altair823
b9ee09f176
Step 6 (Group E) of v0.20.0 sub-item 1 (scanned PDF OCR) plan + Step 7 spillover (IngestEvent variant + IngestItem field for compile boundary) + Step 4 reviewer Minor M-4 fix. E1 — eager PDF OCR engine build at `ingest_with_config_opts` entry, mirror of image OCR pattern (lib.rs:338-347). `pdf.ocr.enabled || always_on` 시 `OllamaVisionOcr::from_parts(endpoint, model, ...)` 호출 + fail-fast `?`. App field 추가 0 (local var only, spec L-1 / Step 1 A1 cosmetic fix 정합). E2 — `ingest_one_pdf_asset` signature extension: +3 param (`pdf_ocr_engine: Option<&OllamaVisionOcr>`, `progress: Option<& mpsc::Sender<IngestEvent>>`, `cancel: Option<&Arc<AtomicBool>>`). `ingest_one_asset` dispatch wrapper + caller (dispatch loop) update. E3 — post-extract enrichment block at `extract_for` 직후 (line 1779). `pdf.ocr.enabled || always_on` 시 `apply_ocr_to_pdf_pages` 호출, PdfOcrProgress → IngestEvent emit (PdfOcrStarted / PdfOcrFinished with ocr_engine), summary 의 pages_ocrd/ms_total 을 IngestItem field 로 carry. PR #187 registry dispatch invariant 보존 (`extract_for(&asset.media_type, ...)` 그대로). E4 — cancel handle propagation: ingest_with_config_cancellable → IngestOpts.cancel → ingest_with_config_opts → ingest_one_asset → ingest_one_pdf_asset (new `cancel` param) → PdfOcrOpts.cancel chain. spec §4.8 line 1159 production wiring. Step 7 spillover (compile boundary): - `kebab_app::ingest_progress::IngestEvent`: PdfOcrStarted { page } + PdfOcrFinished { page, ms, chars, ocr_engine }. serde discriminant `pdf_ocr_started` / `pdf_ocr_finished` (Step 7 G3 wire schema 와 일치). - `kebab_core::IngestItem`: pdf_ocr_pages: Option<u32> + pdf_ocr_ms_total: Option<u64> (warnings/error 사이). 11 non-PDF IngestItem construct site 가 `None` 채움. - `kebab-cli/src/progress.rs` + `kebab-tui/src/ingest_progress.rs`: 새 variant no-op handler (v1에서 per-page progress 미노출, future refinement 시 활성화 가능). - `kebab-store-sqlite/tests/ingest_report_snapshot.rs` + snapshot `ingest_report.snapshot.json`: 2 IngestItem fixture 의 새 field 추가. - Step 7 의 JSON Schema 갱신 + CLI printer activation + snapshot regenerate 는 별 commit (G3/H1/H2 deliverable). M-4 (Step 4 reviewer Minor) — lopdf workspace dep 통합: - workspace `Cargo.toml [workspace.dependencies] lopdf = "0.32"`. - kebab-app + kebab-parse-pdf 의 direct dep → `{ workspace = true }`. Verifier evidence: - workspace test (`cargo test --workspace --no-fail-fast -j 1`): 175 test result summary lines, 0 failures, 0 FAILED. - workspace clippy (`-D warnings`): exit 0, 0 warning. - dep graph baseline (`.omc/state/pdf-ocr-{parse-pdf,app-parse}-deps.baseline.txt`): empty diff for both. spec: docs/superpowers/specs/2026-05-27-pdf-scanned-ocr-spec.md (§4.4 + §4.6 + §4.8) plan: docs/superpowers/plans/2026-05-27-pdf-scanned-ocr-plan.md (Step 6 E1-E4 + Step 7 partial G1+G2) prior:4672cba(Step 5 fix) +fd918a6(Step 5) +9f003ef(Step 4 helper) contract: §9 (additive minor wire bump — Step 7 JSON Schema 완료 시) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
86 lines
4.1 KiB
TOML
86 lines
4.1 KiB
TOML
[package]
|
|
name = "kebab-app"
|
|
version = { workspace = true }
|
|
edition = { workspace = true }
|
|
rust-version = { workspace = true }
|
|
license = { workspace = true }
|
|
repository = { workspace = true }
|
|
description = "Facade — orchestrates components for kb-cli/tui/desktop"
|
|
|
|
[dependencies]
|
|
kebab-core = { path = "../kebab-core" }
|
|
kebab-config = { path = "../kebab-config" }
|
|
kebab-source-fs = { path = "../kebab-source-fs" }
|
|
kebab-parse-md = { path = "../kebab-parse-md" }
|
|
kebab-chunk = { path = "../kebab-chunk" }
|
|
kebab-store-sqlite = { path = "../kebab-store-sqlite" }
|
|
kebab-store-vector = { path = "../kebab-store-vector" }
|
|
kebab-search = { path = "../kebab-search" }
|
|
kebab-embed = { path = "../kebab-embed" }
|
|
kebab-embed-local = { path = "../kebab-embed-local" }
|
|
kebab-llm = { path = "../kebab-llm" }
|
|
kebab-llm-local = { path = "../kebab-llm-local" }
|
|
kebab-rag = { path = "../kebab-rag" }
|
|
# p9-fb-41 PR-9c-2: facade construction of OnnxNliVerifier when
|
|
# `[rag] nli_threshold > 0`. Trait-only consumption via kebab-rag's
|
|
# `with_verifier`; no kebab-nli internals leak into kebab-app code
|
|
# beyond the construction site in `open_with_config`.
|
|
kebab-nli = { path = "../kebab-nli" }
|
|
# P6-4: image extractor + OCR + caption adapters live here. App
|
|
# threads them into the per-asset dispatch (see `ingest_one_asset`
|
|
# image branch). Trait-only consumption — no `kebab-parse-image`
|
|
# internals leak into kb-app code.
|
|
kebab-parse-image = { path = "../kebab-parse-image" }
|
|
# P7-3: PDF text extractor lives here. App threads it into the
|
|
# per-asset dispatch (see `ingest_one_asset` PDF branch) and runs the
|
|
# resulting `CanonicalDocument` through `kebab-chunk::PdfPageV1Chunker`.
|
|
kebab-parse-pdf = { path = "../kebab-parse-pdf" }
|
|
lopdf = { workspace = true }
|
|
# p10-1A-2: Rust AST extractor lives here. App threads it into the
|
|
# per-asset dispatch (see `ingest_one_asset` Code branch) and runs the
|
|
# resulting `CanonicalDocument` through `kebab-chunk::CodeRustAstV1Chunker`.
|
|
kebab-parse-code = { path = "../kebab-parse-code" }
|
|
anyhow = { workspace = true }
|
|
blake3 = { workspace = true }
|
|
serde = { workspace = true }
|
|
serde_json = { workspace = true }
|
|
time = { workspace = true }
|
|
tracing = { workspace = true }
|
|
tracing-subscriber = { version = "0.3", features = ["env-filter", "fmt", "json"] }
|
|
tracing-appender = "0.2"
|
|
toml = "0.8"
|
|
dirs = "5"
|
|
# p9-fb-19: in-process LRU cache for `App::search`. Capacity from
|
|
# `config.search.cache_capacity` (default 256, ~1.3 MB cap).
|
|
lru = { workspace = true }
|
|
# p9-fb-19: NFKC-normalize cache-key queries so `"Foo"` / `"FOO"` /
|
|
# `" foo "` collapse to one entry. Same crate kebab-normalize +
|
|
# kebab-core already use, no version drift.
|
|
unicode-normalization = "0.1"
|
|
# p9-fb-31: GitignoreBuilder for .kebabignore matching in ingest_file_with_config.
|
|
# Same version as kebab-source-fs (0.4) to avoid duplicate dep versions.
|
|
ignore = "0.4"
|
|
# p9-fb-34: opaque pagination cursor encodes payload as base64.
|
|
base64 = { workspace = true }
|
|
|
|
[dev-dependencies]
|
|
rusqlite = { workspace = true }
|
|
tempfile = { workspace = true }
|
|
# Image-pipeline integration tests use wiremock to stub Ollama for OCR
|
|
# / caption HTTP calls. Async runtime to host the mock server only;
|
|
# the kb-app code under test stays sync.
|
|
wiremock = { workspace = true }
|
|
tokio = { workspace = true, features = ["rt-multi-thread"] }
|
|
image = { version = "0.25", default-features = false, features = ["png"] }
|
|
# P7-3 PDF integration tests build in-memory PDF fixtures via the same
|
|
# lopdf builder pattern `kebab-parse-pdf::tests::common` uses; pinned
|
|
# to the same major (0.32) so byte output is identical between the two
|
|
# fixture surfaces.
|
|
lopdf = { workspace = true }
|
|
# error_wire::tests::llm_unreachable_classifies_to_model_unreachable needs a real
|
|
# reqwest::Error (private constructor) — built from a connect-refused call.
|
|
reqwest = { version = "0.12", default-features = false, features = ["blocking", "rustls-tls"] }
|
|
|
|
[lints]
|
|
workspace = true
|