ben/coze-studio
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat(infra): integrate PaddleOCR's PP-StructureV3 as a document parser backend (#714)

Browse Source
This commit is contained in:
Lin Manhui
2025-08-13 16:37:42 +08:00
committed by GitHub
parent 708a6ed0c0
commit 6b60c07c22
30 changed files with 657 additions and 174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
backend/infra/impl/document/parser/builtin/parse_csv_test.go
View File

@@ -47,7 +47,7 @@ func TestParseCSV(t *testing.T) {
},
ChunkingStrategy: nil,
}
p1 := parseCSV(c1)
p1 := ParseCSV(c1)
docs, err := p1(ctx, r1, parser.WithExtraMeta(map[string]any{
"document_id": int64(123),
"knowledge_id": int64(456),
@@ -112,7 +112,7 @@ func TestParseCSV(t *testing.T) {
},
ChunkingStrategy: nil,
}
p2 := parseCSV(c2)
p2 := ParseCSV(c2)
docs, err = p2(ctx, r2, parser.WithExtraMeta(map[string]any{
"document_id": int64(123),
"knowledge_id": int64(456),
@@ -131,7 +131,7 @@ func TestParseCSVBadCases(t *testing.T) {
b, err := io.ReadAll(f)
assert.NoError(t, err)
pfn := parseCSV(&contract.Config{
pfn := ParseCSV(&contract.Config{
FileExtension: "csv",
ParsingStrategy: &contract.ParsingStrategy{
ExtractImage: true,
@@ -154,7 +154,7 @@ func TestParseCSVBadCases(t *testing.T) {
cols, err := document.GetDocumentColumns(resp[0])
assert.NoError(t, err)
cols[5].Nullable = false
npfn := parseCSV(&contract.Config{
npfn := ParseCSV(&contract.Config{
FileExtension: "csv",
ParsingStrategy: &contract.ParsingStrategy{
ExtractImage: true,