mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-11 06:05:45 +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.
76 lines
2.0 KiB
Go
76 lines
2.0 KiB
Go
//go:build cgo && manual
|
|
|
|
package pdf
|
|
|
|
import (
|
|
"os"
|
|
"path/filepath"
|
|
"sync"
|
|
"testing"
|
|
|
|
"ragflow/internal/deepdoc/parser/pdf/pdfium"
|
|
"ragflow/internal/deepdoc/parser/pdf/pdfoxide"
|
|
)
|
|
|
|
// TestPdfsyncSharedMutexAcrossBindings hammers both the cgo pdfium binding and
|
|
// the Rust pdf_oxide binding concurrently on the same document. Both bindings
|
|
// link a single PDFium instance (build.sh collapses the duplicate FPDF_*
|
|
// symbols with --allow-multiple-definition), so each binding must serialize
|
|
// through the SAME process-wide pdfsync.Mu. Two independent mutexes would
|
|
// still interleave calls onto the shared PDFium heap and SIGSEGV. The test
|
|
// therefore only passes if it completes without crashing — it directly
|
|
// exercises the shared-mutex invariant described in pdfsync/pdfsync.go.
|
|
func TestPdfsyncSharedMutexAcrossBindings(t *testing.T) {
|
|
pdfPath := filepath.Join("testdata", "pdfs", "01_english_simple.pdf")
|
|
data, err := os.ReadFile(pdfPath)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
|
|
const goroutines = 16
|
|
const iterations = 3
|
|
|
|
var wg sync.WaitGroup
|
|
for i := 0; i < goroutines; i++ {
|
|
wg.Add(1)
|
|
go func(id int) {
|
|
defer wg.Done()
|
|
usePdfium := id%2 == 0
|
|
for j := 0; j < iterations; j++ {
|
|
if usePdfium {
|
|
if _, _, err := pdfium.PageSize(data, 0); err != nil {
|
|
t.Errorf("pdfium.PageSize: %v", err)
|
|
return
|
|
}
|
|
img, err := pdfium.RenderPage(data, 0, 72)
|
|
if err != nil {
|
|
t.Errorf("pdfium.RenderPage: %v", err)
|
|
return
|
|
}
|
|
if img.Bounds().Dx() <= 0 {
|
|
t.Error("pdfium.RenderPage returned zero-width image")
|
|
return
|
|
}
|
|
} else {
|
|
doc, err := pdfoxide.OpenBytes(data)
|
|
if err != nil {
|
|
t.Errorf("pdfoxide.OpenBytes: %v", err)
|
|
return
|
|
}
|
|
res, err := doc.RenderPage(0, 72)
|
|
doc.Close()
|
|
if err != nil {
|
|
t.Errorf("pdfoxide.RenderPage: %v", err)
|
|
return
|
|
}
|
|
if res.Width <= 0 {
|
|
t.Error("pdfoxide.RenderPage returned zero-width image")
|
|
return
|
|
}
|
|
}
|
|
}
|
|
}(i)
|
|
}
|
|
wg.Wait()
|
|
}
|