diff options
| author | hathach <[email protected]> | 2026-08-21 11:07:27 +0700 |
|---|---|---|
| committer | hathach <[email protected]> | 2026-08-21 11:07:27 +0700 |
| commit | 04d0f71984117b8c72349f4584bd9e26a37b129c (patch) | |
| tree | 1d87e53f8b3b6f94da3fcb03a5da5299c7cd815f /tools | |
| parent | 696c7807f543a6c55656d81a8f6d8969584e9614 (diff) | |
ci: scope the build matrix and the HIL run to what a PR affects
Every PR built all 74 legs (2494 example builds on GHA cmake alone) and flashed
all 30 rig boards, whatever it touched. One classifier now walks the PR diff twice
and answers three questions: which families to build, which examples per family,
and which boards run which tests. Fail-open throughout - anything no rule
classifies, any exception, any unusable output falls back to the full matrix, and
a master push always builds everything.
test/hil/helper/hil_select.py moves to tools/ci_select.py: it is no longer HIL-only,
and tools/ is where the build side can import it. test_hil_select.py follows it as
test_ci_select.py.
Rules (docs/superpowers/specs/2026-08-19-ci-build-family-filter-design.md holds the
full table): a port selects the families whose family.cmake references it, and its
role - a dcd change skips host examples and vice versa; a class selects only the
examples whose tusb_config.h enables its CFG_TU[DH]_ macro, following cross-class
includes; an example selects itself; hw/bsp selects its family or board; hw/mcu and
lib select whoever references them. CMake is the reference for all of it - make
follows whatever cmake decides, family.mk is never scanned.
Empty means empty (maintainer ruling): a rule that classifies a path to nothing
selects nothing. Ports no family references, classes no config enables, libs no
example builds and hw/mcu paths that resolve nowhere are all real - nothing
compiles them, so nothing can validate them, and the master-push build is the net.
Structural tests pin each such case with an explicit allowlist, so the day one
stops being empty it fails pre-commit instead of silently narrowing CI.
Per-example builds: build.py grows a repeatable -e, resolved against the targets
CMake actually registered and batched into one `cmake --build --target a b c`.
build_utils mirrors CMake's family_filter (the whole FAMILY_MCUS list, ${...} and
string(TOUPPER ...) resolved) for the cmake side, while the make side keeps
master's algorithm verbatim - the two build systems answer differently and a shared
answer breaks lpc54's make link. hil-build gains this even on a full selection:
1702 example builds become 515.
Transport: the selection travels as a file, never an argv or env var - a mass-sweep
diff selects 261 KB against a 128 KiB exec limit, and E2BIG would fail the step
before its own fallback could run. CircleCI carries the example map inside the
generated config (pipeline parameters cap at 512 chars), swapped into the parameter
defaults by sentinel match, and drops the scoping wholesale if that rewrite fails.
Every PR-derived value written to $GITHUB_ENV/$GITHUB_OUTPUT is character-screened.
Code metrics follow the scoping: metrics.py emits per-example totals, and
metrics_pair_compare compares the (board, example) pairs present on both sides
instead of a scoped run against a full-matrix average.
The selector's own suite gates it in both providers: a selector that exits 0 with
valid-but-wrong JSON is the one failure fail-open cannot catch, so a red suite
means the full matrix.
Diffstat (limited to 'tools')
| -rwxr-xr-x | tools/build.py | 154 | ||||
| -rwxr-xr-x | tools/build_utils.py | 319 | ||||
| -rwxr-xr-x | tools/ci_select.py | 1084 | ||||
| -rwxr-xr-x | tools/get_deps.py | 4 | ||||
| -rw-r--r-- | tools/metrics.py | 46 |
5 files changed, 1571 insertions, 36 deletions
diff --git a/tools/build.py b/tools/build.py index 51d3d0f70..e7ca1c839 100755 --- a/tools/build.py +++ b/tools/build.py @@ -2,6 +2,7 @@ import argparse import random import os +import re import sys import time import subprocess @@ -99,6 +100,53 @@ def get_examples(family): return all_examples +def resolve_example_target_groups(build_targets, examples, board, extra_defines=()): + """Map generic targets onto per-example targets for a filtered build (-e), as ONE + GROUP PER REQUESTED TARGET: 'all' -> the example executables, anything else (e.g. + tinyusb_metrics) passes through as its own single-entry group. + + Grouped rather than flattened because each group becomes one `cmake --build + --target a b c` invocation: the examples of a group build in parallel (flattening + them into one target per invocation serialises the whole leg - measured +39% at + -j4 and +220% at -j32 on stm32f407disco), while separate groups stay ordered, so a + target that must run after the examples still does. + + extra_defines are this build's -D tokens: MAX3421_HOST=1 there decides + only.txt for the max3421 examples (see build_utils.skip_example). + Returns None when no requested example is buildable on this board.""" + buildable = [e for e in examples + if not build_utils.skip_example(e, board, extra_defines)] + if not buildable: + return None + names = list(dict.fromkeys(e.split('/', 1)[1] for e in buildable)) + return [list(names) if t == 'all' else [t] for t in build_targets] + + +_TARGET_HELP_RE = re.compile(r'^([A-Za-z0-9_.+-]+):') +# role/name, the only shape resolve_example_target_groups and the CMake target names accept +EXAMPLE_RE = re.compile(r'[A-Za-z0-9_]+/[A-Za-z0-9_]+') + + +def parse_target_help(text): + """Bare target names out of `cmake --build <dir> --target help`; the Ninja + generator prints one '<name>: phony' line per target. Names containing '/' are + per-directory utility targets (device/edit_cache) or absolute CMakeFiles paths, + never an example target.""" + return {m.group(1) for m in map(_TARGET_HELP_RE.match, text.splitlines()) if m} + + +def cmake_registered_targets(build_dir): + """The targets CMake actually created in build_dir, or None when that cannot be + read. Ground truth: skip.txt/only.txt only mirrors family_filter, so an example + the role CMakeLists never lists (or a stale -e name) still looks buildable to it + and `cmake --build --target <it>` hard-fails. None keeps the mirror's answer.""" + r = subprocess.run(['cmake', '--build', build_dir, '--target', 'help'], + stdout=subprocess.PIPE, stderr=subprocess.STDOUT) + if r.returncode != 0: + return None + return parse_target_help(r.stdout.decode('utf-8', 'replace')) or None + + def print_build_result(board, build_target, status, duration): if isinstance(duration, (int, float)): duration = "{:.2f}s".format(duration) @@ -107,7 +155,7 @@ def print_build_result(board, build_target, status, duration): # ----------------------------- # CMake # ----------------------------- -def cmake_board(board, build_args, build_name, build_cflags, build_targets): +def cmake_board(board, build_args, build_name, build_cflags, build_targets, examples=None, defines=()): ret = [0, 0, 0] start_time = time.monotonic() @@ -120,8 +168,13 @@ def cmake_board(board, build_args, build_name, build_cflags, build_targets): if family == 'espressif': # for espressif, we have to build example individually all_examples = get_examples(family) + if examples is not None: + all_examples = [e for e in all_examples if e in examples] + if not all_examples: + print_build_result(board, 'examples (PR filter)', 2, '-') + return [0, 0, 1] for example in all_examples: - if build_utils.skip_example(example, board): + if build_utils.skip_example(example, board, defines): ret[2] += 1 else: rcmd = run_cmd([ @@ -130,13 +183,40 @@ def cmake_board(board, build_args, build_name, build_cflags, build_targets): ]) ret[0 if rcmd.returncode == 0 else 1] += 1 else: + # the skip.txt/only.txt prefilter reads no configure output: answer it first, + # so a selection this board builds nothing of costs no cmake run at all + if examples is not None: + examples = [e for e in examples + if not build_utils.skip_example(e, board, defines)] + if not examples: + print_build_result(board, 'examples (PR filter)', 2, '-') + return [0, 0, 1] rcmd = run_cmd(['cmake', 'examples', '-B', build_dir, '-GNinja', f'-DBOARD={board}', '-DCMAKE_BUILD_TYPE=MinSizeRel', '-DLINKERMAP_OPTION=-q -f tinyusb/src', *build_args, *build_flags]) if rcmd.returncode == 0: + target_groups = [[t] for t in build_targets] + if examples is not None: + registered = cmake_registered_targets(build_dir) + if registered is not None: + kept = [e for e in examples if e.split('/', 1)[1] in registered] + for e in examples: + if e not in kept: + print_build_result(board, f'{e} (no such target)', 2, '-') + examples = kept + if not examples: + print_build_result(board, 'examples (no such target)', 2, '-') + return [0, 0, 1] + target_groups = resolve_example_target_groups(build_targets, examples, board, defines) + if registered is None: + # ground truth unavailable, so nothing checked these names against + # what CMake created. ninja validates a whole invocation up front: + # one unknown name in the batch builds NOTHING, where a target each + # builds everything up to it. Give up the parallelism, not the work. + target_groups = [[t] for g in target_groups for t in g] cmd = ["cmake", "--build", build_dir, '--parallel', str(parallel_jobs)] - for target in build_targets: - rcmd = run_cmd(cmd + ['--target', target]) + for group in target_groups: + rcmd = run_cmd(cmd + ['--target'] + group) if rcmd.returncode != 0: break ret[0 if rcmd.returncode == 0 else 1] += 1 @@ -148,9 +228,10 @@ def cmake_board(board, build_args, build_name, build_cflags, build_targets): # ----------------------------- # Make # ----------------------------- -def make_one_example(example, board, make_option, build_targets): - # Check if board is skipped - if build_utils.skip_example(example, board): +def make_one_example(example, board, make_option, build_targets, defines=()): + # Check if board is skipped. Make semantics: family.mk decides, not the + # family.cmake MCU list (see build_utils.skip_example). + if build_utils.skip_example(example, board, defines, build_system='make'): print_build_result(board, example, 2, '-') r = 2 else: @@ -171,10 +252,15 @@ def make_one_example(example, board, make_option, build_targets): return ret -def make_board(board, build_args, build_targets): +def make_board(board, build_args, build_targets, examples=None, defines=()): print(build_separator) family = find_family(board); all_examples = get_examples(family) + if examples is not None: + all_examples = [e for e in all_examples if e in examples] + if not all_examples: + print_build_result(board, 'examples (PR filter)', 2, '-') + return [0, 0, 1] start_time = time.monotonic() ret = [0, 0, 0] if family == 'espressif' or family == 'rp2040': @@ -182,7 +268,7 @@ def make_board(board, build_args, build_targets): final_status = 2 else: with Pool(processes=os.cpu_count()) as pool: - pool_args = list((map(lambda e, b=board, o=f"{build_args}", t=build_targets: [e, b, o, t], all_examples))) + pool_args = list((map(lambda e, b=board, o=f"{build_args}", t=build_targets, d=defines: [e, b, o, t, d], all_examples))) r = pool.starmap(make_one_example, pool_args) # sum all element of same index (column sum) ret = list(map(sum, list(zip(*r)))) @@ -194,29 +280,40 @@ def make_board(board, build_args, build_targets): # ----------------------------- # Build Family # ----------------------------- -def build_boards_list(boards, build_defines, build_system, build_name, build_cflags, build_targets): +def build_boards_list(boards, build_defines, build_system, build_name, build_cflags, build_targets, examples=None): ret = [0, 0, 0] + # the -D tokens are part of the skip.txt/only.txt answer (MAX3421_HOST=1), so + # the -e filter has to see them too; sorted+tuple keeps skip_example cacheable + defines = tuple(sorted(build_defines)) for b in boards: r = [0, 0, 0] if build_system == 'cmake': build_args = [f'-D{d}' for d in build_defines] - r = cmake_board(b, build_args, build_name, build_cflags, build_targets) + r = cmake_board(b, build_args, build_name, build_cflags, build_targets, examples, defines) elif build_system == 'make': build_args = ' '.join(f'{d}' for d in build_defines) - r = make_board(b, build_args, build_targets) + r = make_board(b, build_args, build_targets, examples, defines) ret[0] += r[0] ret[1] += r[1] ret[2] += r[2] return ret -def get_family_boards(family, one_random, one_first): +def get_family_boards(family, one_random, one_first, examples=None, build_system='cmake'): """Get list of boards for a family. Args: family: Family name one_random: If True, return only one random board one_first: If True, return only the first board (alphabetical) + examples: PR example filter (-e). The one-board pick then prefers a board that + can build at least one of them: the family is in the matrix BECAUSE some + board of it builds these examples (ci_select._prune_buildable asks about + every board, since CircleCI builds every board), but GHA builds one. Without + this, lpc54 selected for host/msc_file_explorer picks lpcxpresso54114 - + which every one of those examples skips - and the leg runs to green having + compiled nothing and uploaded no metrics. + build_system: which skip answer to ask for; the two differ (build_utils) Returns: List of board names @@ -238,12 +335,19 @@ def get_family_boards(family, one_random, one_first): # If only-one flags are set, honor select list first, then pick first or random if one_first or one_random: - if preferred_list: + def buildable(board): + # no filter, or nothing in the filter is buildable anywhere: keep today's + # answer rather than inventing a different board + return examples is None or any( + not build_utils.skip_example(e, board, (), build_system) for e in examples) + + if preferred_list and buildable(preferred_list[0]): return [preferred_list[0]] + candidates = [b for b in all_boards if buildable(b)] or all_boards if one_first: - return [all_boards[0]] + return [candidates[0]] if one_random: - return [random.choice(all_boards)] + return [random.choice(candidates)] return all_boards @@ -272,6 +376,8 @@ def main(): parser.add_argument('-j', '--jobs', type=int, default=os.cpu_count(), help='Number of jobs to run in parallel') parser.add_argument('-T', '--target', action='append', default=[], help='Build target to use, may be specified multiple times (default: all)') + parser.add_argument('-e', '--example', action='append', default=[], + help='Only build these examples (role/name, repeatable). Default: all examples') parser.add_argument('-v', '--verbose', action='store_true', help='Verbose output') args = parser.parse_args() @@ -285,9 +391,20 @@ def main(): one_random = args.one_random one_first = args.one_first build_targets = args.target if args.target else ['all'] + examples = args.example or None verbose = args.verbose parallel_jobs = args.jobs + for e in args.example: + if not EXAMPLE_RE.fullmatch(e): + parser.error(f"-e/--example takes 'role/name' (e.g. device/cdc_msc), got '{e}'") + # a name no example dir answers to would silently build nothing on every board + # and still exit 0 (every row is a Skipped, and main() returns the FAILED count). + # The -e lists are generated - from ci_select's example map and from HIL roster + # test names - so a stale one must be loud, not green + if not os.path.isdir(os.path.join('examples', e)): + parser.error(f"-e/--example '{e}': no such example directory examples/{e}") + build_defines.append(f'TOOLCHAIN={toolchain}') if len(families) == 0 and len(boards) == 0: @@ -317,10 +434,11 @@ def main(): # get boards from families and append to boards list all_boards = list(boards) for f in all_families: - all_boards.extend(get_family_boards(f, one_random, one_first)) + all_boards.extend(get_family_boards(f, one_random, one_first, examples, build_system)) # build all boards - result = build_boards_list(all_boards, build_defines, build_system, build_name, build_cflags, build_targets) + result = build_boards_list(all_boards, build_defines, build_system, build_name, build_cflags, build_targets, + examples) total_time = time.monotonic() - total_time print(build_separator) diff --git a/tools/build_utils.py b/tools/build_utils.py index d80ceea7c..2af8fd624 100755 --- a/tools/build_utils.py +++ b/tools/build_utils.py @@ -1,4 +1,5 @@ #!/usr/bin/env python3 +import functools import subprocess import pathlib import re @@ -10,32 +11,180 @@ FAILED = "\033[31mfailed\033[0m" SKIPPED = "\033[33mskipped\033[0m" -def skip_example(example, board): - ex_dir = pathlib.Path('examples/') / example - bsp = pathlib.Path("hw/bsp") +# Every read here is a source file, not user text: decode it the same way on every +# machine. Without this the reads take the locale's encoding, and one of the eight +# tracked non-ASCII files this now touches (hw/bsp/nrf/boards/nrf54lm20dk/board.cmake +# among them) raises UnicodeDecodeError under LC_ALL=C - a ValueError, which sails +# straight through the `except OSError` fail-opens. +_TEXT = {'encoding': 'utf-8', 'errors': 'replace'} - # board within family - board_dir = list(bsp.glob("*/boards/" + board)) - if not board_dir: - # Skip unknown boards - return True +_FAMILY_MCUS_RE = re.compile(r'set\s*\(\s*FAMILY_MCUS\s+([^)]*)\)') +_CMAKE_SET_RE = re.compile(r'set\s*\(\s*([A-Za-z_]\w*)\s+([^)\s]+)') +_CMAKE_VAR_RE = re.compile(r'\$\{([A-Za-z_]\w*)\}') +_CMAKE_CASE_RE = re.compile(r'string\s*\(\s*(TOUPPER|TOLOWER)\s+(\S+)\s+([A-Za-z_]\w*)\s*\)') - board_dir = list(board_dir)[0] - family_dir = board_dir.parent.parent - family = family_dir.name - # family.mk [email protected]_cache(maxsize=None) +def _cmake_sets(path): + """One cmake file's variable assignments as NAME -> first definition seen, as + either a literal value or an ('TOUPPER'|'TOLOWER', source) pair. Only used to + expand ${...} tokens; never mutate the cached dict. + + string(TOUPPER ...) is not decoration: hw/bsp/maxim derives its ONLY FAMILY_MCUS + entry that way (`string(TOUPPER ${MAX_DEVICE} MAX_DEVICE_UPPER)`), as do the eight + at32 families, so dropping those lines left nine families with an empty MCU set.""" + try: + text = pathlib.Path(path).read_text(**_TEXT) + except OSError: + return {} + out = {} + for line in text.splitlines(): + line = line.strip() + if line.startswith('#'): + continue + m = _CMAKE_CASE_RE.match(line) + if m: + # strip quotes like the set() branch below: string(TOUPPER "${VAR}" DST) is + # idiomatic cmake, and keeping them yields a '"NAME"' token that can never + # equal a mcu: entry + out.setdefault(m.group(3), (m.group(1), m.group(2).strip('"'))) + continue + m = _CMAKE_SET_RE.match(line) + if m: + out.setdefault(m.group(1), m.group(2).strip('"')) + return out + + +def _cmake_expand(value, files, depth=0): + """`value` with every ${VAR} replaced, resolving each name against `files` in + order, or None when any name resolves nowhere OR the result still carries a `${`. + That last case is the one _CMAKE_VAR_RE cannot see - a hyphen in the name, a nested + ${${X}}, an unterminated brace - where the loop below finds nothing to substitute + and would otherwise hand the raw text back as if it were a resolved MCU name. + Bounded depth: a cmake file may define a var in terms of another one, and a + self-referential set() must not recurse forever.""" + if depth > 4: + return None + out = value + for name in set(_CMAKE_VAR_RE.findall(value)): + val = None + for f in files: + val = _cmake_sets(f).get(name) + if val is not None: + break + if val is None: + return None + if isinstance(val, tuple): # string(TOUPPER src DST) + src = _cmake_expand(val[1], files, depth + 1) + if src is None: + return None + val = src.upper() if val[0] == 'TOUPPER' else src.lower() + else: + val = _cmake_expand(val, files, depth + 1) + if val is None: + return None + out = out.replace('${' + name + '}', val) + return None if '${' in out else out + + [email protected]_cache(maxsize=None) +def _board_dirs(board): + """(board_dir, family_dir) for a board name, or (None, None). Cached: skip_example + is asked (board x example) times - 566k lstat calls per selector run without this, + since the glob rescans every hw/bsp/*/boards for each example.""" + hits = list(pathlib.Path("hw/bsp").glob("*/boards/" + board)) + if not hits: + return None, None + return hits[0], hits[0].parent.parent + + [email protected]_cache(maxsize=None) +def _family_mcus(family_dir, board_dir): + """The MCU names CMake's family_filter iterates. family_support.cmake:176/190 + loop `foreach(MCU IN LISTS FAMILY_MCUS)`, so a family-wide list (broadcom_64bit + sets "BCM2711 BCM2835") makes ANY of its entries decide skip.txt/only.txt -- not + just the one CFG_TUSB_MCU the configured board names. + + ${...} tokens are expanded from `set(VAR value)` and `string(TOUPPER src VAR)` in + the board's board.cmake first, then in family.cmake: hw/bsp/ra sets + `FAMILY_MCUS RAXXX ${MCU_VARIANT}` and ra6m5_ek/board.cmake sets MCU_VARIANT ra6m5, + which is the token dual/host_info_to_device_cdc/only.txt actually spells; hw/bsp/maxim + sets `FAMILY_MCUS ${MAX_DEVICE_UPPER}`, upper-cased from the board's MAX_DEVICE. A + token resolving nowhere is dropped (nothing can be said about it). + + A family that never spells `set(FAMILY_MCUS ...)` at all gets one more chance: the + name is resolved as a variable, which covers the derived form hw/bsp/espressif uses + (`string(TOUPPER ${IDF_TARGET} FAMILY_MCUS)`). + + Only unconditional set() calls count: nrf and mcx pick FAMILY_MCUS per board + inside if() blocks this does not evaluate, so for those two families the whole + cmake-side MCU set is whatever the CFG_TUSB_MCU scrape in _board_mcu finds. + + nrf: the scrape reads the FIRST CFG_TUSB_MCU token of hw/bsp/nrf/family.mk, so + every nrf board answers NRF54, the NRF5X ones included. Harmless only because no + skip.txt/only.txt names an nrf token today. + + mcx: load-bearing, not academic -- mcu:MCXA15 is live in six examples' skip.txt + (device/{cdc_msc,audio_test,hid_composite,audio_4_channel_mic,midi_test}_freertos + and device/net_lwip_webserver). Those answers come out right only because the + scrape falls through to each board's make-only board.mk, which still spells the + token; an mcx board carrying board.cmake alone (MCU_VARIANT and no CFG_TUSB_MCU) + would scrape 'NONE' and skip EVERY example on it, silently. TestFamilyMcusFallback + fails the day such a board lands. The fix then is to evaluate the + if(MCU_VARIANT STREQUAL ...) branches, not to add another scrape. + """ + fam_cmake = pathlib.Path(family_dir) / "family.cmake" + try: + text = fam_cmake.read_text(**_TEXT) + except OSError: + return frozenset() + board_cmake = pathlib.Path(board_dir) / "board.cmake" + out = set() + depth = 0 + for line in text.splitlines(): + line = line.strip() + m = _FAMILY_MCUS_RE.match(line) + if m and depth == 0: + files = (str(board_cmake), str(fam_cmake)) + for tok in m.group(1).split(): + if tok in ("CACHE", "INTERNAL") or tok.startswith('"'): + continue + val = _cmake_expand(tok, files) + if val: + out.add(val) + if re.match(r'if\s*\(', line): + depth += 1 + elif re.match(r'endif\s*\(', line): + depth = max(0, depth - 1) + if not out: + # FAMILY_MCUS can also be produced rather than set: hw/bsp/espressif derives it + # with `string(TOUPPER ${IDF_TARGET} FAMILY_MCUS)`, which _FAMILY_MCUS_RE cannot + # see, leaving espressif's whole cmake answer resting on the IDF_TARGET scrape + val = _cmake_expand('${FAMILY_MCUS}', (str(board_cmake), str(fam_cmake))) + if val: + out.add(val) + return frozenset(out) + + +def _scrape_mcu(family_dir, board_dir, family): + """(CFG_TUSB_MCU token of this board, the text it was read from), master's + algorithm verbatim: family.mk (family.cmake when there is none) first, falling + back to the board's board.mk (board.cmake when there is none) only when the + family file names no token at all. espressif spells its MCU as + `set(IDF_TARGET "...")` instead. The text comes back with it because the make + path reads MAX3421_HOST out of that same single file - which file that is IS + part of master's answer, so it cannot be re-derived by the caller.""" family_mk = family_dir / "family.mk" if not family_mk.exists(): family_mk = family_dir / "family.cmake" - mk_contents = family_mk.read_text() + mk_contents = family_mk.read_text(**_TEXT) # Find the mcu, first in family mk then board mk if "CFG_TUSB_MCU=OPT_MCU_" not in mk_contents: board_mk = board_dir / "board.mk" if not board_mk.exists(): board_mk = board_dir / "board.cmake" - mk_contents = board_mk.read_text() + mk_contents = board_mk.read_text(**_TEXT) mcu = "NONE" if family == "espressif": @@ -53,6 +202,95 @@ def skip_example(example, board): mcu = opt_mcu[len("OPT_MCU_"):] if mcu != "NONE": break + return mcu, mk_contents + + [email protected]_cache(maxsize=None) +def _board_mcu(board_dir, family_dir, family): + """(CFG_TUSB_MCU of this board, MAX3421_HOST enabled by its cmake BSP). + + MAX3421_HOST is read from family.cmake AND board.cmake rather than only the file + the MCU token came from: feather_rp2040_max3421 sets it in its board.cmake while + its MCU token comes from rp2040's family file, and family_support.cmake:940 + appends MAX3421 to FAMILY_MCUS for it. board.mk is deliberately not read - a + make-only option compiles nothing in a cmake build (and the make path answers + with master's own single-file scrape, see _skip_example_make).""" + family_dir = pathlib.Path(family_dir) + board_dir = pathlib.Path(board_dir) + mcu, _ = _scrape_mcu(family_dir, board_dir, family) + if "${" in mcu: + # the scrape is textual, so a computed token comes back verbatim + # (tm4c board.cmake spells OPT_MCU_TM4C${MCU_SUB_VARIANT}, maxim + # OPT_MCU_${MAX_DEVICE_UPPER}). Expand it the same way FAMILY_MCUS tokens are; + # what still will not resolve stays as-is and _skip_example treats it as + # "MCU unknown" rather than silently matching no mcu: token at all. + mcu = _cmake_expand(mcu, (str(board_dir / "board.cmake"), + str(family_dir / "family.cmake"))) or mcu + + max3421_enabled = False + for f in (family_dir / "family.cmake", board_dir / "board.cmake"): + try: + text = f.read_text(**_TEXT) + except OSError: + continue + # a commented-out `# set(MAX3421_HOST 1)` (feather_nrf52840_express) enables + # nothing; master never hit one because it only read the MCU token's file + if any(not l.lstrip().startswith('#') and + ("MAX3421_HOST=1" in l or 'MAX3421_HOST 1' in l) + for l in text.splitlines()): + max3421_enabled = True + break + + return mcu, max3421_enabled + + [email protected]_cache(maxsize=None) +def _filter_tokens(path): + """skip.txt / only.txt as a token set, or None when the file does not exist.""" + f = pathlib.Path(path) + return frozenset(f.read_text(**_TEXT).split()) if f.exists() else None + + +def skip_example(example, board, extra_defines=(), build_system='cmake'): + """Is this example unbuildable on this board, for this build system? + + The two build systems ask DIFFERENT questions and must not share an answer: + + 'cmake' mirrors CMake's family_filter (hw/bsp/family_support.cmake:171-207), + including the whole FAMILY_MCUS list the family.cmake sets. + + 'make' is master's original algorithm, unchanged. family.mk and family.cmake are + not the same build: hw/bsp/lpc54/family.cmake sets FAMILY_MCUS LPC54 and wires the + ohci host sources, while family.mk builds OPT_MCU_LPC54XXX and compiles no HCD + source at all -- feeding the cmake MCU union to a make build un-skips the host + examples only.txt gates on mcu:LPC54 and they fail to link (undefined hcd_init). + + extra_defines: NAME=VALUE tokens the build passes on the command line + (build.py -D). MAX3421_HOST=1 there enables the max3421 host controller + exactly like a BSP that sets it, and family_support.cmake:940 appends MAX3421 + to FAMILY_MCUS for it -- so a roster board whose MAX3421 comes from the build + args (metro_m4_express) must resolve its only.txt the same way. cmake only: + master's make algorithm never looked at them. + """ + return _skip_example(example, board, tuple(extra_defines), build_system) + + [email protected]_cache(maxsize=None) +def _skip_example_make(example, board): + """master's skip_example, verbatim (tools/build_utils.py @ 9c202e8c6): the + make build's own answer, derived from family.mk/board.mk with the single + CFG_TUSB_MCU token that file names. Do not "improve" it -- it is the mirror of + what `make BOARD=... all` actually compiles.""" + ex_dir = pathlib.Path('examples/') / example + + # board within family + board_dir, family_dir = _board_dirs(board) + if board_dir is None: + # Skip unknown boards + return True + family = family_dir.name + + mcu, mk_contents = _scrape_mcu(family_dir, board_dir, family) # Skip all OPT_MCU_NONE these are WIP port if mcu == "NONE": @@ -68,14 +306,14 @@ def skip_example(example, board): only_file = ex_dir / "only.txt" if skip_file.exists(): - skips = skip_file.read_text().split() + skips = skip_file.read_text(**_TEXT).split() if ("mcu:" + mcu in skips or "board:" + board in skips or "family:" + family in skips): return True if only_file.exists(): - onlys = only_file.read_text().split() + onlys = only_file.read_text(**_TEXT).split() if not ("mcu:" + mcu in onlys or ("mcu:MAX3421" in onlys and max3421_enabled) or "board:" + board in onlys or @@ -85,6 +323,55 @@ def skip_example(example, board): return False [email protected]_cache(maxsize=None) +def _skip_example(example, board, extra_defines, build_system): + if build_system == 'make': + return _skip_example_make(example, board) + + ex_dir = pathlib.Path('examples/') / example + + # board within family + board_dir, family_dir = _board_dirs(board) + if board_dir is None: + # Skip unknown boards + return True + family = family_dir.name + + mcu, max3421_enabled = _board_mcu(str(board_dir), str(family_dir), family) + + # Skip all OPT_MCU_NONE these are WIP port + if mcu == "NONE": + return True + + if any(t.strip().strip('"') == "MAX3421_HOST=1" for t in extra_defines): + max3421_enabled = True + + mcus = set(_family_mcus(str(family_dir), str(board_dir))) + if "${" not in mcu: + mcus.add(mcu) + if not mcus: + # nothing resolved: neither FAMILY_MCUS nor the scraped CFG_TUSB_MCU token + # yielded a name. Answering "skip" here would silently drop EVERY example on + # the board (an only.txt can then never match), so say "buildable" and let + # the real filter decide - build.py checks the targets CMake actually + # registered, and CMake itself is the authority on the make/cmake legs. + return False + if max3421_enabled: + mcus.add("MAX3421") # family_support.cmake:940 + + keys = {"board:" + board, "family:" + family} | {"mcu:" + m for m in mcus} + + skips = _filter_tokens(str(ex_dir / "skip.txt")) + if skips is not None and (skips & keys): + return True + + onlys = _filter_tokens(str(ex_dir / "only.txt")) + if onlys is not None and not (onlys & keys): + return True + + return False + + def build_size(make_cmd): size_output = subprocess.run(make_cmd + ' size', shell=True, stdout=subprocess.PIPE).stdout.decode("utf-8").splitlines() for i, l in enumerate(size_output): diff --git a/tools/ci_select.py b/tools/ci_select.py new file mode 100755 index 000000000..d253f8c01 --- /dev/null +++ b/tools/ci_select.py @@ -0,0 +1,1084 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: MIT +"""PR-diff -> CI selection: which rig boards and which tests a change can affect. + +Lives in tools/ so it can serve both HIL selection and, from Task 3, build-family +selection. Stdlib-only (runs on bare CI runners; imports hil_util for the example +rosters, never hil_test/pyserial — test_hil_util.BottomLayer enforces the stdlib +closure). Fail-open: any file no rule classifies forces the full matrix. See +docs/superpowers/specs/2026-07-29-hil-pr-scoped-selection-design.md and +docs/superpowers/specs/2026-08-19-ci-build-family-filter-design.md. + +JSON: full, boards (name -> 'all' | [tests]), families (bsp families the diff +touches, including ones with no rig board - build-only consumers such as /pre-pr +sample from these), args (hil_test.py args per config) and args_flasher (the same +args split by each board's flasher, for CI legs that split one rig by flasher). +""" +import argparse +import ast +import contextlib +import functools +import glob +import io +import json +import os +import re +import subprocess +import sys + +# tools/ -> repo root is ONE level up. Guarded by TestModuleMove.test_repo_root_guard: +# a wrong parent count here silently re-points every repo-relative glob (it happened +# at the helper/ move). +_REPO_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) +sys.path.insert(0, os.path.join(_REPO_ROOT, 'test', 'hil')) # for `from helper...` +from helper.hil_util import device_tests, dual_tests, host_test + +sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) # tools/, for build helpers +import build_utils +import build as build_py + +ALL_TESTS = {'device': device_tests, 'dual': dual_tests, 'host': host_test} + +# class dir -> config macro suffix exceptions (rule 3); dfu is per-file, handled inline +NET_MACROS = ('ECM_RNDIS', 'NCM') + +def _read(path: str) -> str: + """Read a source file with a fixed encoding. The locale's is not it: several tracked + sources carry non-ASCII bytes, and under LC_ALL=C the decode raises UnicodeDecodeError + - a ValueError, which every `except OSError` fail-open below would let through as a + traceback instead of a full matrix.""" + with open(path, encoding='utf-8', errors='replace') as f: + return f.read() + + +_NONCODE_RE = re.compile( + r'^(docs/|\.claude/|.*\.(md|rst)$|LICENSE)') +# Build-size metrics tooling. HIL axis ONLY: nothing on the rig runs any of it, and +# without this rule these paths are unclassified, so a metrics-only PR booked an +# exclusive full 30-board sweep to validate a script no board executes. +# The BUILD axis deliberately keeps its full-matrix answer: `tinyusb_metrics` runs +# tools/metrics.py as a build target (examples/CMakeLists.txt), and build_util.yml adds +# `--target tinyusb_metrics` to every metrics leg - a break in it fails the build, so a +# build has to exercise it. +_METRICS_RE = re.compile( + r'^(tools/metrics[^/]*\.py$|\.github/scripts/metrics_[^/]*\.py$)') +_FULL_RE = re.compile( + r'^(src/common/|src/osal/|src/tusb\.c$|src/tusb\.h$|src/tusb_option\.h$|' + r'test/hil/|\.github/workflows/build.*\.yml$|\.github/actions/|\.github/scripts/|' + r'tools/build\.py$|tools/cmake/|' + r'hw/bsp/(family_support\.cmake|board_api\.h|board\.c|ansi_escape\.h)$|' + r'examples/build_system/|examples/CMakeLists\.txt$|' + # board_test is HIL infrastructure, not a test: hil_test.py flashes it to park + # every board (variant boundary + end-of-board teardown), so every board depends on it + r'examples/device/board_test/)') + +# --no-renames: with rename detection git reports only a rename's destination, so code +# moved out of an HIL-relevant path would be classified by its new path alone +GIT_DIFF_ARGV = ['git', 'diff', '--no-renames', '--name-only'] + + +def test_role(test: str) -> str: + return test.split('/', 1)[0] # 'device' | 'dual' | 'host' + + +def board_roles(board: dict) -> set: + t = board.get('tests', {}) + roles = set() + if t.get('device'): + roles.add('device') + if t.get('host'): + roles.add('host') + if t.get('dual'): + roles.update(('device', 'host')) + for only in t.get('only', []): + r = test_role(only) + roles.update(('device', 'host') if r == 'dual' else (r,)) + return roles + + +def board_tests(board: dict) -> list: + """Every test this board would run today (mirrors hil_test.test_board's default).""" + t = board.get('tests', {}) + if 'only' in t: + run = list(t['only']) + else: + run = [] + if t.get('device'): + run += device_tests + if t.get('dual'): + run += dual_tests + if t.get('host'): + run += host_test + return [x for x in run if x not in t.get('skip', [])] + + +# cached: called per changed file x roster board, and the tree doesn't change mid-run [email protected]_cache(maxsize=None) +def board_family(board_name: str, repo_root: str): + hits = glob.glob(os.path.join(repo_root, 'hw/bsp/*/boards', board_name)) + return os.path.basename(os.path.dirname(os.path.dirname(hits[0]))) if hits else None + + +# `if (OPTION STREQUAL "1")` guards in family_support.cmake, and the option tokens +# a roster entry passes to the build (NAME=VALUE / -DNAME=VALUE) +_CM_IF_RE = re.compile(r'if\s*\(') +_CM_ELSE_RE = re.compile(r'else(if)?\s*\(') +_CM_ENDIF_RE = re.compile(r'endif\s*\(') +_CM_OPT_RE = re.compile(r'if\s*\(\s*\$?\{?([A-Za-z_]\w*)\}?\s+STREQUAL\s+"?1"?\s*\)') +_CM_PORT_RE = re.compile(r'src/portable/((?:[^/\s]+/)?[^/\s]+)/') +_FALSY = ('', '0', 'off', 'false', 'no') + + [email protected]_cache(maxsize=None) +def port_option_gates(repo_root: str) -> dict: + """port dir -> build options that compile it regardless of the board's family + file, e.g. {'analog/max3421': {'MAX3421_HOST'}} from family_support.cmake.""" + gates = {} + try: + text = _read(os.path.join(repo_root, 'hw/bsp/family_support.cmake')) + except OSError: + return gates + stack = [] # one entry per open if(): its option, or None + for line in text.splitlines(): + line = line.strip() + if _CM_IF_RE.match(line): + m = _CM_OPT_RE.match(line) + stack.append(m.group(1) if m else None) + elif _CM_ELSE_RE.match(line): + if stack: + stack[-1] = None # the guard doesn't hold in this branch + elif _CM_ENDIF_RE.match(line): + if stack: + stack.pop() + opts = {o for o in stack if o} + m = _CM_PORT_RE.search(line) + if opts and m: + gates.setdefault(m.group(1), set()).update(opts) + return gates + + +_CM_SET_RE = re.compile(r'set\s*\(\s*([A-Za-z_]\w*)\s+([^)\s]+)\s*\)') + + +# cached: called per changed portable file x roster board [email protected]_cache(maxsize=None) +def bsp_board_options(board_name: str, repo_root: str) -> frozenset: + """Build options a board turns on in its own BSP: `set(<OPT> <value>)` in + hw/bsp/<family>/boards/<board>/board.cmake, e.g. MAX3421_HOST on the espressif + and rp2040 max3421 boards. CMake only - HIL CI builds nothing with Make, so a + board.mk-only option (e.g. nrf5340dk's MAX3421_HOST) compiles no port here.""" + fam = board_family(board_name, repo_root) + if not fam: + return frozenset() + path = os.path.join(repo_root, 'hw/bsp', fam, 'boards', board_name, 'board.cmake') + try: + text = _read(path) + except OSError: + return frozenset() + out = set() + for line in text.splitlines(): + line = line.strip() + if line.startswith('#'): + continue + m = _CM_SET_RE.match(line) + if m and m.group(2).strip('"').lower() not in _FALSY: + out.add(m.group(1)) + return frozenset(out) + + +def board_options(board: dict, repo_root: str) -> set: + """Build options a board has truthy: the roster entry's build.args plus each + variant's defines (NAME=VALUE) and raw CFLAGS (-DNAME=VALUE), plus whatever its + own board.cmake sets (a board can enable a gated port without the roster saying so).""" + toks = list(board.get('build', {}).get('args', [])) + for v in board.get('variant', []): + toks += list(v.get('defines', [])) + toks += v.get('flags', '').split() + out = set(bsp_board_options(board['name'], repo_root)) + for t in toks: + name, _, val = (t[2:] if t.startswith('-D') else t).partition('=') + if name and val.strip().strip('"').lower() not in _FALSY: + out.add(name.strip()) + return out + + [email protected]_cache(maxsize=None) +def path_families(rel_dir: str, repo_root: str) -> set: + """Board families whose family.cmake (or espressif component CMakeLists) + references rel_dir at a directory boundary. CMake only, on every axis: CMake + is the first-class build system and Make follows it, so family.mk is never + read - a port wired up in family.mk alone (microchip/pic32mz) is built by no + CI job and resolves to nothing. Boundary = '/', whitespace, quote, paren, + brace or end: `${TOP}/hw/mcu/nordic/nrfx` has no trailing slash, while bare + 'microchip/pic' must not match '.../microchip/pic32mz/...'.""" + fams = set() + bsp_root = os.path.join(repo_root, 'hw/bsp') + pat = re.compile(re.escape(rel_dir) + r'(?=[/\s"\')}]|$)', re.M) + for f in glob.glob(os.path.join(bsp_root, '*/family.cmake')) + \ + glob.glob(os.path.join(bsp_root, '*/components/*/CMakeLists.txt')): + try: + if pat.search(_read(f)): + fams.add(os.path.relpath(f, bsp_root).split(os.sep, 1)[0]) + except OSError: + pass + return fams + + +def port_families(port_dir: str, repo_root: str) -> set: + # 'portable/', not 'src/portable/': family.cmake always spells the full literal + # path ('${TOP}/src/portable/...'), but espressif's component CMakeLists.txt + # assigns 'src' into a ${tusb_src} variable first (`${tusb_src}/portable/...`), + # so a leading 'src/' in the needle would never match there and silently drop + # espressif boards (see TestRealRosterPortFamilies). + return path_families('portable/' + port_dir, repo_root) + + +def mcu_families(path: str, repo_root: str) -> set: + """Families referencing a changed hw/mcu path: longest resolving dir prefix, + hw/mcu/<vendor>/<sub>/... down to hw/mcu/<vendor>.""" + parts = path.split('/') + for n in range(len(parts) - 1, 2, -1): + fams = path_families('/'.join(parts[:n]), repo_root) + if fams: + return fams + return set() + + +GET_DEPS_PATH = 'tools/get_deps.py' +_DEPS_DICTS = ('deps_mandatory', 'deps_optional') + + +def _deps_split(text: str): + """(module dump with the two dep-dict assigns removed, {dict name: entries}). + Parsed with ast, never exec'd: this runs on PR content.""" + mod = ast.parse(text) + dicts, rest = {}, [] + for node in mod.body: + if (isinstance(node, ast.Assign) and len(node.targets) == 1 and + isinstance(node.targets[0], ast.Name) and + node.targets[0].id in _DEPS_DICTS and isinstance(node.value, ast.Dict)): + dicts[node.targets[0].id] = ast.literal_eval(node.value) + else: + rest.append(node) + mod.body = rest + # annotate_fields=False keeps the dump readable-length; line numbers are not + # included unless asked for, so reformatting alone never reads as a logic change + return ast.dump(mod, annotate_fields=False), dicts + + +# Family tokens in tools/get_deps.py that name no hw/bsp directory. get_deps matches a +# token against a requested family name verbatim (`f in deps_optional[d][2].split()`), +# so a token like these matches nothing - a stale spelling in get_deps.py, not a +# selector bug, and out of scope to change here. Pinned so that any OTHER unresolvable +# token (real drift) falls open to the full matrix instead of silently selecting +# nothing, and so TestOrphanInvariant fails the day one is fixed or a new one appears. +# sam3x, samd21, samd51, same5x -> pre-rename spellings, listed alongside the current +# samd2x_l2x / samd5x_e5x / same7x in the same entry +# stm32l1, stm32l5 -> no hw/bsp family in the tree at all +_DEPS_ALIAS_TOKENS = frozenset({'sam3x', 'samd21', 'samd51', 'same5x', + 'stm32l1', 'stm32l5'}) + + +def get_deps_changed_families(base_text: str, head_text: str, repo_root: str): + """Families whose tools/get_deps.py dep entries changed between two versions of + the file, or None meaning 'cannot tell - use the full matrix'. + + None on: anything outside deps_mandatory/deps_optional differing (a logic change + to get_deps affects every family), a mandatory `'all'` entry changing, a token + that resolves to no family and is not a known alias, or text that will not parse. + Callers with no base content at all - `--diff-file` mode has no git and therefore + no merge-base blob - pass None themselves. + + An entry that is added, removed or edited contributes the family tokens of BOTH + sides (a removed entry has only a base side). The two dicts are diffed SEPARATELY: + merging them first would hide a move between deps_mandatory and deps_optional, + which changes which families fetch the dep even though the value is untouched.""" + try: + base_rest, base_d = _deps_split(base_text) + head_rest, head_d = _deps_split(head_text) + except (SyntaxError, ValueError, TypeError): + return None + if base_rest != head_rest: + return None + toks = set() + for name in _DEPS_DICTS: + base_x, head_x = base_d.get(name, {}), head_d.get(name, {}) + for key in set(base_x) | set(head_x): + if base_x.get(key) == head_x.get(key): + continue + for entry in (base_x.get(key), head_x.get(key)): + if entry and len(entry) > 2: + toks.update(str(entry[2]).split()) + if 'all' in toks: + return None + fams = set(all_bsp_families(repo_root)) + if toks - fams - _DEPS_ALIAS_TOKENS: + # a changed entry we cannot map to a family. "changed but unmappable" is NOT + # "nothing changed": reading it as the latter empties the entire build matrix + # for a dep bump, so fall open instead + return None + return toks & fams + + +_CLS_INC_RE = re.compile(r'#\s*include\s*[<"]class/([^/"<>]+)/([^"<>]+)[">]') + + [email protected]_cache(maxsize=None) +def class_include_edges(repo_root: str) -> dict: + """'<class>/<header>' -> the other class dirs that include it. A class header + pulled in by a second class ships in every firmware enabling that second class: + src/class/midi/midi{,2}_{device,host}.h include class/audio/audio.h, and + net_device.h includes class/cdc/cdc.h. The class rule derives macros from the + directory name alone, so without this edge a change to the included header + selects only its own class's examples - and on a board that skips those (e.g. + metro_m4_express skips audio_test_freertos), nothing at all. + + Derived from the actual #include lines rather than a hand-written table so it + cannot rot when a class picks up or drops a cross-class include.""" + edges = {} + for f in sorted(glob.glob(os.path.join(repo_root, 'src/class/*/*.[ch]'))): + cls = os.path.basename(os.path.dirname(f)) + try: + text = _read(f) + except OSError: + continue + for inc_cls, inc_hdr in _CLS_INC_RE.findall(text): + if inc_cls != cls: + edges.setdefault(f'{inc_cls}/{inc_hdr}', set()).add(cls) + return edges + + +def class_macros(cls: str, base: str, prefix: str) -> list: + """Config macros that compile a class dir's code, for role prefix TUD/TUH. + `base` refines dfu only (it splits DFU from DFU_RUNTIME per file); pass '' for + a class reached through an include edge, where the widest set is correct.""" + if cls == 'net': + return [f'CFG_{prefix}_{m}' for m in NET_MACROS] + if cls == 'dfu': + if base.startswith('dfu_rt'): + return [f'CFG_{prefix}_DFU_RUNTIME'] + if base.startswith('dfu_device') or base.startswith('dfu_host'): + return [f'CFG_{prefix}_DFU'] + return [f'CFG_{prefix}_DFU', f'CFG_{prefix}_DFU_RUNTIME'] + return [f'CFG_{prefix}_{cls.upper()}'] + + +# A define is OFF only when its value is a literal zero (0, 00, (0)), optionally +# followed by a comment. Anything else counts as ON - including a value this cannot +# evaluate, e.g. `#define CFG_TUH_MIDI CFG_TUH_DEVICE_MAX` (examples/host/midi_rx). +# Fail-open: reading such a define as OFF made midi_host.c select zero families and +# let a compile break merge green. +# +# A macro defined more than once is ON if ANY of its defines is non-zero, because +# the preprocessor branches are not evaluated here: uac2_speaker_fb defines +# CFG_TUD_HID 1 under `#if CFG_AUDIO_DEBUG` and 0 in the #else, and the default +# build (CFG_AUDIO_DEBUG defaults to 1) compiles the HID class in. Deciding on the +# LAST/only match found made that example invisible to CFG_TUD_HID changes. +_DEF_VALUE = r'^[ \t]*#[ \t]*define[ \t]+{}[ \t]+(\S[^\n]*?)[ \t]*$' +_DEF_ZERO_VALUE = re.compile(r'\(?\s*0+\s*\)?\s*(?://.*|/\*.*)?') + + +# Shared rule-recognition primitives. The two classifiers walk the same diff with +# different answers, but they must RECOGNISE the same things: one copy each, so a +# new naming convention cannot land in one walk and be missed by the other. +_PORT_PATH_RE = re.compile(r'src/portable/((?:[^/]+/)?[^/]+)/') + + +def _port_roles(base: str) -> set: + """Which USB role a src/portable file serves, from its name: dcd_*/ *_device is + the device-controller side, hcd_*/ *_host the host side, anything else (shared + headers, glue) both.""" + if re.match(r'(dcd_|.*_device)', base): + return {'device'} + if re.match(r'(hcd_|.*_host)', base): + return {'host'} + return {'device', 'host'} + + +def _class_roles(base: str) -> set: + """Same question for a src/class file: <cls>_device.[ch] / <cls>_host.[ch], + else both - the class's shared header ships in either role.""" + if re.search(r'_device\.[ch]$', base): + return {'device'} + if re.search(r'_host\.[ch]$', base): + return {'host'} + return {'device', 'host'} + + +def _config_enables(cfg_path: str, macros) -> bool: + try: + with open(cfg_path) as f: + text = f.read() + except OSError: + return False + for m in macros: + for value in re.findall(_DEF_VALUE.format(m), text, re.M): + if not _DEF_ZERO_VALUE.fullmatch(value): + return True + return False + + +def examples_enabling(pool, macros, repo_root: str) -> set: + """The 'role/name' entries of `pool` whose src/tusb_config.h turns any of + `macros` on. The pool differs per classifier (HIL test lists vs every example), + the question does not.""" + return {ex for ex in pool + if _config_enables(os.path.join(repo_root, 'examples', ex, 'src', + 'tusb_config.h'), macros)} + + +# cached: called per changed lib file, and the tree doesn't change mid-run [email protected]_cache(maxsize=None) +def lib_examples(lib_name: str, repo_root: str) -> set: + """Examples whose OWN examples/<role>/<name>/{CMakeLists.txt,Makefile} references + lib/<lib_name> at a directory boundary (same boundary rule as path_families, so + 'lib/net' cannot inherit lib/networking's example). + + Per-example on purpose: lib/SEGGER_RTT is named by family_support.cmake's + LOGGER=rtt plumbing, which no CI example build turns on, so a family-file scan + would wrongly narrow it to three families instead of answering 'nobody'.""" + pat = re.compile(re.escape('lib/' + lib_name) + r'(?=[/\s"\')}]|$)', re.M) + out = set() + for ex in all_examples(repo_root): + for f in ('CMakeLists.txt', 'Makefile'): + try: + with open(os.path.join(repo_root, 'examples', ex, f)) as fh: + text = fh.read() + except OSError: + continue + if pat.search(text): + out.add(ex) + break + return out + + +def roster_only_tests(all_boards) -> set: + """Test paths that only appear in a roster board's tests.only list (e.g. + espressif boards), not in the shared device/dual/host_test lists.""" + out = set() + for b in all_boards: + out.update(b.get('tests', {}).get('only', [])) + return out + + +def class_examples(macros, role: str, repo_root: str, extra_tests: set) -> set: + """Tests (from role's + dual lists, plus roster-only-list tests of that role) + whose example config enables any macro.""" + return examples_enabling(role_tests({role}, extra_tests), macros, repo_root) + + +def role_tests(roles: set, extras: set) -> set: + """Every test for the given role(s): each role's own list + dual tests, + plus roster-only-list tests (extras) matching those roles or 'dual'.""" + pool = set(dual_tests) + for r in roles: + pool |= set(ALL_TESTS[r]) + pool |= {t for t in extras if test_role(t) in roles or test_role(t) == 'dual'} + return pool + + +class _Sel: + """Accumulates contributions. board->set(tests) plus 'all-board' markers.""" + def __init__(self): + self.full = False + self.by_board = {} # name -> set of tests, or 'all' + self.roles = set() # roles touched by any contribution + self.families = set() # bsp families touched (incl. off-rig ones: build-only consumers) + self.reasons = [] + + def add(self, boards, tests, reason): + """tests: 'all' or iterable of test paths.""" + self.reasons.append(reason) + for b in boards: + cur = self.by_board.get(b) + if tests == 'all' or cur == 'all': + self.by_board[b] = 'all' + else: + self.by_board[b] = (cur or set()) | set(tests) + + def force_full(self, reason): + self.full = True + self.reasons.append(reason) + + +def _classify_one(path, repo_root, roster_boards, extras: set, s: _Sel, + get_deps_families=None): + base = os.path.basename(path) + if _NONCODE_RE.match(path): + s.reasons.append(f'{path}: non-code, no contribution') + return + if _METRICS_RE.match(path): + s.reasons.append(f'{path}: build-size metrics tooling, no HIL contribution') + return + if _FULL_RE.match(path): + s.force_full(f'{path}: core/infra -> full matrix') + return + + if path == GET_DEPS_PATH: + if get_deps_families is None: + s.force_full(f'{path}: dep changes not resolvable -> full matrix') + return + if not get_deps_families: + s.reasons.append(f'{path}: no dep entry changed, no contribution') + return + fams = sorted(get_deps_families) + s.families.update(fams) + boards = [b['name'] for b in roster_boards + if board_family(b['name'], repo_root) in get_deps_families] + s.roles.update(('device', 'host')) + s.add(boards, 'all', f'{path}: dep entries changed -> families {fams} -> ' + f'boards {boards}') + return + + m = _PORT_PATH_RE.match(path) + if m: + port = m.group(1) + roles = _port_roles(base) + fams = port_families(port, repo_root) + if not fams: + # empty means empty (maintainer ruling), same reading as hw/mcu and as the + # build walk: no family's build references this port, so nothing compiles it + # and there is nothing to run. Forcing the full 30-board rig here bought no + # coverage at all - the build side selected zero families for the same path. + # Live for src/portable/template and the two microchip pic ports; + # TestPortFamiliesCoverage is the drift guard for a port that stops resolving. + s.reasons.append(f'{path}: port {port} maps to no board family, no contribution') + return + s.families.update(fams) + # a board can also pull the port in through a build option (e.g. MAX3421_HOST=1 + # from the roster on metro_m4_express, or from its own board.cmake), which its + # family file never names + gates = port_option_gates(repo_root).get(port, set()) + boards = [b['name'] for b in roster_boards + if (board_family(b['name'], repo_root) in fams or + (gates and board_options(b, repo_root) & gates)) and (board_roles(b) & roles)] + tests = role_tests(roles, extras) + s.roles.update(roles) + why = f'{path}: port {port} -> families {sorted(fams)}' + if gates: + why += f' + option {sorted(gates)}' + s.add(boards, tests, f'{why} -> boards {boards} ({"/".join(sorted(roles))})') + return + + m = re.match(r'src/class/([^/]+)/', path) + if m: + cls = m.group(1) + roles = _class_roles(base) + # this file's own class, plus any class whose headers include it + via = sorted(class_include_edges(repo_root).get(f'{cls}/{base}', ())) + + def macros(prefix): + return (class_macros(cls, base, prefix) + + [m2 for c in via for m2 in class_macros(c, '', prefix)]) + tests = set() + if 'device' in roles: + tests |= class_examples(macros('TUD'), 'device', repo_root, extras) + if 'host' in roles: + tests |= class_examples(macros('TUH'), 'host', repo_root, extras) + boards = [b['name'] for b in roster_boards if board_roles(b) & roles] + s.roles.update(roles) + why = f'{path}: class {cls}' + (f' (+ included by {via})' if via else '') + s.add(boards, tests, f'{why} -> {sorted(tests)} ({"/".join(sorted(roles))})') + return + + m = re.match(r'src/(device|host)/', path) + if m: + role = m.group(1) + boards = [b['name'] for b in roster_boards if role in board_roles(b)] + s.roles.add(role) + s.add(boards, role_tests({role}, extras), f'{path}: core {role} stack -> all {role} tests') + return + + m = re.match(r'hw/bsp/([^/]+)/(?:boards/([^/]+)/)?', path) + if m: + fam, brd = m.group(1), m.group(2) + s.families.add(fam) + if brd: + boards = [b['name'] for b in roster_boards if b['name'] == brd] + why = f'{path}: bsp board {brd}' + else: + boards = [b['name'] for b in roster_boards + if board_family(b['name'], repo_root) == fam] + why = f'{path}: bsp family {fam}' + s.roles.update(('device', 'host')) + s.add(boards, 'all', f'{why} -> boards {boards}') + return + + if re.match(r'hw/mcu/', path): + fams = mcu_families(path, repo_root) + if not fams: + # empty means empty (maintainer ruling): if no family's build references + # the path, no build consumes the change - there is nothing to compile, + # so there is nothing to run either. TestOrphanInvariant's + # test_tracked_mcu_vendors_resolve is the drift guard: a real vendor dir + # that stops resolving fails pre-commit instead of silently vanishing + s.reasons.append(f'{path}: hw/mcu path resolves to no family, no contribution') + return + s.families.update(fams) + boards = [b['name'] for b in roster_boards + if board_family(b['name'], repo_root) in fams] + s.roles.update(('device', 'host')) + s.add(boards, 'all', f'{path}: mcu dir -> families {sorted(fams)} -> boards {boards}') + return + + m = re.match(r'lib/([^/]+)/', path) + if m: + lib = m.group(1) + # only the tests whose example builds the lib, and only those the rig runs + tests = {e for e in lib_examples(lib, repo_root) + if any(e in pool for pool in ALL_TESTS.values()) or e in extras} + if not tests: + s.reasons.append(f'{path}: lib {lib} used by no HIL test, no contribution') + return + roles = set() + for test in tests: + r = test_role(test) + roles.update(('device', 'host') if r == 'dual' else (r,)) + boards = [b['name'] for b in roster_boards] + s.roles.update(roles) + s.add(boards, sorted(tests), f'{path}: lib {lib} -> {sorted(tests)} on all boards') + return + + m = _BUILD_EX_RE.match(path) + if m: + if m.group(1) not in _HIL_EX_ROLES: + # examples/typec: the build matrix compiles it, nothing on the rig runs it + s.reasons.append(f'{path}: {m.group(1)} example, no HIL contribution') + return + test = f'{m.group(1)}/{m.group(2)}' + known = any(test in pool for pool in ALL_TESTS.values()) or test in extras + if known: + boards = [b['name'] for b in roster_boards] + role = test_role(test) + s.roles.update(('device', 'host') if role == 'dual' else (role,)) + s.add(boards, [test], f'{path}: example -> {test} on all boards') + else: + s.reasons.append(f'{path}: example not in HIL lists, no contribution') + return + + s.force_full(f'{path}: unclassified -> full matrix') + + +def classify(changed_files, repo_root, rosters, get_deps_families=None): + all_boards = [] + seen = set() + for _, boards in rosters: + for b in boards: + if b['name'] not in seen: + seen.add(b['name']) + all_boards.append(b) + + extras = roster_only_tests(all_boards) + s = _Sel() + # no early exit once full: keep classifying so `families` still reports every + # family the diff touches (build-only consumers need it). Nothing after the first + # force_full can change full/boards/args - the full branch below ignores by_board. + for path in changed_files: + _classify_one(path, repo_root, all_boards, extras, s, get_deps_families) + + if s.full: + return {'full': True, 'boards': {b['name']: 'all' for b in all_boards}, + 'families': sorted(s.families), 'reasons': s.reasons} + + # role pruning: single-role selections drop the other role's tests and boards + by_name = {b['name']: b for b in all_boards} + out = {} + for name, tests in s.by_board.items(): + allowed = board_tests(by_name[name]) + if tests == 'all': + kept = list(allowed) + else: + kept = [t for t in allowed if t in tests] + if s.roles and s.roles != {'device', 'host'}: + role = next(iter(s.roles)) + kept = [t for t in kept if test_role(t) in (role, 'dual')] + if kept: + out[name] = 'all' if set(kept) == set(allowed) else sorted(kept) + return {'full': False, 'boards': out, 'families': sorted(s.families), + 'reasons': s.reasons} + + +def _board_args(name, chosen) -> list: + parts = [f'-b {name}'] + if chosen != 'all': + parts.append(f'-bt {name}:{",".join(chosen)}') + return parts + + +def hil_examples(sel, rosters): + """{board: examples hil-build must produce}: the board's selected tests plus + device/board_test, which hil_test.py flashes to park at every variant + boundary and at end-of-board teardown. Emitted for full selections too - the + HIL example universe is a fraction of the tree regardless of the diff.""" + by_name = {} + for _, boards in rosters: + for b in boards: + by_name.setdefault(b['name'], []).append(b) + if sel['full']: + chosen = {n: 'all' for n in by_name} + else: + chosen = sel['boards'] + out = {} + for name, tests in chosen.items(): + if tests == 'all': + # a board named by two rosters (rig migration, or shared between rigs) + # may run different tests on each: union them. Superset firmware costs a + # build; a missing image fails the run on whichever rig lost the toss. + run = set().union(*(board_tests(b) for b in by_name[name])) + else: + run = set(tests) + out[name] = sorted(run | {'device/board_test'}) + return out + + +def selection_args(sel, rosters): + """hil_test.py args per config. Empty means either 'full matrix' or 'nothing + selected' - callers must read sel['full'] to tell them apart.""" + args = {} + for cfg_path, boards in rosters: + parts = [] + if not sel['full']: + for b in boards: + chosen = sel['boards'].get(b['name']) + if chosen is not None: + parts += _board_args(b['name'], chosen) + args[os.path.basename(cfg_path)] = ' '.join(parts) + return args + + +def selection_args_by_flasher(sel, rosters): + """{config: {flasher name: args}}. CI runs one rig as several jobs split by + flasher (esptool vs the rest); each must gate on its own subset, otherwise the + other leg runs a filter matching zero boards and reports a vacuous green.""" + out = {} + for cfg_path, boards in rosters: + per = {} + if not sel['full']: + for b in boards: + chosen = sel['boards'].get(b['name']) + if chosen is None: + continue + per.setdefault(b.get('flasher', {}).get('name', ''), []).extend( + _board_args(b['name'], chosen)) + out[os.path.basename(cfg_path)] = {f: ' '.join(p) for f, p in per.items()} + return out + + +def merge_base(base, repo_root): + return subprocess.run(['git', 'merge-base', 'HEAD', base], cwd=repo_root, + capture_output=True, text=True, check=True).stdout.strip() + + +def git_show(spec, repo_root): + return subprocess.run(['git', 'show', spec], cwd=repo_root, + capture_output=True, text=True, check=True).stdout + + +def changed_files_from_git(base, repo_root): + diff = subprocess.run(GIT_DIFF_ARGV + [f'{merge_base(base, repo_root)}..HEAD'], + cwd=repo_root, capture_output=True, text=True, check=True).stdout + return [l for l in diff.splitlines() if l.strip()] + + +def get_deps_families_from_git(base, repo_root): + """The changed dep entries' families for a --base run, or None (-> full matrix) + if git cannot produce both sides of tools/get_deps.py.""" + try: + mb = merge_base(base, repo_root) + return get_deps_changed_families(git_show(f'{mb}:{GET_DEPS_PATH}', repo_root), + git_show(f'HEAD:{GET_DEPS_PATH}', repo_root), + repo_root) + except (subprocess.CalledProcessError, OSError) as e: + print(f'ci_select: {GET_DEPS_PATH}: base content unreadable ({e})', file=sys.stderr) + return None + + +def main(): + ap = argparse.ArgumentParser(description=__doc__) + g = ap.add_mutually_exclusive_group(required=True) + g.add_argument('--base', help='git ref to diff against (merge-base..HEAD)') + g.add_argument('--diff-file', help='newline-separated changed-file list') + ap.add_argument('configs', nargs='*', help='rig roster JSON file(s); omit for the build view alone') + a = ap.parse_args() + + repo_root = _REPO_ROOT + rosters = [] + for c in a.configs: + with open(c) as f: + rosters.append((c, json.load(f)['boards'])) + + files = (_read(a.diff_file).splitlines() if a.diff_file + else changed_files_from_git(a.base, repo_root)) + files = [f for f in files if f.strip()] + + # --diff-file has no git and so no base content: the rule falls open to full + gd = (get_deps_families_from_git(a.base, repo_root) + if a.base and GET_DEPS_PATH in files else None) + + s = classify(files, repo_root, rosters, gd) + s['args'] = selection_args(s, rosters) + s['args_flasher'] = selection_args_by_flasher(s, rosters) + if rosters: + s['hil_examples'] = hil_examples(s, rosters) + s['build'] = classify_build(files, repo_root, gd) + for r in s['build']['reasons']: + print(f'ci_select[build]: {r}', file=sys.stderr) + for r in s['reasons']: + print(f'ci_select: {r}', file=sys.stderr) + print(json.dumps(s)) + + +# ------------------------------------------------------------- +# Build-axis classifier (spec rule table, docs/superpowers/specs/ +# 2026-08-19-ci-build-family-filter-design.md). Independent of the HIL +# classifier: same diff, second walk, its own fail-open. +# ------------------------------------------------------------- +# Both walks recognise an example path with the SAME regex, so a role can never be +# known to one walk and unclassified (-> full matrix) to the other. What differs is the +# answer: the rig runs device/host/dual tests, while the build matrix also compiles +# examples/typec, which nothing on the rig runs. +_EX_ROLES = ('device', 'dual', 'host', 'typec') +_HIL_EX_ROLES = ('device', 'host', 'dual') +_BUILD_EX_RE = re.compile(r'examples/(%s)/([^/]+)/' % '|'.join(_EX_ROLES)) + + [email protected]_cache(maxsize=None) +def all_examples(repo_root: str) -> tuple: + """Every examples/<role>/<name> with a CMakeLists.txt, as 'role/name'.""" + out = [] + for role in _EX_ROLES: + for d in sorted(glob.glob(os.path.join(repo_root, 'examples', role, '*/'))): + if os.path.isfile(os.path.join(d, 'CMakeLists.txt')): + out.append(f'{role}/{os.path.basename(d.rstrip(os.sep))}') + return tuple(out) + + +def role_examples(repo_root: str, roles) -> set: + want = set(roles) + return {e for e in all_examples(repo_root) if e.split('/', 1)[0] in want} + + [email protected]_cache(maxsize=None) +def all_bsp_families(repo_root: str) -> tuple: + return tuple(sorted(d for d in os.listdir(os.path.join(repo_root, 'hw/bsp')) + if os.path.isdir(os.path.join(repo_root, 'hw/bsp', d)))) + + +def _build_class_examples(cls: str, base: str, roles: set, repo_root: str) -> set: + """Examples (all 46, not the HIL lists) whose tusb_config.h enables the class's + macros for the given roles, plus classes that #include the changed header.""" + via = sorted(class_include_edges(repo_root).get(f'{cls}/{base}', ())) + out = set() + for prefix, role in (('TUD', 'device'), ('TUH', 'host')): + if role not in roles: + continue + macros = class_macros(cls, base, prefix) + \ + [m for c in via for m in class_macros(c, '', prefix)] + out |= examples_enabling(all_examples(repo_root), macros, repo_root) + return out + + +class _BSel: + """family -> set(examples) | 'all', unioned per family.""" + def __init__(self): + self.full = False + self.fam_ex = {} + self.reasons = [] + + def add(self, fams, examples, reason): + self.reasons.append(reason) + for f in fams: + cur = self.fam_ex.get(f) + if examples == 'all' or cur == 'all': + self.fam_ex[f] = 'all' + else: + self.fam_ex[f] = (cur or set()) | set(examples) + + def force_full(self, reason): + self.full = True + self.reasons.append(reason) + + +def _classify_build_one(path, repo_root, s: _BSel, get_deps_families=None): + base = os.path.basename(path) + if _NONCODE_RE.match(path): # rule 1 + return + if re.match(r'test/hil/', path): # rule 2 + s.reasons.append(f'{path}: HIL harness, no build contribution') + return + if path == GET_DEPS_PATH: # get_deps rule + if get_deps_families is None: + s.force_full(f'{path}: dep changes not resolvable -> full build matrix') + return + if not get_deps_families: + s.reasons.append(f'{path}: no dep entry changed, no contribution') + return + fams = sorted(get_deps_families) + s.add(fams, 'all', f'{path}: dep entries changed -> families {fams}') + return + m = _PORT_PATH_RE.match(path) + if m: # rules 3-5 + port = m.group(1) + fams = port_families(port, repo_root) + roles = _port_roles(base) + exs = 'all' if roles == {'device', 'host'} else \ + role_examples(repo_root, tuple(roles) + ('dual',)) + s.add(fams, exs, f'{path}: port {port} -> families {sorted(fams)}') + return + if re.match(r'hw/bsp/[^/]+/', path): # rule 6 + fam = path.split('/')[2] + s.add({fam}, 'all', f'{path}: bsp family {fam}') + return + if re.match(r'hw/mcu/', path): # rule 7 + fams = mcu_families(path, repo_root) + if not fams: + # empty means empty, same reading as the HIL walk: no family's build + # references the path, so no build compiles it + s.reasons.append(f'{path}: hw/mcu path resolves to no family, no contribution') + return + s.add(fams, 'all', f'{path}: mcu -> families {sorted(fams)}') + return + m = re.match(r'src/class/([^/]+)/', path) + if m: # rules 8-10 + cls = m.group(1) + roles = _class_roles(base) + exs = _build_class_examples(cls, base, roles, repo_root) + if not exs: + # Empty means empty - maintainer decision. No example config enables this + # class, so no build exercises it and + # nothing is selected. The file IS still parsed by every full build + # (src/CMakeLists.txt, src/tinyusb.mk list class sources unconditionally, + # the CFG_ guard sits inside), so a break outside the guard surfaces on the + # next master push - the accepted safety net. + s.reasons.append(f'{path}: class {cls} enabled by no example config, ' + f'no contribution') + return + s.add(all_bsp_families(repo_root), exs, + f'{path}: class {cls} -> {sorted(exs)}') + return + m = re.match(r'src/(device|host)/', path) + if m: # rules 11-12 + role = m.group(1) + s.add(all_bsp_families(repo_root), role_examples(repo_root, (role, 'dual')), + f'{path}: core {role} stack') + return + m = _BUILD_EX_RE.match(path) + if m: # rules 13-14 + ex = f'{m.group(1)}/{m.group(2)}' + if ex in all_examples(repo_root): + s.add(all_bsp_families(repo_root), {ex}, f'{path}: example {ex}') + else: + # a deleted example builds nothing; removing it from the role + # CMakeLists (rule 15) is what forces the full matrix + s.reasons.append(f'{path}: not an example dir, no build contribution') + return + m = re.match(r'lib/([^/]+)/', path) + if m: # lib rule + lib = m.group(1) + exs = lib_examples(lib, repo_root) + if not exs: + # empty means empty: no example's build pulls this lib in, so no build + # compiles it (lib/SEGGER_RTT is only reached through LOGGER=rtt, which + # no CI build sets) + s.reasons.append(f'{path}: lib {lib} built by no example, no contribution') + return + s.add(all_bsp_families(repo_root), exs, f'{path}: lib {lib} -> {sorted(exs)}') + return + s.force_full(f'{path}: unclassified -> full build matrix') # rules 15-17 + + +def _in_repo(repo_root): + """build_utils/build.py use repo-relative paths; scope a chdir around them. + get_family_boards also prints on an empty family - swallow stdout so the + selector's machine-read JSON stays clean (diagnostics belong on stderr).""" + old = os.getcwd() + os.chdir(repo_root) + try: + with contextlib.redirect_stdout(io.StringIO()): + yield + finally: + os.chdir(old) + + +def _prune_buildable(fams, fam_ex, repo_root): + """Intersect each family's selection with what the family can build at all + (build_utils.skip_example - the same skip.txt/only.txt data CMake's + family_filter reads). + + ANY board of the family counts, not just the one GHA's --one-first picks: + CircleCI's cmake legs build every board of a family, so an example gated to a + single board (only.txt board:mimxrt1060_evk) would otherwise lose ALL compile + coverage exactly when a PR touches it. get_family_boards(.., False, False) is + that full list, with the same CI skip lists the build jobs apply. + + EITHER build system counts too. This one list gates CircleCI's make legs as well + as its cmake ones, and the two answer different questions (build_utils.skip_example): + examples/device/dfu carries `mcu:BCM2835` in skip.txt, which the cmake FAMILY_MCUS + union applies to every broadcom_64bit board while the make scrape applies it to + none - asking cmake alone drops the only aarch64-gcc family in the matrix and + `build-make-aarch64-gcc` stops compiling dfu at all.""" + out_fams, out_ex, reasons = [], {}, [] + allex = list(all_examples(repo_root)) + with _in_repo(repo_root): + for fam in fams: + if not os.path.isdir(os.path.join(repo_root, 'hw/bsp', fam, 'boards')): + # a PR that deletes or renames hw/bsp/<fam> still names it in the + # diff (rule 6); the family builds nothing now, and get_family_boards + # would raise FileNotFoundError out of the whole selector + reasons.append(f'{fam}: family dir gone from tree, dropped') + continue + try: + boards = build_py.get_family_boards(fam, False, False) + except OSError as e: # belt and braces: never traceback here + reasons.append(f'{fam}: boards unreadable ({e}), dropped') + continue + if not boards: + out_fams.append(fam) # unknown layout: keep unfiltered + continue + # what this family's build path can even see, asked the same way for + # every family. build.py's espressif branch builds get_examples('espressif') + # only (the *_freertos examples plus a short extra list); keeping the family + # for anything else spins up CI's most expensive leg to skip every example + # it was given. Identical to the unfiltered list on all 81 other families. + pool = set(build_py.get_examples(fam)) + try: + buildable = [e for e in allex if e in pool and + any(not build_utils.skip_example(e, b) or + not build_utils.skip_example(e, b, (), 'make') + for b in boards)] + except OSError as e: + # a family mid-bring-up (boards/ but no family.cmake/family.mk yet) + # reads as unbuildable to the scrape; keep it rather than tracebacking + # out of the selector and losing the scoping for the whole PR + reasons.append(f'{fam}: mcu scrape unreadable ({e}), kept unfiltered') + out_fams.append(fam) + continue + want = fam_ex.get(fam) + have = set(buildable) + kept = buildable if want is None else [e for e in want if e in have] + if not kept: + continue # this diff builds nothing for this family + out_fams.append(fam) + if set(kept) != set(buildable): + out_ex[fam] = kept + return out_fams, out_ex, reasons + + +def classify_build(changed_files, repo_root, get_deps_families=None): + s = _BSel() + for p in changed_files: + _classify_build_one(p, repo_root, s, get_deps_families) + if s.full: + return {'full': True, 'families': list(all_bsp_families(repo_root)), + 'family_examples': {}, 'reasons': s.reasons} + fams = sorted(s.fam_ex) + fam_ex = {f: sorted(e) for f, e in s.fam_ex.items() if e != 'all'} + fams, fam_ex, pruned = _prune_buildable(fams, fam_ex, repo_root) + s.reasons += pruned + return {'full': False, 'families': fams, 'family_examples': fam_ex, + 'reasons': s.reasons} + + +if __name__ == '__main__': + main() diff --git a/tools/get_deps.py b/tools/get_deps.py index f8161a933..12bec4861 100755 --- a/tools/get_deps.py +++ b/tools/get_deps.py @@ -386,6 +386,10 @@ def main(): parser.add_argument('-f1', '--build-flags-on', action='append', default=[], help='Have no effect') parser.add_argument('--build-name', default=None, help='Have no effect') parser.add_argument('--cflag', action='append', default=[], help='Have no effect') + # build-matrix entries carry -e for tools/build.py; they reach get_deps.py + # verbatim (.github/actions/get_deps, build.yml's hil-hfp-iar) and an + # argparse error here reds the Get Dependencies step of every scoped PR + parser.add_argument('-e', '--example', action='append', default=[], help='Have no effect') args = parser.parse_args() families = args.families diff --git a/tools/metrics.py b/tools/metrics.py index 0e29fc1ab..b97b2b206 100644 --- a/tools/metrics.py +++ b/tools/metrics.py @@ -83,7 +83,7 @@ def parse_bloaty_csv(csv_text, filters=None): return {"files": files, "TOTAL": total_all} -def combine_files(input_files, filters=None): +def combine_files(input_files, filters=None, only_examples=None): """Combine multiple metrics inputs (bloaty CSV or metrics JSON) into a single data set.""" filters = filters or [] @@ -98,6 +98,22 @@ def combine_files(input_files, filters=None): if fin.endswith(".json"): with open(fin, "r", encoding="utf-8") as f: json_data = json.load(f) + if fin.endswith('_by_example.json') and isinstance(json_data, dict) and \ + all(isinstance(v, dict) and 'files' in v for v in json_data.values()): + # a metrics_by_example.json: one data entry per example. Keyed on + # the filename, which IS the contract (write_by_example, the CMake + # rule and metrics_pair_compare all spell that suffix) - a shape + # sniff would silently reroute any coincidentally-shaped JSON. + for ex in sorted(json_data): + if only_examples and ex not in only_examples: + continue + sub = {'files': list(json_data[ex]['files'])} + if filters: + sub['files'] = [f for f in sub['files'] + if f.get('path') and any(x in f['path'] for x in filters)] + all_json_data['file_list'].append(f'{fin}:{ex}') + all_json_data['data'].append(sub) + continue if filters: json_data["files"] = [ f @@ -316,6 +332,25 @@ def write_json_output(json_data, path): json.dump(json_data, outf, indent=2) +def write_by_example(all_json_data, path): + """{<role>/<example>: {files: [...]}} from the data combine_files already parsed + - re-reading and re-parsing every input a second time bought nothing. + + Inputs are map.json files laid out as <build>/<role>/<example>/<name>.map.json + (examples/CMakeLists.txt's pattern), so the example name is the last two path + components; a metrics_by_example.json input already carries its own name in the + file_list entry ('<file>.json:<role>/<name>').""" + out = {} + for fin, data in zip(all_json_data["file_list"], all_json_data["data"]): + _, sep, ex = fin.partition('.json:') + if not sep: + d = os.path.dirname(os.path.abspath(fin)) + ex = f'{os.path.basename(os.path.dirname(d))}/{os.path.basename(d)}' + out.setdefault(ex, {'files': []})['files'] += data.get('files', []) + with open(path, 'w', encoding='utf-8') as f: + json.dump(out, f) + + def render_combine_table(json_data, sort_order='name+'): """Render averaged sizes as markdown table lines (no title).""" files = json_data.get("files", []) @@ -579,7 +614,8 @@ def render_compare_table(rows, include_sum): def cmd_combine(args): """Handle combine subcommand.""" input_files = expand_files(args.files) - all_json_data = combine_files(input_files, args.filters) + only_examples = set(args.only_examples.split(',')) if args.only_examples else None + all_json_data = combine_files(input_files, args.filters, only_examples=only_examples) json_average = compute_avg(all_json_data) if json_average is None: @@ -594,6 +630,8 @@ def cmd_combine(args): if args.markdown_out: write_combine_markdown(json_average, args.out + '.md', sort_order=args.sort, title="TinyUSB Average Code Size Metrics") + if args.by_example: + write_by_example(all_json_data, args.out + '_by_example.json') def cmd_compare(args): @@ -633,6 +671,10 @@ def main(argv=None): combine_parser.add_argument('-S', '--sort', dest='sort', default='size-', choices=['size', 'size-', 'size+', 'name', 'name-', 'name+'], help='Sort order: size/size- (descending), size+ (ascending), name/name+ (ascending), name- (descending). Default: size-') + combine_parser.add_argument('--by-example', dest='by_example', action='store_true', + help='Also write <out>_by_example.json: per-example file lists keyed by role/example') + combine_parser.add_argument('--only-examples', dest='only_examples', default='', + help='Comma-separated role/example ids to keep when reading by-example JSON inputs') # Compare subcommand compare_parser = subparsers.add_parser('compare', help='Compare two metrics inputs (bloaty CSV or metrics JSON)') |