repopulate new index 1 with language titles for sorting

srophe · Nov 20, 2024 · 2b721f1 · 2b721f1
1 parent efef676
commit 2b721f1
Showing 1 changed file with 24 additions and 25 deletions.
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
@@ -64,11 +64,10 @@ jobs:
 
       - name: Specify specific XML files and 25 per category 
         run: |
-          # find ./data/persons/tei -name '*.xml' | head -n 25 > xml_files.txt
-          # find ./data/places/tei -name '*.xml' | head -n 25 >> xml_files.txt
-          # find ./data/works/tei -name '*.xml' | head -n 25 > xml_files.txt
-          find ./data/bibl/tei -name '*.xml' | head -n 25 > xml_files.txt
-          
+          find ./data/persons/tei -name '*.xml' | head -n 25 > xml_files.txt
+          find ./data/places/tei -name '*.xml' | head -n 25 >> xml_files.txt
+          find ./data/works/tei -name '*.xml' | head -n 25 >> xml_files.txt
+          find ./data/bibl/tei -name '*.xml' | head -n 25 >> xml_files.txt
           find ./data/subjects/tei -name '*.xml' | head -n 25 >> xml_files.txt
 
           echo "./data/persons/tei/25.xml" >> xml_files.txt
@@ -120,7 +119,7 @@ jobs:
             # Extract the filename and create the index header for OpenSearch bulk format
             filename=$(basename ${file%.xml})
             echo "Processing $filename for JSON"
-            printf "{\"index\":{\"_index\":\"syriaca-index-6\",\"_id\":\"$type-$filename\"}}\n" >> bulk_data.json
+            printf "{\"index\":{\"_index\":\"syriaca-index-1\",\"_id\":\"$type-$filename\"}}\n" >> bulk_data.json
 
             # Apply XSLT for JSON conversion and append it to bulk_data.json directly
             java -jar saxon.jar -s:$file -xsl:json-stylesheet.xsl docType="$type" | tr -d '\n' >> bulk_data.json
@@ -167,7 +166,7 @@ jobs:
       # Step 7: Upload files to S3 
       - name: Upload JSON file to S3 
         run: |
-          aws s3 cp bulk_data.json s3://srophe-syriaca-front-end/json-data/advancedsearchfields/bulk_data_index_6.json
+          aws s3 cp bulk_data.json s3://srophe-syriaca-front-end/json-data/advancedsearchfields/bulk_data_index_1.json
         env:
           AWS_REGION: ${{ secrets.AWS_REGION }}
           AWS_ACCOUNT_ID: ${{ secrets.AWS_ACCOUNT_ID }}
@@ -195,23 +194,23 @@ jobs:
 
       # Step 8: Upload JSON data to OpenSearch 
 
-      # - name: JSON file to OpenSearch
+      - name: JSON file to OpenSearch
 
-      #   env:
-      #     OPENSEARCH_URL: ${{ secrets.OPENSEARCH_URL }}
-      #     OPENSEARCH_USER: ${{ secrets.OPENSEARCH_USER }}
-      #     OPENSEARCH_PASSWORD: ${{ secrets.OPENSEARCH_PASSWORD }}
-      #   run: |
-      #     RESPONSE=$(curl -s -o response.json -w "%{http_code}" -XPOST "$OPENSEARCH_URL/_bulk" \
-      #     -H "Content-Type: application/json" \
-      #     -u "$OPENSEARCH_USER:$OPENSEARCH_PASSWORD" \
-      #     --data-binary "@bulk_data.json")
-      #     echo "HTTP response code: $RESPONSE"
-      #     cat response.json
-
-      #     # Check for errors in the response
-      #     if grep -q '"errors":true' response.json; then
-      #       echo "Errors occurred during bulk upload"
-      #       exit 1
-      #     fi
+        env:
+          OPENSEARCH_URL: ${{ secrets.OPENSEARCH_URL }}
+          OPENSEARCH_USER: ${{ secrets.OPENSEARCH_USER }}
+          OPENSEARCH_PASSWORD: ${{ secrets.OPENSEARCH_PASSWORD }}
+        run: |
+          RESPONSE=$(curl -s -o response.json -w "%{http_code}" -XPOST "$OPENSEARCH_URL/_bulk" \
+          -H "Content-Type: application/json" \
+          -u "$OPENSEARCH_USER:$OPENSEARCH_PASSWORD" \
+          --data-binary "@bulk_data.json")
+          echo "HTTP response code: $RESPONSE"
+          cat response.json
+
+          # Check for errors in the response
+          if grep -q '"errors":true' response.json; then
+            echo "Errors occurred during bulk upload"
+            exit 1
+          fi