mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-12 06:35:44 +08:00
12787996d1
feat(ingestion): mirror Go pipeline progress into the document table;
harden resume guards
- pipeline: bind the owning document via WithDocumentID; after each
TrackProgress event aggregate ingestion_task_log progress and mirror
progress/run/progress_msg back into the document table, so GET
/api/v1/datasets/{dataset_id}/documents reflects live Go pipeline
progress without a bespoke endpoint.
- canvas: extend the S3 resume guard to reject legacy no-op nodes (e.g.
ExitLoop) so component_total equals the count of progress-reporting
components and the aggregate percent can reach 100%.
- runtime/canvas: route progress through TrackProgress; add interrupt
test coverage (r3_interrupt_test.go).
- dao/entity: add IngestionTask.DocumentID column and AggregateProgress
support used by the mirror; IngestionTaskLog keeps a Checkpoint column
alongside the progress fields.
feat(deepdoc): cache DocAnalyzer inference results in Redis (1h TTL)
- Redis-backed DocAnalyzerCache decorator over inference.Client; cache
key = "ddoc:cache:<method>:" + sha256 of the JPEG-encoded image bytes
(deterministic).
- TTL = 1h; hits skip the inner HTTP call and return cached JSON; inner
errors are not cached.
refactor(deepdoc): align figure cropping with Python cropout + bounded
page caches
- CropSectionByDLA mirrors Python cropout: best-overlap DLA
figure/equation region, fallback to section bbox per page, vertical
concat on gray background.
- sliding-window page-image cache bounds peak memory to the recent
window instead of the whole PDF.
- rename DLADebug -> DLARegions across parser/chunker/tests.
refactor(parser): drop lib_type selector; align NewXxxParser with
NewPDFParser
- remove config["lib_type"] lookup and the libType param/field/switch
from all nine constructors; surface the CGO-required error at
ParseWithResult time instead of construction time; drop resolveLibType,
its test, and the four lib_type constants.
feat(utility): add a reusable workerpool for bounded concurrent
execution
- internal/utility/workerpool.go (+ tests).
refactor: translate Chinese prose comments to English in non-harness Go
files.
chore: upgrade github.com/cloudwego/eino from v0.9.9 to v0.9.12.
60 lines
1.9 KiB
Go
60 lines
1.9 KiB
Go
//go:build cgo && integration
|
|
|
|
package pdf
|
|
|
|
import (
|
|
"context"
|
|
"reflect"
|
|
"testing"
|
|
|
|
pdf "ragflow/internal/deepdoc/parser/pdf/type"
|
|
)
|
|
|
|
// TestParser_PageParallel_DeterministicOrder verifies the plan's real-fixture
|
|
// acceptance criteria: pool size 1 and pool size 4 must produce stable
|
|
// Sections, Tables, Metrics, and per-page PNG-equivalent images on the named
|
|
// PDF fixtures. With Config.Parallelism removed, page concurrency is governed
|
|
// by the process-wide worker pool.
|
|
func TestParser_PageParallel_DeterministicOrder(t *testing.T) {
|
|
client := mustConnectInferenceClient(t)
|
|
|
|
fixtures := []string{
|
|
"03_multipage.pdf",
|
|
"06_table_content.pdf",
|
|
"07_mixed_content.pdf",
|
|
"19_multipage_chunk.pdf",
|
|
}
|
|
|
|
runParse := func(t *testing.T, name string, poolSize int) *pdf.ParseResult {
|
|
t.Helper()
|
|
setPoolSize(t, poolSize)
|
|
p := NewParser(pdf.DefaultParserConfig())
|
|
result, err := p.Parse(context.Background(), mustReadPDF(t, name), client)
|
|
if err != nil {
|
|
t.Fatalf("fixture=%s poolSize=%d: Parse: %v", name, poolSize, err)
|
|
}
|
|
t.Cleanup(func() { result.Close() })
|
|
return result
|
|
}
|
|
|
|
for _, name := range fixtures {
|
|
t.Run(name, func(t *testing.T) {
|
|
baseline := runParse(t, name, 1)
|
|
parallel := runParse(t, name, 4)
|
|
|
|
if !reflect.DeepEqual(stableSections(baseline.Sections), stableSections(parallel.Sections)) {
|
|
t.Fatalf("fixture=%s: Sections diverged between poolSize=1 and poolSize=4", name)
|
|
}
|
|
if !reflect.DeepEqual(stableTables(baseline.Tables), stableTables(parallel.Tables)) {
|
|
t.Fatalf("fixture=%s: Tables diverged between poolSize=1 and poolSize=4", name)
|
|
}
|
|
if !reflect.DeepEqual(baseline.Metrics, parallel.Metrics) {
|
|
t.Fatalf("fixture=%s: Metrics diverged: %#v vs %#v", name, baseline.Metrics, parallel.Metrics)
|
|
}
|
|
if !reflect.DeepEqual(baseline.PageHeight, parallel.PageHeight) {
|
|
t.Fatalf("fixture=%s: PageHeight diverged between poolSize=1 and poolSize=4", name)
|
|
}
|
|
})
|
|
}
|
|
}
|