idx, respecting brackets,
    braces, and string/char literals."""
    assert text[open_idx] == "("
    depth = 0
    i = open_idx
    in_str = False
    in_char = False
    while i < len(text):
        c = text[i]
        if in_str:
            if c == "\\":
                i += 2
                continue
            if c == '"':
                in_str = False
        elif in_char:
            if c == "\\":
                i += 2
                continue
            if c == "'":
                in_char = False
        elif c == '"':
            in_str = True
        elif c == "'" and _is_char_literal_open(text, i):
            in_char = True
        elif c in "([{":
            depth += 1
        elif c in ")]}":
            depth -= 1
            if depth == 0:
                return i
        i += 1
    return None


def _is_binary_context(text: str, i: int) -> bool:
    """At position i (start of `|`, `&`, or `^`), is the previous non-whitespace
    character one that makes this a binary operator (not unary `&`)?"""
    j = i - 1
    while j >= 0 and text[j] in " \t\n":
        j -= 1
    if j < 0:
        return False
    return text[j].isalnum() or text[j] in "_)]}\"'"


def needs_parens(expr: str) -> bool:
    """True if expr contains a top-level operator that would interact badly
    with the framework's Decomposer (which captures via `<=`, applies one
    comparison via CapturedExpression's overloads, then yields a Result that
    has no operators).

    Detected: `&&`, `||`, `==`, `!=`, `<=`, `>=`, `|`, `&`, `^`. Bare `<` /
    `>` are intentionally skipped because they are commonly template
    brackets (`vector<int>`, `static_cast<T>`) which this scanner can't
    distinguish from comparison without a real C++ parser; if a real
    comparison with bare `<`/`>` ends up in an operand, the resulting build
    error is easy to spot and fix at the call site.

    Compound assignments (|=, &=, ^=) and unary `&` (address-of) are skipped."""
    depth = 0
    i = 0
    in_str = False
    in_char = False
    n = len(expr)
    while i < n:
        c = expr[i]
        if in_str:
            if c == "\\":
                i += 2
                continue
            if c == '"':
                in_str = False
            i += 1
            continue
        if in_char:
            if c == "\\":
                i += 2
                continue
            if c == "'":
                in_char = False
            i += 1
            continue
        if c == '"':
            in_str = True
            i += 1
            continue
        if c == "'" and _is_char_literal_open(expr, i):
            in_char = True
            i += 1
            continue
        if c in "([{":
            depth += 1
            i += 1
            continue
        if c in ")]}":
            depth -= 1
            i += 1
            continue
        if depth == 0:
            two = expr[i : i + 2] if i + 1 < n else ""
            if two in ("&&", "||", "==", "!=", "<=", ">="):
                return True
            if c in "|&^" and two[1:] != "=" and _is_binary_context(expr, i):
                return True
        i += 1
    return False


# Backwards-compat alias for has_top_level_bitwise's old name.
has_top_level_bitwise = needs_parens


def wrap_if_bitwise(expr: str) -> str:
    expr = expr.strip()
    return f"({expr})" if needs_parens(expr) else expr


def split_top_level_args(args: str) -> list[str]:
    """Split macro arg-list on top-level commas."""
    parts: list[str] = []
    depth = 0
    last = 0
    i = 0
    in_str = False
    in_char = False
    while i < len(args):
        c = args[i]
        if in_str:
            if c == "\\":
                i += 2
                continue
            if c == '"':
                in_str = False
        elif in_char:
            if c == "\\":
                i += 2
                continue
            if c == "'":
                in_char = False
        elif c == '"':
            in_str = True
        elif c == "'" and _is_char_literal_open(args, i):
            in_char = True
        elif c in "([{":
            depth += 1
        elif c in ")]}":
            depth -= 1
        elif c == "," and depth == 0:
            parts.append(args[last:i])
            last = i + 1
        i += 1
    parts.append(args[last:])
    return parts


# ---------------------------------------------------------------------------
# Macro tables
# ---------------------------------------------------------------------------

SIMPLE_RENAMES = {
    "BOOST_CHECK": "CHECK",
    "BOOST_REQUIRE": "REQUIRE",
    "BOOST_TEST": "CHECK",
    "BOOST_TEST_REQUIRE": "REQUIRE",
    "BOOST_CHECK_NO_THROW": "CHECK_NOTHROW",
    "BOOST_REQUIRE_NO_THROW": "REQUIRE_NOTHROW",
    "BOOST_CHECK_THROW": "CHECK_THROWS_AS",
    "BOOST_CHECK_EXCEPTION": "CHECK_EXCEPTION",
    "BOOST_TEST_MESSAGE": "TEST_MESSAGE",
    "BOOST_WARN_MESSAGE": "WARN_MESSAGE",
}

MESSAGE_RENAMES = {
    "BOOST_CHECK_MESSAGE": "CHECK",
    "BOOST_REQUIRE_MESSAGE": "REQUIRE",
}

COMPARISON_REWRITES = {
    "BOOST_CHECK_EQUAL":   ("CHECK", "=="),
    "BOOST_REQUIRE_EQUAL": ("REQUIRE", "=="),
    "BOOST_CHECK_NE":      ("CHECK", "!="),
    "BOOST_CHECK_LT":      ("CHECK", "<"),
    "BOOST_CHECK_LE":      ("CHECK", "<="),
    "BOOST_CHECK_GT":      ("CHECK", ">"),
    "BOOST_CHECK_GE":      ("CHECK", ">="),
    "BOOST_REQUIRE_NE":    ("REQUIRE", "!="),
    "BOOST_REQUIRE_LT":    ("REQUIRE", "<"),
    "BOOST_REQUIRE_LE":    ("REQUIRE", "<="),
    "BOOST_REQUIRE_GT":    ("REQUIRE", ">"),
    "BOOST_REQUIRE_GE":    ("REQUIRE", ">="),
}

COMMENTED_OUT = (
    "BOOST_TEST_INFO",
    "BOOST_TEST_INFO_SCOPE",
)

REPORTED_ONLY = (
    "BOOST_CHECK_CLOSE",
)

STRUCTURAL_MACROS = (
    "BOOST_AUTO_TEST_CASE",
    "BOOST_FIXTURE_TEST_CASE",
    "BOOST_AUTO_TEST_SUITE",
    "BOOST_FIXTURE_TEST_SUITE",
    "BOOST_AUTO_TEST_SUITE_END",
    "BOOST_CHECK_EQUAL_COLLECTIONS",
    "BOOST_ERROR",
)

ALL_KNOWN = (
    list(SIMPLE_RENAMES)
    + list(MESSAGE_RENAMES)
    + list(COMPARISON_REWRITES)
    + list(COMMENTED_OUT)
    + list(REPORTED_ONLY)
    + list(STRUCTURAL_MACROS)
)
# Longer names first so the alternation doesn't match a prefix.
KNOWN_SORTED = sorted(set(ALL_KNOWN), key=len, reverse=True)
MACRO_RE = re.compile(r"\b(" + "|".join(re.escape(m) for m in KNOWN_SORTED) + r")\s*\(")


# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------

def quote_name(name_arg: str) -> str:
    return f'"{name_arg.strip()}"'


def collapse_iter_pair(begin_expr: str, end_expr: str) -> str:
    """X.begin()/X.end() -> X. X->begin()/X->end() -> *X. Else subrange()."""
    b = begin_expr.strip()
    e = end_expr.strip()
    m_b = re.match(r"^(.+)\.begin\s*\(\s*\)$", b)
    m_e = re.match(r"^(.+)\.end\s*\(\s*\)$", e)
    if m_b and m_e and m_b.group(1).strip() == m_e.group(1).strip():
        return m_b.group(1).strip()
    m_b = re.match(r"^(.+)->begin\s*\(\s*\)$", b)
    m_e = re.match(r"^(.+)->end\s*\(\s*\)$", e)
    if m_b and m_e and m_b.group(1).strip() == m_e.group(1).strip():
        return f"*({m_b.group(1).strip()})"
    return f"std::ranges::subrange({b}, {e})"


# ---------------------------------------------------------------------------
# Main rewrite
# ---------------------------------------------------------------------------

def rewrite_includes_and_module(text: str) -> str:
    # Any boost/test include -> framework include.
    text = re.sub(
        r"^#include\s*<boost/test/[^>]+>\s*$",
        "#include <test/util/framework.hpp>",
        text,
        flags=re.MULTILINE,
    )
    # BOOST_TEST_MODULE in standalone test files -> framework main hook.
    text = re.sub(
        r"^#define\s+BOOST_TEST_MODULE\b.*$",
        "#define BITCOIN_TEST_MAIN",
        text,
        flags=re.MULTILINE,
    )
    # Collapse adjacent duplicate framework includes (a boost file may have
    # included two headers from boost/test/).
    text = re.sub(
        r"(#include <test/util/framework\.hpp>\n)(?:[ \t]*#include <test/util/framework\.hpp>\n)+",
        r"\1",
        text,
    )
    return text


def file_namespaces(text: str) -> set[str]:
    """Return the set of namespace names declared anywhere in the file. Used
    to decide whether to wrap a test suite body in a matching namespace —
    Boost.Test opens `namespace <suite>` implicitly, but the framework does
    not, so a fixture/helper defined in `namespace foo` won't be visible
    inside the suite body without an explicit re-open."""
    return set(re.findall(r"^[ \t]*namespace[ \t]+([A-Za-z_][A-Za-z0-9_]*)[ \t]*\{", text, re.MULTILINE))


def rewrite_macros(text: str):
    """Walk macro calls in order, applying conversions while tracking the
    current fixture-suite stack. Returns (new_text, reports)."""
    out: list[str] = []
    cursor = 0
    # Each entry: (fixture-or-None, opened-namespace-or-None)
    suite_stack: list[tuple[str | None, str | None]] = []
    declared_namespaces = file_namespaces(text)
    reports: dict[str, list[int]] = {}

    for m in MACRO_RE.finditer(text):
        macro = m.group(1)
        call_start = m.start()
        paren_open = m.end() - 1
        paren_close = find_matching_paren(text, paren_open)
        if paren_close is None:
            continue
        args_text = text[paren_open + 1 : paren_close]
        line = text.count("\n", 0, call_start) + 1

        replacement: str | None = None

        if macro in SIMPLE_RENAMES:
            target = SIMPLE_RENAMES[macro]
            # CHECK/REQUIRE go through Decomposer; a stray top-level bitwise
            # op would be applied to a Result. Wrap the whole expression.
            if target in ("CHECK", "REQUIRE") and has_top_level_bitwise(args_text):
                replacement = f"{target}(({args_text}))"
            else:
                replacement = f"{target}({args_text})"

        elif macro in MESSAGE_RENAMES:
            args = split_top_level_args(args_text)
            if len(args) >= 2:
                expr = wrap_if_bitwise(args[0])
                msg = ",".join(args[1:]).strip()
                replacement = f"{MESSAGE_RENAMES[macro]}({expr}, {msg})"

        elif macro in COMPARISON_REWRITES:
            new_name, op = COMPARISON_REWRITES[macro]
            args = split_top_level_args(args_text)
            if len(args) == 2:
                a = wrap_if_bitwise(args[0])
                b = wrap_if_bitwise(args[1])
                replacement = f"{new_name}({a} {op} {b})"

        elif macro == "BOOST_CHECK_EQUAL_COLLECTIONS":
            args = split_top_level_args(args_text)
            if len(args) == 4:
                lhs = collapse_iter_pair(args[0], args[1])
                rhs = collapse_iter_pair(args[2], args[3])
                replacement = f"CHECK_EQUAL_RANGES({lhs}, {rhs})"

        elif macro == "BOOST_ERROR":
            replacement = f"CHECK(false, {args_text.strip()})"

        elif macro == "BOOST_AUTO_TEST_CASE":
            args = split_top_level_args(args_text)
            name = quote_name(args[0])
            fixture = suite_stack[-1][0] if suite_stack else None
            if fixture:
                replacement = f"FIXTURE_TEST_CASE({name}, {fixture})"
            else:
                replacement = f"TEST_CASE({name})"

        elif macro == "BOOST_FIXTURE_TEST_CASE":
            args = split_top_level_args(args_text)
            if len(args) >= 2:
                name = quote_name(args[0])
                fixture = args[1].strip()
                replacement = f"FIXTURE_TEST_CASE({name}, {fixture})"

        elif macro == "BOOST_AUTO_TEST_SUITE":
            args = split_top_level_args(args_text)
            suite_name = args[0].strip()
            ns = suite_name if suite_name in declared_namespaces else None
            suite_stack.append((None, ns))
            prefix = f"namespace {ns} {{\n" if ns else ""
            replacement = f'{prefix}TEST_SUITE_BEGIN("{suite_name}")'

        elif macro == "BOOST_FIXTURE_TEST_SUITE":
            args = split_top_level_args(args_text)
            if len(args) >= 2:
                suite_name = args[0].strip()
                fixture = args[1].strip()
                ns = suite_name if suite_name in declared_namespaces else None
                suite_stack.append((fixture, ns))
                prefix = f"namespace {ns} {{\n" if ns else ""
                replacement = f'{prefix}TEST_SUITE_BEGIN("{suite_name}")'

        elif macro == "BOOST_AUTO_TEST_SUITE_END":
            ns = suite_stack.pop()[1] if suite_stack else None
            suffix = f"\n}} // namespace {ns}" if ns else ""
            replacement = f"TEST_SUITE_END(){suffix}"

        elif macro in COMMENTED_OUT:
            replacement = f"/* {macro}({args_text}) */"

        elif macro in REPORTED_ONLY:
            reports.setdefault(macro, []).append(line)

        if replacement is None:
            continue

        out.append(text[cursor:call_start])
        out.append(replacement)
        cursor = paren_close + 1

    out.append(text[cursor:])
    return "".join(out), reports


def find_remaining_boost(text: str, exclude: set[str]) -> dict[str, list[int]]:
    """Scan for any BOOST_* identifier still present, excluding known-allowed
    ones (e.g. macros we deliberately left untouched)."""
    remaining: dict[str, list[int]] = {}
    for m in re.finditer(r"\bBOOST_[A-Z_]+", text):
        name = m.group(0)
        if name in exclude:
            continue
        line = text.count("\n", 0, m.start()) + 1
        remaining.setdefault(name, []).append(line)
    return remaining


def transform(text: str) -> tuple[str, dict[str, list[int]]]:
    text = rewrite_includes_and_module(text)
    text, reports = rewrite_macros(text)
    leftover = find_remaining_boost(text, exclude=set(REPORTED_ONLY))
    for macro, lines in leftover.items():
        reports.setdefault(macro, []).extend(lines)
    return text, reports


# ---------------------------------------------------------------------------
# CLI
# ---------------------------------------------------------------------------

def iter_source_files(paths: list[Path]):
    for p in paths:
        if p.is_file():
            if p.suffix in (".cpp", ".h", ".hpp", ".cc"):
                yield p
            continue
        for f in p.rglob("*"):
            if f.is_file() and f.suffix in (".cpp", ".h", ".hpp", ".cc"):
                yield f


def main() -> int:
    ap = argparse.ArgumentParser(
        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
    )
    ap.add_argument("paths", nargs="+", type=Path)
    ap.add_argument("--check", action="store_true", help="Exit 1 if any file would change")
    ap.add_argument("--quiet", action="store_true")
    args = ap.parse_args()

    total = 0
    changed = 0
    all_reports: dict[Path, dict[str, list[int]]] = {}

    for path in iter_source_files(args.paths):
        total += 1
        original = path.read_text()
        new_text, reports = transform(original)
        if new_text != original:
            changed += 1
            if not args.check:
                path.write_text(new_text)
            if not args.quiet:
                verb = "would rewrite" if args.check else "rewrote"
                print(f"{verb} {path}")
        if reports:
            all_reports[path] = reports

    if all_reports and not args.quiet:
        print("\nUnconverted BOOST_* identifiers (manual review):")
        for path in sorted(all_reports):
            for macro in sorted(all_reports[path]):
                for ln in all_reports[path][macro]:
                    print(f"  {path}:{ln}: {macro}")

    if not args.quiet:
        verb = "would rewrite" if args.check else "rewrote"
        print(f"\n{verb} {changed}/{total} file(s)")

    return 1 if args.check and changed > 0 else 0


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

[ismaelsadeeq]

Concept ACK, nice work

❯ build/bin/test_bitcoin
Running 658 test cases...

658 tests: 658 passed, 0 failed, 0 skipped (26431755 checks)

[josibake]

Concept ACK

Overall, looking great! Did some testing and uncovered a lil bug, will continue reading through the code tomorrow. There are also some stale document comments , not a priority but something to fix before the final pass.

[josibake]

I don't think this is being used. I ran some old justfile commands I had laying around and testdatadir wasn't used, but the tests ran. I suspect this is because test/main.cpp reads framework::user_args() but I don't see opts.passthrough being copied in.

[rustaceanrob]

Should be fixed in eccc7db. Please give 77bf05d a spin when you get a chance.