feat(p10-1d): code-cpp-ast-v1 chunker + snapshot test
Identical chunker body to code-c-ast-v1 (per-language work happens in the CppAstExtractor, Task C). Snapshot fixture covers nested namespace + class + ctor/dtor + method + operator overload + template fn + free fn + top-level main, verifying namespace::Class::method symbol convention per design §3.4. 5 chunks emitted: - <top-level> (includes, namespace opening) - kebab::chunk::MdHeadingV1Chunker (class unit) - kebab::identity (template function) - kebab::global_helper (free function in namespace) - main (top-level main function) Template function symbols emit without <T> parameters per spec convention. Namespace::Class::method pattern verified. All tests pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
200
crates/kebab-chunk/tests/code_cpp_ast_snapshot.rs
Normal file
200
crates/kebab-chunk/tests/code_cpp_ast_snapshot.rs
Normal file
@@ -0,0 +1,200 @@
|
||||
//! Snapshot test pinning the `Vec<Chunk>` JSON for a
|
||||
//! representative C++ code `CanonicalDocument`.
|
||||
//!
|
||||
//! This is an integration test. `kebab-parse-code` is intentionally NOT
|
||||
//! a dev-dep (design §6.3 / §8 boundary: AST extraction is parser-side).
|
||||
//! The `CanonicalDocument` is built inline from hand-crafted `Block::Code`
|
||||
//! units, which is the same pattern used in `code_c_ast_v1.rs`'s
|
||||
//! internal `code_doc` test helper.
|
||||
//!
|
||||
//! Set `UPDATE_SNAPSHOTS=1` to re-bake the baseline.
|
||||
|
||||
use std::path::PathBuf;
|
||||
|
||||
use kebab_chunk::CodeCppAstV1Chunker;
|
||||
use kebab_core::{
|
||||
AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock, CommonBlock,
|
||||
Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel, WorkspacePath,
|
||||
id_for_block, id_for_doc,
|
||||
};
|
||||
use serde_json::Value;
|
||||
use time::OffsetDateTime;
|
||||
|
||||
fn fixtures_dir() -> PathBuf {
|
||||
PathBuf::from(env!("CARGO_MANIFEST_DIR"))
|
||||
.join("tests")
|
||||
.join("fixtures")
|
||||
}
|
||||
|
||||
fn fixed_doc() -> CanonicalDocument {
|
||||
let wp = WorkspacePath("projects/record.cpp".into());
|
||||
let aid = AssetId("c".repeat(64));
|
||||
// Pin parser_version so doc_id / block_ids are reproducible.
|
||||
let pv = ParserVersion("code-cpp-v1".into());
|
||||
let doc_id = id_for_doc(&wp, &aid, &pv);
|
||||
|
||||
// Representative units (C++ specific):
|
||||
// 0. includes + namespace opening (lines 1–4, ≤200)
|
||||
// 1. class definition (lines 6–20, ≤200)
|
||||
// 2. template function (lines 22–25, ≤200)
|
||||
// 3. namespace closing + free fn (lines 27–29, ≤200)
|
||||
// 4. main fn (lines 31–34, ≤200)
|
||||
let raw_units: Vec<(&str, u32, u32, String)> = vec![
|
||||
(
|
||||
"<top-level>",
|
||||
1,
|
||||
4,
|
||||
"#include <string>\n#include <vector>\n\nnamespace kebab {".to_string(),
|
||||
),
|
||||
(
|
||||
"kebab::chunk::MdHeadingV1Chunker",
|
||||
6,
|
||||
20,
|
||||
"class MdHeadingV1Chunker {\npublic:\n MdHeadingV1Chunker() = default;\n ~MdHeadingV1Chunker() = default;\n\n std::string chunk_doc(const std::string& doc) {\n return doc;\n }\n\n int operator()(int x) const {\n return x * 2;\n }\n\nprivate:\n int counter_ = 0;\n};".to_string(),
|
||||
),
|
||||
(
|
||||
"kebab::identity",
|
||||
22,
|
||||
25,
|
||||
"template <typename T>\nT identity(T value) {\n return value;\n}".to_string(),
|
||||
),
|
||||
(
|
||||
"kebab::global_helper",
|
||||
27,
|
||||
29,
|
||||
"void global_helper() {\n // free function in kebab namespace\n}".to_string(),
|
||||
),
|
||||
(
|
||||
"main",
|
||||
31,
|
||||
34,
|
||||
"int main() {\n kebab::chunk::MdHeadingV1Chunker c;\n return 0;\n}".to_string(),
|
||||
),
|
||||
];
|
||||
|
||||
let blocks: Vec<Block> = raw_units
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(i, (sym, ls, le, code))| {
|
||||
let span = SourceSpan::Code {
|
||||
line_start: *ls,
|
||||
line_end: *le,
|
||||
symbol: Some((*sym).to_string()),
|
||||
lang: Some("cpp".into()),
|
||||
};
|
||||
let bid = id_for_block(&doc_id, "code", &[], i as u32, &span);
|
||||
Block::Code(CodeBlock {
|
||||
common: CommonBlock {
|
||||
block_id: bid,
|
||||
heading_path: vec![],
|
||||
source_span: span,
|
||||
},
|
||||
lang: Some("cpp".into()),
|
||||
code: code.clone(),
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
|
||||
CanonicalDocument {
|
||||
doc_id,
|
||||
source_asset_id: aid,
|
||||
workspace_path: wp,
|
||||
title: "record.cpp".into(),
|
||||
lang: Lang("und".into()),
|
||||
blocks,
|
||||
metadata: Metadata {
|
||||
aliases: vec![],
|
||||
tags: vec![],
|
||||
created_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
|
||||
updated_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
|
||||
source_type: SourceType::Note,
|
||||
trust_level: TrustLevel::Primary,
|
||||
user_id_alias: None,
|
||||
user: Default::default(),
|
||||
repo: Some("kebab".into()),
|
||||
git_branch: Some("main".into()),
|
||||
git_commit: Some("0".repeat(40)),
|
||||
code_lang: Some("cpp".into()),
|
||||
},
|
||||
provenance: Provenance { events: vec![] },
|
||||
parser_version: pv,
|
||||
schema_version: 1,
|
||||
doc_version: 1,
|
||||
last_chunker_version: None,
|
||||
last_embedding_version: None,
|
||||
}
|
||||
}
|
||||
|
||||
fn fixed_policy() -> ChunkPolicy {
|
||||
ChunkPolicy {
|
||||
target_tokens: 500,
|
||||
overlap_tokens: 80,
|
||||
respect_markdown_headings: false,
|
||||
chunker_version: ChunkerVersion("code-cpp-ast-v1".into()),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn code_cpp_ast_chunks_snapshot() {
|
||||
let doc = fixed_doc();
|
||||
let policy = fixed_policy();
|
||||
|
||||
let chunks = CodeCppAstV1Chunker.chunk(&doc, &policy).expect("chunk");
|
||||
let actual = serde_json::to_value(&chunks).unwrap();
|
||||
|
||||
let dir = fixtures_dir();
|
||||
let baseline_path = dir.join("code-sample.cpp.chunks.snapshot.json");
|
||||
let baseline_text = match std::fs::read_to_string(&baseline_path) {
|
||||
Ok(s) => s,
|
||||
Err(_) if std::env::var("UPDATE_SNAPSHOTS").is_ok() => {
|
||||
std::fs::create_dir_all(&dir).unwrap();
|
||||
let pretty = serde_json::to_string_pretty(&actual).unwrap();
|
||||
std::fs::write(&baseline_path, format!("{pretty}\n")).unwrap();
|
||||
return;
|
||||
}
|
||||
Err(e) => panic!(
|
||||
"missing baseline {}; run with UPDATE_SNAPSHOTS=1 to create: {e}",
|
||||
baseline_path.display()
|
||||
),
|
||||
};
|
||||
let expected: Value = serde_json::from_str(&baseline_text).expect("baseline parses as json");
|
||||
|
||||
if actual != expected {
|
||||
if std::env::var("UPDATE_SNAPSHOTS").is_ok() {
|
||||
let pretty = serde_json::to_string_pretty(&actual).unwrap();
|
||||
std::fs::write(&baseline_path, format!("{pretty}\n")).unwrap();
|
||||
eprintln!("updated baseline {}", baseline_path.display());
|
||||
return;
|
||||
}
|
||||
let pretty = serde_json::to_string_pretty(&actual).unwrap();
|
||||
panic!(
|
||||
"code-cpp-ast-v1 chunks snapshot drift\n\
|
||||
--- expected ({}) ---\n{baseline_text}\n\
|
||||
--- actual ---\n{pretty}\n\
|
||||
If intentional, re-run with UPDATE_SNAPSHOTS=1.",
|
||||
baseline_path.display()
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// Determinism cross-check: re-running the same pipeline yields the same
|
||||
/// chunk_ids byte-for-byte.
|
||||
#[test]
|
||||
fn code_cpp_ast_chunks_are_deterministic() {
|
||||
let policy = fixed_policy();
|
||||
let baseline: Vec<String> = CodeCppAstV1Chunker
|
||||
.chunk(&fixed_doc(), &policy)
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.map(|c| c.chunk_id.0)
|
||||
.collect();
|
||||
for _ in 0..5 {
|
||||
let again: Vec<String> = CodeCppAstV1Chunker
|
||||
.chunk(&fixed_doc(), &policy)
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.map(|c| c.chunk_id.0)
|
||||
.collect();
|
||||
assert_eq!(again, baseline);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user