fix: error when parsing tables with only headers in docx/pdf (#271)

2025-07-29 21:16:17 +08:00 · 2025-07-29 21:16:17 +08:00 · 02b4171576
parent 0d83a5e7bc
commit 02b4171576
1 changed files with 5 additions and 0 deletions
--- a/backend/infra/impl/document/parser/builtin/py_parser_protocol.go
+++ b/backend/infra/impl/document/parser/builtin/py_parser_protocol.go
@ -249,6 +249,11 @@ func formatTablesInDocument(input []*schema.Document) (output []*schema.Document
 				values = append(values, col.Name)
 			}
 			write(values)
+			if colOnly, err := document.GetDocumentColumnsOnly(doc); err != nil {
+				return nil, err
+			} else if colOnly {
+				break
+			}
 		}

 		data, err := document.GetDocumentColumnData(doc)