TIKA-4358 -- turn on extraction of incremental update metadata as def…

…ault (#2062) * TIKA-4358 -- turn on extraction of incremental update metadata as default
apache · Nov 21, 2024 · 45a16c4 · 45a16c4
1 parent ff9d722
commit 45a16c4
Show file tree

Hide file tree

Showing 4 changed files with 6 additions and 5 deletions.
diff --git a/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java b/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
@@ -342,7 +342,7 @@ private void configurePDFExtractSettings() {
             pdfParserConfig.setExtractIncrementalUpdateInfo(true);
             pdfParserConfig.setParseIncrementalUpdates(true);
             String warn = "As a convenience, TikaCLI has turned on extraction of\n" +
-                    "inline images and incremental updates for the PDFParser (TIKA-2374, " +
+                    "inline images and parsing of incremental updates for the PDFParser (TIKA-2374, " +
                     "TIKA-4017 and TIKA-4354).\n" +
                     "This is not the default behavior in Tika generally or in tika-server.";
             LOG.info(warn);

diff --git a/tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java b/tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java
@@ -219,7 +219,7 @@ public void testMetadataOutput() throws Exception {
     public void testJsonMetadataOutput() throws Exception {
         String json = getParamOutContent("--json", "--digest=MD2", resourcePrefix + "testJsonMultipleInts.html");
         //TIKA-1310
-        assertTrue(json.contains("\"fb:admins\":\"1,2,3,4\","));
+        assertTrue(json.contains("\"" + "fb:admins\":\"1,2,3,4\","));
         assertTrue(json.contains("\"X-TIKA:digest:MD2\":"));
     }
 

diff --git a/...ules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java b/...ules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
@@ -153,7 +153,7 @@ public ImageType getImageType() {
 
     private Renderer renderer;
 
-    private boolean extractIncrementalUpdateInfo = false;
+    private boolean extractIncrementalUpdateInfo = true;
 
     private boolean parseIncrementalUpdates = false;
 
@@ -876,7 +876,8 @@ public int getMaxIncrementalUpdates() {
     }
 
     /**
-     * The maximum number of incremental updates to parse.
+     * The maximum number of incremental updates to parse if
+     * {@link #setParseIncrementalUpdates(boolean)} is set to <code>true</code>
      *
      * @param maxIncrementalUpdates
      */

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
@@ -237,7 +237,7 @@ public String getPassword(Metadata metadata) {
         assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE));
         assertEquals("true", metadata.get("pdf:encrypted"));
         //pdf:encrypted, X-Parsed-By and Content-Type
-        assertEquals(5, metadata.names().length, "very little metadata should be parsed");
+        assertEquals(8, metadata.names().length, "very little metadata should be parsed");
         assertEquals(0, handler.toString().length());
     }