test(ingest): config invalidation e2e + parser_version assert 갱신
- config_invalidation.rs(신규): 동일config=전skip / 청킹변경=md+code재색인 /
[ingest.code]변경=코드만 / search변경=재색인0 (회귀가드) end-to-end.
- code_ingest_smoke / pdf_pipeline: 저장 parser_version 이 이제
"{base}|{sig}" composite 라, exact assert 를 base 접두사(split('|').next()) 비교로 갱신.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -162,7 +162,9 @@ fn ingest_3_page_pdf_produces_one_doc_and_per_page_chunks() {
|
||||
"one chunk per non-empty page"
|
||||
);
|
||||
assert_eq!(
|
||||
pdf_item.parser_version.as_ref().map(|p| p.0.as_str()),
|
||||
pdf_item.parser_version
|
||||
.as_ref()
|
||||
.map(|p| p.0.split('|').next().unwrap()),
|
||||
Some("pdf-text-v1")
|
||||
);
|
||||
assert_eq!(
|
||||
@@ -477,7 +479,10 @@ fn inspect_doc_surfaces_page_spans() {
|
||||
.find(|i| i.doc_path.0.ends_with("inspect.pdf"))
|
||||
.unwrap();
|
||||
let doc = kebab_app::inspect_doc_with_config(cfg, pdf_item.doc_id.as_ref().unwrap()).unwrap();
|
||||
assert_eq!(doc.parser_version.0, "pdf-text-v1");
|
||||
// v0.26.2: stored parser_version is now `pdf-text-v1|<ingest-config-sig>`
|
||||
// (the signature folds chunking / pdf.ocr settings for skip detection).
|
||||
// Assert the base identity by taking the prefix before the first '|'.
|
||||
assert_eq!(doc.parser_version.0.split('|').next().unwrap(), "pdf-text-v1");
|
||||
assert_eq!(doc.blocks.len(), 3);
|
||||
for block in &doc.blocks {
|
||||
match block {
|
||||
|
||||
Reference in New Issue
Block a user