[tika] 01/02: improve htmlparser

[ta...@apache.org]

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

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

commit 66417f619ba430f8c9e8ab0d903ebfecf936b071
Author: TALLISON <ta...@apache.org>
AuthorDate: Fri Jul 6 11:09:27 2018 -0400

    improve htmlparser
---
 .../java/org/apache/tika/io/TikaInputStream.java   | 11 +++++++++-
 .../org/apache/tika/parser/html/HtmlParser.java    | 25 ++++++++++++++++++++++
 2 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java b/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java
index 785acc7..96f922f 100644
--- a/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java
+++ b/tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java
@@ -502,6 +502,8 @@ public class TikaInputStream extends TaggedInputStream {
      */
     private Object openContainer;
 
+    private int consecutiveEOFs = 0;
+
     /**
      * Creates a TikaInputStream instance. This private constructor is used
      * by the static factory methods based on the available information.
@@ -718,6 +720,7 @@ public class TikaInputStream extends TaggedInputStream {
         super.reset();
         position = mark;
         mark = -1;
+        consecutiveEOFs = 0;
     }
 
     @Override
@@ -735,9 +738,15 @@ public class TikaInputStream extends TaggedInputStream {
     }
 
     @Override
-    protected void afterRead(int n) {
+    protected void afterRead(int n) throws IOException {
         if (n != -1) {
             position += n;
+        } else {
+            consecutiveEOFs++;
+            if (consecutiveEOFs > 1000) {
+                throw new IOException("Read too many -1 (EOFs); there could be an infinite loop." +
+                        "If you think your file is not corrupt, please open an issue on Tika's JIRA");
+            }
         }
     }
 
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
index a1ef0da..adf591a 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
@@ -29,6 +29,8 @@ import org.apache.tika.config.Field;
 import org.apache.tika.detect.AutoDetectReader;
 import org.apache.tika.detect.EncodingDetector;
 import org.apache.tika.exception.TikaException;
+import org.apache.tika.io.TemporaryResources;
+import org.apache.tika.io.TikaInputStream;
 import org.apache.tika.metadata.Metadata;
 import org.apache.tika.mime.MediaType;
 import org.apache.tika.parser.AbstractEncodingDetectorParser;
@@ -40,6 +42,8 @@ import org.slf4j.LoggerFactory;
 import org.xml.sax.ContentHandler;
 import org.xml.sax.SAXException;
 
+import javax.swing.text.AbstractDocument;
+
 /**
  * HTML parser. Uses TagSoup to turn the input document to HTML SAX events,
  * and post-processes the events to produce XHTML and metadata expected by
@@ -90,6 +94,27 @@ public class HtmlParser extends AbstractEncodingDetectorParser {
             Metadata metadata, ParseContext context)
             throws IOException, SAXException, TikaException {
 
+        TemporaryResources tmp = null;
+        try {
+            if (!TikaInputStream.isTikaInputStream(stream)) {
+                tmp = new TemporaryResources();
+                stream = TikaInputStream.get(stream, tmp);
+            }
+            //AutoDetectReader can throw exceptions during
+            //initialization.  If we just created a
+            //TemporaryResources, we need to make sure to close it.
+            parseImpl(stream, handler, metadata, context);
+        } finally {
+            if (tmp != null) {
+                tmp.close();
+            }
+        }
+
+    }
+
+
+    private void parseImpl(InputStream stream, ContentHandler handler,
+            Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
         // Automatically detect the character encoding
         try (AutoDetectReader reader = new AutoDetectReader(new CloseShieldInputStream(stream),
                 metadata, getEncodingDetector(context))) {