mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-15 23:57:14 +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.
62 lines
2.1 KiB
Go
62 lines
2.1 KiB
Go
//go:build cgo
|
|
|
|
package parser
|
|
|
|
import (
|
|
"archive/zip"
|
|
"bytes"
|
|
"testing"
|
|
)
|
|
|
|
func TestDOCXParser_ParseWithResult_CGOMinimalDocument(t *testing.T) {
|
|
p := NewDOCXParser()
|
|
data := minimalDOCX(t, "Hello from DOCX parser")
|
|
res := p.ParseWithResult("sample.docx", data)
|
|
if res.Err != nil {
|
|
t.Fatalf("ParseWithResult: %v", res.Err)
|
|
}
|
|
if got, want := res.OutputFormat, "markdown"; got != want {
|
|
t.Fatalf("OutputFormat = %q, want %q", got, want)
|
|
}
|
|
if res.Markdown == "" {
|
|
t.Fatal("Markdown is empty; want parsed content")
|
|
}
|
|
}
|
|
|
|
func minimalDOCX(t *testing.T, text string) []byte {
|
|
t.Helper()
|
|
var buf bytes.Buffer
|
|
zw := zip.NewWriter(&buf)
|
|
writeZipFile(t, zw, "[Content_Types].xml", `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
|
<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
|
|
<Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
|
|
<Default Extension="xml" ContentType="application/xml"/>
|
|
<Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>
|
|
</Types>`)
|
|
writeZipFile(t, zw, "_rels/.rels", `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
|
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
|
|
<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/>
|
|
</Relationships>`)
|
|
writeZipFile(t, zw, "word/document.xml", `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
|
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
|
|
<w:body>
|
|
<w:p><w:r><w:t>`+text+`</w:t></w:r></w:p>
|
|
</w:body>
|
|
</w:document>`)
|
|
if err := zw.Close(); err != nil {
|
|
t.Fatalf("zip close: %v", err)
|
|
}
|
|
return buf.Bytes()
|
|
}
|
|
|
|
func writeZipFile(t *testing.T, zw *zip.Writer, name, body string) {
|
|
t.Helper()
|
|
w, err := zw.Create(name)
|
|
if err != nil {
|
|
t.Fatalf("create zip entry %s: %v", name, err)
|
|
}
|
|
if _, err := w.Write([]byte(body)); err != nil {
|
|
t.Fatalf("write zip entry %s: %v", name, err)
|
|
}
|
|
}
|