CHANGES.txt

+Release 1.21 - 05/14/2019
+
+   * Add optional AUTO mode to OCR'ing of PDFs.  If tesseract is installed
+     and on the path, and this option is selected programmatically
+     or via TikaConfig(), the PDFParser will use heuristics to decide
+     whether or not to run OCR per page on PDFs. (TIKA-2749)
+
+   * The ZipContainerDetector's default behavior was changed to run
+     streaming detection up to its markLimit.  Users can get the
+     legacy behavior (spool-to-file/rely-on-underlying-file-in-TikaInputStream)
+     by setting markLimit=-1. The POIFSContainerDetector requires an underlying file;
+     it will try to spool the file to disk; if the file's length is > markLimit,
+     it will not attempt detection; set markLimit to -1 for legacy behavior (TIKA-2849).
+
+   * Upgrade PDFBox to 2.0.14 (TIKA-2834).
+
+   * Add CSV detection and replace TXTParser with TextAndCSVParser;
+     users can turn off CSV detection by excluding the TextAndCSVParser
+     and adding back the TXTParser via tika-config (TIKA-2833).
+
+   * Add a CSVParser.  CSV detection is currently based solely on filename
+     and/or information conveyed via Metadata (TIKA-2826).
+
+   * General upgrades: asm, bouncycastle, commons-codec, commons-lang3, cxf,
+     guava, h2, httpcomponents, jackcess, junrar, Lucene, mime4j, opennlp, parso,
+     sqlite-jdbc (provided), zstd-jni (provided) (TIKA-2824)
+
+   * Bundle xerces2 with tika-parsers (TIKA-2802).
+
+   * Upgrade jaxb to 2.3.2 (TIKA-2819).
+
+   * Upgrade jackson to 2.9.8 (TIKA-2717).
+
+   * Update tika-eval's common tokens lists (TIKA-2822).
+
+   * Handle bad tags in tika-eval more robustly (TIKA-2810).
+
+   * Add reports for tags in tika-eval (TIKA-2809).
+
+   * Extract text from SDT element within textboxes in .docx files (TIKA-2807).
+
+   * Try to handle truncated OOXML files more robustly (TIKA-2765).
+
 Release 1.20 - 12/17/2018
 
    * Upgrade to POI 4.0.1 (TIKA-2751).

debian/changelog

+tika (1.21-1) unstable; urgency=medium
+
+  * New upstream release
+    - Refreshed the patches
+    - New dependency on libprotobuf-java
+    - Ignore the build dependency on ossindex-maven-plugin
+    - Ignore the new dependency on jakarta.activation (not used)
+  * Standards-Version updated to 4.4.0
+
+ -- Emmanuel Bourg <ebourg@apache.org>  Thu, 11 Jul 2019 22:48:11 +0200
+
 tika (1.20-1) unstable; urgency=medium
 
   * New upstream release

debian/control

@@ -34,6 +34,7 @@ Build-Depends:
  libmaven-shade-plugin-java,
  libmetadata-extractor-java (>= 2.8~),
  libpdfbox2-java (>= 2.0.13-2~),
+ libprotobuf-java,
  librome-java (>= 1.6),
  libslf4j-java,
  libtagsoup-java,
@@ -41,7 +42,7 @@ Build-Depends:
  libvorbis-java (>= 0.8-3~),
  libxmpcore-java,
  maven-debian-helper (>= 2.0)
-Standards-Version: 4.3.0
+Standards-Version: 4.4.0
 Vcs-Git: https://salsa.debian.org/java-team/tika.git
 Vcs-Browser: https://salsa.debian.org/java-team/tika
 Homepage: http://tika.apache.org

debian/maven.ignoreRules

@@ -16,6 +16,7 @@ com.healthmarketscience.jackcess jackcess-encrypt * * * *
 com.levigo.jbig2 levigo-jbig2-imageio * * * *
 com.epam parso * * * *
 com.pff java-libpst * * * *
+com.sun.activation jakarta.activation * * * *
 de.thetaphi forbiddenapis * * * *
 edu.ucar cdm * * * *
 edu.ucar grib * * * *
@@ -47,5 +48,6 @@ org.codehaus.gmaven groovy-maven-plugin * * * *
 org.codehaus.mojo clirr-maven-plugin * * * *
 org.codehaus.mojo versions-maven-plugin * * * *
 org.opengis geoapi * * * *
+org.sonatype.ossindex.maven ossindex-maven-plugin * * * *
 org.xerial sqlite-jdbc * * * *
 org.mockito * * * * *

debian/patches/06-optional-parser-dependencies.patch

@@ -3,7 +3,7 @@ Author: Emmanuel Bourg <ebourg@apache.org>
 Forwarded: no
 --- a/tika-parsers/pom.xml
 +++ b/tika-parsers/pom.xml
-@@ -115,6 +115,7 @@
+@@ -119,6 +119,7 @@
        <groupId>org.gagravarr</groupId>
        <artifactId>vorbis-java-tika</artifactId>
        <version>${vorbis.version}</version>
@@ -11,7 +11,7 @@ Forwarded: no
        <exclusions>
          <exclusion>
            <groupId>org.apache.tika</groupId>
-@@ -135,26 +136,31 @@
+@@ -139,26 +140,31 @@
        <groupId>org.tallison</groupId>
        <artifactId>jmatio</artifactId>
        <version>1.5</version>
@@ -43,7 +43,7 @@ Forwarded: no
      </dependency>
      <dependency>
        <groupId>com.epam</groupId>
-@@ -177,11 +183,13 @@
+@@ -181,11 +187,13 @@
        <groupId>commons-codec</groupId>
        <artifactId>commons-codec</artifactId>
        <version>${codec.version}</version>
@@ -57,7 +57,7 @@ Forwarded: no
        <exclusions>
          <exclusion>
            <groupId>commons-logging</groupId>
-@@ -193,6 +201,7 @@
+@@ -197,6 +205,7 @@
        <groupId>org.apache.pdfbox</groupId>
        <artifactId>pdfbox-tools</artifactId>
        <version>${pdfbox.version}</version>
@@ -65,7 +65,7 @@ Forwarded: no
        <exclusions>
          <exclusion>
            <groupId>commons-logging</groupId>
-@@ -208,6 +217,7 @@
+@@ -212,6 +221,7 @@
        <groupId>org.apache.pdfbox</groupId>
        <artifactId>jempbox</artifactId>
        <version>${jempbox.version}</version>
@@ -73,7 +73,7 @@ Forwarded: no
      </dependency>
      <!-- TIKA-370: PDFBox declares the Bouncy Castle dependencies
           as optional, but we prefer to have them always to avoid
-@@ -216,16 +226,19 @@
+@@ -220,16 +230,19 @@
        <groupId>org.bouncycastle</groupId>
        <artifactId>bcmail-jdk15on</artifactId>
        <version>${bouncycastle.version}</version>
@@ -93,7 +93,7 @@ Forwarded: no
        <exclusions>
          <exclusion>
            <groupId>commons-codec</groupId>
-@@ -237,11 +250,13 @@
+@@ -241,11 +254,13 @@
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-scratchpad</artifactId>
        <version>${poi.version}</version>
@@ -107,23 +107,23 @@ Forwarded: no
        <exclusions>
          <exclusion>
            <groupId>stax</groupId>
-@@ -257,6 +272,7 @@
+@@ -261,6 +276,7 @@
        <groupId>com.healthmarketscience.jackcess</groupId>
        <artifactId>jackcess</artifactId>
-       <version>2.1.12</version>
+       <version>3.0.1</version>
 +      <optional>true</optional>
        <exclusions>
          <exclusion>
-           <groupId>commons-logging</groupId>
-@@ -268,6 +284,7 @@
+           <groupId>org.apache.commons</groupId>
+@@ -276,6 +292,7 @@
        <groupId>com.healthmarketscience.jackcess</groupId>
        <artifactId>jackcess-encrypt</artifactId>
-       <version>2.1.4</version>
+       <version>3.0.0</version>
 +      <optional>true</optional>
        <exclusions>
          <exclusion>
            <groupId>org.bouncycastle</groupId>
-@@ -285,31 +302,37 @@
+@@ -293,31 +310,37 @@
        <groupId>org.ccil.cowan.tagsoup</groupId>
        <artifactId>tagsoup</artifactId>
        <version>1.2.1</version>
@@ -132,7 +132,7 @@ Forwarded: no
      <dependency>
        <groupId>org.ow2.asm</groupId>
        <artifactId>asm</artifactId>
-       <version>7.0</version>
+       <version>7.1</version>
 +      <optional>true</optional>
      </dependency>
      <dependency>
@@ -161,7 +161,7 @@ Forwarded: no
        <exclusions>
          <exclusion>
            <groupId>org.jdom</groupId>
-@@ -321,16 +344,19 @@
+@@ -329,16 +352,19 @@
        <groupId>org.gagravarr</groupId>
        <artifactId>vorbis-java-core</artifactId>
        <version>${vorbis.version}</version>
@@ -181,7 +181,7 @@ Forwarded: no
        <exclusions>
          <exclusion>
            <groupId>commons-io</groupId>
-@@ -344,11 +370,13 @@
+@@ -352,11 +378,13 @@
        <groupId>com.pff</groupId>
        <artifactId>java-libpst</artifactId>
        <version>0.8.1</version>
@@ -190,12 +190,12 @@ Forwarded: no
      <dependency>
        <groupId>com.github.junrar</groupId>
        <artifactId>junrar</artifactId>
-       <version>2.0.0</version>
+       <version>4.0.0</version>
 +      <optional>true</optional>
        <exclusions>
          <exclusion>
            <groupId>commons-logging</groupId>
-@@ -383,6 +411,7 @@
+@@ -391,6 +419,7 @@
        <artifactId>commons-exec</artifactId>
        <version>${commonsexec.version}</version>
        <scope>compile</scope>
@@ -203,15 +203,15 @@ Forwarded: no
      </dependency>
  
      <!-- Provided dependencies -->
-@@ -397,6 +426,7 @@
+@@ -405,6 +434,7 @@
        <groupId>org.apache.opennlp</groupId>
        <artifactId>opennlp-tools</artifactId>
-       <version>1.9.0</version>
+       <version>1.9.1</version>
 +      <optional>true</optional>
      </dependency>
  
      <dependency>
-@@ -409,6 +439,7 @@
+@@ -417,6 +447,7 @@
        <groupId>com.googlecode.json-simple</groupId>
        <artifactId>json-simple</artifactId>
        <version>1.1.1</version>
@@ -219,7 +219,7 @@ Forwarded: no
        <exclusions>
          <exclusion>
            <groupId>junit</groupId>
-@@ -426,11 +457,13 @@
+@@ -434,11 +465,13 @@
        <groupId>com.github.openjson</groupId>
        <artifactId>openjson</artifactId>
        <version>1.0.10</version>
@@ -233,7 +233,15 @@ Forwarded: no
      </dependency>
  
      <!-- logging dependencies -->
-@@ -594,6 +627,7 @@
+@@ -551,6 +584,7 @@
+       <groupId>com.google.protobuf</groupId>
+       <artifactId>protobuf-java</artifactId>
+       <version>3.7.1</version>
++      <optional>true</optional>
+     </dependency>
+     <dependency>
+       <groupId>edu.ucar</groupId>
+@@ -633,6 +667,7 @@
        <groupId>org.apache.commons</groupId>
        <artifactId>commons-csv</artifactId>
        <version>1.6</version>

debian/patches/09-ignore-unsupported-parsers.patch

@@ -3,7 +3,7 @@ Author: Emmanuel Bourg <ebourg@apache.org>
 Forwarded: not-needed
 --- a/tika-parsers/pom.xml
 +++ b/tika-parsers/pom.xml
-@@ -918,6 +918,40 @@
+@@ -962,6 +962,40 @@
            </execution>
          </executions>
        </plugin>

pom.xml

@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.20</version>
+    <version>1.21</version>
     <relativePath>tika-parent/pom.xml</relativePath>
   </parent>
 

tika-app/pom.xml

@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.20</version>
+    <version>1.21</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 

tika-app/src/test/java/org/apache/tika/extractor/TestEmbeddedDocumentUtil.java

@@ -38,9 +38,9 @@ public class TestEmbeddedDocumentUtil {
         Parser p = new AutoDetectParser();
         ParseContext parseContext = new ParseContext();
         parseContext.set(Parser.class, p);
-        Parser txtParser = EmbeddedDocumentUtil.tryToFindExistingLeafParser(org.apache.tika.parser.txt.TXTParser.class, parseContext);
+        Parser txtParser = EmbeddedDocumentUtil.tryToFindExistingLeafParser(org.apache.tika.parser.csv.TextAndCSVParser.class, parseContext);
         assertNotNull(txtParser);
-        assertEquals(org.apache.tika.parser.txt.TXTParser.class, txtParser.getClass());
+        assertEquals(org.apache.tika.parser.csv.TextAndCSVParser.class, txtParser.getClass());
 
     }
 
@@ -51,8 +51,8 @@ public class TestEmbeddedDocumentUtil {
                 new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.TEXT, -1));
         ParseContext parseContext = new ParseContext();
         parseContext.set(Parser.class, wrapper);
-        Parser txtParser = EmbeddedDocumentUtil.tryToFindExistingLeafParser(org.apache.tika.parser.txt.TXTParser.class, parseContext);
+        Parser txtParser = EmbeddedDocumentUtil.tryToFindExistingLeafParser(org.apache.tika.parser.csv.TextAndCSVParser.class, parseContext);
         assertNotNull(txtParser);
-        assertEquals(org.apache.tika.parser.txt.TXTParser.class, txtParser.getClass());
+        assertEquals(org.apache.tika.parser.csv.TextAndCSVParser.class, txtParser.getClass());
     }
 }

tika-batch/pom.xml

@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.20</version>
+    <version>1.21</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
@@ -104,23 +104,6 @@
 
   <build>
     <plugins>
-      <plugin>
-        <artifactId>maven-remote-resources-plugin</artifactId>
-        <version>1.5</version>
-        <executions>
-          <execution>
-            <goals>
-              <goal>bundle</goal>
-            </goals>
-          </execution>
-        </executions>
-        <configuration>
-          <includes>
-            <include>**/*.xml</include>
-          </includes>
-        </configuration>
-      </plugin>
-
       <plugin>
         <groupId>org.apache.felix</groupId>
         <artifactId>maven-bundle-plugin</artifactId>

tika-batch/src/main/java/org/apache/tika/batch/BatchProcess.java

@@ -139,7 +139,13 @@ public class BatchProcess implements Callable<ParallelFileProcessingResult> {
         try {
             int numConsumers = consumersManager.getConsumers().size();
             // fileResourceCrawler, statusReporter, the Interrupter, timeoutChecker
-            int numNonConsumers = 4;
+            int numNonConsumers = 2;
+            if (interrupter != null) {
+                numNonConsumers++;
+            }
+            if (reporter != null) {
+                numNonConsumers++;
+            }
 
             ExecutorService ex = Executors.newFixedThreadPool(numConsumers
                     + numNonConsumers);
@@ -174,9 +180,13 @@ public class BatchProcess implements Callable<ParallelFileProcessingResult> {
         LOG.info("BatchProcess starting up");
 
         state.start = System.currentTimeMillis();
+        if (interrupter != null) {
             completionService.submit(interrupter);
-        completionService.submit(fileResourceCrawler);
+        }
+        if (reporter != null) {
             completionService.submit(reporter);
+        }
+        completionService.submit(fileResourceCrawler);
         completionService.submit(timeoutChecker);
 
         for (FileResourceConsumer consumer : consumersManager.getConsumers()) {
@@ -237,7 +247,9 @@ public class BatchProcess implements Callable<ParallelFileProcessingResult> {
         CompletionService<IFileProcessorFutureResult> completionService,
         TimeoutChecker timeoutChecker, State state) {
 
+        if (reporter != null) {
             reporter.setIsShuttingDown(true);
+        }
         int added = fileResourceCrawler.getAdded();
         int considered = fileResourceCrawler.getConsidered();
 

tika-batch/src/main/java/org/apache/tika/batch/builders/BatchProcessBuilder.java

@@ -131,10 +131,13 @@ public class BatchProcessBuilder {
         //build crawler
         crawler = buildCrawler(queue, keyNodes.get("crawler"), runtimeAttributes);
 
+        if (keyNodes.containsKey(reporter)) {
             reporter = buildReporter(crawler, consumersManager, keyNodes.get("reporter"), runtimeAttributes);
+        }
 
+        if (keyNodes.containsKey("interrupter")) {
             interrupter = buildInterrupter(keyNodes.get("interrupter"), pauseOnEarlyTerminationMillis, runtimeAttributes);
-
+        }
         BatchProcess proc = new BatchProcess(
                 crawler, consumersManager, reporter, interrupter);
 

tika-bundle/pom.xml

@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.20</version>
+    <version>1.21</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 
@@ -238,6 +238,9 @@
               com.adobe.xmp.properties;resolution:=optional,
               com.github.luben.zstd;resolution:=optional,
               com.github.openjson;resolution:=optional,
+              com.google.common.util.concurrent.internal;resolution:=optional,
+              com.google.errorprone.annotations;resolution:=optional,
+              com.google.errorprone.annotations.concurrent;resolution:=optional,
               com.google.protobuf;resolution:=optional,
               com.ibm.icu.text;resolution:=optional,
               com.parso;resolution:=optional,
@@ -327,6 +330,7 @@
               org.bouncycastle.operator.bc;resolution:=optional,
               org.bouncycastle.tsp;resolution:=optional,
               org.brotli.dec;resolution:=optional,
+              org.checkerframework.checker.nullness.qual;resolution:=optional,
               org.cyberneko.html.xercesbridge;resolution:=optional,
               org.etsi.uri.x01903.v14;resolution:=optional,
               org.ibex.nestedvm;resolution:=optional,

tika-core/pom.xml

@@ -25,7 +25,7 @@
   <parent>
     <groupId>org.apache.tika</groupId>
     <artifactId>tika-parent</artifactId>
-    <version>1.20</version>
+    <version>1.21</version>
     <relativePath>../tika-parent/pom.xml</relativePath>
   </parent>
 

tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentUtil.java

@@ -269,9 +269,7 @@ public class EmbeddedDocumentUtil implements Serializable {
     }
 
     private static Parser findInComposite(CompositeParser p, Class clazz, ParseContext context) {
-        Map<MediaType, Parser> map = p.getParsers(context);
-        for (Map.Entry<MediaType, Parser> e : map.entrySet()) {
-            Parser candidate = e.getValue();
+        for (Parser candidate : p.getAllComponentParsers()) {
             if (equals(candidate, clazz)) {
                 return candidate;
             }

tika-core/src/main/java/org/apache/tika/io/BoundedInputStream.java

+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.tika.io;
+
+import java.io.IOException;
+import java.io.InputStream;
+
+/**
+ * Very slight modification of Commons' BoundedInputStream
+ * so that we can figure out if this hit the bound or not.
+ */
+public class BoundedInputStream extends InputStream {
+
+
+    private final static int EOF = -1;
+    private final long max;
+    private final InputStream in;
+    private long pos;
+
+    public BoundedInputStream(long max, InputStream in) {
+        this.max = max;
+        this.in = in;
+    }
+
+    @Override
+    public int read() throws IOException {
+        if (max >= 0 && pos >= max) {
+            return EOF;
+        }
+        final int result = in.read();
+        pos++;
+        return result;
+    }
+
+    /**
+     * Invokes the delegate's <code>read(byte[])</code> method.
+     *
+     * @param b the buffer to read the bytes into
+     * @return the number of bytes read or -1 if the end of stream or
+     * the limit has been reached.
+     * @throws IOException if an I/O error occurs
+     */
+    @Override
+    public int read(final byte[] b) throws IOException {
+        return this.read(b, 0, b.length);
+    }
+
+    /**
+     * Invokes the delegate's <code>read(byte[], int, int)</code> method.
+     *
+     * @param b   the buffer to read the bytes into
+     * @param off The start offset
+     * @param len The number of bytes to read
+     * @return the number of bytes read or -1 if the end of stream or
+     * the limit has been reached.
+     * @throws IOException if an I/O error occurs
+     */
+    @Override
+    public int read(final byte[] b, final int off, final int len) throws IOException {
+        if (max >= 0 && pos >= max) {
+            return EOF;
+        }
+        final long maxRead = max >= 0 ? Math.min(len, max - pos) : len;
+        final int bytesRead = in.read(b, off, (int) maxRead);
+
+        if (bytesRead == EOF) {
+            return EOF;
+        }
+
+        pos += bytesRead;
+        return bytesRead;
+    }
+
+    /**
+     * Invokes the delegate's <code>skip(long)</code> method.
+     *
+     * @param n the number of bytes to skip
+     * @return the actual number of bytes skipped
+     * @throws IOException if an I/O error occurs
+     */
+    @Override
+    public long skip(final long n) throws IOException {
+        final long toSkip = max >= 0 ? Math.min(n, max - pos) : n;
+        final long skippedBytes = in.skip(toSkip);
+        pos += skippedBytes;
+        return skippedBytes;
+    }
+
+    @Override
+    public void reset() throws IOException {
+        in.reset();
+        pos = 0;
+    }
+
+    @Override
+    public void mark(int readLimit) {
+        in.mark(readLimit);
+    }
+
+    public boolean hasHitBound() {
+        return pos >= max;
+    }
+}
+

tika-core/src/main/java/org/apache/tika/io/IOUtils.java

@@ -1183,4 +1183,35 @@ public class IOUtils {
         return (ch2 == -1);
     }
 
+    /**
+     * Reads bytes from an input stream.
+     * This implementation guarantees that it will read as many bytes
+     * as possible before giving up; this may not always be the case for
+     * subclasses of {@link InputStream}.
+     *
+     * @param input where to read input from
+     * @param buffer destination
+     * @param offset initial offset into buffer
+     * @param length length to read, must be >= 0
+     * @return actual length read; may be less than requested if EOF was reached
+     * @throws IOException if a read error occurs
+     * @since 2.2
+     */
+    public static int read(final InputStream input, final byte[] buffer, final int offset, final int length)
+            throws IOException {
+        if (length < 0) {
+            throw new IllegalArgumentException("Length must not be negative: " + length);
+        }
+        int remaining = length;
+        while (remaining > 0) {
+            final int location = length - remaining;
+            final int count = input.read(buffer, offset + location, remaining);
+            if (count == -1) { // EOF
+                break;
+            }
+            remaining -= count;
+        }
+        return length - remaining;
+    }
+
 }

tika-core/src/main/java/org/apache/tika/io/TikaInputStream.java

@@ -578,14 +578,45 @@ public class TikaInputStream extends TaggedInputStream {
         return path != null;
     }
 
+
+    /**
+     * If the user created this TikaInputStream with a file,
+     * the original file will be returned.  If not, the entire stream
+     * will be spooled to a temporary file which will be deleted
+     * upon the close of this TikaInputStream
+     * @return
+     * @throws IOException
+     */
     public Path getPath() throws IOException {
+        return getPath(-1);
+    }
+
+    /**
+     *
+     * @param maxBytes if this is less than 0 and if an underlying file doesn't already exist,
+     *                 the full file will be spooled to disk
+     * @return the original path used in the initialization of this TikaInputStream,
+     * a temporary file if the stream was shorter than <code>maxBytes</code>, or <code>null</code>
+     * if the underlying stream was longer than maxBytes.
+     * @throws IOException
+     */
+    public Path getPath(int maxBytes) throws IOException {
         if (path == null) {
             if (position > 0) {
                 throw new IOException("Stream is already being read");
             } else {
-                // Spool the entire stream into a temporary file
                 path = tmp.createTempFile();
+                if (maxBytes > -1) {
+                    try (InputStream lookAhead = new LookaheadInputStream(in, maxBytes)) {
+                        Files.copy(lookAhead, path, REPLACE_EXISTING);
+                        if (Files.size(path) >= maxBytes) {
+                            return null;
+                        }
+                    }
+                } else {
+                    // Spool the entire stream into a temporary file
                     Files.copy(in, path, REPLACE_EXISTING);
+                }
 
                 // Create a new input stream and make sure it'll get closed
                 InputStream newStream = Files.newInputStream(path);

tika-core/src/main/java/org/apache/tika/metadata/Metadata.java

@@ -407,6 +407,45 @@ public class Metadata implements CreativeCommons, Geographic, HttpHeaders,
         set(property, Integer.toString(value));
     }
 
+    /**
+     * Adds the integer value of the identified metadata property.
+     *
+     * @since Apache Tika 1.21
+     * @param property seq integer property definition
+     * @param value    property value
+     */
+    public void add(Property property, int value) {
+        if(property.getPrimaryProperty().getPropertyType() != PropertyType.SEQ) {
+            throw new PropertyTypeException(PropertyType.SEQ, property.getPrimaryProperty().getPropertyType());
+        }
+        if(property.getPrimaryProperty().getValueType() != Property.ValueType.INTEGER) {
+            throw new PropertyTypeException(Property.ValueType.INTEGER, property.getPrimaryProperty().getValueType());
+        }
+        add(property, Integer.toString(value));
+    }
+
+    /**
+     * Gets the array of ints of the identified "seq" integer metadata property.
+     *
+     * @since Apache Tika 1.21
+     * @param property seq integer property definition
+     * @return array of ints
+     */
+    public int[] getIntValues(Property property) {
+        if(property.getPrimaryProperty().getPropertyType() != PropertyType.SEQ) {
+            throw new PropertyTypeException(PropertyType.SEQ, property.getPrimaryProperty().getPropertyType());
+        }
+        if(property.getPrimaryProperty().getValueType() != Property.ValueType.INTEGER) {
+            throw new PropertyTypeException(Property.ValueType.INTEGER, property.getPrimaryProperty().getValueType());
+        }
+        String[] vals = getValues(property);
+        int[] ret = new int[vals.length];
+        for (int i = 0; i < vals.length; i++) {
+            ret[i] = Integer.parseInt(vals[i]);
+        }
+        return ret;
+    }
+
     /**
      * Sets the real or rational value of the identified metadata property.
      *

tika-core/src/main/java/org/apache/tika/metadata/PDF.java

@@ -70,4 +70,9 @@ public interface PDF {
      * in the document: on document open, before close, etc.
      */
     Property ACTION_TRIGGER = Property.internalText(PDF_PREFIX+"actionTrigger");
+
+    Property CHARACTERS_PER_PAGE = Property.internalIntegerSequence(PDF_PREFIX+"charsPerPage");
+
+    Property UNMAPPED_UNICODE_CHARS_PER_PAGE =
+            Property.internalIntegerSequence(PDF_PREFIX+"unmappedUnicodeCharsPerPage");
 }