TIKA-4171 -- fix regression when field names are missing in the XFAEx…

…tractor (#1679)
apache · Mar 25, 2024 · a323ee5 · a323ee5
1 parent d3553b3
commit a323ee5
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 1 deletion.
diff --git a/...modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/XFAExtractor.java b/...modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/XFAExtractor.java
@@ -123,6 +123,9 @@ void extract(InputStream xfaIs, XHTMLContentHandler xhtml, Metadata m, ParseCont
                     (field.toolTip == null || field.toolTip.trim().length() == 0) ? fieldName :
                             field.toolTip;
             String[] fieldValues = pdfObjRToValues.getValues(fieldName);
+            if (fieldValues.length == 0) {
+                fieldValues = new String[]{""};
+            }
             for (String fieldValue : fieldValues) {
                 AttributesImpl attrs = new AttributesImpl();
                 attrs.addAttribute("", "fieldName", "fieldName", "CDATA", fieldName);

diff --git a/...odules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java b/...odules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
@@ -986,7 +986,7 @@ public void testXFAExtractionBasic() throws Exception {
         while (matcher.find()) {
             listItems++;
         }
-        assertEquals(24, listItems);
+        assertEquals(27, listItems);
     }
 
     @Test