Merge pull request #70 from jamesvillarrubia/update-to-nlm-2.9.2_v2

Update to nlm 2.9.2 v2
nlmatics · Jul 26, 2024 · b3608fe · b3608fe
2 parents 465e6a1 + 39b1c1b
commit b3608fe
Show file tree

Hide file tree

Showing 4 changed files with 5 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -32,7 +32,7 @@ There are two ways to process these types of documents
 1. Install latest version of java from https://www.oracle.com/java/technologies/downloads/
 2. Run the tika server:
 ```
- java -jar <path_to_nlm_ingestor>/jars/tika-server-standard-nlm-modified-2.9.2_v1.jar
+java -jar <path_to_nlm_ingestor>/jars/tika-server-standard-nlm-modified-2.9.2_v2.jar
 ```
 3. Install the ingestor
 ```

diff --git a/jars/tika-server-standard-nlm-modified-2.9.2_v2.jar b/jars/tika-server-standard-nlm-modified-2.9.2_v2.jar
diff --git a/nlm_ingestor/file_parser/tika_parser.py b/nlm_ingestor/file_parser/tika_parser.py
@@ -16,7 +16,9 @@ def parse_to_html(self, filepath, do_ocr=False):
         # Turn off OCR by default
         timeout = 3000
         headers = {
-            "X-Tika-OCRskipOcr": "true"
+            "X-Tika-OCRskipOcr": "true",
+            "X-Tika-PDFOcrStrategy": "auto",
+            "X-Tika-PDFExtractFontNames": "true"
         }
         if do_ocr:
             headers = {

diff --git a/run.sh b/run.sh
@@ -1,4 +1,4 @@
 #!/bin/bash
 # latest version of java and a python environment where requirements are installed is required
-nohup java -jar jars/tika-server-standard-nlm-modified-2.9.2_v1.jar > /dev/null 2>&1 &
+nohup java -jar jars/tika-server-standard-nlm-modified-2.9.2_v2.jar > /dev/null 2>&1 &
 python -m nlm_ingestor.ingestion_daemon