[tika] branch branch_1x updated: TIKA-3382 -- improve writelimitreached handling in numerous parsers -- clean up PDFParser

[tallison]

This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch branch_1x
in repository https://gitbox.apache.org/repos/asf/tika.git


The following commit(s) were added to refs/heads/branch_1x by this push:
     new ba72c86  TIKA-3382 -- improve writelimitreached handling in numerous 
parsers -- clean up PDFParser
ba72c86 is described below

commit ba72c8625ee7e9cc3956e2b141c84ee7319c4f78
Author: tallison <talli...@apache.org>
AuthorDate: Mon May 3 18:06:01 2021 -0400

    TIKA-3382 -- improve writelimitreached handling in numerous parsers -- 
clean up PDFParser
---
 .../apache/tika/parser/pdf/AbstractPDF2XHTML.java    | 20 ++------------------
 .../java/org/apache/tika/parser/pdf/PDF2XHTML.java   | 11 -----------
 2 files changed, 2 insertions(+), 29 deletions(-)

diff --git 
a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java 
b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
index 2cc610e..1a4f768 100644
--- 
a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
+++ 
b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
@@ -88,6 +88,7 @@ import org.apache.pdfbox.tools.imageio.ImageIOUtil;
 import org.apache.pdfbox.util.Matrix;
 import org.apache.pdfbox.util.Vector;
 import org.apache.tika.exception.TikaException;
+import org.apache.tika.exception.WriteLimitReachedException;
 import org.apache.tika.extractor.EmbeddedDocumentExtractor;
 import org.apache.tika.extractor.EmbeddedDocumentUtil;
 import org.apache.tika.io.TemporaryResources;
@@ -426,8 +427,7 @@ class AbstractPDF2XHTML extends PDFTextStripper {
 
     void handleCatchableIOE(IOException e) throws IOException {
         if (config.getCatchIntermediateIOExceptions()) {
-
-            if (isWriteLimitReached(e, 0)) {
+            if (WriteLimitReachedException.isWriteLimitReached(e)) {
                 throw e;
             }
 
@@ -442,22 +442,6 @@ class AbstractPDF2XHTML extends PDFTextStripper {
         }
     }
 
-    boolean isWriteLimitReached(Throwable t, int depth) {
-        if (depth > MAX_RECURSION_DEPTH) {
-            return false;
-        }
-        if (t == null) {
-            return false;
-        }
-        if (t instanceof SAXException) {
-
-            String msg = t.getMessage();
-            if (msg != null && msg.contains("Your document contained more 
than")) {
-                return true;
-            }
-        }
-        return isWriteLimitReached(t.getCause(), depth + 1);
-    }
     void doOCROnCurrentPage() throws IOException, TikaException, SAXException {
         if (config.getOcrStrategy().equals(NO_OCR)) {
             return;
diff --git 
a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java 
b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
index f92fdfd..5f9e4b9 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/pdf/PDF2XHTML.java
@@ -116,22 +116,11 @@ class PDF2XHTML extends AbstractPDF2XHTML {
             }
         }
         if (pdf2XHTML.exceptions.size() > 0) {
-            tryWriteLimitReached(pdf2XHTML.exceptions);
             //throw the first
             throw new TikaException("Unable to extract PDF content", 
pdf2XHTML.exceptions.get(0));
         }
     }
 
-    private static void tryWriteLimitReached(List<IOException> exceptions) {
-        WriteOutContentHandler tmp = new WriteOutContentHandler();
-        for (IOException e : exceptions) {
-            if (tmp.isWriteLimitReached(e)) {
-
-            }
-
-        }
-    }
-
     @Override
     public void processPage(PDPage page) throws IOException {
         try {