Files
ragflow/internal/parser/parser/docx_parser_test.go
Jack 0403d19b5a fix: honor parser params and image VLM system_prompt in Go ingestion (#17334)
## Summary
Fix the Go ingestion pipeline so that several parser setup switches and
the
image VLM prompt are actually honored end-to-end (previously the DSL
fields
existed but the Go code never read them).

- **DOCX** (`docx_parser.go`, `docx_postprocess.go`): read `remove_toc`
and
  `remove_header_footer`; apply to both JSON and markdown output paths
  (outline-based TOC removal with a text-heuristic fallback, plus
  header/footer section filtering).
- **HTML** (`html_parser.go`, `html_postprocess.go`, `text_toc.go`):
read
`remove_header_footer` (pre-parse strip of `<header>`/`<footer>` and
ARIA
`banner`/`contentinfo`) and `remove_toc` (post-parse
`remove_contents_table`
  heuristic).
- **Markdown** (`markdown_parser.go`): read `flatten_media_to_text` and
force
  media blocks to text when enabled.
- **Image VLM** (`media_dispatch.go`): read `system_prompt` instead of
`prompt`
  so the user-configured image VLM prompt is no longer silently dropped
  (`prompt` remains the video family key).

All flags are wired through `ConfigureFromSetup`, which the dispatch
layer
already invokes for every family, so the behavior is live rather than
dead code.

## Test plan
- New unit tests: `docx_postprocess_test.go`, `html_parser_test.go`,
`text_toc_test.go`, `markdown_parser_test.go`, `media_dispatch_test.go`.
- `bash build.sh --test ./internal/parser/parser/...
./internal/ingestion/component/...`

## Notes
- The `File` component is excluded from this migration scope.
- Relates to the Python→Go parity diff (Parser 1.8–1.11, 1.15).
2026-07-24 14:42:26 +08:00

271 lines
9.4 KiB
Go

//go:build cgo
//
// Copyright 2026 The InfiniFlow Authors. All Rights Reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
package parser
import (
"encoding/base64"
"encoding/json"
"strings"
"testing"
)
func TestBuildDOCXJSONSections_Paragraphs(t *testing.T) {
ir := `{"sections":[{"title":"","elements":[
{"type":"paragraph","content":[{"type":"text","text":"Hello world"}],"style":"Normal"}
]}]}`
sections := buildDOCXJSONSections(ir)
if len(sections) != 1 {
t.Fatalf("got %d sections, want 1", len(sections))
}
item := sections[0]
if got, ok := item["text"].(string); !ok || got != "Hello world" {
t.Errorf("text = %q, want %q", got, "Hello world")
}
if got, ok := item["doc_type_kwd"].(string); !ok || got != "text" {
t.Errorf("doc_type_kwd = %q, want %q", got, "text")
}
}
func TestBuildDOCXJSONSections_Headings(t *testing.T) {
ir := `{"sections":[{"title":"","elements":[
{"type":"heading","level":1,"content":[{"type":"text","text":"Chapter 1"}]}
]}]}`
sections := buildDOCXJSONSections(ir)
if len(sections) != 1 {
t.Fatalf("got %d sections, want 1", len(sections))
}
item := sections[0]
if got, ok := item["text"].(string); !ok || got != "Chapter 1" {
t.Errorf("text = %q, want %q", got, "Chapter 1")
}
if got, ok := item["doc_type_kwd"].(string); !ok || got != "text" {
t.Errorf("doc_type_kwd = %q, want %q", got, "text")
}
if got, ok := item["ck_type"].(string); !ok || got != "heading" {
t.Errorf("ck_type = %q, want %q", got, "heading")
}
}
func TestBuildDOCXJSONSections_Images(t *testing.T) {
b64 := base64.StdEncoding.EncodeToString([]byte("fake-image-data"))
ir := `{"sections":[{"title":"","elements":[
{"type":"image","data":"` + b64 + `"}
]}]}`
sections := buildDOCXJSONSections(ir)
if len(sections) != 1 {
t.Fatalf("got %d sections, want 1", len(sections))
}
item := sections[0]
if got, ok := item["text"].(string); !ok || got != "" {
t.Errorf("text = %q, want empty", got)
}
if got, ok := item["image"].(string); !ok || got != b64 {
t.Errorf("image = %q, want %q", got, b64)
}
if got, ok := item["doc_type_kwd"].(string); !ok || got != "image" {
t.Errorf("doc_type_kwd = %q, want %q", got, "image")
}
}
func TestBuildDOCXJSONSections_Tables(t *testing.T) {
ir := `{"sections":[{"title":"","elements":[
{"type":"table","rows":[
{"cells":[{"content":[{"type":"paragraph","content":[{"type":"text","text":"A1"}]}]},{"content":[{"type":"paragraph","content":[{"type":"text","text":"B1"}]}]}]},
{"cells":[{"content":[{"type":"paragraph","content":[{"type":"text","text":"A2"}]}]},{"content":[{"type":"paragraph","content":[{"type":"text","text":"B2"}]}]}]}
]}
]}]}`
sections := buildDOCXJSONSections(ir)
if len(sections) != 1 {
t.Fatalf("got %d sections, want 1", len(sections))
}
item := sections[0]
html, ok := item["text"].(string)
if !ok {
t.Fatal("text field missing or not string")
}
if !strings.Contains(html, "<table>") || !strings.Contains(html, "</table>") {
t.Errorf("html = %q, missing <table> tags", html)
}
if !strings.Contains(html, "<tr>") || !strings.Contains(html, "</tr>") {
t.Errorf("html = %q, missing <tr> tags", html)
}
if !strings.Contains(html, "<td>A1</td>") || !strings.Contains(html, "<td>B2</td>") {
t.Errorf("html = %q, missing cell content", html)
}
if got, ok := item["doc_type_kwd"].(string); !ok || got != "table" {
t.Errorf("doc_type_kwd = %q, want %q", got, "table")
}
}
func TestBuildDOCXJSONSections_MixedContent(t *testing.T) {
ir := `{"sections":[{"title":"","elements":[
{"type":"paragraph","content":[{"type":"text","text":"First para"}]},
{"type":"image","data":"aW1hZ2U="},
{"type":"table","rows":[{"cells":[{"content":[{"type":"paragraph","content":[{"type":"text","text":"cell"}]}]}]}]},
{"type":"heading","level":2,"content":[{"type":"text","text":"Sub title"}]}
]}]}`
sections := buildDOCXJSONSections(ir)
if len(sections) != 4 {
t.Fatalf("got %d sections, want 4", len(sections))
}
// paragraph first
if got, _ := sections[0]["doc_type_kwd"].(string); got != "text" {
t.Errorf("item[0].doc_type_kwd = %q, want %q", got, "text")
}
// image second
if got, _ := sections[1]["doc_type_kwd"].(string); got != "image" {
t.Errorf("item[1].doc_type_kwd = %q, want %q", got, "image")
}
// table third
if got, _ := sections[2]["doc_type_kwd"].(string); got != "table" {
t.Errorf("item[2].doc_type_kwd = %q, want %q", got, "table")
}
// heading fourth
if got, _ := sections[3]["doc_type_kwd"].(string); got != "text" {
t.Errorf("item[3].doc_type_kwd = %q, want %q", got, "text")
}
if got, _ := sections[3]["ck_type"].(string); got != "heading" {
t.Errorf("item[3].ck_type = %q, want %q", got, "heading")
}
}
func TestBuildDOCXJSONSections_List(t *testing.T) {
ir := `{"sections":[{"title":"","elements":[
{"type":"list","ordered":false,"items":[
{"content":[{"type":"paragraph","content":[{"type":"text","text":"Item 1"}]}]},
{"content":[{"type":"paragraph","content":[{"type":"text","text":"Item 2"}]}]},
{"content":[{"type":"paragraph","content":[{"type":"text","text":"Item 3"}]}]}
],"level":0}
]}]}`
sections := buildDOCXJSONSections(ir)
if len(sections) != 3 {
t.Fatalf("got %d sections, want 3 (each list item should be a section)", len(sections))
}
for i, want := range []string{"Item 1", "Item 2", "Item 3"} {
if got, _ := sections[i]["text"].(string); got != want {
t.Errorf("section[%d].text = %q, want %q", i, got, want)
}
if got, ok := sections[i]["doc_type_kwd"].(string); !ok || got != "text" {
t.Errorf("section[%d].doc_type_kwd = %q, want %q", i, got, "text")
}
}
}
func TestBuildDOCXJSONSections_TextBox(t *testing.T) {
ir := `{"sections":[{"title":"","elements":[
{"type":"text_box","content":[{"type":"paragraph","content":[{"type":"text","text":"Boxed paragraph"}]}],"width_emu":null}
]}]}`
sections := buildDOCXJSONSections(ir)
if len(sections) != 1 {
t.Fatalf("got %d sections, want 1 (text_box content should become a section)", len(sections))
}
if got, _ := sections[0]["text"].(string); got != "Boxed paragraph" {
t.Errorf("text = %q, want %q", got, "Boxed paragraph")
}
if got, ok := sections[0]["doc_type_kwd"].(string); !ok || got != "text" {
t.Errorf("doc_type_kwd = %q, want %q", got, "text")
}
}
func TestBuildDOCXJSONSections_MixedWithList(t *testing.T) {
ir := `{"sections":[{"title":"","elements":[
{"type":"paragraph","content":[{"type":"text","text":"Preamble"}],"style":"Normal"},
{"type":"list","ordered":false,"items":[
{"content":[{"type":"paragraph","content":[{"type":"text","text":"Bullet A"}]}]},
{"content":[{"type":"paragraph","content":[{"type":"text","text":"Bullet B"}]}]}
],"level":0},
{"type":"paragraph","content":[{"type":"text","text":"Trailer"}],"style":"Normal"}
]}]}`
sections := buildDOCXJSONSections(ir)
if len(sections) != 4 {
t.Fatalf("got %d sections, want 4 (para + 2 list items + para)", len(sections))
}
wants := []string{"Preamble", "Bullet A", "Bullet B", "Trailer"}
for i, want := range wants {
if got, _ := sections[i]["text"].(string); got != want {
t.Errorf("section[%d].text = %q, want %q", i, got, want)
}
}
}
func TestBuildDOCXJSONSections_EmptySkipped(t *testing.T) {
ir := `{"sections":[{"title":"","elements":[
{"type":"paragraph","content":[{"type":"text","text":""}]},
{"type":"paragraph","content":[{"type":"text","text":"Only this matters"}]},
{"type":"table","rows":[]}
]}]}`
sections := buildDOCXJSONSections(ir)
if len(sections) != 1 {
t.Fatalf("got %d sections, want 1 (only non-empty paragraph)", len(sections))
}
if got, _ := sections[0]["text"].(string); got != "Only this matters" {
t.Errorf("text = %q, want %q", got, "Only this matters")
}
}
func TestDocxIRTableToHTML_Empty(t *testing.T) {
el := docxIRElement{Type: "table", Rows: []docxIRRow{}}
html := docxIRTableToHTML(el)
if html != "<table></table>" {
t.Errorf("empty table html = %q, want %q", html, "<table></table>")
}
}
func TestDocxIRTableToHTML_Single(t *testing.T) {
el := docxIRElement{
Type: "table",
Rows: []docxIRRow{{
Cells: []docxIRCell{{
Content: []docxIRElement{{
Type: "paragraph",
Content: json.RawMessage(`[{"type":"text","text":"hello"}]`),
}},
}},
}},
}
html := docxIRTableToHTML(el)
want := "<table><tr><td>hello</td></tr></table>"
if html != want {
t.Errorf("single cell html = %q, want %q", html, want)
}
}
func TestDocxIRTableToHTML_MultiRowCol(t *testing.T) {
cell := func(text string) docxIRCell {
return docxIRCell{
Content: []docxIRElement{{
Type: "paragraph",
Content: rawJSON([]docxIRRun{{Type: "text", Text: text}}),
}},
}
}
el := docxIRElement{
Type: "table",
Rows: []docxIRRow{
{Cells: []docxIRCell{cell("A1"), cell("B1")}},
{Cells: []docxIRCell{cell("A2"), cell("B2")}},
},
}
html := docxIRTableToHTML(el)
want := "<table><tr><td>A1</td><td>B1</td></tr><tr><td>A2</td><td>B2</td></tr></table>"
if html != want {
t.Errorf("multi cell html = %q, want %q", html, want)
}
}