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

2025-08-13 16:37:42 +08:00
parent 708a6ed0c0
commit 6b60c07c22
30 changed files with 657 additions and 174 deletions
--- a/backend/infra/impl/document/parser/builtin/parse_markdown_test.go
+++ b/backend/infra/impl/document/parser/builtin/parse_markdown_test.go
@@ -37,7 +37,7 @@ func TestParseMarkdown(t *testing.T) {
 	mockStorage := ms.NewMockStorage(ctrl)
 	mockStorage.EXPECT().PutObject(gomock.Any(), gomock.Any(), gomock.Any()).Return(nil).AnyTimes()

-	pfn := parseMarkdown(&contract.Config{
+	pfn := ParseMarkdown(&contract.Config{
 		FileExtension: contract.FileExtensionMarkdown,
 		ParsingStrategy: &contract.ParsingStrategy{
 			ExtractImage: true,