Additional header required to get style tags for visual processing.

nlmatics · Jun 12, 2024 · 436d0fc · 436d0fc
1 parent 21bc8fe
commit 436d0fc
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/nlm_ingestor/file_parser/tika_parser.py b/nlm_ingestor/file_parser/tika_parser.py
@@ -23,6 +23,7 @@ def parse_to_html(self, filepath, do_ocr=False):
                 "X-Tika-OCRskipOcr": "false",
                 "X-Tika-OCRoutputType": "hocr",
                 "X-Tika-Timeout-Millis": str(100 * timeout),
+                "X-Tika-PDFOcrStrategy": "ocr_only",
                 "X-Tika-OCRtimeoutSeconds": str(timeout),
             }