Files
ragflow/internal/parser/parser/docx_parser_cgo_test.go
Jack bb6b43b5c9 fix: docx/email parsing, extractor LLM driver, and chunker alignment (#17144)
## Summary

Three groups of changes across the Go ingestion pipeline:

### 1. DOCX parsing improvements
- **docx_parser.go**: Enhanced DOCX parsing with better structure
extraction and media handling
- **docx_parser_cgo_test.go**, **docx_parser_test.go**: Companion tests
- **office_parsers_no_cgo.go**: Stub sync for non-CGO builds

### 2. Email (.eml) parsing: base64 Content-Transfer-Encoding decoding
- **email_parser.go** (`decodeCTE`): Added Content-Transfer-Encoding
decoding for base64 and quoted-printable. Go's `mime/multipart.Reader`
does not decode Content-Transfer-Encoding automatically, so attachments
with `Content-Transfer-Encoding: base64` remained base64-encoded in the
output. The new `decodeCTE` helper is called after reading each
multipart part's raw bytes in `readMailBody`, mirroring Python's
`part.get_payload(decode=True)`.
- **email_parser_test.go**: Two new tests — simple base64 attachment and
nested multipart/alternative with base64 attachment.

### 3. Extractor LLM driver fix + ModelDriver consolidation
- **extractor.go**: Fixed a bug where the Extractor component used
`ModelFactory.CreateModelDriver()`, which creates bare model instances
without API keys or provider configuration. Switched to
`models.GetPreconfiguredDriver()` which resolves the actual
pre-configured driver from `ProviderManager`, matching the codepath used
by `llm.go`. This fixes auto keyword/question extraction in DSL
pipelines that require LLM calls.
- **get_driver.go** (new): Extracted shared `GetPreconfiguredDriver()`
from `llm.go:newChatModelDriver()` so both `llm.go` and `extractor.go`
use the same codepath.
- **get_driver_test.go** (new): Tests for the shared driver resolution.
- **llm.go**: Replaced inline driver resolution with
`models.GetPreconfiguredDriver()`.

### 4. Chunker fixes and observability
- **group.go** (`extractLineRecords`): Fixed to also read `markdown` and
`html` payload keys — previously it only read `text`/`content`, causing
GroupTitleChunker to silently return empty results for markdown-format
parser output.
- **common.go** (`compileDelimPattern`): Aligned with Python's
`_compile_delimiter_pattern` — only backtick-wrapped delimiters produce
an active regex pattern; plain delimiters are not compiled into the
split regex.
- **token.go** (`applyChildrenDelim`): Set `DocType` and `CKType` to
`"text"` on created ChunkDocs so the token-size merge path correctly
identifies and merges text segments.
- **parser.go**, **extractor.go**, **tokenizer.go**, **group.go**,
**hierarchy.go**: Added debug-level logging for pipeline diagnostics.
- **parser_dispatch_test.go**, **group_test.go**: New tests.

## Verification
- All Go tests pass: `bash build.sh --test ./internal/parser/parser/...`
and `bash build.sh --test ./internal/ingestion/component/...`
- Build succeeds: `bash build.sh --go`
2026-07-21 13:51:17 +08:00

128 lines
4.0 KiB
Go

//go:build cgo
package parser
import (
"archive/zip"
"bytes"
"testing"
)
func TestDOCXParser_ParseWithResult_JSON(t *testing.T) {
p := NewDOCXParser()
p.outputFormat = "json"
data := minimalDOCX(t, "Hello from JSON path")
res := p.ParseWithResult("sample.docx", data)
if res.Err != nil {
t.Fatalf("ParseWithResult: %v", res.Err)
}
if got, want := res.OutputFormat, "json"; got != want {
t.Fatalf("OutputFormat = %q, want %q", got, want)
}
if len(res.JSON) == 0 {
t.Fatal("JSON items is empty; expected parsed content")
}
for i, item := range res.JSON {
if _, ok := item["text"]; !ok {
t.Errorf("item[%d] missing 'text' field", i)
}
if _, ok := item["doc_type_kwd"]; !ok {
t.Errorf("item[%d] missing 'doc_type_kwd' field", i)
}
}
}
func TestDOCXParser_ConfigureFromSetup_JSON(t *testing.T) {
p := NewDOCXParser()
p.ConfigureFromSetup(map[string]any{"output_format": "json"})
if p.outputFormat != "json" {
t.Fatalf("After ConfigureFromSetup, outputFormat = %q, want %q", p.outputFormat, "json")
}
if p.libType != "" {
t.Errorf("libType unexpectedly = %q", p.libType)
}
// Full round-trip: json config → json output
data := minimalDOCX(t, "Config test")
res := p.ParseWithResult("sample.docx", data)
if res.Err != nil {
t.Fatalf("ParseWithResult: %v", res.Err)
}
if res.OutputFormat != "json" {
t.Errorf("OutputFormat = %q, want %q", res.OutputFormat, "json")
}
if len(res.JSON) == 0 {
t.Error("JSON items is empty")
}
}
func TestDOCXParser_ConfigureFromSetup_Markdown(t *testing.T) {
p := NewDOCXParser()
p.ConfigureFromSetup(map[string]any{"output_format": "markdown"})
if p.outputFormat != "markdown" {
t.Fatalf("After ConfigureFromSetup, outputFormat = %q, want %q", p.outputFormat, "markdown")
}
data := minimalDOCX(t, "Config md test")
res := p.ParseWithResult("sample.docx", data)
if res.Err != nil {
t.Fatalf("ParseWithResult: %v", res.Err)
}
if res.OutputFormat != "markdown" {
t.Errorf("OutputFormat = %q, want %q", res.OutputFormat, "markdown")
}
if res.Markdown == "" {
t.Error("Markdown is empty")
}
}
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)
}
}