mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
e530de5ad2
Adds crates/headroom-core/src/transforms/code_compressor.rs (1,882 lines): the AST-aware CodeCompressor ported to Rust on tree-sitter, with grammars for Python, JavaScript, TypeScript, Go, Rust, Java, C and C++. Parity-only, like #1153. Nothing calls it: the only references outside the module are the pub mod / pub use declarations in transforms/mod.rs, and live_zone.rs still routes SourceCode to a no-op. The pyo3 bridge is untouched and no Python source changes, so the engine is unreachable from the shipped package. #1155 wires it into live-zone dispatch. Every grammar is pinned with '=' to the exact version of the corresponding Python tree-sitter-<lang> PyPI wheel. Same version on crates.io and PyPI means the same grammar.js, hence the same generated parser.c, hence node-for-node identical ASTs — the precondition for byte-parity. A canary over 9 samples x 8 languages confirmed identical node-type and line-span trees at these pins; bumping any pin requires re-running it and re-recording the fixtures. Ships 30 recorded parity fixtures, a CodeCompressorComparator in headroom-parity, and scripts/record_code_compressor_fixtures.py. Verified byte-identical to the recorded Python output: [code_aware_compressor] total=30 matched=30 skipped=0 diffed=0 Full harness on the merge result: 227 fixtures, 182 matched, 45 skipped (cache_aligner + ccr stubs), 0 diffed, exit 0 — with kompress at 21/21 under ONNX Runtime 1.24.4 (see #2591). Also verified cargo check -p headroom-core --no-default-features passes, so the static-musl path stays intact.
83 lines
2.7 KiB
Python
83 lines
2.7 KiB
Python
#!/usr/bin/env python3
|
|
"""Record standard parity fixtures for the CodeAwareCompressor only.
|
|
|
|
Installs the individual-grammar parser patch, then drives the Python
|
|
`CodeAwareCompressor` (enable_ccr=False, fallback_to_kompress=False) over
|
|
`_varied_code_inputs()` while `record_all()` has the `compress` method
|
|
patched, so only `tests/parity/fixtures/code_aware_compressor/` is
|
|
(re)written — no churn to other transforms' fixtures.
|
|
|
|
The grammar wheels must be installed at the versions the Rust crates pin
|
|
(same version number on PyPI + crates.io = same grammar source = identical
|
|
ASTs; verified by the grammar-parity canary):
|
|
|
|
pip install tree-sitter==0.25.2 \\
|
|
tree-sitter-python==0.25.0 tree-sitter-javascript==0.25.0 \\
|
|
tree-sitter-typescript==0.23.2 tree-sitter-go==0.25.0 \\
|
|
tree-sitter-rust==0.24.2 tree-sitter-java==0.23.5 \\
|
|
tree-sitter-c==0.24.2 tree-sitter-cpp==0.23.4
|
|
python scripts/record_code_compressor_fixtures.py
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
REPO = Path(__file__).resolve().parent.parent
|
|
sys.path.insert(0, str(REPO))
|
|
|
|
|
|
def main() -> int:
|
|
from tests.parity.recorder import (
|
|
_docstring_mode_inputs,
|
|
_varied_code_inputs,
|
|
install_individual_grammar_parsers,
|
|
record_all,
|
|
)
|
|
|
|
statuses = record_all()
|
|
if not statuses.get("code_aware_compressor", "").startswith("patched"):
|
|
print(
|
|
f"code_aware_compressor not patched: {statuses.get('code_aware_compressor')}",
|
|
file=sys.stderr,
|
|
)
|
|
return 1
|
|
|
|
install_individual_grammar_parsers()
|
|
|
|
from headroom.transforms.code_compressor import (
|
|
CodeAwareCompressor,
|
|
CodeCompressorConfig,
|
|
DocstringMode,
|
|
)
|
|
|
|
inputs = _varied_code_inputs()
|
|
cac = CodeAwareCompressor(CodeCompressorConfig(enable_ccr=False, fallback_to_kompress=False))
|
|
for s in inputs:
|
|
cac.compress(s)
|
|
|
|
# Non-default docstring modes (FULL / REMOVE) over docstring-bearing
|
|
# samples — distinct config hash → distinct fixtures.
|
|
ds_inputs = _docstring_mode_inputs()
|
|
extra = 0
|
|
for mode in (DocstringMode.FULL, DocstringMode.REMOVE):
|
|
c = CodeAwareCompressor(
|
|
CodeCompressorConfig(enable_ccr=False, fallback_to_kompress=False, docstring_mode=mode)
|
|
)
|
|
for s in ds_inputs:
|
|
c.compress(s)
|
|
extra += 1
|
|
|
|
out_dir = REPO / "tests" / "parity" / "fixtures" / "code_aware_compressor"
|
|
n = len(list(out_dir.glob("*.json")))
|
|
print(
|
|
f"recorded {n} code_aware_compressor fixtures "
|
|
f"from {len(inputs)} default + {extra} docstring-mode inputs -> {out_dir}",
|
|
file=sys.stderr,
|
|
)
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|