Compare commits
13 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 9c9e391b15 | |||
| f95cd55484 | |||
| ab288135e9 | |||
| c19aa006d0 | |||
| f1a4f67e12 | |||
| 6463c52827 | |||
| 2559d0d95a | |||
| 4524830306 | |||
| 8cdd3903c7 | |||
| 8b89961ada | |||
| eec90996aa | |||
| ce1c778b4a | |||
| 453ec15df4 |
57
Cargo.lock
generated
57
Cargo.lock
generated
@@ -4127,7 +4127,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-app"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"base64 0.22.1",
|
||||
@@ -4172,7 +4172,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-chunk"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -4187,7 +4187,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-cli"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"clap",
|
||||
@@ -4208,7 +4208,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-config"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"dirs 5.0.1",
|
||||
@@ -4223,7 +4223,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-core"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -4237,7 +4237,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-embed"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -4251,7 +4251,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-embed-local"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"fastembed",
|
||||
@@ -4264,7 +4264,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-eval"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-app",
|
||||
@@ -4283,7 +4283,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-llm"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-core",
|
||||
@@ -4292,7 +4292,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-llm-local"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-config",
|
||||
@@ -4309,7 +4309,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-mcp"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-app",
|
||||
@@ -4327,7 +4327,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-normalize"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-core",
|
||||
@@ -4342,7 +4342,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-parse-code"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"gix",
|
||||
@@ -4352,6 +4352,7 @@ dependencies = [
|
||||
"time",
|
||||
"tracing",
|
||||
"tree-sitter",
|
||||
"tree-sitter-go",
|
||||
"tree-sitter-javascript",
|
||||
"tree-sitter-python",
|
||||
"tree-sitter-rust",
|
||||
@@ -4360,7 +4361,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-parse-image"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"ab_glyph",
|
||||
"anyhow",
|
||||
@@ -4384,7 +4385,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-parse-md"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"kebab-core",
|
||||
@@ -4401,7 +4402,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-parse-pdf"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -4414,7 +4415,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-parse-types"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"kebab-core",
|
||||
"serde",
|
||||
@@ -4422,7 +4423,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-rag"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -4443,7 +4444,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-search"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"globset",
|
||||
@@ -4462,7 +4463,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-source-fs"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -4481,7 +4482,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-store-sqlite"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"blake3",
|
||||
@@ -4502,7 +4503,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-store-vector"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"arrow",
|
||||
@@ -4526,7 +4527,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "kebab-tui"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"crossterm",
|
||||
@@ -8527,6 +8528,16 @@ dependencies = [
|
||||
"tree-sitter-language",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tree-sitter-go"
|
||||
version = "0.25.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c8560a4d2f835cc0d4d2c2e03cbd0dde2f6114b43bc491164238d333e28b16ea"
|
||||
dependencies = [
|
||||
"cc",
|
||||
"tree-sitter-language",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tree-sitter-javascript"
|
||||
version = "0.25.0"
|
||||
|
||||
@@ -31,7 +31,7 @@ edition = "2024"
|
||||
rust-version = "1.85"
|
||||
license = "MIT OR Apache-2.0"
|
||||
repository = "https://github.com/altair823/kebab"
|
||||
version = "0.11.0"
|
||||
version = "0.12.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
anyhow = "1"
|
||||
@@ -94,6 +94,8 @@ tree-sitter-rust = "0.24"
|
||||
tree-sitter-python = "0.25.0"
|
||||
tree-sitter-typescript = "0.23.2"
|
||||
tree-sitter-javascript = "0.25.0"
|
||||
# Go grammar for code ingest (kebab-parse-code, p10-1C-Go).
|
||||
tree-sitter-go = "0.25.0"
|
||||
|
||||
# Disk-footprint trim for dev / test builds. Codegen, opt-level, and
|
||||
# behavior are unchanged — only DWARF debug info is reduced (line
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
|
||||
## 한 줄 요약
|
||||
|
||||
P0–P5 + P6 + P7 + P9-1/2/3/4 (Library / Search / Ask / Inspect) 머지 완료. `kebab ingest` 가 markdown / image / PDF 모두 처리. `kebab search` / `kebab ask` 가 매체 가로질러 결과 + page citation 반환. `kebab tui` 가 4 패널 (Library + Search + Ask + Inspect) 제공 — 사용자가 `?` 로 ask, `/` 로 search, Library Enter / Search `i` 로 inspect, Search `g` 로 editor jump. 다음 후보 = P9-5 (desktop tauri) 또는 보류 중인 P8 (audio) 의 시스템 dep brainstorm.
|
||||
P0–P5 + P6 + P7 + P9-1/2/3/4 (Library / Search / Ask / Inspect) 머지 완료. `kebab ingest` 가 markdown / image / PDF / 소스코드 (Rust / Python / TS / JS / Go) 처리. `kebab search` / `kebab ask` 가 매체 가로질러 결과 + page / code citation 반환. `kebab tui` 가 4 패널 (Library + Search + Ask + Inspect) 제공. 다음 후보 = P10-1C-JavaKotlin 또는 P9-5 (desktop tauri) 또는 보류 중인 P8 (audio).
|
||||
|
||||
## Phase 로드맵
|
||||
|
||||
@@ -20,7 +20,7 @@ P0–P5 + P6 + P7 + P9-1/2/3/4 (Library / Search / Ask / Inspect) 머지 완료.
|
||||
| **P7** | PDF text + page citation | `kebab-parse-pdf` | P5 | ✅ 완료 (3/3 component, page-level chunker + ingest wiring) |
|
||||
| **P8** | 음성 transcription + timestamp citation | `kebab-parse-audio` | P5 | ⏸ 보류 (whisper-rs 시스템 dep brainstorm 필요) |
|
||||
| **P9** | TUI + desktop app | `kebab-tui`, `kebab-desktop` | P5 | 🟡 진행 (4/5 component — P9-1/2/3/4 완료 [Library / Search / Ask / Inspect], P9-5 desktop 예정 · 도그푸딩 피드백 **20/20 ✅**) |
|
||||
| **P10** | code ingest framework | `kebab-parse-code` | P5 | 🟡 진행 중 — 1A-1 ✅ (wire schema + parse-code skeleton + filter flags), 1A-2 ✅ (Rust AST chunker, tree-sitter-rust, `code-rust-ast-v1` — v0.7.0), **1B 🟡 PR 오픈** (Python `code-python-ast-v1` + TypeScript `code-ts-ast-v1` + JavaScript `code-js-ast-v1` — 3 언어 dogfooding 가능, v0.8.0 대기) |
|
||||
| **P10** | code ingest framework | `kebab-parse-code` | P5 | 🟡 진행 중 — 1A-1 ✅ (wire schema + parse-code skeleton + filter flags), 1A-2 ✅ (Rust AST chunker, `code-rust-ast-v1` — v0.7.0), 1B ✅ (Python/TS/JS AST chunkers — v0.8.0 이후), **1C-Go ✅ (Go AST chunker, `code-go-ast-v1` — v0.12.0)**, 1C-JavaKotlin ⏳ (후속 PR) |
|
||||
|
||||
P0~P5 직렬. P6~P9 P5 이후 병렬 가능.
|
||||
|
||||
|
||||
@@ -42,7 +42,7 @@ cargo install --git https://gitea.altair823.xyz/altair823-org/kebab.git --bin ke
|
||||
# 첫 실행 — XDG 경로에 데이터 디렉토리 + config.toml 생성
|
||||
kebab init
|
||||
|
||||
# config 손보고 — workspace.root, 모델 endpoint 등 설정 (지원 형식: md / png / jpg / pdf / rs / py / ts / js)
|
||||
# config 손보고 — workspace.root, 모델 endpoint 등 설정 (지원 형식: md / png / jpg / pdf / rs / py / ts / js / go)
|
||||
${EDITOR:-vi} ~/.config/kebab/config.toml
|
||||
|
||||
# 색인 (Markdown / 이미지 / PDF 모두 한 번에)
|
||||
@@ -70,7 +70,7 @@ kebab doctor
|
||||
| 명령 | 동작 |
|
||||
|------|------|
|
||||
| `kebab init` | XDG 경로에 데이터 디렉토리 + config.toml 생성 |
|
||||
| `kebab ingest [<path>]` | Markdown / 이미지 / PDF / Rust 소스코드 색인 (idempotent). TTY 에서는 stderr 진행 바, non-TTY (CI / pipe) 는 stderr 한 줄씩, `--json` 은 stdout 에 `ingest_progress.v1` 라인 streaming 후 마지막에 `ingest_report.v1`. Ctrl-C 한 번이면 현재 asset 마무리 후 abort (부분 commit 보존, idempotent re-run), 두 번째 Ctrl-C 는 hard exit. Markdown title 이 frontmatter 에 없어도 첫 H1 → H2 → 첫 paragraph 80 자 → 파일명 순으로 자동 채움 (parser_version `md-frontmatter-v2`) — 기존 색인된 doc 도 다음 ingest 에서 새 title 로 갱신. **Incremental** (p9-fb-23): 두 번째 이후의 ingest 는 변하지 않은 doc (blake3 + parser/chunker/embedder version 모두 동일) 의 parse/chunk/embed/vector upsert 를 자동 스킵. final summary 에 `N unchanged` 카운트 표시. `--force-reingest` 로 skip 무시 강제 재처리. **지원 형식** (extractor 자동 결정 — config 에 명시 불가): Markdown (`.md`), 이미지 (`.png` / `.jpg` / `.jpeg`, OCR + caption), PDF (`.pdf`), **소스코드** (`.rs` → `code-rust-ast-v1`, `.py` → `code-python-ast-v1`, `.ts`/`.tsx` → `code-ts-ast-v1`, `.js`/`.mjs`/`.cjs`/`.jsx` → `code-js-ast-v1` — 모두 tree-sitter AST chunker). 다른 확장자는 자동 skip — `IngestItem.warnings` 에 사유 (`"unsupported media type: .docx"` 등), `IngestReport.skipped_by_extension` 에 카운트 분류, CLI / TUI summary 에 breakdown 표시. 코드 chunk 는 `citation.kind = "code"` 에 `citation.lang = "<lang>"` + `symbol` + line range 를 담고, SearchHit top-level 에 `code_lang` + `repo` (`.git/` walk-up 의 디렉토리 이름) 가 backfill 됨. `--code-lang rust` / `--code-lang python` / `--code-lang typescript` / `--code-lang javascript` / `--media code` filter 로 언어별·코드 전용 검색 가능 (p10-1A-1 filter flags). Python symbol 은 workspace 경로 → dotted module path prefix (예: `kebab_eval.metrics.compute_mrr`), TS/JS symbol 은 slash-style module path prefix (예: `src/Foo.Foo.search`). |
|
||||
| `kebab ingest [<path>]` | Markdown / 이미지 / PDF / Rust 소스코드 색인 (idempotent). TTY 에서는 stderr 진행 바, non-TTY (CI / pipe) 는 stderr 한 줄씩, `--json` 은 stdout 에 `ingest_progress.v1` 라인 streaming 후 마지막에 `ingest_report.v1`. Ctrl-C 한 번이면 현재 asset 마무리 후 abort (부분 commit 보존, idempotent re-run), 두 번째 Ctrl-C 는 hard exit. Markdown title 이 frontmatter 에 없어도 첫 H1 → H2 → 첫 paragraph 80 자 → 파일명 순으로 자동 채움 (parser_version `md-frontmatter-v2`) — 기존 색인된 doc 도 다음 ingest 에서 새 title 로 갱신. **Incremental** (p9-fb-23): 두 번째 이후의 ingest 는 변하지 않은 doc (blake3 + parser/chunker/embedder version 모두 동일) 의 parse/chunk/embed/vector upsert 를 자동 스킵. final summary 에 `N unchanged` 카운트 표시. `--force-reingest` 로 skip 무시 강제 재처리. **지원 형식** (extractor 자동 결정 — config 에 명시 불가): Markdown (`.md`), 이미지 (`.png` / `.jpg` / `.jpeg`, OCR + caption), PDF (`.pdf`), **소스코드** (`.rs` → `code-rust-ast-v1`, `.py` → `code-python-ast-v1`, `.ts`/`.tsx` → `code-ts-ast-v1`, `.js`/`.mjs`/`.cjs`/`.jsx` → `code-js-ast-v1`, `.go` → `code-go-ast-v1` — 모두 tree-sitter AST chunker). 다른 확장자는 자동 skip — `IngestItem.warnings` 에 사유 (`"unsupported media type: .docx"` 등), `IngestReport.skipped_by_extension` 에 카운트 분류, CLI / TUI summary 에 breakdown 표시. 코드 chunk 는 `citation.kind = "code"` 에 `citation.lang = "<lang>"` + `symbol` + line range 를 담고, SearchHit top-level 에 `code_lang` + `repo` (`.git/` walk-up 의 디렉토리 이름) 가 backfill 됨. `--code-lang rust` / `--code-lang python` / `--code-lang typescript` / `--code-lang javascript` / `--code-lang go` / `--media code` filter 로 언어별·코드 전용 검색 가능 (p10-1A-1 filter flags). Python symbol 은 workspace 경로 → dotted module path prefix (예: `kebab_eval.metrics.compute_mrr`), TS/JS symbol 은 slash-style module path prefix (예: `src/Foo.Foo.search`), Go symbol 은 `package.Func` / `package.(*Receiver).Method` 형식. |
|
||||
| `kebab search --mode {lexical,vector,hybrid} "<query>" [--no-cache] [--max-tokens N] [--snippet-chars N] [--cursor <opaque>] [--tag T] [--lang L] [--path-glob G] [--trust-min LEVEL] [--media TYPE] [--ingested-after RFC3339] [--doc-id ID] [--trace] [--bulk] [--repo NAME ...] [--code-lang LIST]` | 검색. hybrid는 RRF fusion, citation 포함. 같은 process 안에서 동일 query (NFKC + trim + lowercase 정규화) 반복 시 in-process LRU 캐시 hit (capacity = `[search] cache_capacity`, default 256). `--no-cache` 로 강제 bypass — 디버깅용. ingest commit 발생 시 `kv['corpus_revision']` bump 으로 모든 entry 자동 stale. **`--max-tokens` / `--snippet-chars` / `--cursor` (p9-fb-34)** — agent budget controls. `--json` 출력은 `search_response.v1` wrapper (`{hits, next_cursor, truncated}`) — pre-fb-34 의 bare array 와 호환 안 됨. mismatched cursor → `error.v1.code = stale_cursor`. **filter flags (p9-fb-36):** `--tag` 는 반복 가능 flag (`--tag rust --tag async`) 로 OR 매칭, `--media` 는 `,` 구분 다중 값 OR 매칭, 나머지 flags 간은 AND 조합. `--trust-min` 은 `primary\|secondary\|generated` 중 하나 (해당 level 이상 포함). `--ingested-after` 는 RFC3339 UTC — 파싱 실패 시 `error.v1.code = config_invalid` (exit 2). `--media md` 는 `markdown` alias 로 정규화. 알 수 없는 `--media` 값은 무조건 empty hits (오류 아님). **`--trace` (p9-fb-37)** — `search_response.v1.trace` 에 lexical / vector pre-fusion 후보 + RRF union + per-stage timing (`lexical_ms` / `vector_ms` / `fusion_ms` / `total_ms`) 노출. trace 요청은 캐시 우회 (`--no-cache` 없이도 항상 cold). **`--bulk` (p9-fb-42)** — stdin ndjson 으로 N query 한 번에 실행. `--json` 면 stdout per-query ndjson (`bulk_search_item.v1`) + stderr summary (`bulk_summary: total=N succeeded=S failed=F`). Cap 100. agent 가 query decomposition 후 sub-query 일괄 실행 시 single round-trip — App instance 재사용으로 캐시 / embedder cold-start 비용 한 번만. Per-query failure 는 item 의 `error` (error.v1) 에 격리, 다른 query 계속 진행. **code corpus filters (p10-1A-1):** `--repo` 는 반복 가능 (`--repo kebab --repo other`) OR 매칭. `--code-lang` 는 반복 또는 comma 다중 값 (`--code-lang rust,python`), 알 수 없는 값은 빈 hits. `--media code` 는 Tier 1/2/3 모든 code chunk 포함. 1A-1 시점에서는 indexed 된 code chunk 가 없어 filter 가 항상 빈 결과 — 1A-2 (Rust AST chunker) 머지 이후 실효. |
|
||||
| `kebab list docs` | 색인된 문서 목록 |
|
||||
| `kebab inspect doc <id>` / `kebab inspect chunk <id>` | raw record 보기 |
|
||||
@@ -132,7 +132,7 @@ flowchart TB
|
||||
|
||||
subgraph Pipeline["도메인 + 파이프라인"]
|
||||
parse["parse-md / parse-pdf / parse-image / parse-code"]
|
||||
chunker["chunker (md-heading-v1, pdf-page-v1, code-rust-ast-v1, code-python-ast-v1, code-ts-ast-v1, code-js-ast-v1)"]
|
||||
chunker["chunker (md-heading-v1, pdf-page-v1, code-rust-ast-v1, code-python-ast-v1, code-ts-ast-v1, code-js-ast-v1, code-go-ast-v1)"]
|
||||
embedder["embedder (fastembed multilingual-e5-large)"]
|
||||
retriever["retriever (lexical / vector / hybrid RRF)"]
|
||||
rag["RAG pipeline"]
|
||||
|
||||
@@ -189,10 +189,12 @@ fn fetch_span(
|
||||
// (markdown / note / paper / reference / inbox) is the *user-facing*
|
||||
// category, not the rendering format — the actual byte-level format
|
||||
// lives on the source `RawAsset.media_type`. Look it up via
|
||||
// workspace_path (unique key per asset).
|
||||
if let Some(asset) = <kebab_store_sqlite::SqliteStore as DocumentStore>::get_asset_by_workspace_path(
|
||||
// doc.source_asset_id (PRIMARY KEY) so twin files (identical content
|
||||
// at different paths) always read *this* document's own asset row,
|
||||
// not whichever twin last wrote `assets.workspace_path`.
|
||||
if let Some(asset) = <kebab_store_sqlite::SqliteStore as DocumentStore>::get_asset(
|
||||
&app.sqlite,
|
||||
&doc.workspace_path,
|
||||
&doc.source_asset_id,
|
||||
)? {
|
||||
if matches!(
|
||||
asset.media_type,
|
||||
|
||||
@@ -39,7 +39,7 @@ use std::sync::Arc;
|
||||
use anyhow::{Context, anyhow};
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use kebab_chunk::{CodeJsAstV1Chunker, CodePythonAstV1Chunker, CodeRustAstV1Chunker, CodeTsAstV1Chunker, MdHeadingV1Chunker, PdfPageV1Chunker};
|
||||
use kebab_chunk::{CodeGoAstV1Chunker, CodeJsAstV1Chunker, CodePythonAstV1Chunker, CodeRustAstV1Chunker, CodeTsAstV1Chunker, MdHeadingV1Chunker, PdfPageV1Chunker};
|
||||
use kebab_core::{
|
||||
Answer, Block, CanonicalDocument, Chunk, ChunkId, ChunkPolicy, ChunkerVersion, Chunker,
|
||||
DocFilter, DocSummary, DocumentId, DocumentStore, Embedder, EmbeddingInput,
|
||||
@@ -50,7 +50,7 @@ use kebab_core::{
|
||||
use kebab_llm_local::OllamaLanguageModel;
|
||||
use kebab_normalize::build_canonical_document;
|
||||
use kebab_parse_image::{ImageExtractor, OllamaVisionOcr, apply_caption, apply_ocr};
|
||||
use kebab_parse_code::{JavascriptAstExtractor, PythonAstExtractor, RustAstExtractor, TypescriptAstExtractor};
|
||||
use kebab_parse_code::{GoAstExtractor, JavascriptAstExtractor, PythonAstExtractor, RustAstExtractor, TypescriptAstExtractor};
|
||||
use kebab_parse_pdf::PdfTextExtractor;
|
||||
use kebab_parse_md::{BodyHints, parse_blocks, parse_frontmatter};
|
||||
use kebab_source_fs::FsSourceConnector;
|
||||
@@ -950,7 +950,7 @@ fn ingest_one_asset(
|
||||
}
|
||||
// p10-1A-2 / 1B: code ingest dispatch.
|
||||
MediaType::Code(lang)
|
||||
if matches!(lang.as_str(), "rust" | "python" | "typescript" | "javascript") =>
|
||||
if matches!(lang.as_str(), "rust" | "python" | "typescript" | "javascript" | "go") =>
|
||||
{
|
||||
return ingest_one_code_asset(
|
||||
app,
|
||||
@@ -1827,6 +1827,7 @@ fn ingest_one_code_asset(
|
||||
"python" => ParserVersion(kebab_parse_code::PYTHON_PARSER_VERSION.to_string()),
|
||||
"typescript" => ParserVersion(kebab_parse_code::TS_PARSER_VERSION.to_string()),
|
||||
"javascript" => ParserVersion(kebab_parse_code::JS_PARSER_VERSION.to_string()),
|
||||
"go" => ParserVersion(kebab_parse_code::GO_PARSER_VERSION.to_string()),
|
||||
other => anyhow::bail!("unsupported code_lang: {other}"),
|
||||
};
|
||||
|
||||
@@ -1836,6 +1837,7 @@ fn ingest_one_code_asset(
|
||||
"python" => CodePythonAstV1Chunker.chunker_version(),
|
||||
"typescript" => CodeTsAstV1Chunker.chunker_version(),
|
||||
"javascript" => CodeJsAstV1Chunker.chunker_version(),
|
||||
"go" => CodeGoAstV1Chunker.chunker_version(),
|
||||
other => anyhow::bail!("unreachable chunker_version: {other}"),
|
||||
};
|
||||
|
||||
@@ -1874,6 +1876,9 @@ fn ingest_one_code_asset(
|
||||
"javascript" => JavascriptAstExtractor::new()
|
||||
.extract(&ctx, &bytes)
|
||||
.context("kb-parse-code::JavascriptAstExtractor::extract (code:javascript)")?,
|
||||
"go" => GoAstExtractor::new()
|
||||
.extract(&ctx, &bytes)
|
||||
.context("kb-parse-code::GoAstExtractor::extract (code:go)")?,
|
||||
other => anyhow::bail!("unreachable (extract): {other}"),
|
||||
};
|
||||
|
||||
@@ -1891,6 +1896,9 @@ fn ingest_one_code_asset(
|
||||
"javascript" => CodeJsAstV1Chunker
|
||||
.chunk(&canonical, chunk_policy)
|
||||
.context("kb-chunk::CodeJsAstV1Chunker::chunk (code:javascript)")?,
|
||||
"go" => CodeGoAstV1Chunker
|
||||
.chunk(&canonical, chunk_policy)
|
||||
.context("kb-chunk::CodeGoAstV1Chunker::chunk (code:go)")?,
|
||||
other => anyhow::bail!("unreachable (chunk): {other}"),
|
||||
};
|
||||
|
||||
|
||||
@@ -390,6 +390,77 @@ fn javascript_file_ingests_and_searches_as_code_citation() {
|
||||
);
|
||||
}
|
||||
|
||||
/// p10-1c-go Task F: a `.go` file in a sub-directory is ingested and the
|
||||
/// resulting `Citation::Code` hit must carry `lang="go"`,
|
||||
/// `symbol="chunk.ParseDoc"`, and `line_start >= 1`.
|
||||
/// The sub-directory (`chunk/`) ensures the Go package-prefix wiring
|
||||
/// produces a non-empty module prefix so the fully-qualified symbol assertion
|
||||
/// exercises that path end-to-end.
|
||||
#[test]
|
||||
fn go_file_ingests_and_searches_as_code_citation() {
|
||||
let env = TestEnv::lexical_only();
|
||||
|
||||
let pkg_dir = env.workspace_root.join("chunk");
|
||||
std::fs::create_dir_all(&pkg_dir).unwrap();
|
||||
std::fs::write(
|
||||
pkg_dir.join("ast.go"),
|
||||
"package chunk\n\nfunc ParseDoc(input string) string {\n return input\n}\n",
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false)
|
||||
.expect("ingest must succeed");
|
||||
assert_eq!(report.errors, 0);
|
||||
assert!(report.new >= 1);
|
||||
|
||||
let go_item = report
|
||||
.items
|
||||
.as_ref()
|
||||
.expect("items present")
|
||||
.iter()
|
||||
.find(|i| i.doc_path.0.ends_with("ast.go"))
|
||||
.expect("ast.go item present");
|
||||
assert_eq!(
|
||||
go_item.parser_version.as_ref().map(|p| p.0.as_str()),
|
||||
Some("code-go-v1"),
|
||||
"parser_version must be code-go-v1"
|
||||
);
|
||||
assert_eq!(
|
||||
go_item.chunker_version.as_ref().map(|c| c.0.as_str()),
|
||||
Some("code-go-ast-v1"),
|
||||
"chunker_version must be code-go-ast-v1"
|
||||
);
|
||||
|
||||
let hits = kebab_app::search_with_config(env.config.clone(), lexical_query("ParseDoc"))
|
||||
.expect("search must succeed");
|
||||
let h = hits
|
||||
.iter()
|
||||
.find(|h| matches!(&h.citation, kebab_core::Citation::Code { .. }))
|
||||
.expect("Citation::Code hit");
|
||||
match &h.citation {
|
||||
kebab_core::Citation::Code {
|
||||
lang,
|
||||
symbol,
|
||||
line_start,
|
||||
..
|
||||
} => {
|
||||
assert_eq!(lang.as_deref(), Some("go"), "citation.lang must be 'go'");
|
||||
assert_eq!(
|
||||
symbol.as_deref(),
|
||||
Some("chunk.ParseDoc"),
|
||||
"citation.symbol must be 'chunk.ParseDoc'"
|
||||
);
|
||||
assert!(*line_start >= 1, "line_start must be >=1");
|
||||
}
|
||||
_ => unreachable!(),
|
||||
}
|
||||
assert_eq!(
|
||||
h.code_lang.as_deref(),
|
||||
Some("go"),
|
||||
"SearchHit.code_lang must be 'go'"
|
||||
);
|
||||
}
|
||||
|
||||
/// Re-ingesting the same `.rs` file without changes must report
|
||||
/// `Unchanged` (incremental-skip path exercised).
|
||||
#[test]
|
||||
|
||||
176
crates/kebab-app/tests/twin_files_fetch_span.rs
Normal file
176
crates/kebab-app/tests/twin_files_fetch_span.rs
Normal file
@@ -0,0 +1,176 @@
|
||||
//! Regression test for the twin-file fetch_span media-type lookup bug.
|
||||
//!
|
||||
//! Twin files (identical content at different workspace paths) share one
|
||||
//! `assets` row whose PRIMARY KEY is the blake3 content hash. The old
|
||||
//! `fetch_span` implementation called
|
||||
//! `get_asset_by_workspace_path(&doc.workspace_path)` to check whether the
|
||||
//! media type was PDF/audio (and therefore reject span fetch). For a twin
|
||||
//! file that lookup could silently return the *other* twin's asset row if
|
||||
//! `assets.workspace_path` had been overwritten on the most recent ingest of
|
||||
//! the sibling — making the media-type branch decision incorrect.
|
||||
//!
|
||||
//! Fix: `fetch_span` now uses the 2-step lookup
|
||||
//! `get_document_by_workspace_path` → `doc.source_asset_id` → `get_asset`
|
||||
//! so the result is always anchored to the requesting document, not
|
||||
//! whichever twin last updated `assets.workspace_path`.
|
||||
//!
|
||||
//! This test builds a twin-file scenario (two .md files at different paths
|
||||
//! with identical content), ingests both, then calls `fetch_span` on each
|
||||
//! twin's `doc_id` and asserts it succeeds. Before the fix, if the asset
|
||||
//! row's workspace_path happened to point at the wrong twin the span could
|
||||
//! return an incorrect `span_not_supported` for a non-PDF/audio file, or
|
||||
//! conversely allow span on a PDF twin by accident. After the fix, the
|
||||
//! lookup is always doc-specific.
|
||||
|
||||
mod common;
|
||||
|
||||
use common::TestEnv;
|
||||
use kebab_app::ingest_with_config;
|
||||
use kebab_core::{DocumentStore, FetchKind, FetchOpts, FetchQuery, IngestItemKind};
|
||||
|
||||
#[test]
|
||||
fn twin_files_fetch_span_uses_correct_asset() {
|
||||
let env = TestEnv::lexical_only();
|
||||
|
||||
// Write two markdown files with identical content at different paths.
|
||||
let dir_a = env.workspace_root.join("src_a");
|
||||
let dir_b = env.workspace_root.join("src_b");
|
||||
std::fs::create_dir_all(&dir_a).unwrap();
|
||||
std::fs::create_dir_all(&dir_b).unwrap();
|
||||
|
||||
// The content must produce at least 1 line so span fetch is non-trivial.
|
||||
let content = "# Twin\n\nLine one.\n\nLine two.\n\nLine three.\n";
|
||||
std::fs::write(dir_a.join("note.md"), content).unwrap();
|
||||
std::fs::write(dir_b.join("note.md"), content).unwrap();
|
||||
|
||||
// Ingest all files (fixture workspace + our two new twins).
|
||||
let report = ingest_with_config(env.config.clone(), env.scope(), false)
|
||||
.expect("ingest must succeed");
|
||||
assert_eq!(report.errors, 0, "no ingest errors; report={report:?}");
|
||||
|
||||
// Both twin paths must appear as New in the report.
|
||||
let items = report.items.as_ref().expect("items must be present");
|
||||
let twin_items: Vec<_> = items
|
||||
.iter()
|
||||
.filter(|i| {
|
||||
i.doc_path.0.ends_with("src_a/note.md")
|
||||
|| i.doc_path.0.ends_with("src_b/note.md")
|
||||
})
|
||||
.collect();
|
||||
assert_eq!(
|
||||
twin_items.len(),
|
||||
2,
|
||||
"exactly 2 twin items expected; items={items:?}"
|
||||
);
|
||||
for item in &twin_items {
|
||||
assert_eq!(
|
||||
item.kind,
|
||||
IngestItemKind::New,
|
||||
"each twin must be New; item={item:?}"
|
||||
);
|
||||
}
|
||||
|
||||
// Resolve doc_ids for both workspace paths.
|
||||
// The ingest layer normalises workspace_path to the path relative to
|
||||
// workspace_root (e.g. "src_a/note.md"), so we look up by that form.
|
||||
let store = kebab_store_sqlite::SqliteStore::open(&env.config).unwrap();
|
||||
store.run_migrations().unwrap();
|
||||
|
||||
// Find the twin items by matching on suffix so the test is robust to
|
||||
// however the workspace root is represented.
|
||||
let items = report.items.as_ref().expect("items must be present");
|
||||
let path_a_str = items
|
||||
.iter()
|
||||
.find(|i| i.doc_path.0.ends_with("src_a/note.md"))
|
||||
.map(|i| i.doc_path.0.clone())
|
||||
.expect("src_a/note.md must appear in ingest report");
|
||||
let path_b_str = items
|
||||
.iter()
|
||||
.find(|i| i.doc_path.0.ends_with("src_b/note.md"))
|
||||
.map(|i| i.doc_path.0.clone())
|
||||
.expect("src_b/note.md must appear in ingest report");
|
||||
|
||||
let path_a = kebab_core::WorkspacePath(path_a_str);
|
||||
let path_b = kebab_core::WorkspacePath(path_b_str);
|
||||
|
||||
let doc_a = store
|
||||
.get_document_by_workspace_path(&path_a)
|
||||
.expect("get_document_by_workspace_path path_a")
|
||||
.expect("doc_a must exist after ingest");
|
||||
let doc_b = store
|
||||
.get_document_by_workspace_path(&path_b)
|
||||
.expect("get_document_by_workspace_path path_b")
|
||||
.expect("doc_b must exist after ingest");
|
||||
|
||||
// Both twins share one asset_id (same content hash).
|
||||
assert_eq!(
|
||||
doc_a.source_asset_id, doc_b.source_asset_id,
|
||||
"twin files must share one asset_id"
|
||||
);
|
||||
|
||||
// Open App and issue span fetch on each twin's doc_id.
|
||||
let app = env.app();
|
||||
|
||||
let result_a = app
|
||||
.fetch(
|
||||
FetchQuery::Span {
|
||||
doc_id: doc_a.doc_id.clone(),
|
||||
line_start: 1,
|
||||
line_end: 2,
|
||||
},
|
||||
FetchOpts::default(),
|
||||
)
|
||||
.expect("fetch_span on twin A must succeed for a markdown file");
|
||||
assert_eq!(result_a.kind, FetchKind::Span);
|
||||
assert!(
|
||||
result_a.text.as_deref().is_some_and(|t| !t.is_empty()),
|
||||
"span text for twin A must not be empty"
|
||||
);
|
||||
|
||||
let result_b = app
|
||||
.fetch(
|
||||
FetchQuery::Span {
|
||||
doc_id: doc_b.doc_id.clone(),
|
||||
line_start: 1,
|
||||
line_end: 2,
|
||||
},
|
||||
FetchOpts::default(),
|
||||
)
|
||||
.expect("fetch_span on twin B must succeed for a markdown file");
|
||||
assert_eq!(result_b.kind, FetchKind::Span);
|
||||
assert!(
|
||||
result_b.text.as_deref().is_some_and(|t| !t.is_empty()),
|
||||
"span text for twin B must not be empty"
|
||||
);
|
||||
|
||||
// Ingest again to force the asset.workspace_path flip-flop, then
|
||||
// re-check. Pre-fix this was the scenario that triggered the bug:
|
||||
// after the second ingest the asset row's workspace_path could point
|
||||
// at either twin, making one twin's span fetch behave incorrectly.
|
||||
let report2 = ingest_with_config(env.config.clone(), env.scope(), false)
|
||||
.expect("second ingest must succeed");
|
||||
assert_eq!(report2.errors, 0, "no ingest errors on second run; report={report2:?}");
|
||||
|
||||
// Re-open app after second ingest and verify span still works on both.
|
||||
let app2 = env.app();
|
||||
|
||||
app2.fetch(
|
||||
FetchQuery::Span {
|
||||
doc_id: doc_a.doc_id.clone(),
|
||||
line_start: 1,
|
||||
line_end: 3,
|
||||
},
|
||||
FetchOpts::default(),
|
||||
)
|
||||
.expect("fetch_span on twin A after flip-flop must still succeed");
|
||||
|
||||
app2.fetch(
|
||||
FetchQuery::Span {
|
||||
doc_id: doc_b.doc_id.clone(),
|
||||
line_start: 1,
|
||||
line_end: 3,
|
||||
},
|
||||
FetchOpts::default(),
|
||||
)
|
||||
.expect("fetch_span on twin B after flip-flop must still succeed");
|
||||
}
|
||||
322
crates/kebab-chunk/src/code_go_ast_v1.rs
Normal file
322
crates/kebab-chunk/src/code_go_ast_v1.rs
Normal file
@@ -0,0 +1,322 @@
|
||||
//! `code-go-ast-v1` — maps a tree-sitter-derived Go AST
|
||||
//! `CanonicalDocument` (one `Block::Code` per semantic unit, each with
|
||||
//! `SourceSpan::Code`) to chunks 1:1. A unit longer than
|
||||
//! `AST_CHUNK_MAX_LINES` is split into `<symbol> [part i/N]` sub-chunks
|
||||
//! at blank-line paragraph boundaries (design §9.1 oversize fallback).
|
||||
//!
|
||||
//! tree-sitter is intentionally NOT a dependency here: AST work is
|
||||
//! parser-side (`kebab-parse-code`, design §6.3). This chunker only
|
||||
//! consumes the `CanonicalDocument`.
|
||||
//!
|
||||
//! `AST_CHUNK_MAX_LINES` is a constant matching
|
||||
//! `IngestCodeCfg::default().ast_chunk_max_lines` (200). Per-medium
|
||||
//! config threading needs a chunker registry (P+); same deviation
|
||||
//! pattern as `pdf-page-v1`'s pinned `chunker_version`
|
||||
//! (`tasks/HOTFIXES.md`).
|
||||
|
||||
use kebab_core::{
|
||||
Block, BlockId, CanonicalDocument, Chunk, ChunkPolicy, Chunker, ChunkerVersion, DocumentId,
|
||||
SourceSpan, id_for_chunk,
|
||||
};
|
||||
|
||||
const VERSION_LABEL: &str = "code-go-ast-v1";
|
||||
const BYTES_PER_TOKEN: usize = 3;
|
||||
const POLICY_HASH_HEX_LEN: usize = 16;
|
||||
const AST_CHUNK_MAX_LINES: u32 = 200;
|
||||
|
||||
#[derive(Clone, Copy, Debug, Default)]
|
||||
pub struct CodeGoAstV1Chunker;
|
||||
|
||||
impl Chunker for CodeGoAstV1Chunker {
|
||||
fn chunker_version(&self) -> ChunkerVersion {
|
||||
ChunkerVersion(VERSION_LABEL.to_string())
|
||||
}
|
||||
|
||||
fn policy_hash(&self, policy: &ChunkPolicy) -> String {
|
||||
let bytes = serde_json_canonicalizer::to_vec(policy)
|
||||
.expect("canonical JSON serialization of ChunkPolicy must not fail");
|
||||
let hex = blake3::hash(&bytes).to_hex().to_string();
|
||||
hex[..POLICY_HASH_HEX_LEN].to_string()
|
||||
}
|
||||
|
||||
fn chunk(
|
||||
&self,
|
||||
doc: &CanonicalDocument,
|
||||
policy: &ChunkPolicy,
|
||||
) -> anyhow::Result<Vec<Chunk>> {
|
||||
for b in &doc.blocks {
|
||||
let c = match b {
|
||||
Block::Code(c) => c,
|
||||
_ => anyhow::bail!(
|
||||
"CodeGoAstV1Chunker only handles code docs (got non-Code block)"
|
||||
),
|
||||
};
|
||||
if !matches!(c.common.source_span, SourceSpan::Code { .. }) {
|
||||
anyhow::bail!(
|
||||
"CodeGoAstV1Chunker only handles code docs (got non-Code source_span)"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
let base_policy_hash = self.policy_hash(policy);
|
||||
let chunker_version = self.chunker_version();
|
||||
let mut out: Vec<Chunk> = Vec::new();
|
||||
|
||||
for b in &doc.blocks {
|
||||
let cb = match b {
|
||||
Block::Code(c) => c,
|
||||
_ => unreachable!("validated above"),
|
||||
};
|
||||
let (ls, le, symbol, lang) = match &cb.common.source_span {
|
||||
SourceSpan::Code { line_start, line_end, symbol, lang } => {
|
||||
(*line_start, *line_end, symbol.clone(), lang.clone())
|
||||
}
|
||||
_ => unreachable!("validated above"),
|
||||
};
|
||||
let block_ids: Vec<BlockId> = vec![cb.common.block_id.clone()];
|
||||
let span_lines = le.saturating_sub(ls) + 1;
|
||||
|
||||
if span_lines <= AST_CHUNK_MAX_LINES {
|
||||
let span = SourceSpan::Code {
|
||||
line_start: ls,
|
||||
line_end: le,
|
||||
symbol: symbol.clone(),
|
||||
lang: lang.clone(),
|
||||
};
|
||||
out.push(make_chunk(
|
||||
doc, &chunker_version, &block_ids, &base_policy_hash,
|
||||
None, span, cb.code.clone(),
|
||||
));
|
||||
} else {
|
||||
let parts = split_oversize(&cb.code);
|
||||
let n = parts.len();
|
||||
for (i, (off_start, off_end, text)) in parts.into_iter().enumerate() {
|
||||
let part_ls = ls + off_start;
|
||||
let part_le = ls + off_end;
|
||||
let part_sym = symbol
|
||||
.as_ref()
|
||||
.map(|s| format!("{s} [part {}/{n}]", i + 1));
|
||||
let span = SourceSpan::Code {
|
||||
line_start: part_ls,
|
||||
line_end: part_le,
|
||||
symbol: part_sym,
|
||||
lang: lang.clone(),
|
||||
};
|
||||
out.push(make_chunk(
|
||||
doc, &chunker_version, &block_ids, &base_policy_hash,
|
||||
Some(part_ls), span, text,
|
||||
));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
tracing::debug!(
|
||||
target: "kebab-chunk",
|
||||
doc_id = %doc.doc_id,
|
||||
chunks = out.len(),
|
||||
"code-go-ast-v1 chunked",
|
||||
);
|
||||
Ok(out)
|
||||
}
|
||||
}
|
||||
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
fn make_chunk(
|
||||
doc: &CanonicalDocument,
|
||||
chunker_version: &ChunkerVersion,
|
||||
block_ids: &[BlockId],
|
||||
base_policy_hash: &str,
|
||||
split_key: Option<u32>,
|
||||
span: SourceSpan,
|
||||
text: String,
|
||||
) -> Chunk {
|
||||
let id_hash = match split_key {
|
||||
Some(k) => format!("{base_policy_hash}#L{k}"),
|
||||
None => base_policy_hash.to_string(),
|
||||
};
|
||||
let chunk_id = id_for_chunk(&doc.doc_id, chunker_version, block_ids, &id_hash);
|
||||
let token_estimate = text.len().div_ceil(BYTES_PER_TOKEN);
|
||||
Chunk {
|
||||
chunk_id,
|
||||
doc_id: DocumentId(doc.doc_id.0.clone()),
|
||||
block_ids: block_ids.to_vec(),
|
||||
text,
|
||||
heading_path: Vec::new(),
|
||||
source_spans: vec![span],
|
||||
token_estimate,
|
||||
chunker_version: chunker_version.clone(),
|
||||
policy_hash: base_policy_hash.to_string(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Split an oversize unit at blank-line paragraph boundaries, greedily
|
||||
/// gluing paragraphs until ~`AST_CHUNK_MAX_LINES` lines accumulate.
|
||||
/// Returns `(line_offset_start, line_offset_end, text)` where offsets are
|
||||
/// 0-based within the unit (caller adds the unit's absolute `line_start`).
|
||||
fn split_oversize(code: &str) -> Vec<(u32, u32, String)> {
|
||||
let lines: Vec<&str> = code.split('\n').collect();
|
||||
let total = lines.len() as u32;
|
||||
let mut out: Vec<(u32, u32, String)> = Vec::new();
|
||||
let mut start: u32 = 0;
|
||||
while start < total {
|
||||
let mut end = (start + AST_CHUNK_MAX_LINES).min(total);
|
||||
let floor = start + (AST_CHUNK_MAX_LINES * 4 / 5);
|
||||
if end < total {
|
||||
if let Some(b) = (floor.min(end)..end)
|
||||
.rev()
|
||||
.find(|&i| lines[i as usize].trim().is_empty())
|
||||
{
|
||||
end = b + 1;
|
||||
}
|
||||
}
|
||||
let text = lines[start as usize..end as usize].join("\n");
|
||||
out.push((start, end.saturating_sub(1), text));
|
||||
start = end;
|
||||
}
|
||||
if out.is_empty() {
|
||||
out.push((0, total.saturating_sub(1), code.to_string()));
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use kebab_core::{
|
||||
Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock, CommonBlock,
|
||||
SourceSpan, id_for_block, id_for_doc, AssetId, Lang, Metadata, ParserVersion, Provenance,
|
||||
SourceType, TrustLevel, WorkspacePath,
|
||||
};
|
||||
use time::OffsetDateTime;
|
||||
|
||||
fn code_doc(units: &[(&str, u32, u32, &str)]) -> CanonicalDocument {
|
||||
let wp = WorkspacePath("crates/x/src/a.go".into());
|
||||
let aid = AssetId("a".repeat(64));
|
||||
let pv = ParserVersion("code-go-v1".into());
|
||||
let doc_id = id_for_doc(&wp, &aid, &pv);
|
||||
let blocks = 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("go".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("go".into()),
|
||||
code: (*code).to_string(),
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
CanonicalDocument {
|
||||
doc_id, source_asset_id: aid, workspace_path: wp, title: "a".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("go".into()),
|
||||
},
|
||||
provenance: Provenance { events: vec![] },
|
||||
parser_version: pv, schema_version: 1, doc_version: 1,
|
||||
last_chunker_version: None, last_embedding_version: None,
|
||||
}
|
||||
}
|
||||
fn policy() -> ChunkPolicy {
|
||||
ChunkPolicy { target_tokens: 500, overlap_tokens: 80,
|
||||
respect_markdown_headings: false,
|
||||
chunker_version: ChunkerVersion(VERSION_LABEL.into()) }
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn chunker_version_is_code_go_ast_v1() {
|
||||
assert_eq!(CodeGoAstV1Chunker.chunker_version(),
|
||||
ChunkerVersion("code-go-ast-v1".into()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn one_chunk_per_unit_preserves_code_span() {
|
||||
let doc = code_doc(&[
|
||||
("parse", 1, 3, "func parse() {\n\t// x\n}"),
|
||||
("Foo.double", 5, 7, "func double() int {\n\t//\n\treturn 0\n}"),
|
||||
]);
|
||||
let chunks = CodeGoAstV1Chunker.chunk(&doc, &policy()).unwrap();
|
||||
assert_eq!(chunks.len(), 2);
|
||||
for c in &chunks {
|
||||
assert_eq!(c.source_spans.len(), 1);
|
||||
assert!(matches!(c.source_spans[0], SourceSpan::Code { .. }));
|
||||
assert_eq!(c.heading_path, Vec::<String>::new());
|
||||
assert_eq!(c.chunker_version.0, "code-go-ast-v1");
|
||||
}
|
||||
match &chunks[0].source_spans[0] {
|
||||
SourceSpan::Code { symbol, line_start, line_end, .. } => {
|
||||
assert_eq!(symbol.as_deref(), Some("parse"));
|
||||
assert_eq!((*line_start, *line_end), (1, 3));
|
||||
}
|
||||
_ => unreachable!(),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn oversize_unit_splits_into_parts_with_unique_ids() {
|
||||
let body = (0..500).map(|i| format!("\tx{i} := {i}")).collect::<Vec<_>>().join("\n");
|
||||
let code = format!("func big() {{\n{body}\n}}");
|
||||
let doc = code_doc(&[("big", 1, 502, &code)]);
|
||||
let chunks = CodeGoAstV1Chunker.chunk(&doc, &policy()).unwrap();
|
||||
assert!(chunks.len() >= 2, "oversize unit must split, got {}", chunks.len());
|
||||
for c in &chunks {
|
||||
match &c.source_spans[0] {
|
||||
SourceSpan::Code { symbol, .. } => {
|
||||
assert!(symbol.as_deref().unwrap().starts_with("big [part "),
|
||||
"part-numbered symbol, got {symbol:?}");
|
||||
}
|
||||
_ => unreachable!(),
|
||||
}
|
||||
}
|
||||
let mut ids: Vec<&str> = chunks.iter().map(|c| c.chunk_id.0.as_str()).collect();
|
||||
let n = ids.len(); ids.sort(); ids.dedup();
|
||||
assert_eq!(ids.len(), n, "chunk_ids unique across split parts");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn non_code_doc_errors() {
|
||||
use kebab_core::TextBlock;
|
||||
let mut doc = code_doc(&[("parse", 1, 1, "func parse() {}")]);
|
||||
doc.blocks = vec![Block::Paragraph(TextBlock {
|
||||
common: CommonBlock {
|
||||
block_id: kebab_core::BlockId("b".into()),
|
||||
heading_path: vec![],
|
||||
source_span: SourceSpan::Line { start: 1, end: 1 },
|
||||
},
|
||||
text: "x".into(), inlines: vec![],
|
||||
})];
|
||||
let err = CodeGoAstV1Chunker.chunk(&doc, &policy()).unwrap_err();
|
||||
assert!(err.to_string().contains("CodeGoAstV1Chunker"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_chunk_ids_1000() {
|
||||
let doc = code_doc(&[("parse", 1, 2, "func parse() {}\n")]);
|
||||
let base: Vec<String> = CodeGoAstV1Chunker.chunk(&doc, &policy())
|
||||
.unwrap().into_iter().map(|c| c.chunk_id.0).collect();
|
||||
for _ in 0..1000 {
|
||||
let again: Vec<String> = CodeGoAstV1Chunker.chunk(&doc, &policy())
|
||||
.unwrap().into_iter().map(|c| c.chunk_id.0).collect();
|
||||
assert_eq!(again, base);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn policy_hash_matches_md_heading_v1() {
|
||||
let p = policy();
|
||||
assert_eq!(CodeGoAstV1Chunker.policy_hash(&p),
|
||||
crate::MdHeadingV1Chunker.policy_hash(&p));
|
||||
}
|
||||
}
|
||||
@@ -15,6 +15,7 @@
|
||||
//! embedder, the retriever, the LLM, the RAG layer, or the UI layers.
|
||||
//! It consumes `CanonicalDocument` purely through `kb-core` types.
|
||||
|
||||
mod code_go_ast_v1;
|
||||
mod code_js_ast_v1;
|
||||
mod code_python_ast_v1;
|
||||
mod code_rust_ast_v1;
|
||||
@@ -22,6 +23,7 @@ mod code_ts_ast_v1;
|
||||
mod md_heading_v1;
|
||||
mod pdf_page_v1;
|
||||
|
||||
pub use code_go_ast_v1::CodeGoAstV1Chunker;
|
||||
pub use code_js_ast_v1::CodeJsAstV1Chunker;
|
||||
pub use code_python_ast_v1::CodePythonAstV1Chunker;
|
||||
pub use code_rust_ast_v1::CodeRustAstV1Chunker;
|
||||
|
||||
221
crates/kebab-chunk/tests/code_go_ast_snapshot.rs
Normal file
221
crates/kebab-chunk/tests/code_go_ast_snapshot.rs
Normal file
@@ -0,0 +1,221 @@
|
||||
//! Snapshot test pinning the `Vec<Chunk>` JSON for a
|
||||
//! representative Go 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_rust_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::CodeGoAstV1Chunker;
|
||||
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("kebab_eval/metrics.go".into());
|
||||
let aid = AssetId("b".repeat(64));
|
||||
// Pin parser_version so doc_id / block_ids are reproducible.
|
||||
let pv = ParserVersion("code-go-v1".into());
|
||||
let doc_id = id_for_doc(&wp, &aid, &pv);
|
||||
|
||||
// Build a >200-line function body to force split_oversize.
|
||||
let big_body: String = {
|
||||
let header = "func BigCompute(data []int) int {\n";
|
||||
let body: String = (0..210u32)
|
||||
.map(|i| format!("\tv{i} := 0\n\tif {i} < len(data) {{\n\t\tv{i} = data[{i}]\n\t}}\n"))
|
||||
.collect();
|
||||
let footer = "\treturn len(data)\n}";
|
||||
format!("{header}{body}{footer}")
|
||||
};
|
||||
let big_line_count = big_body.lines().count() as u32;
|
||||
let big_line_end = 48 + big_line_count - 1;
|
||||
|
||||
// Representative units:
|
||||
// 0. import block (lines 1–5, ≤200)
|
||||
// 1. free fn `ComputeMRR` (lines 7–12, ≤200)
|
||||
// 2. struct `MetricsCollector` (lines 14–20, ≤200)
|
||||
// 3. struct `BaseEvaluator` (lines 22–30, ≤200)
|
||||
// 4. method `Run` (lines 32–38, ≤200)
|
||||
// 5. method `Report` (lines 40–46, ≤200)
|
||||
// 6. BigCompute (>200 lines) to force split_oversize
|
||||
let raw_units: Vec<(&str, u32, u32, String)> = vec![
|
||||
(
|
||||
"imports",
|
||||
1,
|
||||
5,
|
||||
"import (\n\t\"fmt\"\n\t\"os\"\n\t\"strings\"\n)".to_string(),
|
||||
),
|
||||
(
|
||||
"ComputeMRR",
|
||||
7,
|
||||
12,
|
||||
"func ComputeMRR(scores []float64) float64 {\n\tif len(scores) == 0 {\n\t\treturn 0.0\n\t}\n\t_ = fmt.Sprintf(\"%v\", scores)\n\treturn 1.0 / float64(len(scores))\n}".to_string(),
|
||||
),
|
||||
(
|
||||
"MetricsCollector",
|
||||
14,
|
||||
20,
|
||||
"type MetricsCollector struct {\n\tScores []float64\n\tLabels []string\n\tCounts map[string]int\n\tTotals map[string]float64\n\tTags []string\n}".to_string(),
|
||||
),
|
||||
(
|
||||
"BaseEvaluator",
|
||||
22,
|
||||
30,
|
||||
"type BaseEvaluator struct {\n\tName string\n}\n\nfunc (e *BaseEvaluator) Evaluate(data []string) error {\n\t_ = os.Stderr\n\t_ = strings.Join(data, \",\")\n\treturn nil\n}".to_string(),
|
||||
),
|
||||
(
|
||||
"MetricsCollector.Run",
|
||||
32,
|
||||
38,
|
||||
"func (m *MetricsCollector) Run(inputs []float64) {\n\tfor _, inp := range inputs {\n\t\tm.Scores = append(\n\t\t\tm.Scores,\n\t\t\tinp,\n\t\t)\n\t}\n}".to_string(),
|
||||
),
|
||||
(
|
||||
"MetricsCollector.Report",
|
||||
40,
|
||||
46,
|
||||
"func (m *MetricsCollector) Report() map[string]interface{} {\n\treturn map[string]interface{}{\n\t\t\"mean\": 0.0,\n\t\t\"count\": len(m.Scores),\n\t\t\"tags\": m.Tags,\n\t}\n}".to_string(),
|
||||
),
|
||||
("BigCompute", 48, big_line_end, big_body),
|
||||
];
|
||||
|
||||
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("go".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("go".into()),
|
||||
code: code.clone(),
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
|
||||
CanonicalDocument {
|
||||
doc_id,
|
||||
source_asset_id: aid,
|
||||
workspace_path: wp,
|
||||
title: "metrics.go".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("go".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-go-ast-v1".into()),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn code_go_ast_chunks_snapshot() {
|
||||
let doc = fixed_doc();
|
||||
let policy = fixed_policy();
|
||||
|
||||
let chunks = CodeGoAstV1Chunker.chunk(&doc, &policy).expect("chunk");
|
||||
let actual = serde_json::to_value(&chunks).unwrap();
|
||||
|
||||
let dir = fixtures_dir();
|
||||
let baseline_path = dir.join("code-sample.go.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-go-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_go_ast_chunks_are_deterministic() {
|
||||
let policy = fixed_policy();
|
||||
let baseline: Vec<String> = CodeGoAstV1Chunker
|
||||
.chunk(&fixed_doc(), &policy)
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.map(|c| c.chunk_id.0)
|
||||
.collect();
|
||||
for _ in 0..5 {
|
||||
let again: Vec<String> = CodeGoAstV1Chunker
|
||||
.chunk(&fixed_doc(), &policy)
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.map(|c| c.chunk_id.0)
|
||||
.collect();
|
||||
assert_eq!(again, baseline);
|
||||
}
|
||||
}
|
||||
233
crates/kebab-chunk/tests/fixtures/code-sample.go.chunks.snapshot.json
vendored
Normal file
233
crates/kebab-chunk/tests/fixtures/code-sample.go.chunks.snapshot.json
vendored
Normal file
@@ -0,0 +1,233 @@
|
||||
[
|
||||
{
|
||||
"block_ids": [
|
||||
"c182bf37e32c7fc1b868bd617f8eaf66"
|
||||
],
|
||||
"chunk_id": "43de518d946dc18ec040ae20d74e0cff",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 5,
|
||||
"line_start": 1,
|
||||
"symbol": "imports"
|
||||
}
|
||||
],
|
||||
"text": "import (\n\t\"fmt\"\n\t\"os\"\n\t\"strings\"\n)",
|
||||
"token_estimate": 12
|
||||
},
|
||||
{
|
||||
"block_ids": [
|
||||
"c9992cdcfdf3c2a7700a4abc4782a8a4"
|
||||
],
|
||||
"chunk_id": "af4c382a83f1e8cdea495d8b33c11abc",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 12,
|
||||
"line_start": 7,
|
||||
"symbol": "ComputeMRR"
|
||||
}
|
||||
],
|
||||
"text": "func ComputeMRR(scores []float64) float64 {\n\tif len(scores) == 0 {\n\t\treturn 0.0\n\t}\n\t_ = fmt.Sprintf(\"%v\", scores)\n\treturn 1.0 / float64(len(scores))\n}",
|
||||
"token_estimate": 50
|
||||
},
|
||||
{
|
||||
"block_ids": [
|
||||
"5f18dc3e79fe946ba05d32c3bfc00684"
|
||||
],
|
||||
"chunk_id": "4be6d8f180bc19b8651877e5264852ac",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 20,
|
||||
"line_start": 14,
|
||||
"symbol": "MetricsCollector"
|
||||
}
|
||||
],
|
||||
"text": "type MetricsCollector struct {\n\tScores []float64\n\tLabels []string\n\tCounts map[string]int\n\tTotals map[string]float64\n\tTags []string\n}",
|
||||
"token_estimate": 45
|
||||
},
|
||||
{
|
||||
"block_ids": [
|
||||
"3009cc022ca832c323393e4f9bcdb388"
|
||||
],
|
||||
"chunk_id": "3ae182f4c6d304ee7f0aaf447142f948",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 30,
|
||||
"line_start": 22,
|
||||
"symbol": "BaseEvaluator"
|
||||
}
|
||||
],
|
||||
"text": "type BaseEvaluator struct {\n\tName string\n}\n\nfunc (e *BaseEvaluator) Evaluate(data []string) error {\n\t_ = os.Stderr\n\t_ = strings.Join(data, \",\")\n\treturn nil\n}",
|
||||
"token_estimate": 53
|
||||
},
|
||||
{
|
||||
"block_ids": [
|
||||
"e0e83d1d7f9327a1902ae9a8f67c1f1c"
|
||||
],
|
||||
"chunk_id": "b962f14980e756bb8ba514e2282756cd",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 38,
|
||||
"line_start": 32,
|
||||
"symbol": "MetricsCollector.Run"
|
||||
}
|
||||
],
|
||||
"text": "func (m *MetricsCollector) Run(inputs []float64) {\n\tfor _, inp := range inputs {\n\t\tm.Scores = append(\n\t\t\tm.Scores,\n\t\t\tinp,\n\t\t)\n\t}\n}",
|
||||
"token_estimate": 44
|
||||
},
|
||||
{
|
||||
"block_ids": [
|
||||
"0e6a572bc3fe2bd6d173fe614bd1b763"
|
||||
],
|
||||
"chunk_id": "441c695e990e7f49188068433e313e87",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 46,
|
||||
"line_start": 40,
|
||||
"symbol": "MetricsCollector.Report"
|
||||
}
|
||||
],
|
||||
"text": "func (m *MetricsCollector) Report() map[string]interface{} {\n\treturn map[string]interface{}{\n\t\t\"mean\": 0.0,\n\t\t\"count\": len(m.Scores),\n\t\t\"tags\": m.Tags,\n\t}\n}",
|
||||
"token_estimate": 53
|
||||
},
|
||||
{
|
||||
"block_ids": [
|
||||
"5d269745b2e5dbdcbef0c09ba54b0bd6"
|
||||
],
|
||||
"chunk_id": "7a942d871c588ec69426290561f05179",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 247,
|
||||
"line_start": 48,
|
||||
"symbol": "BigCompute [part 1/5]"
|
||||
}
|
||||
],
|
||||
"text": "func BigCompute(data []int) int {\n\tv0 := 0\n\tif 0 < len(data) {\n\t\tv0 = data[0]\n\t}\n\tv1 := 0\n\tif 1 < len(data) {\n\t\tv1 = data[1]\n\t}\n\tv2 := 0\n\tif 2 < len(data) {\n\t\tv2 = data[2]\n\t}\n\tv3 := 0\n\tif 3 < len(data) {\n\t\tv3 = data[3]\n\t}\n\tv4 := 0\n\tif 4 < len(data) {\n\t\tv4 = data[4]\n\t}\n\tv5 := 0\n\tif 5 < len(data) {\n\t\tv5 = data[5]\n\t}\n\tv6 := 0\n\tif 6 < len(data) {\n\t\tv6 = data[6]\n\t}\n\tv7 := 0\n\tif 7 < len(data) {\n\t\tv7 = data[7]\n\t}\n\tv8 := 0\n\tif 8 < len(data) {\n\t\tv8 = data[8]\n\t}\n\tv9 := 0\n\tif 9 < len(data) {\n\t\tv9 = data[9]\n\t}\n\tv10 := 0\n\tif 10 < len(data) {\n\t\tv10 = data[10]\n\t}\n\tv11 := 0\n\tif 11 < len(data) {\n\t\tv11 = data[11]\n\t}\n\tv12 := 0\n\tif 12 < len(data) {\n\t\tv12 = data[12]\n\t}\n\tv13 := 0\n\tif 13 < len(data) {\n\t\tv13 = data[13]\n\t}\n\tv14 := 0\n\tif 14 < len(data) {\n\t\tv14 = data[14]\n\t}\n\tv15 := 0\n\tif 15 < len(data) {\n\t\tv15 = data[15]\n\t}\n\tv16 := 0\n\tif 16 < len(data) {\n\t\tv16 = data[16]\n\t}\n\tv17 := 0\n\tif 17 < len(data) {\n\t\tv17 = data[17]\n\t}\n\tv18 := 0\n\tif 18 < len(data) {\n\t\tv18 = data[18]\n\t}\n\tv19 := 0\n\tif 19 < len(data) {\n\t\tv19 = data[19]\n\t}\n\tv20 := 0\n\tif 20 < len(data) {\n\t\tv20 = data[20]\n\t}\n\tv21 := 0\n\tif 21 < len(data) {\n\t\tv21 = data[21]\n\t}\n\tv22 := 0\n\tif 22 < len(data) {\n\t\tv22 = data[22]\n\t}\n\tv23 := 0\n\tif 23 < len(data) {\n\t\tv23 = data[23]\n\t}\n\tv24 := 0\n\tif 24 < len(data) {\n\t\tv24 = data[24]\n\t}\n\tv25 := 0\n\tif 25 < len(data) {\n\t\tv25 = data[25]\n\t}\n\tv26 := 0\n\tif 26 < len(data) {\n\t\tv26 = data[26]\n\t}\n\tv27 := 0\n\tif 27 < len(data) {\n\t\tv27 = data[27]\n\t}\n\tv28 := 0\n\tif 28 < len(data) {\n\t\tv28 = data[28]\n\t}\n\tv29 := 0\n\tif 29 < len(data) {\n\t\tv29 = data[29]\n\t}\n\tv30 := 0\n\tif 30 < len(data) {\n\t\tv30 = data[30]\n\t}\n\tv31 := 0\n\tif 31 < len(data) {\n\t\tv31 = data[31]\n\t}\n\tv32 := 0\n\tif 32 < len(data) {\n\t\tv32 = data[32]\n\t}\n\tv33 := 0\n\tif 33 < len(data) {\n\t\tv33 = data[33]\n\t}\n\tv34 := 0\n\tif 34 < len(data) {\n\t\tv34 = data[34]\n\t}\n\tv35 := 0\n\tif 35 < len(data) {\n\t\tv35 = data[35]\n\t}\n\tv36 := 0\n\tif 36 < len(data) {\n\t\tv36 = data[36]\n\t}\n\tv37 := 0\n\tif 37 < len(data) {\n\t\tv37 = data[37]\n\t}\n\tv38 := 0\n\tif 38 < len(data) {\n\t\tv38 = data[38]\n\t}\n\tv39 := 0\n\tif 39 < len(data) {\n\t\tv39 = data[39]\n\t}\n\tv40 := 0\n\tif 40 < len(data) {\n\t\tv40 = data[40]\n\t}\n\tv41 := 0\n\tif 41 < len(data) {\n\t\tv41 = data[41]\n\t}\n\tv42 := 0\n\tif 42 < len(data) {\n\t\tv42 = data[42]\n\t}\n\tv43 := 0\n\tif 43 < len(data) {\n\t\tv43 = data[43]\n\t}\n\tv44 := 0\n\tif 44 < len(data) {\n\t\tv44 = data[44]\n\t}\n\tv45 := 0\n\tif 45 < len(data) {\n\t\tv45 = data[45]\n\t}\n\tv46 := 0\n\tif 46 < len(data) {\n\t\tv46 = data[46]\n\t}\n\tv47 := 0\n\tif 47 < len(data) {\n\t\tv47 = data[47]\n\t}\n\tv48 := 0\n\tif 48 < len(data) {\n\t\tv48 = data[48]\n\t}\n\tv49 := 0\n\tif 49 < len(data) {\n\t\tv49 = data[49]",
|
||||
"token_estimate": 847
|
||||
},
|
||||
{
|
||||
"block_ids": [
|
||||
"5d269745b2e5dbdcbef0c09ba54b0bd6"
|
||||
],
|
||||
"chunk_id": "3f44ba43c9415652e2705bb667776e76",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 447,
|
||||
"line_start": 248,
|
||||
"symbol": "BigCompute [part 2/5]"
|
||||
}
|
||||
],
|
||||
"text": "\t}\n\tv50 := 0\n\tif 50 < len(data) {\n\t\tv50 = data[50]\n\t}\n\tv51 := 0\n\tif 51 < len(data) {\n\t\tv51 = data[51]\n\t}\n\tv52 := 0\n\tif 52 < len(data) {\n\t\tv52 = data[52]\n\t}\n\tv53 := 0\n\tif 53 < len(data) {\n\t\tv53 = data[53]\n\t}\n\tv54 := 0\n\tif 54 < len(data) {\n\t\tv54 = data[54]\n\t}\n\tv55 := 0\n\tif 55 < len(data) {\n\t\tv55 = data[55]\n\t}\n\tv56 := 0\n\tif 56 < len(data) {\n\t\tv56 = data[56]\n\t}\n\tv57 := 0\n\tif 57 < len(data) {\n\t\tv57 = data[57]\n\t}\n\tv58 := 0\n\tif 58 < len(data) {\n\t\tv58 = data[58]\n\t}\n\tv59 := 0\n\tif 59 < len(data) {\n\t\tv59 = data[59]\n\t}\n\tv60 := 0\n\tif 60 < len(data) {\n\t\tv60 = data[60]\n\t}\n\tv61 := 0\n\tif 61 < len(data) {\n\t\tv61 = data[61]\n\t}\n\tv62 := 0\n\tif 62 < len(data) {\n\t\tv62 = data[62]\n\t}\n\tv63 := 0\n\tif 63 < len(data) {\n\t\tv63 = data[63]\n\t}\n\tv64 := 0\n\tif 64 < len(data) {\n\t\tv64 = data[64]\n\t}\n\tv65 := 0\n\tif 65 < len(data) {\n\t\tv65 = data[65]\n\t}\n\tv66 := 0\n\tif 66 < len(data) {\n\t\tv66 = data[66]\n\t}\n\tv67 := 0\n\tif 67 < len(data) {\n\t\tv67 = data[67]\n\t}\n\tv68 := 0\n\tif 68 < len(data) {\n\t\tv68 = data[68]\n\t}\n\tv69 := 0\n\tif 69 < len(data) {\n\t\tv69 = data[69]\n\t}\n\tv70 := 0\n\tif 70 < len(data) {\n\t\tv70 = data[70]\n\t}\n\tv71 := 0\n\tif 71 < len(data) {\n\t\tv71 = data[71]\n\t}\n\tv72 := 0\n\tif 72 < len(data) {\n\t\tv72 = data[72]\n\t}\n\tv73 := 0\n\tif 73 < len(data) {\n\t\tv73 = data[73]\n\t}\n\tv74 := 0\n\tif 74 < len(data) {\n\t\tv74 = data[74]\n\t}\n\tv75 := 0\n\tif 75 < len(data) {\n\t\tv75 = data[75]\n\t}\n\tv76 := 0\n\tif 76 < len(data) {\n\t\tv76 = data[76]\n\t}\n\tv77 := 0\n\tif 77 < len(data) {\n\t\tv77 = data[77]\n\t}\n\tv78 := 0\n\tif 78 < len(data) {\n\t\tv78 = data[78]\n\t}\n\tv79 := 0\n\tif 79 < len(data) {\n\t\tv79 = data[79]\n\t}\n\tv80 := 0\n\tif 80 < len(data) {\n\t\tv80 = data[80]\n\t}\n\tv81 := 0\n\tif 81 < len(data) {\n\t\tv81 = data[81]\n\t}\n\tv82 := 0\n\tif 82 < len(data) {\n\t\tv82 = data[82]\n\t}\n\tv83 := 0\n\tif 83 < len(data) {\n\t\tv83 = data[83]\n\t}\n\tv84 := 0\n\tif 84 < len(data) {\n\t\tv84 = data[84]\n\t}\n\tv85 := 0\n\tif 85 < len(data) {\n\t\tv85 = data[85]\n\t}\n\tv86 := 0\n\tif 86 < len(data) {\n\t\tv86 = data[86]\n\t}\n\tv87 := 0\n\tif 87 < len(data) {\n\t\tv87 = data[87]\n\t}\n\tv88 := 0\n\tif 88 < len(data) {\n\t\tv88 = data[88]\n\t}\n\tv89 := 0\n\tif 89 < len(data) {\n\t\tv89 = data[89]\n\t}\n\tv90 := 0\n\tif 90 < len(data) {\n\t\tv90 = data[90]\n\t}\n\tv91 := 0\n\tif 91 < len(data) {\n\t\tv91 = data[91]\n\t}\n\tv92 := 0\n\tif 92 < len(data) {\n\t\tv92 = data[92]\n\t}\n\tv93 := 0\n\tif 93 < len(data) {\n\t\tv93 = data[93]\n\t}\n\tv94 := 0\n\tif 94 < len(data) {\n\t\tv94 = data[94]\n\t}\n\tv95 := 0\n\tif 95 < len(data) {\n\t\tv95 = data[95]\n\t}\n\tv96 := 0\n\tif 96 < len(data) {\n\t\tv96 = data[96]\n\t}\n\tv97 := 0\n\tif 97 < len(data) {\n\t\tv97 = data[97]\n\t}\n\tv98 := 0\n\tif 98 < len(data) {\n\t\tv98 = data[98]\n\t}\n\tv99 := 0\n\tif 99 < len(data) {\n\t\tv99 = data[99]",
|
||||
"token_estimate": 850
|
||||
},
|
||||
{
|
||||
"block_ids": [
|
||||
"5d269745b2e5dbdcbef0c09ba54b0bd6"
|
||||
],
|
||||
"chunk_id": "e4763e10f059d97f40c2932761b56c3e",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 647,
|
||||
"line_start": 448,
|
||||
"symbol": "BigCompute [part 3/5]"
|
||||
}
|
||||
],
|
||||
"text": "\t}\n\tv100 := 0\n\tif 100 < len(data) {\n\t\tv100 = data[100]\n\t}\n\tv101 := 0\n\tif 101 < len(data) {\n\t\tv101 = data[101]\n\t}\n\tv102 := 0\n\tif 102 < len(data) {\n\t\tv102 = data[102]\n\t}\n\tv103 := 0\n\tif 103 < len(data) {\n\t\tv103 = data[103]\n\t}\n\tv104 := 0\n\tif 104 < len(data) {\n\t\tv104 = data[104]\n\t}\n\tv105 := 0\n\tif 105 < len(data) {\n\t\tv105 = data[105]\n\t}\n\tv106 := 0\n\tif 106 < len(data) {\n\t\tv106 = data[106]\n\t}\n\tv107 := 0\n\tif 107 < len(data) {\n\t\tv107 = data[107]\n\t}\n\tv108 := 0\n\tif 108 < len(data) {\n\t\tv108 = data[108]\n\t}\n\tv109 := 0\n\tif 109 < len(data) {\n\t\tv109 = data[109]\n\t}\n\tv110 := 0\n\tif 110 < len(data) {\n\t\tv110 = data[110]\n\t}\n\tv111 := 0\n\tif 111 < len(data) {\n\t\tv111 = data[111]\n\t}\n\tv112 := 0\n\tif 112 < len(data) {\n\t\tv112 = data[112]\n\t}\n\tv113 := 0\n\tif 113 < len(data) {\n\t\tv113 = data[113]\n\t}\n\tv114 := 0\n\tif 114 < len(data) {\n\t\tv114 = data[114]\n\t}\n\tv115 := 0\n\tif 115 < len(data) {\n\t\tv115 = data[115]\n\t}\n\tv116 := 0\n\tif 116 < len(data) {\n\t\tv116 = data[116]\n\t}\n\tv117 := 0\n\tif 117 < len(data) {\n\t\tv117 = data[117]\n\t}\n\tv118 := 0\n\tif 118 < len(data) {\n\t\tv118 = data[118]\n\t}\n\tv119 := 0\n\tif 119 < len(data) {\n\t\tv119 = data[119]\n\t}\n\tv120 := 0\n\tif 120 < len(data) {\n\t\tv120 = data[120]\n\t}\n\tv121 := 0\n\tif 121 < len(data) {\n\t\tv121 = data[121]\n\t}\n\tv122 := 0\n\tif 122 < len(data) {\n\t\tv122 = data[122]\n\t}\n\tv123 := 0\n\tif 123 < len(data) {\n\t\tv123 = data[123]\n\t}\n\tv124 := 0\n\tif 124 < len(data) {\n\t\tv124 = data[124]\n\t}\n\tv125 := 0\n\tif 125 < len(data) {\n\t\tv125 = data[125]\n\t}\n\tv126 := 0\n\tif 126 < len(data) {\n\t\tv126 = data[126]\n\t}\n\tv127 := 0\n\tif 127 < len(data) {\n\t\tv127 = data[127]\n\t}\n\tv128 := 0\n\tif 128 < len(data) {\n\t\tv128 = data[128]\n\t}\n\tv129 := 0\n\tif 129 < len(data) {\n\t\tv129 = data[129]\n\t}\n\tv130 := 0\n\tif 130 < len(data) {\n\t\tv130 = data[130]\n\t}\n\tv131 := 0\n\tif 131 < len(data) {\n\t\tv131 = data[131]\n\t}\n\tv132 := 0\n\tif 132 < len(data) {\n\t\tv132 = data[132]\n\t}\n\tv133 := 0\n\tif 133 < len(data) {\n\t\tv133 = data[133]\n\t}\n\tv134 := 0\n\tif 134 < len(data) {\n\t\tv134 = data[134]\n\t}\n\tv135 := 0\n\tif 135 < len(data) {\n\t\tv135 = data[135]\n\t}\n\tv136 := 0\n\tif 136 < len(data) {\n\t\tv136 = data[136]\n\t}\n\tv137 := 0\n\tif 137 < len(data) {\n\t\tv137 = data[137]\n\t}\n\tv138 := 0\n\tif 138 < len(data) {\n\t\tv138 = data[138]\n\t}\n\tv139 := 0\n\tif 139 < len(data) {\n\t\tv139 = data[139]\n\t}\n\tv140 := 0\n\tif 140 < len(data) {\n\t\tv140 = data[140]\n\t}\n\tv141 := 0\n\tif 141 < len(data) {\n\t\tv141 = data[141]\n\t}\n\tv142 := 0\n\tif 142 < len(data) {\n\t\tv142 = data[142]\n\t}\n\tv143 := 0\n\tif 143 < len(data) {\n\t\tv143 = data[143]\n\t}\n\tv144 := 0\n\tif 144 < len(data) {\n\t\tv144 = data[144]\n\t}\n\tv145 := 0\n\tif 145 < len(data) {\n\t\tv145 = data[145]\n\t}\n\tv146 := 0\n\tif 146 < len(data) {\n\t\tv146 = data[146]\n\t}\n\tv147 := 0\n\tif 147 < len(data) {\n\t\tv147 = data[147]\n\t}\n\tv148 := 0\n\tif 148 < len(data) {\n\t\tv148 = data[148]\n\t}\n\tv149 := 0\n\tif 149 < len(data) {\n\t\tv149 = data[149]",
|
||||
"token_estimate": 917
|
||||
},
|
||||
{
|
||||
"block_ids": [
|
||||
"5d269745b2e5dbdcbef0c09ba54b0bd6"
|
||||
],
|
||||
"chunk_id": "24176c911d0bacf9a29fa7f8251f5036",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 847,
|
||||
"line_start": 648,
|
||||
"symbol": "BigCompute [part 4/5]"
|
||||
}
|
||||
],
|
||||
"text": "\t}\n\tv150 := 0\n\tif 150 < len(data) {\n\t\tv150 = data[150]\n\t}\n\tv151 := 0\n\tif 151 < len(data) {\n\t\tv151 = data[151]\n\t}\n\tv152 := 0\n\tif 152 < len(data) {\n\t\tv152 = data[152]\n\t}\n\tv153 := 0\n\tif 153 < len(data) {\n\t\tv153 = data[153]\n\t}\n\tv154 := 0\n\tif 154 < len(data) {\n\t\tv154 = data[154]\n\t}\n\tv155 := 0\n\tif 155 < len(data) {\n\t\tv155 = data[155]\n\t}\n\tv156 := 0\n\tif 156 < len(data) {\n\t\tv156 = data[156]\n\t}\n\tv157 := 0\n\tif 157 < len(data) {\n\t\tv157 = data[157]\n\t}\n\tv158 := 0\n\tif 158 < len(data) {\n\t\tv158 = data[158]\n\t}\n\tv159 := 0\n\tif 159 < len(data) {\n\t\tv159 = data[159]\n\t}\n\tv160 := 0\n\tif 160 < len(data) {\n\t\tv160 = data[160]\n\t}\n\tv161 := 0\n\tif 161 < len(data) {\n\t\tv161 = data[161]\n\t}\n\tv162 := 0\n\tif 162 < len(data) {\n\t\tv162 = data[162]\n\t}\n\tv163 := 0\n\tif 163 < len(data) {\n\t\tv163 = data[163]\n\t}\n\tv164 := 0\n\tif 164 < len(data) {\n\t\tv164 = data[164]\n\t}\n\tv165 := 0\n\tif 165 < len(data) {\n\t\tv165 = data[165]\n\t}\n\tv166 := 0\n\tif 166 < len(data) {\n\t\tv166 = data[166]\n\t}\n\tv167 := 0\n\tif 167 < len(data) {\n\t\tv167 = data[167]\n\t}\n\tv168 := 0\n\tif 168 < len(data) {\n\t\tv168 = data[168]\n\t}\n\tv169 := 0\n\tif 169 < len(data) {\n\t\tv169 = data[169]\n\t}\n\tv170 := 0\n\tif 170 < len(data) {\n\t\tv170 = data[170]\n\t}\n\tv171 := 0\n\tif 171 < len(data) {\n\t\tv171 = data[171]\n\t}\n\tv172 := 0\n\tif 172 < len(data) {\n\t\tv172 = data[172]\n\t}\n\tv173 := 0\n\tif 173 < len(data) {\n\t\tv173 = data[173]\n\t}\n\tv174 := 0\n\tif 174 < len(data) {\n\t\tv174 = data[174]\n\t}\n\tv175 := 0\n\tif 175 < len(data) {\n\t\tv175 = data[175]\n\t}\n\tv176 := 0\n\tif 176 < len(data) {\n\t\tv176 = data[176]\n\t}\n\tv177 := 0\n\tif 177 < len(data) {\n\t\tv177 = data[177]\n\t}\n\tv178 := 0\n\tif 178 < len(data) {\n\t\tv178 = data[178]\n\t}\n\tv179 := 0\n\tif 179 < len(data) {\n\t\tv179 = data[179]\n\t}\n\tv180 := 0\n\tif 180 < len(data) {\n\t\tv180 = data[180]\n\t}\n\tv181 := 0\n\tif 181 < len(data) {\n\t\tv181 = data[181]\n\t}\n\tv182 := 0\n\tif 182 < len(data) {\n\t\tv182 = data[182]\n\t}\n\tv183 := 0\n\tif 183 < len(data) {\n\t\tv183 = data[183]\n\t}\n\tv184 := 0\n\tif 184 < len(data) {\n\t\tv184 = data[184]\n\t}\n\tv185 := 0\n\tif 185 < len(data) {\n\t\tv185 = data[185]\n\t}\n\tv186 := 0\n\tif 186 < len(data) {\n\t\tv186 = data[186]\n\t}\n\tv187 := 0\n\tif 187 < len(data) {\n\t\tv187 = data[187]\n\t}\n\tv188 := 0\n\tif 188 < len(data) {\n\t\tv188 = data[188]\n\t}\n\tv189 := 0\n\tif 189 < len(data) {\n\t\tv189 = data[189]\n\t}\n\tv190 := 0\n\tif 190 < len(data) {\n\t\tv190 = data[190]\n\t}\n\tv191 := 0\n\tif 191 < len(data) {\n\t\tv191 = data[191]\n\t}\n\tv192 := 0\n\tif 192 < len(data) {\n\t\tv192 = data[192]\n\t}\n\tv193 := 0\n\tif 193 < len(data) {\n\t\tv193 = data[193]\n\t}\n\tv194 := 0\n\tif 194 < len(data) {\n\t\tv194 = data[194]\n\t}\n\tv195 := 0\n\tif 195 < len(data) {\n\t\tv195 = data[195]\n\t}\n\tv196 := 0\n\tif 196 < len(data) {\n\t\tv196 = data[196]\n\t}\n\tv197 := 0\n\tif 197 < len(data) {\n\t\tv197 = data[197]\n\t}\n\tv198 := 0\n\tif 198 < len(data) {\n\t\tv198 = data[198]\n\t}\n\tv199 := 0\n\tif 199 < len(data) {\n\t\tv199 = data[199]",
|
||||
"token_estimate": 917
|
||||
},
|
||||
{
|
||||
"block_ids": [
|
||||
"5d269745b2e5dbdcbef0c09ba54b0bd6"
|
||||
],
|
||||
"chunk_id": "438127626378632c03780d10603de32c",
|
||||
"chunker_version": "code-go-ast-v1",
|
||||
"doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
|
||||
"heading_path": [],
|
||||
"policy_hash": "6cfe77abe2b0e5c3",
|
||||
"source_spans": [
|
||||
{
|
||||
"kind": "code",
|
||||
"lang": "go",
|
||||
"line_end": 890,
|
||||
"line_start": 848,
|
||||
"symbol": "BigCompute [part 5/5]"
|
||||
}
|
||||
],
|
||||
"text": "\t}\n\tv200 := 0\n\tif 200 < len(data) {\n\t\tv200 = data[200]\n\t}\n\tv201 := 0\n\tif 201 < len(data) {\n\t\tv201 = data[201]\n\t}\n\tv202 := 0\n\tif 202 < len(data) {\n\t\tv202 = data[202]\n\t}\n\tv203 := 0\n\tif 203 < len(data) {\n\t\tv203 = data[203]\n\t}\n\tv204 := 0\n\tif 204 < len(data) {\n\t\tv204 = data[204]\n\t}\n\tv205 := 0\n\tif 205 < len(data) {\n\t\tv205 = data[205]\n\t}\n\tv206 := 0\n\tif 206 < len(data) {\n\t\tv206 = data[206]\n\t}\n\tv207 := 0\n\tif 207 < len(data) {\n\t\tv207 = data[207]\n\t}\n\tv208 := 0\n\tif 208 < len(data) {\n\t\tv208 = data[208]\n\t}\n\tv209 := 0\n\tif 209 < len(data) {\n\t\tv209 = data[209]\n\t}\n\treturn len(data)\n}",
|
||||
"token_estimate": 191
|
||||
}
|
||||
]
|
||||
@@ -8,7 +8,7 @@ use serde_json::Value;
|
||||
use crate::asset::{RawAsset, WorkspacePath};
|
||||
use crate::chunk::Chunk;
|
||||
use crate::document::{Block, CanonicalDocument};
|
||||
use crate::ids::{ChunkId, DocumentId};
|
||||
use crate::ids::{AssetId, ChunkId, DocumentId};
|
||||
use crate::jobs::{JobFilter, JobId, JobKind, JobRow, JobStatus};
|
||||
use crate::media::MediaType;
|
||||
use crate::search::{DocFilter, DocSummary, SearchFilters, SearchHit, SearchQuery};
|
||||
@@ -161,10 +161,23 @@ pub trait DocumentStore {
|
||||
fn get_document(&self, id: &DocumentId) -> anyhow::Result<Option<CanonicalDocument>>;
|
||||
fn get_chunk(&self, id: &ChunkId) -> anyhow::Result<Option<Chunk>>;
|
||||
fn list_documents(&self, filter: &DocFilter) -> anyhow::Result<Vec<DocSummary>>;
|
||||
/// Look up an asset row by its `asset_id` (PRIMARY KEY = blake3
|
||||
/// content hash). Twin-file safe: asset_id is PK so there is
|
||||
/// exactly one row per unique content hash, regardless of how many
|
||||
/// `documents` rows share it. Use this instead of
|
||||
/// `get_asset_by_workspace_path` when you already have a
|
||||
/// `CanonicalDocument` (which carries `source_asset_id`).
|
||||
fn get_asset(&self, id: &AssetId) -> anyhow::Result<Option<RawAsset>>;
|
||||
|
||||
/// p9-fb-23: look up an asset row by its workspace path. Used by
|
||||
/// the incremental-ingest skip path to compare the freshly
|
||||
/// computed blake3 checksum against what's already in SQLite. The
|
||||
/// schema enforces a unique workspace_path per asset.
|
||||
///
|
||||
/// NOTE: for twin files (identical content at different paths),
|
||||
/// `assets.workspace_path` is "last-registered path" — it
|
||||
/// flip-flops on every ingest. Prefer `get_asset` (by asset_id)
|
||||
/// when you have a `CanonicalDocument.source_asset_id`.
|
||||
fn get_asset_by_workspace_path(
|
||||
&self,
|
||||
path: &WorkspacePath,
|
||||
|
||||
@@ -19,6 +19,7 @@ tree-sitter-rust = { workspace = true }
|
||||
tree-sitter-python = { workspace = true }
|
||||
tree-sitter-typescript = { workspace = true }
|
||||
tree-sitter-javascript = { workspace = true }
|
||||
tree-sitter-go = { workspace = true }
|
||||
|
||||
[dev-dependencies]
|
||||
tempfile = { workspace = true }
|
||||
|
||||
451
crates/kebab-parse-code/src/go.rs
Normal file
451
crates/kebab-parse-code/src/go.rs
Normal file
@@ -0,0 +1,451 @@
|
||||
//! `kebab-parse-code::go` — tree-sitter Go AST extractor (P10-1C-Go Task D).
|
||||
//!
|
||||
//! Implements [`kebab_core::Extractor`] for [`MediaType::Code("go")`].
|
||||
//! Walks the tree-sitter parse tree and emits one [`Block::Code`] per
|
||||
//! top-level AST semantic unit (free fn, method, each type spec) carrying
|
||||
//! [`SourceSpan::Code`] with the unit's self-reference symbol path
|
||||
//! (design §3.4 Go row). Glue declarations (`import` / `const` / `var`)
|
||||
//! collapse into one grouped `<top-level>` (or `<module>`) unit.
|
||||
//!
|
||||
//! Unlike the Python/TS/JS extractors which path-derive their module
|
||||
//! prefix from the workspace file path, Go's package identity comes from
|
||||
//! the source itself (the leading `package` clause) — `extract_package`
|
||||
//! reads it from the AST. If the `package_clause` is missing (invalid Go
|
||||
//! in practice) the prefix falls back to `"<unknown>"`.
|
||||
//!
|
||||
//! Doc comments immediately preceding an item are folded into that
|
||||
//! item's line range via `unit_start` (1B pattern). Go has no separate
|
||||
//! attribute/decorator AST nodes.
|
||||
//!
|
||||
//! Per design §3.4 / §9.1 / §9 versioning.
|
||||
|
||||
use anyhow::Result;
|
||||
use kebab_core::{
|
||||
Block, CanonicalDocument, CodeBlock, CommonBlock, Extractor, Lang, MediaType, Metadata,
|
||||
ParserVersion, Provenance, ProvenanceEvent, ProvenanceKind, SourceSpan, SourceType, TrustLevel,
|
||||
id_for_block, id_for_doc,
|
||||
};
|
||||
use serde_json::Map;
|
||||
use time::OffsetDateTime;
|
||||
|
||||
use crate::scaffold::{filename_from_workspace_path, join_symbol, strip_extension};
|
||||
|
||||
pub const PARSER_VERSION: &str = "code-go-v1";
|
||||
|
||||
/// Go AST extractor. Per-unit blocks via tree-sitter-go 0.25
|
||||
/// (`LANGUAGE: LanguageFn`) parsed by tree-sitter 0.26.
|
||||
pub struct GoAstExtractor;
|
||||
|
||||
impl GoAstExtractor {
|
||||
pub fn new() -> Self {
|
||||
Self
|
||||
}
|
||||
}
|
||||
|
||||
impl Default for GoAstExtractor {
|
||||
fn default() -> Self {
|
||||
Self::new()
|
||||
}
|
||||
}
|
||||
|
||||
impl Extractor for GoAstExtractor {
|
||||
fn supports(&self, m: &MediaType) -> bool {
|
||||
matches!(m, MediaType::Code(l) if l == "go")
|
||||
}
|
||||
|
||||
fn parser_version(&self) -> ParserVersion {
|
||||
ParserVersion(PARSER_VERSION.to_string())
|
||||
}
|
||||
|
||||
fn extract(
|
||||
&self,
|
||||
ctx: &kebab_core::ExtractContext<'_>,
|
||||
bytes: &[u8],
|
||||
) -> Result<CanonicalDocument> {
|
||||
let asset = ctx.asset;
|
||||
if !self.supports(&asset.media_type) {
|
||||
anyhow::bail!(
|
||||
"kebab-parse-code: unsupported media_type for GoAstExtractor: {:?}",
|
||||
asset.media_type
|
||||
);
|
||||
}
|
||||
|
||||
let parser_version = self.parser_version();
|
||||
let doc_id = id_for_doc(&asset.workspace_path, &asset.asset_id, &parser_version);
|
||||
|
||||
let source = String::from_utf8(bytes.to_vec())
|
||||
.map_err(|e| anyhow::anyhow!("kebab-parse-code: Go source is not valid UTF-8: {e}"))?;
|
||||
|
||||
let blocks = build_blocks(&source, &doc_id)?;
|
||||
let unit_count = blocks.len() as u32;
|
||||
|
||||
let now = OffsetDateTime::now_utc();
|
||||
let mut events: Vec<ProvenanceEvent> = Vec::with_capacity(2);
|
||||
events.push(ProvenanceEvent {
|
||||
at: asset.discovered_at,
|
||||
agent: "kb-source-fs".to_string(),
|
||||
kind: ProvenanceKind::Discovered,
|
||||
note: None,
|
||||
});
|
||||
events.push(ProvenanceEvent {
|
||||
at: now,
|
||||
agent: "kb-parse-code".to_string(),
|
||||
kind: ProvenanceKind::Parsed,
|
||||
note: Some(format!(
|
||||
"parser_version={}; unit_count={}",
|
||||
parser_version.0, unit_count
|
||||
)),
|
||||
});
|
||||
|
||||
let title = {
|
||||
let fname = filename_from_workspace_path(&asset.workspace_path.0);
|
||||
strip_extension(&fname)
|
||||
};
|
||||
|
||||
// Resolve the file's absolute path for repo detection. If the
|
||||
// source URI carries a relative path, anchor it at the workspace
|
||||
// root so the `.git/` walk-up starts from the right place.
|
||||
let abs_path = match &asset.source_uri {
|
||||
kebab_core::SourceUri::File(p) => {
|
||||
if p.is_absolute() {
|
||||
p.clone()
|
||||
} else {
|
||||
ctx.workspace_root.join(p)
|
||||
}
|
||||
}
|
||||
kebab_core::SourceUri::Kb(_) => ctx.workspace_root.to_path_buf(),
|
||||
};
|
||||
let (repo, git_branch, git_commit) = match crate::repo::detect_repo(&abs_path) {
|
||||
Some(r) => (Some(r.name), r.branch, r.commit),
|
||||
None => (None, None, None),
|
||||
};
|
||||
|
||||
let metadata = Metadata {
|
||||
aliases: Vec::new(),
|
||||
tags: Vec::new(),
|
||||
created_at: asset.discovered_at,
|
||||
updated_at: asset.discovered_at,
|
||||
source_type: SourceType::Note,
|
||||
trust_level: TrustLevel::Primary,
|
||||
user_id_alias: None,
|
||||
user: Map::new(),
|
||||
repo,
|
||||
git_branch,
|
||||
git_commit,
|
||||
code_lang: Some("go".to_string()),
|
||||
};
|
||||
|
||||
tracing::debug!(
|
||||
target: "kebab-parse-code",
|
||||
"extracted Go doc_id={} workspace_path={} units={}",
|
||||
doc_id.0,
|
||||
asset.workspace_path.0,
|
||||
unit_count
|
||||
);
|
||||
|
||||
Ok(CanonicalDocument {
|
||||
doc_id,
|
||||
source_asset_id: asset.asset_id.clone(),
|
||||
workspace_path: asset.workspace_path.clone(),
|
||||
title,
|
||||
lang: Lang("und".to_string()),
|
||||
blocks,
|
||||
metadata,
|
||||
provenance: Provenance { events },
|
||||
parser_version,
|
||||
schema_version: 1,
|
||||
doc_version: 1,
|
||||
last_chunker_version: None,
|
||||
last_embedding_version: None,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
/// p10-1C-Go: extract `package` declaration text from a tree-sitter-go
|
||||
/// `source_file`. Returns `None` if no `package_clause` (invalid Go in
|
||||
/// practice but defense-in-depth). Per design §3.4 Go row.
|
||||
fn extract_package(root: tree_sitter::Node, src: &str) -> Option<String> {
|
||||
let mut cur = root.walk();
|
||||
for child in root.named_children(&mut cur) {
|
||||
if child.kind() == "package_clause" {
|
||||
let mut c2 = child.walk();
|
||||
for sub in child.named_children(&mut c2) {
|
||||
if sub.kind() == "package_identifier" {
|
||||
return Some(src[sub.start_byte()..sub.end_byte()].to_string());
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
fn build_blocks(
|
||||
source: &str,
|
||||
doc_id: &kebab_core::DocumentId,
|
||||
) -> anyhow::Result<Vec<kebab_core::Block>> {
|
||||
let mut parser = tree_sitter::Parser::new();
|
||||
parser
|
||||
.set_language(&tree_sitter_go::LANGUAGE.into())
|
||||
.map_err(|e| anyhow::anyhow!("set tree-sitter-go language: {e}"))?;
|
||||
let tree = parser
|
||||
.parse(source.as_bytes(), None)
|
||||
.ok_or_else(|| anyhow::anyhow!("tree-sitter failed to parse Go source"))?;
|
||||
let lines: Vec<&str> = source.split('\n').collect();
|
||||
|
||||
let root = tree.root_node();
|
||||
let mod_prefix = extract_package(root, source).unwrap_or_else(|| "<unknown>".to_string());
|
||||
|
||||
// units: (symbol, line_start, line_end, is_real_semantic_unit).
|
||||
// Glue groups are pushed with a sentinel symbol + is_real=false so a
|
||||
// post-pass can decide `<module>` vs `<top-level>` (1B post-pass
|
||||
// mirror).
|
||||
let mut units: Vec<(String, u32, u32, bool)> = Vec::new();
|
||||
// (is_import 0/1, s, e). `is_import` flags `import_declaration` —
|
||||
// used by the glue flush to pick `<module>` vs `<top-level>`
|
||||
// provisional label.
|
||||
let mut glue: Vec<(usize, u32, u32)> = Vec::new();
|
||||
|
||||
fn node_name_text<'a>(n: &tree_sitter::Node, src: &'a str) -> Option<&'a str> {
|
||||
n.child_by_field_name("name")
|
||||
.map(|c| &src[c.start_byte()..c.end_byte()])
|
||||
}
|
||||
/// Walk preceding `comment` siblings to extend the unit's line range
|
||||
/// upward, folding leading doc / line comments into the unit. Go has
|
||||
/// no decorator/attribute nodes — doc comments are simply preceding
|
||||
/// `comment` siblings (the 1B pattern).
|
||||
fn unit_start(n: &tree_sitter::Node) -> u32 {
|
||||
let mut start = n.start_position().row as u32 + 1;
|
||||
let mut prev = n.prev_sibling();
|
||||
while let Some(p) = prev {
|
||||
if p.kind() == "comment" {
|
||||
start = p.start_position().row as u32 + 1;
|
||||
prev = p.prev_sibling();
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
start
|
||||
}
|
||||
|
||||
/// Extract the receiver type text for a `method_declaration`. The
|
||||
/// returned slice INCLUDES the leading `*` for pointer receivers
|
||||
/// (`(*Foo).Bar`) per design §3.4 Go row example. Returns `None` if
|
||||
/// the receiver is malformed (defense in depth).
|
||||
fn receiver_type_text<'a>(method_node: &tree_sitter::Node, src: &'a str) -> Option<&'a str> {
|
||||
let recv = method_node.child_by_field_name("receiver")?;
|
||||
let mut cw = recv.walk();
|
||||
for p in recv.named_children(&mut cw) {
|
||||
if p.kind() == "parameter_declaration" {
|
||||
if let Some(ty) = p.child_by_field_name("type") {
|
||||
return Some(&src[ty.start_byte()..ty.end_byte()]);
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
let mut cur = root.walk();
|
||||
for child in root.named_children(&mut cur) {
|
||||
let s = unit_start(&child);
|
||||
let e = child.end_position().row as u32 + 1;
|
||||
match child.kind() {
|
||||
"function_declaration" => {
|
||||
if let Some(name) = node_name_text(&child, source) {
|
||||
glue.retain(|(_, gs, _)| *gs < s);
|
||||
flush_glue(&mut glue, &mut units, &mod_prefix);
|
||||
let sym = join_symbol(&mod_prefix, &[], name);
|
||||
units.push((sym, s, e, true));
|
||||
}
|
||||
}
|
||||
"method_declaration" => {
|
||||
if let Some(name_node) = child.child_by_field_name("name") {
|
||||
glue.retain(|(_, gs, _)| *gs < s);
|
||||
flush_glue(&mut glue, &mut units, &mod_prefix);
|
||||
let owner = receiver_type_text(&child, source).unwrap_or("<unknown>");
|
||||
let method_name = &source[name_node.start_byte()..name_node.end_byte()];
|
||||
let sym = format!("{mod_prefix}.({owner}).{method_name}");
|
||||
units.push((sym, s, e, true));
|
||||
}
|
||||
}
|
||||
"type_declaration" => {
|
||||
// One unit per inner `type_spec`. Each type_spec gets
|
||||
// the type_declaration's whole upward-folded `s` range
|
||||
// start so doc comments are attached to the first spec;
|
||||
// subsequent specs use their own start. Match 1B
|
||||
// pattern: keep the outer `s` only when there's a single
|
||||
// spec; otherwise use the spec's own start.
|
||||
let mut tcur = child.walk();
|
||||
let specs: Vec<tree_sitter::Node> = child
|
||||
.named_children(&mut tcur)
|
||||
.filter(|c| c.kind() == "type_spec")
|
||||
.collect();
|
||||
let single = specs.len() == 1;
|
||||
for spec in specs {
|
||||
let name_node = match spec.child_by_field_name("name") {
|
||||
Some(n) => n,
|
||||
None => continue,
|
||||
};
|
||||
let spec_s = if single {
|
||||
s
|
||||
} else {
|
||||
spec.start_position().row as u32 + 1
|
||||
};
|
||||
let spec_e = spec.end_position().row as u32 + 1;
|
||||
glue.retain(|(_, gs, _)| *gs < spec_s);
|
||||
flush_glue(&mut glue, &mut units, &mod_prefix);
|
||||
let name = &source[name_node.start_byte()..name_node.end_byte()];
|
||||
let sym = join_symbol(&mod_prefix, &[], name);
|
||||
units.push((sym, spec_s, spec_e, true));
|
||||
}
|
||||
}
|
||||
"import_declaration" => {
|
||||
glue.push((1, s, e));
|
||||
}
|
||||
"const_declaration" | "var_declaration" => {
|
||||
glue.push((0, s, e));
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
flush_glue(&mut glue, &mut units, &mod_prefix);
|
||||
|
||||
// `<module>` is correct only when the file produced no real unit.
|
||||
// Otherwise the import/const/var-only group becomes `<top-level>`
|
||||
// (same post-pass as 1B). Match on the suffix so the demotion stays
|
||||
// mod-prefix-agnostic.
|
||||
let has_real_unit = units.iter().any(|(_, _, _, is_real)| *is_real);
|
||||
if has_real_unit {
|
||||
for (sym, _, _, is_real) in units.iter_mut() {
|
||||
if !*is_real && sym.ends_with("<module>") {
|
||||
let pre = &sym[..sym.len() - "<module>".len()];
|
||||
*sym = format!("{pre}<top-level>");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let total_lines = lines.len() as u32;
|
||||
let mut blocks = Vec::with_capacity(units.len());
|
||||
for (ordinal, (symbol, ls, le, _is_real)) in units.into_iter().enumerate() {
|
||||
let line_start = ls.max(1);
|
||||
let line_end = le.min(total_lines.max(1));
|
||||
let span = SourceSpan::Code {
|
||||
line_start,
|
||||
line_end,
|
||||
symbol: Some(symbol),
|
||||
lang: Some("go".to_string()),
|
||||
};
|
||||
let block_id = id_for_block(doc_id, "code", &[], ordinal as u32, &span);
|
||||
let code = lines[(line_start as usize - 1)..=(line_end as usize - 1)].join("\n");
|
||||
blocks.push(Block::Code(CodeBlock {
|
||||
common: CommonBlock {
|
||||
block_id,
|
||||
heading_path: Vec::new(),
|
||||
source_span: span,
|
||||
},
|
||||
lang: Some("go".to_string()),
|
||||
code,
|
||||
}));
|
||||
}
|
||||
Ok(blocks)
|
||||
}
|
||||
|
||||
fn flush_glue(
|
||||
glue: &mut Vec<(usize, u32, u32)>,
|
||||
units: &mut Vec<(String, u32, u32, bool)>,
|
||||
mod_prefix: &str,
|
||||
) {
|
||||
if glue.is_empty() {
|
||||
return;
|
||||
}
|
||||
let s = glue.iter().map(|(_, a, _)| *a).min().unwrap();
|
||||
let e = glue.iter().map(|(_, _, b)| *b).max().unwrap();
|
||||
// Provisional label: `<module>` only if the group is exclusively
|
||||
// imports (1A's `only_mod_decls` analog). The post-pass demotes any
|
||||
// `<module>` to `<top-level>` if the file produced any real unit.
|
||||
let only_imports = glue.iter().all(|(is_import, _, _)| *is_import == 1);
|
||||
let label = if only_imports { "<module>" } else { "<top-level>" };
|
||||
units.push((join_symbol(mod_prefix, &[], label), s, e, false));
|
||||
glue.clear();
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use kebab_core::{Block, MediaType, SourceSpan};
|
||||
|
||||
fn extract_fixture() -> kebab_core::CanonicalDocument {
|
||||
let bytes = std::fs::read(concat!(
|
||||
env!("CARGO_MANIFEST_DIR"),
|
||||
"/tests/fixtures/sample.go"
|
||||
))
|
||||
.unwrap();
|
||||
// Reuse the cross-language test-support helper promoted in 1B.
|
||||
let asset = crate::rust::tests_support::fixed_code_asset("crates/x/src/sample.go", "go");
|
||||
let cfg = kebab_core::ExtractConfig::default();
|
||||
let root = std::path::PathBuf::from("/tmp");
|
||||
let ctx = kebab_core::ExtractContext {
|
||||
asset: &asset,
|
||||
workspace_root: &root,
|
||||
config: &cfg,
|
||||
};
|
||||
GoAstExtractor::new().extract(&ctx, &bytes).unwrap()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn extractor_supports_only_media_code_go() {
|
||||
let e = GoAstExtractor::new();
|
||||
assert!(e.supports(&MediaType::Code("go".into())));
|
||||
assert!(!e.supports(&MediaType::Code("rust".into())));
|
||||
assert!(!e.supports(&MediaType::Markdown));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn go_units_match_design_3_4_symbols() {
|
||||
let doc = extract_fixture();
|
||||
let mut syms: Vec<String> = doc
|
||||
.blocks
|
||||
.iter()
|
||||
.filter_map(|b| match b {
|
||||
Block::Code(c) => match &c.common.source_span {
|
||||
SourceSpan::Code { symbol, lang, .. } => {
|
||||
assert_eq!(lang.as_deref(), Some("go"));
|
||||
symbol.clone()
|
||||
}
|
||||
_ => None,
|
||||
},
|
||||
_ => None,
|
||||
})
|
||||
.collect();
|
||||
syms.sort();
|
||||
assert!(syms.iter().any(|s| s == "chunk.Free"), "got {syms:?}");
|
||||
assert!(syms.iter().any(|s| s == "chunk.init"), "got {syms:?}");
|
||||
assert!(
|
||||
syms.iter().any(|s| s == "chunk.MdHeadingV1Chunker"),
|
||||
"got {syms:?}"
|
||||
);
|
||||
assert!(
|
||||
syms.iter()
|
||||
.any(|s| s == "chunk.(*MdHeadingV1Chunker).ChunkDoc"),
|
||||
"got {syms:?}"
|
||||
);
|
||||
assert!(
|
||||
syms.iter()
|
||||
.any(|s| s == "chunk.(MdHeadingV1Chunker).Name2"),
|
||||
"got {syms:?}"
|
||||
);
|
||||
assert!(syms.iter().any(|s| s == "chunk.Stringer"), "got {syms:?}");
|
||||
// import + const grouped into one glue unit (no isolated `<module>`).
|
||||
assert!(
|
||||
syms.iter().any(|s| s == "chunk.<top-level>"),
|
||||
"got {syms:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_across_runs() {
|
||||
let a = extract_fixture();
|
||||
for _ in 0..50 {
|
||||
assert_eq!(extract_fixture().blocks, a.blocks);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -13,6 +13,7 @@
|
||||
//! `kebab-parse-*` crates per design §8: must NOT depend on store / embed
|
||||
//! / llm / rag.
|
||||
|
||||
pub mod go;
|
||||
pub mod javascript;
|
||||
pub mod lang;
|
||||
pub mod python;
|
||||
@@ -22,6 +23,7 @@ pub(crate) mod scaffold;
|
||||
pub mod skip;
|
||||
pub mod typescript;
|
||||
|
||||
pub use go::{PARSER_VERSION as GO_PARSER_VERSION, GoAstExtractor};
|
||||
pub use javascript::{PARSER_VERSION as JS_PARSER_VERSION, JavascriptAstExtractor};
|
||||
pub use lang::{code_lang_for_path, module_path_for_python, module_path_for_tsjs};
|
||||
pub use python::{PARSER_VERSION as PYTHON_PARSER_VERSION, PythonAstExtractor};
|
||||
|
||||
34
crates/kebab-parse-code/tests/fixtures/sample.go
vendored
Normal file
34
crates/kebab-parse-code/tests/fixtures/sample.go
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
// sample.go
|
||||
package chunk
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"strings"
|
||||
)
|
||||
|
||||
const Version = "v1"
|
||||
|
||||
type MdHeadingV1Chunker struct {
|
||||
Name string
|
||||
}
|
||||
|
||||
// ChunkDoc returns a stub list of strings.
|
||||
func (m *MdHeadingV1Chunker) ChunkDoc(input string) []string {
|
||||
return []string{m.Name}
|
||||
}
|
||||
|
||||
func (m MdHeadingV1Chunker) Name2() string {
|
||||
return m.Name
|
||||
}
|
||||
|
||||
type Stringer interface {
|
||||
String() string
|
||||
}
|
||||
|
||||
func Free(x int) int {
|
||||
return x + 1
|
||||
}
|
||||
|
||||
func init() {
|
||||
fmt.Println(strings.ToUpper("init"))
|
||||
}
|
||||
@@ -46,6 +46,9 @@ pub(crate) fn media_type_for(path: &Path) -> MediaType {
|
||||
"ts" | "tsx" | "mts" | "cts" => MediaType::Code("typescript".into()),
|
||||
"js" | "mjs" | "cjs" | "jsx" => MediaType::Code("javascript".into()),
|
||||
|
||||
// p10-1C-Go: Go ingest activated.
|
||||
"go" => MediaType::Code("go".into()),
|
||||
|
||||
// Empty string (no extension) and any other extension: bucket as
|
||||
// Other and let downstream extractors decide if they support it.
|
||||
_ => MediaType::Other(ext),
|
||||
@@ -119,6 +122,11 @@ mod tests {
|
||||
assert_eq!(media_type_for(Path::new("docs/page.mdx")), MediaType::Markdown);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn go_files_map_to_media_code_go() {
|
||||
assert_eq!(media_type_for(Path::new("a/b.go")), MediaType::Code("go".into()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn unknown_and_missing_extension() {
|
||||
assert_eq!(
|
||||
|
||||
@@ -264,6 +264,28 @@ impl kebab_core::DocumentStore for SqliteStore {
|
||||
}))
|
||||
}
|
||||
|
||||
fn get_asset(
|
||||
&self,
|
||||
id: &kebab_core::AssetId,
|
||||
) -> Result<Option<kebab_core::RawAsset>> {
|
||||
let conn = self.lock_conn();
|
||||
let result = conn.query_row(
|
||||
r#"SELECT
|
||||
asset_id, source_uri, workspace_path, media_type,
|
||||
byte_len, checksum, storage_kind, storage_path,
|
||||
discovered_at
|
||||
FROM assets
|
||||
WHERE asset_id = ?"#,
|
||||
rusqlite::params![id.0.as_str()],
|
||||
asset_from_row,
|
||||
);
|
||||
match result {
|
||||
Ok(asset) => Ok(Some(asset)),
|
||||
Err(rusqlite::Error::QueryReturnedNoRows) => Ok(None),
|
||||
Err(e) => Err(e.into()),
|
||||
}
|
||||
}
|
||||
|
||||
fn get_asset_by_workspace_path(
|
||||
&self,
|
||||
path: &kebab_core::WorkspacePath,
|
||||
@@ -632,7 +654,8 @@ fn rows_optional<T>(err: rusqlite::Error) -> rusqlite::Result<Option<T>> {
|
||||
|
||||
/// Reconstruct a [`kebab_core::RawAsset`] from one `assets` row.
|
||||
/// Row mapper for `RawAsset`. Column names are self-documenting; the
|
||||
/// SELECT in [`DocumentStore::get_asset_by_workspace_path`] must include
|
||||
/// SELECTs in [`DocumentStore::get_asset`] and
|
||||
/// [`DocumentStore::get_asset_by_workspace_path`] must both include
|
||||
/// all nine columns by their schema names.
|
||||
fn asset_from_row(row: &rusqlite::Row<'_>) -> rusqlite::Result<kebab_core::RawAsset> {
|
||||
use std::path::PathBuf;
|
||||
|
||||
@@ -652,6 +652,20 @@ pub fn purge_deleted_workspace_path(
|
||||
/// path (which has bytes + computed `storage_kind/path`) and the
|
||||
/// `DocumentStore::put_asset` path (which only has the `RawAsset` and
|
||||
/// reads `storage_kind/path` from `asset.stored`).
|
||||
///
|
||||
/// **`assets.workspace_path` is "last-registered path" semantics for
|
||||
/// twin files** (two source files with identical content share one
|
||||
/// `assets` row keyed on `asset_id = blake3(content)`). Each ingest
|
||||
/// of either twin overwrites `workspace_path` with whichever path was
|
||||
/// seen most recently — this is intentional and correct after PR #146
|
||||
/// made `try_skip_unchanged` document-centric (uses
|
||||
/// `get_document_by_workspace_path`, not `get_asset_by_workspace_path`)
|
||||
/// and PR #149 made `reset --orphans-only` document-centric too.
|
||||
/// Do NOT "fix" the flip-flop by adding a UNIQUE constraint on
|
||||
/// `workspace_path` in the `assets` table — twin de-dup is load-bearing.
|
||||
/// When you need media_type for a known document, use the 2-step lookup
|
||||
/// `get_document_by_workspace_path` → `doc.source_asset_id` →
|
||||
/// `get_asset(asset_id)` so the result is twin-safe.
|
||||
pub(crate) fn upsert_asset_row(
|
||||
conn: &Connection,
|
||||
asset: &kebab_core::RawAsset,
|
||||
|
||||
@@ -22,7 +22,7 @@ Cargo workspace, 함수 호출 기반 모듈러 모놀리스. UI binary (`kebab-
|
||||
| OCR | Ollama vision LM (default `gemma4:e4b`) — `OcrEngine` trait 으로 Tesseract / Apple Vision 등 future swap (HOTFIXES P6-2) |
|
||||
| Image caption | Ollama vision LM, runtime gate `image.caption.enabled` (default OFF) |
|
||||
| PDF parser | `lopdf` per-page 텍스트, `chunker_version = "pdf-page-v1"` 가 PDF 자산에 하드코딩 (HOTFIXES P7-3) |
|
||||
| code parser | `tree-sitter` + `tree-sitter-rust` / `tree-sitter-python` / `tree-sitter-typescript` / `tree-sitter-javascript` — **parser-side** (`kebab-parse-code`), chunker-side 아님 (design §6.3). chunker versions: Rust = `code-rust-ast-v1`, Python = `code-python-ast-v1`, TypeScript = `code-ts-ast-v1`, JavaScript = `code-js-ast-v1`. `ast_chunk_max_lines = 200` 상수 고정 (HOTFIXES 2026-05-19 — Chunker trait 이 per-medium config 미노출). |
|
||||
| code parser | `tree-sitter` + `tree-sitter-rust` / `tree-sitter-python` / `tree-sitter-typescript` / `tree-sitter-javascript` / `tree-sitter-go` — **parser-side** (`kebab-parse-code`), chunker-side 아님 (design §6.3). chunker versions: Rust = `code-rust-ast-v1`, Python = `code-python-ast-v1`, TypeScript = `code-ts-ast-v1`, JavaScript = `code-js-ast-v1`, Go = `code-go-ast-v1`. `ast_chunk_max_lines = 200` 상수 고정 (HOTFIXES 2026-05-19 — Chunker trait 이 per-medium config 미노출). |
|
||||
| 1B symbol path | workspace path → module path: Python = dotted prefix (`kebab_eval.metrics.compute_mrr`), TypeScript/JavaScript = slash-style prefix (`src/Foo.Foo.search`). Rust 1A-2 는 file-scope nesting 만 (workspace prefix 없음, 비일관 수용 — HOTFIXES 2026-05-20). |
|
||||
| TUI | Ratatui + crossterm — P9-1 Library 패널, P9-2/3/4 진행 예정 |
|
||||
| Desktop | Tauri 2 + `pdfjs-dist` (native PDF render backend 금지) — P9-5 |
|
||||
@@ -52,7 +52,7 @@ flowchart TB
|
||||
ppdf["kebab-parse-pdf"]
|
||||
pimg["kebab-parse-image"]
|
||||
paud["kebab-parse-audio<br/>(P8 보류)"]
|
||||
pcode["kebab-parse-code<br/>(P10-1A-2 + P10-1B)"]
|
||||
pcode["kebab-parse-code<br/>(P10-1A-2 + P10-1B + P10-1C-Go)"]
|
||||
ptypes["kebab-parse-types"]
|
||||
norm["kebab-normalize"]
|
||||
chunk["kebab-chunk"]
|
||||
@@ -127,7 +127,7 @@ flowchart TB
|
||||
|
||||
UI → store/llm/parse 직접 의존 금지. 모든 user-facing 진입은 `kebab-app` facade 만 통한다 (frozen 설계 §8). `kebab-cli` 가 `--config <path>` flag 를 honor 하려면 `kebab_app::*_with_config(cfg, …)` companion 을 통해 Config 을 명시적으로 thread 하는 패턴 — 자세한 이유는 [tasks/HOTFIXES.md](../tasks/HOTFIXES.md) 의 `--config` 항목.
|
||||
|
||||
`kebab-parse-code` 의 외부 tree-sitter grammar crate 의존: P10-1A-2 에서 `tree-sitter-rust` 추가, P10-1B 에서 `tree-sitter-python` / `tree-sitter-typescript` / `tree-sitter-javascript` 추가. 모두 `kebab-parse-code` 에만 격리 (facade 룰 — UI crate / chunker 가 직접 import 금지).
|
||||
`kebab-parse-code` 의 외부 tree-sitter grammar crate 의존: P10-1A-2 에서 `tree-sitter-rust` 추가, P10-1B 에서 `tree-sitter-python` / `tree-sitter-typescript` / `tree-sitter-javascript` 추가, P10-1C-Go 에서 `tree-sitter-go` 추가. 모두 `kebab-parse-code` 에만 격리 (facade 룰 — UI crate / chunker 가 직접 import 금지).
|
||||
|
||||
## 디렉토리 구조
|
||||
|
||||
@@ -165,7 +165,7 @@ kebab/
|
||||
│ ├── kebab-source-fs/ # 워크스페이스 walk + checksum (P1-1)
|
||||
│ ├── kebab-parse-md/ # Markdown frontmatter + blocks (P1-2/3)
|
||||
│ ├── kebab-normalize/ # ParsedBlock → CanonicalDocument (P1-4)
|
||||
│ ├── kebab-chunk/ # heading-aware + pdf-page-v1 + code-rust-ast-v1 + code-python-ast-v1 + code-ts-ast-v1 + code-js-ast-v1 chunker (P1-5, P7-2, P10-1A-2, P10-1B)
|
||||
│ ├── kebab-chunk/ # heading-aware + pdf-page-v1 + code-rust-ast-v1 + code-python-ast-v1 + code-ts-ast-v1 + code-js-ast-v1 + code-go-ast-v1 chunker (P1-5, P7-2, P10-1A-2, P10-1B, P10-1C-Go)
|
||||
│ ├── kebab-store-sqlite/ # SQLite + FTS5 (V001/V002/V003) (P1-6, P2-1, P3-3)
|
||||
│ ├── kebab-search/ # Lexical + Vector + Hybrid retriever (P2-2, P3-4)
|
||||
│ ├── kebab-embed/ kebab-embed-local/ # Embedder trait + fastembed adapter (P3-1, P3-2)
|
||||
@@ -175,7 +175,7 @@ kebab/
|
||||
│ ├── kebab-eval/ # golden query runner + metrics (P5-1, P5-2)
|
||||
│ ├── kebab-parse-image/ # ImageExtractor + Ollama OCR + caption (P6)
|
||||
│ ├── kebab-parse-pdf/ # lopdf per-page text extractor (P7-1)
|
||||
│ ├── kebab-parse-code/ # tree-sitter AST extractors: Rust (P10-1A-2), Python + TypeScript + JavaScript (P10-1B); chunker lives in kebab-chunk
|
||||
│ ├── kebab-parse-code/ # tree-sitter AST extractors: Rust (P10-1A-2), Python + TypeScript + JavaScript (P10-1B), Go (P10-1C-Go); chunker lives in kebab-chunk
|
||||
│ ├── kebab-app/ # facade (P0 시그니처 + P3-5/P6-4/P7-3 본체)
|
||||
│ ├── kebab-tui/ # Ratatui shell + Library 패널 (P9-1)
|
||||
│ ├── kebab-mcp/ # stdio MCP server — tools: schema, doctor, search, ask (P9-FB-30)
|
||||
|
||||
@@ -401,6 +401,27 @@ KB --json schema | jq '.stats.code_lang_breakdown'
|
||||
- `const foo = () => {...}` 같은 expression-level 함수는 `<top-level>` glue 로 잡힘 (declaration-level 단위만 1B 1차 범위). 자세한 내용: `tasks/HOTFIXES.md` (2026-05-20).
|
||||
- `.gitignore` honor — `node_modules/` / `__pycache__/` / `.venv/` 등 built-in 안전망 자동 skip.
|
||||
|
||||
## P10-1C-Go Go 코드 색인
|
||||
|
||||
P10-1B 와 동일한 격리 KB 설정. `.go` 파일을 워크스페이스에 두고 ingest 하면 `code-go-ast-v1` chunker 가 package 단위 AST 로 처리한다.
|
||||
|
||||
```bash
|
||||
cat > /tmp/kebab-smoke/workspace/sample_code/hello.go <<'EOF'
|
||||
package main
|
||||
|
||||
import "fmt"
|
||||
|
||||
func Hello(name string) string {
|
||||
return fmt.Sprintf("Hello, %s!", name)
|
||||
}
|
||||
EOF
|
||||
|
||||
KB ingest
|
||||
KB search --mode hybrid "Hello" --code-lang go --json | \
|
||||
jq '{hits: [.hits[] | {symbol: .citation.symbol, lang: .citation.lang}]}'
|
||||
# 기대: symbol = "main.Hello", lang = "go"
|
||||
```
|
||||
|
||||
## 검증 체크리스트
|
||||
|
||||
- `kebab doctor` 가 `--config` path 를 honor 하고 그 안의 `storage.data_dir` 를 출력 (XDG default 가 아님).
|
||||
@@ -433,6 +454,7 @@ rm -rf /tmp/kebab-smoke # 통째로 정리
|
||||
- (P7-3) 한 PDF 가 N 페이지면 `kebab ingest` 가 N 개 (또는 그 이상의, 페이지 길면 multi-chunk) 의 chunk 를 한 transaction 안에서 commit. 500 페이지 책 → 500+ chunk 한 번에 → embedding throughput 가 bottleneck. 임베딩 활성 워크스페이스에서 큰 PDF 를 처음 ingest 하면 분-단위 시간 + WAL 크기 증가 가능 — P+ 스케일 hardening task 까지 정상 동작이지만 비용은 측정 가능.
|
||||
- (P10-1A-2) `.rs` 파일을 워크스페이스에 두면 `kebab ingest` 결과에 `new` 카운터에 포함. `kebab search --mode hybrid "<함수명>" --code-lang rust --json` 가 `citation.kind = "code"`, `citation.lang = "rust"` (SearchHit top-level `code_lang` 도 동일), `citation.symbol` (함수/타입 이름), `citation.line_start` / `citation.line_end` 를 반환하면 wiring 정상. `kebab schema --json | jq .stats.code_lang_breakdown` 에 `"rust": N` 이 나오면 chunk 가 색인됨.
|
||||
- (P10-1B) `.py` / `.ts` / `.tsx` / `.js` / `.mjs` / `.cjs` / `.jsx` 파일을 워크스페이스에 두면 `kebab ingest` 결과에 `new` 카운터에 포함. `--code-lang python` / `--code-lang typescript` / `--code-lang javascript` 검색이 `citation.symbol` 에 module path prefix 를 포함한 결과를 반환하면 wiring 정상. `kebab schema --json | jq .stats.code_lang_breakdown` 에 해당 언어 카운트 등장 확인.
|
||||
- (P10-1C-Go) `.go` 파일을 워크스페이스에 두면 `kebab ingest` 가 `code-go-ast-v1` 로 처리. `--code-lang go` 검색이 `citation.symbol` 에 `<package>.<Func>` / `<package>.(*Receiver).<Method>` 형식 결과를 반환하면 wiring 정상. `kebab schema --json | jq .stats.code_lang_breakdown` 에 `"go": N` 등장 확인.
|
||||
- (P7-3 + follow-up) 동일 path 에 byte 가 다른 PDF 를 두 번째 ingest 하면 `purge_vector_orphans_for_workspace_path` 가 옛 chunk_id 를 LanceDB 에서 먼저 삭제, 이어서 `purge_orphan_at_workspace_path` 가 옛 doc / chunks / embedding_records 를 SQLite 에서 sweep. 새 byte 가 새 `doc_id` 로 색인됨. `IngestReport` 에 그 자산만 `new+=1` (다른 자산은 `updated`). 두 store 모두 정합 — 옛 본문 검색 시 옛 chunks 가 더 이상 surface 되지 않음.
|
||||
|
||||
### Embedding upgrade (fb-39b)
|
||||
|
||||
540
docs/superpowers/plans/2026-05-20-p10-1c-go-ast-chunker.md
Normal file
540
docs/superpowers/plans/2026-05-20-p10-1c-go-ast-chunker.md
Normal file
@@ -0,0 +1,540 @@
|
||||
# p10-1C-Go Implementation Plan
|
||||
|
||||
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development to implement this plan task-by-task.
|
||||
|
||||
**Goal:** Activate Go code ingest end-to-end on top of 1A-2 (Rust) + 1B (Python/TS/JS) infrastructure. Add `tree-sitter-go` grammar + `GoAstExtractor` + `code-go-ast-v1` chunker + media routing + app dispatch arm.
|
||||
|
||||
**Architecture:** Mirror 1A-2 / 1B exactly. `kebab-parse-code/src/go.rs` walks tree-sitter-go parse tree; emits one `Block::Code` per top-level AST semantic unit with `SourceSpan::Code { symbol, lang: Some("go") }`. Symbol prefix = **source-extracted package name** (from `package_clause` AST node — design §3.4 Go row). `kebab-chunk/src/code_go_ast_v1.rs` is a near-duplicate of `code-rust-ast-v1`. App dispatch's `ingest_one_code_asset` (PR #142 generalized 4-arm match) gets a 5th arm.
|
||||
|
||||
**Tech Stack:** Rust 2024 workspace, `tree-sitter` 0.26 (already in workspace), `tree-sitter-go` (NEW), 1A-2/1B infrastructure unchanged.
|
||||
|
||||
**Memory note:** Host has been OOM-killed previously. Use `cargo test -p <crate>` and `cargo check -p <crate>` only. ONE full-suite invocation reserved for Task G gate.
|
||||
|
||||
---
|
||||
|
||||
## Pre-flight
|
||||
|
||||
Branch `feat/p10-1c-go` already exists.
|
||||
|
||||
- [ ] **Disk hygiene**: `cargo clean` if previous artifacts are bloated. Skip if disk is comfortable (`df -h /`).
|
||||
|
||||
Reference files:
|
||||
- 1A-2 Rust extractor: `crates/kebab-parse-code/src/rust.rs` — closest single-language scaffold template.
|
||||
- 1B Python extractor (closest analog for "class-nesting recursion" — Go doesn't have classes but has package as the single prefix): `crates/kebab-parse-code/src/python.rs`.
|
||||
- 1A-2 chunker scaffold: `crates/kebab-chunk/src/code_rust_ast_v1.rs`.
|
||||
- 1B dispatch generalization: `crates/kebab-app/src/lib.rs::ingest_one_code_asset` (~L1645, 4-arm match).
|
||||
- 1A-2 source-fs routing: `crates/kebab-source-fs/src/media.rs` `"rs" =>` arm.
|
||||
|
||||
---
|
||||
|
||||
## Task A: Workspace dep `tree-sitter-go`
|
||||
|
||||
**Files:**
|
||||
- Modify: `Cargo.toml` (workspace `[workspace.dependencies]`, after `tree-sitter-javascript` line)
|
||||
- Modify: `crates/kebab-parse-code/Cargo.toml`
|
||||
|
||||
- [ ] **Step 1**: `cargo add tree-sitter-go -p kebab-parse-code` to resolve version.
|
||||
|
||||
- [ ] **Step 2**: Lift the resolved version into `[workspace.dependencies]` after `tree-sitter-javascript`:
|
||||
|
||||
```toml
|
||||
# Go grammar for code ingest (kebab-parse-code, p10-1C).
|
||||
tree-sitter-go = "<resolved>"
|
||||
```
|
||||
|
||||
Switch the crate's entry to `{ workspace = true }` matching existing tree-sitter-* style.
|
||||
|
||||
- [ ] **Step 3**: `cargo build -p kebab-parse-code` → clean. Unused dep warning is fine.
|
||||
|
||||
- [ ] **Step 4**: Commit:
|
||||
|
||||
```bash
|
||||
git add Cargo.toml Cargo.lock crates/kebab-parse-code/Cargo.toml
|
||||
git commit -m "build(p10-1c-go): add tree-sitter-go workspace dep
|
||||
|
||||
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task B: source-fs media routing `.go` → `MediaType::Code("go")`
|
||||
|
||||
**Files:**
|
||||
- Modify: `crates/kebab-source-fs/src/media.rs` (add arm after the existing JS arm at ~L44)
|
||||
- Test: same file's test module
|
||||
|
||||
- [ ] **Step 1 (failing test)** — add to existing tests near `py_ts_js_files_map_to_media_code`:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn go_files_map_to_media_code_go() {
|
||||
assert_eq!(media_type_for(Path::new("a/b.go")), MediaType::Code("go".into()));
|
||||
}
|
||||
```
|
||||
|
||||
- [ ] **Step 2**: Run → FAIL.
|
||||
|
||||
- [ ] **Step 3**: Add the arm before the catch-all `_ => MediaType::Other(ext)`:
|
||||
|
||||
```rust
|
||||
// p10-1C-Go: Go ingest activated.
|
||||
"go" => MediaType::Code("go".into()),
|
||||
```
|
||||
|
||||
- [ ] **Step 4**: Run → PASS. `cargo test -p kebab-source-fs` → no regression.
|
||||
|
||||
- [ ] **Step 5**: clippy clean, commit:
|
||||
|
||||
```bash
|
||||
git add crates/kebab-source-fs/
|
||||
git commit -m "feat(p10-1c-go): route .go to MediaType::Code(go)
|
||||
|
||||
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task C: App dispatch allowlist + bail arm for "go"
|
||||
|
||||
**Files:**
|
||||
- Modify: `crates/kebab-app/src/lib.rs` (dispatch match guard + 4 internal match arms in `ingest_one_code_asset`)
|
||||
|
||||
- [ ] **Step 1**: Find the `MediaType::Code(lang) if matches!(lang.as_str(), "rust" | "python" | "typescript" | "javascript")` arm (~L953). Add `"go"` to the allowlist:
|
||||
|
||||
```rust
|
||||
MediaType::Code(lang)
|
||||
if matches!(lang.as_str(), "rust" | "python" | "typescript" | "javascript" | "go") =>
|
||||
{
|
||||
```
|
||||
|
||||
- [ ] **Step 2**: In `ingest_one_code_asset`'s 4 `match code_lang` blocks (parser_version, chunker_version, extract, chunk), add a "go" arm that `bail!()`s for now (extractor + chunker land in Task D/E). Mirror the Python/TS/JS bail-then-activate pattern:
|
||||
|
||||
```rust
|
||||
let parser_version = match code_lang {
|
||||
// ... existing arms ...
|
||||
"go" => anyhow::bail!("go ingest not yet wired (p10-1c-go Task F)"),
|
||||
other => anyhow::bail!("unsupported code_lang: {other}"),
|
||||
};
|
||||
// similar for chunker_version / extract / chunk matches
|
||||
```
|
||||
|
||||
- [ ] **Step 3**: `cargo test -p kebab-app --lib` → existing 52 lib tests stay green. `cargo test -p kebab-app --test code_ingest_smoke` → 6 stay green (Rust path unaffected).
|
||||
|
||||
- [ ] **Step 4**: clippy clean, commit:
|
||||
|
||||
```bash
|
||||
git add crates/kebab-app/
|
||||
git commit -m "refactor(p10-1c-go): add go to ingest dispatch allowlist (bail until Task F)
|
||||
|
||||
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task D: `GoAstExtractor` (`kebab-parse-code/src/go.rs`)
|
||||
|
||||
**Files:**
|
||||
- Create: `crates/kebab-parse-code/src/go.rs`
|
||||
- Modify: `crates/kebab-parse-code/src/lib.rs` (`pub mod go;` + re-exports `GO_PARSER_VERSION`, `GoAstExtractor`)
|
||||
- Create: `crates/kebab-parse-code/tests/fixtures/sample.go`
|
||||
|
||||
Scaffold mirrors `crates/kebab-parse-code/src/rust.rs` line-for-line for the `CanonicalDocument` skeleton (Extractor trait impl, `id_for_doc`, ProvenanceEvent, final `CanonicalDocument` literal). The novel parts:
|
||||
|
||||
### Constants
|
||||
|
||||
```rust
|
||||
pub const PARSER_VERSION: &str = "code-go-v1";
|
||||
|
||||
pub struct GoAstExtractor;
|
||||
// new() + Default
|
||||
// supports: matches!(m, MediaType::Code(l) if l == "go")
|
||||
// agent = "kb-parse-code"
|
||||
// metadata.code_lang = Some("go")
|
||||
// SourceType::Note (no SourceType::Code variant)
|
||||
// repo/git_branch/git_commit via detect_repo
|
||||
```
|
||||
|
||||
### Package extraction
|
||||
|
||||
Unlike 1B's path-based `module_path_for_python` / `_for_tsjs`, the Go package prefix comes from the **source code's `package` declaration** (design §3.4). tree-sitter-go's grammar:
|
||||
|
||||
- Root: `source_file`
|
||||
- First named child is typically `package_clause` → contains `package_identifier` child whose text is the package name.
|
||||
|
||||
Helper (local to `go.rs`):
|
||||
|
||||
```rust
|
||||
/// Returns the package name from a tree-sitter-go `source_file`, or
|
||||
/// `None` if the file has no `package_clause` (invalid Go in practice,
|
||||
/// but be defensive).
|
||||
fn extract_package(root: tree_sitter::Node, src: &str) -> Option<String> {
|
||||
let mut cur = root.walk();
|
||||
for child in root.named_children(&mut cur) {
|
||||
if child.kind() == "package_clause" {
|
||||
// `package_clause` has a `package_identifier` named child.
|
||||
let mut c2 = child.walk();
|
||||
for sub in child.named_children(&mut c2) {
|
||||
if sub.kind() == "package_identifier" {
|
||||
return Some(src[sub.start_byte()..sub.end_byte()].to_string());
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
```
|
||||
|
||||
### Semantic-unit rules
|
||||
|
||||
| node kind | unit | symbol |
|
||||
|-----------|------|--------|
|
||||
| `function_declaration` (name field) | 1 | `<pkg>.<fn_name>` |
|
||||
| `method_declaration` | 1 | `<pkg>.(<TypeText>).<MethodName>` where `<TypeText>` includes a leading `*` if the receiver is `pointer_type`. Examples: `chunk.(*MdHeadingV1Chunker).ChunkDoc`, `chunk.(Foo).Bar`. |
|
||||
| `type_declaration` (struct / interface / type alias) | 1 per inner `type_spec` | `<pkg>.<TypeName>` |
|
||||
| `const_declaration`, `var_declaration`, `import_declaration` (single or block) | glue | `<pkg>.<top-level>` (or `<pkg>.<package>` if file has ZERO real units AND glue is import-only — same `<module>` post-pass pattern as 1B Python, renamed to `<package>` to avoid colliding with Go's `package` keyword? — actually use `<module>` per design §3.4 — see "module / namespace 만 있고 symbol 없는 경우" line) |
|
||||
|
||||
`unit_start` walks `comment` siblings (same as 1B). Go doesn't have separate attribute / decorator nodes.
|
||||
|
||||
Method receiver pointer detection:
|
||||
|
||||
```rust
|
||||
// In the method_declaration arm:
|
||||
let receiver = child.child_by_field_name("receiver"); // parameter_list
|
||||
let receiver_type_text = receiver.and_then(|r| {
|
||||
let mut cw = r.walk();
|
||||
for p in r.named_children(&mut cw) {
|
||||
if p.kind() == "parameter_declaration" {
|
||||
// type field is either type_identifier (value) or pointer_type (ptr)
|
||||
if let Some(ty) = p.child_by_field_name("type") {
|
||||
let s = &src[ty.start_byte()..ty.end_byte()];
|
||||
return Some(s.to_string()); // includes leading "*" if pointer_type
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
});
|
||||
// Format: "(*Foo)" or "(Foo)" — wrap in parens, preserve leading "*" if any.
|
||||
let owner = receiver_type_text
|
||||
.map(|t| format!("({t})"))
|
||||
.unwrap_or_else(|| "()".to_string());
|
||||
let method_name = name_text(&child, src);
|
||||
// symbol = format!("{pkg}.{owner}.{method_name}")
|
||||
```
|
||||
|
||||
Read tree-sitter-go's grammar.json or node-types.json (in the registry source) if any field name above differs in the resolved crate version.
|
||||
|
||||
### Fixture `tests/fixtures/sample.go`:
|
||||
|
||||
```go
|
||||
// sample.go
|
||||
package chunk
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"strings"
|
||||
)
|
||||
|
||||
const Version = "v1"
|
||||
|
||||
type MdHeadingV1Chunker struct {
|
||||
Name string
|
||||
}
|
||||
|
||||
// ChunkDoc returns a stub list of strings.
|
||||
func (m *MdHeadingV1Chunker) ChunkDoc(input string) []string {
|
||||
return []string{m.Name}
|
||||
}
|
||||
|
||||
func (m MdHeadingV1Chunker) Name2() string {
|
||||
return m.Name
|
||||
}
|
||||
|
||||
type Stringer interface {
|
||||
String() string
|
||||
}
|
||||
|
||||
func Free(x int) int {
|
||||
return x + 1
|
||||
}
|
||||
|
||||
func init() {
|
||||
fmt.Println(strings.ToUpper("init"))
|
||||
}
|
||||
```
|
||||
|
||||
### Test module
|
||||
|
||||
Mirror Python's test shape (use `crate::rust::tests_support::fixed_code_asset` from 1B):
|
||||
|
||||
```rust
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use kebab_core::{Block, MediaType, SourceSpan};
|
||||
|
||||
fn extract_fixture() -> kebab_core::CanonicalDocument {
|
||||
let bytes = std::fs::read(
|
||||
concat!(env!("CARGO_MANIFEST_DIR"), "/tests/fixtures/sample.go"),
|
||||
).unwrap();
|
||||
let asset = crate::rust::tests_support::fixed_code_asset(
|
||||
"crates/x/src/sample.go", "go",
|
||||
);
|
||||
let cfg = kebab_core::ExtractConfig::default();
|
||||
let root = std::path::PathBuf::from("/tmp");
|
||||
let ctx = kebab_core::ExtractContext { asset: &asset, workspace_root: &root, config: &cfg };
|
||||
GoAstExtractor::new().extract(&ctx, &bytes).unwrap()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn extractor_supports_only_media_code_go() {
|
||||
let e = GoAstExtractor::new();
|
||||
assert!(e.supports(&MediaType::Code("go".into())));
|
||||
assert!(!e.supports(&MediaType::Code("rust".into())));
|
||||
assert!(!e.supports(&MediaType::Markdown));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn go_units_match_design_3_4_symbols() {
|
||||
let doc = extract_fixture();
|
||||
let mut syms: Vec<String> = doc.blocks.iter().filter_map(|b| match b {
|
||||
Block::Code(c) => match &c.common.source_span {
|
||||
SourceSpan::Code { symbol, lang, .. } => {
|
||||
assert_eq!(lang.as_deref(), Some("go"));
|
||||
symbol.clone()
|
||||
}
|
||||
_ => None,
|
||||
},
|
||||
_ => None,
|
||||
}).collect();
|
||||
syms.sort();
|
||||
assert!(syms.iter().any(|s| s == "chunk.Free"), "got {syms:?}");
|
||||
assert!(syms.iter().any(|s| s == "chunk.init"));
|
||||
assert!(syms.iter().any(|s| s == "chunk.MdHeadingV1Chunker"));
|
||||
assert!(syms.iter().any(|s| s == "chunk.(*MdHeadingV1Chunker).ChunkDoc"));
|
||||
assert!(syms.iter().any(|s| s == "chunk.(MdHeadingV1Chunker).Name2"));
|
||||
assert!(syms.iter().any(|s| s == "chunk.Stringer"));
|
||||
assert!(syms.iter().any(|s| s == "chunk.<top-level>")); // import + const grouped
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_across_runs() {
|
||||
let a = extract_fixture();
|
||||
for _ in 0..50 { assert_eq!(extract_fixture().blocks, a.blocks); }
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Step list
|
||||
|
||||
- [ ] Step 1: create fixture + test module.
|
||||
- [ ] Step 2: run → FAIL (`GoAstExtractor` undefined).
|
||||
- [ ] Step 3: implement `go.rs`. Scaffold mirrors `python.rs` (Extractor impl + extract scaffold + `build_blocks` returning blocks). `build_blocks` does: extract_package → walk root's named children → branch per node kind per the table above → emit `Block::Code` with `SourceSpan::Code { symbol, lang: Some("go") }`. Use the same `flush_glue` / glue grouping / `<top-level>` vs `<module>` post-pass as Python (rename to `<package>` if user prefers, but spec §3.4 says `<module>` so keep that name for cross-language consistency).
|
||||
- [ ] Step 4: wire into `lib.rs`:
|
||||
|
||||
```rust
|
||||
pub mod go;
|
||||
pub use go::{PARSER_VERSION as GO_PARSER_VERSION, GoAstExtractor};
|
||||
```
|
||||
|
||||
- [ ] Step 5: `cargo test -p kebab-parse-code` → all pass (Rust/Python/TS/JS + new Go). `cargo clippy -p kebab-parse-code --all-targets -- -D warnings` clean.
|
||||
- [ ] Step 6: commit:
|
||||
|
||||
```bash
|
||||
git add crates/kebab-parse-code/
|
||||
git commit -m "feat(p10-1c-go): tree-sitter-go AST extractor (GoAstExtractor)
|
||||
|
||||
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task E: `code-go-ast-v1` chunker
|
||||
|
||||
**Files:**
|
||||
- Create: `crates/kebab-chunk/src/code_go_ast_v1.rs`
|
||||
- Modify: `crates/kebab-chunk/src/lib.rs`
|
||||
|
||||
Identical pattern to PR #142 Task I (TS) / Task L (JS) — near-duplicate of `code_rust_ast_v1.rs` with substitutions:
|
||||
- `const VERSION_LABEL: &str = "code-go-ast-v1";`
|
||||
- struct name `CodeGoAstV1Chunker`
|
||||
- error message says `"CodeGoAstV1Chunker only handles..."`
|
||||
- module doc-comment prose `Rust` → `Go`, `code-rust-ast-v1` → `code-go-ast-v1`
|
||||
|
||||
`split_oversize` / `make_chunk` / `AST_CHUNK_MAX_LINES = 200` / `BYTES_PER_TOKEN = 3` / `POLICY_HASH_HEX_LEN = 16` IDENTICAL (language-agnostic).
|
||||
|
||||
Test module: copy from `code_ts_ast_v1.rs` and substitute names. KEEP cross-chunker `policy_hash_matches_md_heading_v1`.
|
||||
|
||||
Wire into `crates/kebab-chunk/src/lib.rs`:
|
||||
|
||||
```rust
|
||||
mod code_go_ast_v1;
|
||||
pub use code_go_ast_v1::CodeGoAstV1Chunker;
|
||||
```
|
||||
|
||||
(Alphabetical placement.)
|
||||
|
||||
Verify + commit:
|
||||
- `cargo test -p kebab-chunk code_go_ast` PASS (~6 tests)
|
||||
- `cargo test -p kebab-chunk` full per-crate green
|
||||
- `cargo clippy -p kebab-chunk --all-targets -- -D warnings` clean
|
||||
|
||||
```bash
|
||||
git add crates/kebab-chunk/
|
||||
git commit -m "feat(p10-1c-go): code-go-ast-v1 chunker (1:1 + oversize split)
|
||||
|
||||
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task F: Activate Go in app dispatch
|
||||
|
||||
**Files:**
|
||||
- Modify: `crates/kebab-app/src/lib.rs` (replace 4 "go" bail! arms with real calls)
|
||||
- Modify: `crates/kebab-app/tests/code_ingest_smoke.rs` (add Go integration test)
|
||||
|
||||
Replace the 4 `"go" => anyhow::bail!(...)` arms in `ingest_one_code_asset` (added in Task C) with real:
|
||||
|
||||
```rust
|
||||
"go" => ParserVersion(kebab_parse_code::GO_PARSER_VERSION.to_string()),
|
||||
// ...
|
||||
"go" => CodeGoAstV1Chunker.chunker_version(),
|
||||
// ...
|
||||
"go" => kebab_parse_code::GoAstExtractor::new()
|
||||
.extract(&ctx, &bytes)
|
||||
.context("kb-parse-code::GoAstExtractor::extract (code:go)")?,
|
||||
// ...
|
||||
"go" => CodeGoAstV1Chunker
|
||||
.chunk(&canonical, chunk_policy)
|
||||
.context("kb-chunk::CodeGoAstV1Chunker::chunk (code:go)")?,
|
||||
```
|
||||
|
||||
Add imports at top of lib.rs:
|
||||
- `kebab_chunk::CodeGoAstV1Chunker`
|
||||
- `kebab_parse_code::GoAstExtractor`
|
||||
|
||||
Integration test (mirror PR #142's `python_file_ingests_and_searches_as_code_citation`):
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn go_file_ingests_and_searches_as_code_citation() {
|
||||
// ... TempDir + Config harness same as Python/TS test ...
|
||||
let pkg_dir = env.workspace_root.join("chunk");
|
||||
std::fs::create_dir_all(&pkg_dir).unwrap();
|
||||
std::fs::write(
|
||||
pkg_dir.join("ast.go"),
|
||||
"package chunk\n\nfunc ParseDoc(input string) string {\n return input\n}\n",
|
||||
).unwrap();
|
||||
|
||||
let report = kebab_app::ingest_with_config(/* ... */).unwrap();
|
||||
assert!(report.new >= 1);
|
||||
let go_item = report.items.as_ref().unwrap().iter()
|
||||
.find(|i| i.doc_path.0.ends_with("ast.go")).expect("ast.go item");
|
||||
assert_eq!(go_item.parser_version.as_ref().unwrap().0, "code-go-v1");
|
||||
assert_eq!(go_item.chunker_version.as_ref().unwrap().0, "code-go-ast-v1");
|
||||
|
||||
let hits = kebab_app::search_with_config(/* search "ParseDoc" */).unwrap();
|
||||
let h = hits.iter().find(|h| matches!(h.citation, kebab_core::Citation::Code { .. }))
|
||||
.expect("Citation::Code hit");
|
||||
match &h.citation {
|
||||
kebab_core::Citation::Code { lang, symbol, line_start, .. } => {
|
||||
assert_eq!(lang.as_deref(), Some("go"));
|
||||
assert_eq!(symbol.as_deref(), Some("chunk.ParseDoc"));
|
||||
assert!(*line_start >= 1);
|
||||
}
|
||||
_ => unreachable!(),
|
||||
}
|
||||
assert_eq!(h.code_lang.as_deref(), Some("go"));
|
||||
}
|
||||
```
|
||||
|
||||
Verify:
|
||||
- `cargo test -p kebab-app --test code_ingest_smoke` → 7/7 (6 existing + 1 new go)
|
||||
- `cargo test -p kebab-app --lib` → 52/52 (no regression)
|
||||
- clippy clean
|
||||
|
||||
```bash
|
||||
git add crates/kebab-app/
|
||||
git commit -m "feat(p10-1c-go): activate Go in ingest_one_code_asset dispatch
|
||||
|
||||
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task G: Snapshot + full-suite gate + manual SMOKE
|
||||
|
||||
**Files:**
|
||||
- Create: `crates/kebab-chunk/tests/code_go_ast_snapshot.rs` + fixture + baseline (mirror `code_python_ast_snapshot.rs` from PR #142)
|
||||
|
||||
- [ ] **Step 1**: Add snapshot integration test. In-memory `CanonicalDocument` (no kebab-parse-code dep — boundary §6.3). Generate baseline: `UPDATE_SNAPSHOTS=1 cargo test -p kebab-chunk code_go_ast_snapshot` → re-run without env → PASS.
|
||||
|
||||
- [ ] **Step 2**: Full-suite gate (the ONE invocation allowed this PR):
|
||||
|
||||
```bash
|
||||
cargo clippy --workspace --all-targets -- -D warnings
|
||||
cargo test --workspace --no-fail-fast -j 1
|
||||
```
|
||||
|
||||
Both must be CLEAN/GREEN.
|
||||
|
||||
- [ ] **Step 3**: Manual SMOKE (optional but recommended — mirror PR #142 SMOKE):
|
||||
|
||||
```bash
|
||||
cargo build --release # OR debug if RAM-tight
|
||||
rm -rf /tmp/kebab-go-smoke && mkdir -p /tmp/kebab-go-smoke/ws/chunk
|
||||
echo 'package chunk
|
||||
|
||||
func ParseDoc(input string) string { return input }
|
||||
' > /tmp/kebab-go-smoke/ws/chunk/ast.go
|
||||
# adapt isolated config from docs/SMOKE.md
|
||||
./target/release/kebab --config /tmp/kebab-go-smoke/config.toml ingest --json | jq '.items[].parser_version' | sort -u
|
||||
./target/release/kebab --config /tmp/kebab-go-smoke/config.toml search "ParseDoc" --code-lang go --json | jq '.hits[0]'
|
||||
```
|
||||
|
||||
Expected: `code-go-v1` in parser_versions; Citation::Code with symbol `chunk.ParseDoc`.
|
||||
|
||||
- [ ] **Step 4**: Commit snapshot only (full-suite + SMOKE are gates, not commit content):
|
||||
|
||||
```bash
|
||||
git add crates/kebab-chunk/tests/
|
||||
git commit -m "test(p10-1c-go): code-go-ast-v1 chunker snapshot + full-suite gate
|
||||
|
||||
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task H: Docs + version bump
|
||||
|
||||
- README: 지원 형식 row — add Go (`.go`, `code-go-ast-v1`).
|
||||
- HANDOFF: P10 phase row note 1C-Go merged (Go active). Java/Kotlin remain pending.
|
||||
- ARCHITECTURE: directory tree note for kebab-parse-code includes `go.rs` (Java/Kotlin coming in next PR). Decisions table — no new row (1C-Go follows the 1A-2/1B convention).
|
||||
- SMOKE: extend the P10 section with a 1-line note for Go (or compact Go example).
|
||||
- tasks/INDEX + tasks/p10/INDEX: flip the row for 1C-Go to 🟡 (PR open) → ✅ on merge. The 1C row in p10/INDEX may need a split — `p10-1C-Go ⏳ → 🟡` and `p10-1C-JavaKotlin ⏳ unchanged` (since user split into 2 PRs).
|
||||
- frozen design §10.1: add a one-liner — "p10-1C-Go 활성화 (Go)" (Java/Kotlin will get its own line in the next PR).
|
||||
- `Cargo.toml`: workspace version `0.11.1 → 0.12.0` (minor — dogfooding surface 확장, 새 chunker + extractor 활성화).
|
||||
|
||||
```bash
|
||||
git add -A
|
||||
git commit -m "docs(p10-1c-go): README/HANDOFF/ARCHITECTURE/SMOKE/INDEX + chore: bump version 0.11.1 → 0.12.0
|
||||
|
||||
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Finalize: PR + review loop + release
|
||||
|
||||
Per workflow memory (gitea-pr + review loop, no single-shot):
|
||||
|
||||
- [ ] `gitea-pr` → PR title `feat(p10-1C-Go): tree-sitter-go AST extractor + chunker — Go 코드 색인 활성화`
|
||||
- [ ] Review loop until APPROVE → merge → main pull → branch cleanup → `cargo clean` → `gitea-release v0.12.0`.
|
||||
|
||||
---
|
||||
|
||||
## Self-Review (filled by plan author)
|
||||
|
||||
- **Spec coverage**: design §1C Go (extractor + chunker + activation) → Tasks D/E/F; §3.3 (`code-go-ast-v1`) → Task E; §3.4 symbol path → Task D (extract_package + method receiver pointer detection); §6.1 (`kebab-parse-code/src/go.rs`) → Task D; §6.2 (`kebab-chunk/src/code_go_ast_v1.rs`) → Task E; §6.3 dep graph (`tree-sitter-go` parser-side) → Task A; §9.1 Tier-1 + oversize fallback → Task E (1A-2 split_oversize reused identically).
|
||||
- **No placeholders**: novel logic (`extract_package`, method receiver pointer detection, fixture, test assertions, dispatch arm additions) given concretely. Mechanical mirrors (chunker, integration test, snapshot test) pinned to exact existing files with substitutions.
|
||||
- **Type consistency**: `GoAstExtractor` / `GO_PARSER_VERSION = "code-go-v1"` / `CodeGoAstV1Chunker` / `VERSION_LABEL = "code-go-ast-v1"` used consistently across Tasks A-H. `MediaType::Code("go")` in routing + dispatch. `Citation::Code` with `lang: Some("go")` in integration test.
|
||||
@@ -1545,6 +1545,8 @@ transitional 형태) 의 source of truth.
|
||||
|
||||
**p10-1B 활성화 (Python / TypeScript / JavaScript) (2026-05-20)**: Python (`code-python-ast-v1`, `.py`), TypeScript (`code-ts-ast-v1`, `.ts`/`.tsx`), JavaScript (`code-js-ast-v1`, `.js`/`.mjs`/`.cjs`/`.jsx`) AST chunker 활성화. symbol path 는 workspace 경로 → module path prefix: Python = dotted (예: `kebab_eval.metrics.compute_mrr`), TypeScript/JavaScript = slash-style (예: `src/Foo.Foo.search`). Rust 1A-2 의 file-scope-only symbol 과 비일관 수용 (HOTFIXES 2026-05-20). expression-level 함수 (`const foo = () => {}`) 는 glue 처리 (HOTFIXES 2026-05-20).
|
||||
|
||||
**p10-1C-Go 활성화 (Go) (2026-05-20)**: Go (`code-go-ast-v1`, `.go`) AST chunker 활성화. symbol = `<package>.<Func>` / `<package>.(*Receiver).<Method>` 형식. Java / Kotlin 은 후속 PR (p10-1C-JavaKotlin) 에서 별도 활성화.
|
||||
|
||||
### 10.2 MCP server transport (fb-30)
|
||||
|
||||
`kebab mcp` 가 stdio JSON-RPC server. Rust SDK = `rmcp 1.6`. Tool surface
|
||||
|
||||
@@ -142,7 +142,8 @@ P0~P5 는 직렬. P6~P9 는 P5 이후 병렬 가능.
|
||||
- [p10-1A-1 code ingest framework](p10/p10-1a-1-code-ingest-framework.md) — ✅ 머지
|
||||
- [p10-1A-2 Rust AST chunker](p10/p10-1a-2-rust-ast-chunker.md) — ✅ 머지
|
||||
- [p10-1B Python + TS/JS AST chunkers](p10/p10-1b-py-ts-js-ast-chunkers.md) — 🟡 PR 오픈 (코드 완성, 머지 대기)
|
||||
- p10-1C Go + Java + Kotlin AST chunkers — ⏳
|
||||
- p10-1C-Go Go AST chunker — 🟡 PR 오픈 (v0.12.0, `code-go-ast-v1`)
|
||||
- p10-1C-JavaKotlin Java + Kotlin AST chunkers — ⏳
|
||||
- p10-1D C + C++ AST chunkers — ⏳
|
||||
- p10-2 Tier 2 resource-aware — ⏳
|
||||
- p10-3 Tier 3 paragraph + line-window fallback — ⏳
|
||||
|
||||
@@ -5,7 +5,8 @@
|
||||
| 1A-1 | code ingest framework (wire schema, parse-code crate skeleton, filter flags, skip policy, config 절) | ✅ 머지 |
|
||||
| 1A-2 | Rust AST chunker | ✅ 머지 |
|
||||
| 1B | Python + TS/JS AST chunkers | 🟡 PR 오픈 (코드 완성, 머지 대기) |
|
||||
| 1C | Go + Java + Kotlin AST chunkers | ⏳ |
|
||||
| 1C-Go | Go AST chunker (`code-go-ast-v1`) | 🟡 PR 오픈 (v0.12.0) |
|
||||
| 1C-JavaKotlin | Java + Kotlin AST chunkers | ⏳ |
|
||||
| 1D | C + C++ AST chunkers | ⏳ |
|
||||
| 2 | Tier 2 resource-aware (k8s / Dockerfile / manifest) | ⏳ |
|
||||
| 3 | Tier 3 paragraph + line-window fallback | ⏳ |
|
||||
|
||||
54
tasks/p10/p10-1c-go-ast-chunker.md
Normal file
54
tasks/p10/p10-1c-go-ast-chunker.md
Normal file
@@ -0,0 +1,54 @@
|
||||
# p10-1C-Go — Go AST chunker
|
||||
|
||||
**Status:** 🟡 진행 중
|
||||
**Contract sections:** §3.3 (chunker_version `code-go-ast-v1`), §3.4 (symbol path — Go `package.Func` / `package.(*Receiver).Method`), §3.5 (code_lang `go`, ext `.go`), §6.1 (`kebab-parse-code/src/go.rs`), §6.2 (`kebab-chunk/src/code_go_ast_v1.rs`), §9.1 (Tier 1 AST per-language + oversize fallback).
|
||||
**Design:** [2026-05-15-kebab-code-ingest-design.md](../../docs/superpowers/specs/2026-05-15-kebab-code-ingest-design.md) §1C (Go 부분 — Java + Kotlin 은 후속 PR).
|
||||
**Plan:** [2026-05-20-p10-1c-go-ast-chunker.md](../../docs/superpowers/plans/2026-05-20-p10-1c-go-ast-chunker.md).
|
||||
|
||||
## Goal
|
||||
|
||||
1A-2 / 1B 인프라 위에 Go AST chunker 활성화. 사용자 결정으로 1C 의 3 언어 (Go + Java + Kotlin) 를 2 PR 로 분할 — Go 가 method receiver / package convention 면에서 Java/Kotlin (JVM family) 과 다르므로 별 PR. 본 PR 머지 시점부터 Go 프로젝트 dogfooding 가능.
|
||||
|
||||
## 동결된 설계 결정 (이 task 로 확정)
|
||||
|
||||
- **Symbol path 의 package prefix = 소스 코드의 `package` 선언에서 추출** (design §3.4 그대로). 1B 의 workspace-path 변환과 다름 — Go 는 언어 자체에 `package` declaration 이 있어 그게 canonical source. tree-sitter-go 의 `source_file` root 의 첫 named child `package_clause` 에서 추출. 빈 경우 (이론상 invalid Go, 실용엔 거의 없음) `<unknown>` 또는 fallback `<package>` (1A `<module>` 패턴과 유사).
|
||||
- **Method receiver 표현** (design 예시 그대로): `package.(*Receiver).Method` (포인터 receiver), `package.(Receiver).Method` (value receiver). tree-sitter-go 의 `method_declaration` 의 `receiver` field 에서 type + pointer 여부 추출. 예: `func (m *MdHeadingV1Chunker) ChunkDoc(...)` → symbol `chunk.(*MdHeadingV1Chunker).ChunkDoc`.
|
||||
- **Top-level unit 종류**:
|
||||
- `function_declaration` → 1 unit, symbol `package.Func`
|
||||
- `method_declaration` → 1 unit, symbol `package.(*Receiver).Method` / `package.(Receiver).Method`
|
||||
- `type_declaration` (struct / interface / type alias) → 1 unit each, symbol `package.TypeName`
|
||||
- `const_declaration`, `var_declaration`, `import_declaration` (블록 또는 단일) → glue, grouped → `package.<top-level>` (1A/1B 패턴)
|
||||
- **Go 의 generic 처리**: `func Foo[T any](...)` 또는 `type Foo[T any] struct{}` 의 type parameter 는 symbol 에 미포함 (Go 자체도 보통 symbol 에 안 적음). 단순 `package.Foo` 만.
|
||||
- **Test detection**: Go 의 `func TestXxx(t *testing.T)` 는 *일반 fn 으로 emit*. test 감지 boost/penalty 등 ranking 영향은 본 task 범위 밖 (ranking brainstorm 보류 메모리 따름).
|
||||
- frozen design 자체는 변경 없음 (§3.4 의 Go 행이 이미 본 결정과 일치). §10.1 에 1C-Go 활성화 한 줄 추가.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- `cargo test --workspace --no-fail-fast -j 1` passes (memory-conscious: per-crate 위주, full-suite gate 는 docs task 직전 1회).
|
||||
- `cargo clippy --workspace --all-targets -- -D warnings` passes.
|
||||
- Go fixture (`tests/fixtures/sample.go`) ingest → chunk snapshot 안정 + `Citation::Code` 의 symbol 이 §3.4 컨벤션 일치 (`pkg.Func` / `pkg.(*Receiver).Method`).
|
||||
- 격리 TempDir KB 에 Go 파일 두고 `kebab search --code-lang go --json` 가 `Citation::Code { lang: "go", symbol: "...", ... }` 반환.
|
||||
- `kebab schema --json | jq .stats.code_lang_breakdown` 에 `"go"` 카운트.
|
||||
- README + HANDOFF + ARCHITECTURE + SMOKE + tasks/INDEX + tasks/p10/INDEX 갱신.
|
||||
- frozen design §10.1 한 줄 추가.
|
||||
- workspace `Cargo.toml` minor bump (0.11.1 → 0.12.0).
|
||||
|
||||
## Allowed dependencies
|
||||
|
||||
- `kebab-parse-code` 에 `tree-sitter-go` 추가 (workspace deps). 기존 deps 유지.
|
||||
- `kebab-chunk` 의 새 모듈 `code_go_ast_v1.rs` — kebab-core + serde_json_canonicalizer + blake3 + anyhow + tracing. tree-sitter 절대 import 금지.
|
||||
- `kebab-app`, `kebab-source-fs` 변경 — 새 crate dep 없음.
|
||||
|
||||
## Forbidden dependencies
|
||||
|
||||
- `kebab-chunk` 가 `tree-sitter-go` 직접 import 금지.
|
||||
- UI crate 가 `kebab-parse-code` 직접 import 금지.
|
||||
- `kebab-parse-code` 가 store / embed / llm / rag 직접 import 금지.
|
||||
|
||||
## Risks / notes
|
||||
|
||||
- tree-sitter-go 의 `package_clause` node 가 root 의 첫 named child 인지 grammar 버전에 따라 다를 수 있음 — extractor 가 `source_file` 전체를 named_children iterate 하면서 첫 `package_clause` 잡는 방식이 안전.
|
||||
- `method_declaration` 의 receiver pointer 여부: tree-sitter-go AST 에서 receiver type 이 `pointer_type` 노드면 `*Receiver`, 그냥 `type_identifier` 면 `Receiver`. 정확한 텍스트 추출 필요.
|
||||
- Generic type parameter (`[T any]`) 가 method_declaration / function_declaration 의 name field 와 별도 child — name 만 추출하면 generic 부분 자동 제외.
|
||||
- 1B Python/TS/JS 패턴 (helpers from lang.rs) 와 *다른* 모델 — 본 task 의 mod_prefix 는 source-side AST 에서 추출, helper fn 불필요.
|
||||
- 머지 후 deviation 은 `tasks/HOTFIXES.md` 에 dated 로그 + 본 spec `Risks / notes` 에 one-line cross-link.
|
||||
Reference in New Issue
Block a user