vmario/docs
1
0
Fork 0
mirror of https://github.com/sismics/docs.git synced 2024-11-22 14:07:55 +01:00
Code Issues Packages Projects Releases Wiki Activity

Closes #59: Use TwelveMonkeys' ImageIO plugin for JPEG

Browse Source
This commit is contained in:
jendib 2016-01-24 15:44:40 +01:00
parent 456fc5b991
commit 3172a5f216
9 changed files with 84 additions and 118 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -60,7 +60,6 @@ or download the sources from GitHub.
From the `docs-parent` directory: From the `docs-parent` directory:
mvn -Pinit validate -N
mvn clean -DskipTests install mvn clean -DskipTests install
#### Run a stand-alone version #### Run a stand-alone version

25
docs-core/pom.xml
View File

@ -113,11 +113,6 @@
<artifactId>bcprov-jdk15on</artifactId> <artifactId>bcprov-jdk15on</artifactId>
</dependency> </dependency>
<dependency>
<groupId>com.levigo.jbig2</groupId>
<artifactId>levigo-jbig2-imageio</artifactId>
</dependency>
<dependency> <dependency>
<groupId>fr.opensagres.xdocreport</groupId> <groupId>fr.opensagres.xdocreport</groupId>
<artifactId>org.odftoolkit.odfdom.converter.pdf</artifactId> <artifactId>org.odftoolkit.odfdom.converter.pdf</artifactId>
@ -127,16 +122,26 @@
<groupId>fr.opensagres.xdocreport</groupId> <groupId>fr.opensagres.xdocreport</groupId>
<artifactId>org.apache.poi.xwpf.converter.pdf</artifactId> <artifactId>org.apache.poi.xwpf.converter.pdf</artifactId>
</dependency> </dependency>
<!-- OCR dependencies -->
<dependency> <dependency>
<groupId>jna</groupId> <groupId>net.java.dev.jna</groupId>
<artifactId>jna</artifactId> <artifactId>jna</artifactId>
</dependency> </dependency>
<!-- ImageIO plugins -->
<dependency>
<groupId>com.levigo.jbig2</groupId>
<artifactId>levigo-jbig2-imageio</artifactId>
</dependency>
<dependency>
<groupId>com.twelvemonkeys.imageio</groupId>
<artifactId>imageio-jpeg</artifactId>
</dependency>
<dependency> <dependency>
<groupId>jai</groupId> <groupId>com.github.jai-imageio</groupId>
<artifactId>imageio</artifactId> <artifactId>jai-imageio-core</artifactId>
</dependency> </dependency>
<!-- Test dependencies --> <!-- Test dependencies -->

26
docs-core/src/main/java/com/sismics/tess4j/ImageIOHelper.java
View File

@ -38,9 +38,9 @@ import javax.imageio.stream.ImageOutputStream;
import org.w3c.dom.NodeList; import org.w3c.dom.NodeList;
import com.sun.media.imageio.plugins.tiff.TIFFImageWriteParam; import com.github.jaiimageio.impl.plugins.tiff.TIFFImageReaderSpi;
import com.sun.media.imageioimpl.plugins.tiff.TIFFImageReaderSpi; import com.github.jaiimageio.impl.plugins.tiff.TIFFImageWriterSpi;
import com.sun.media.imageioimpl.plugins.tiff.TIFFImageWriterSpi; import com.github.jaiimageio.plugins.tiff.TIFFImageWriteParam;
public class ImageIOHelper { public class ImageIOHelper {
@ -51,26 +51,26 @@ public class ImageIOHelper {
* Gets pixel data of an * Gets pixel data of an
* <code>IIOImage</code> object. * <code>IIOImage</code> object.
* *
* @param image an * @param oimage an
* <code>IIOImage</code> object * <code>IIOImage</code> object
* @return a byte buffer of pixel data * @return a byte buffer of pixel data
* @throws Exception * @throws Exception
*/ */
public static ByteBuffer getImageByteBuffer(IIOImage image) throws IOException { public static ByteBuffer getImageByteBuffer(BufferedImage oimage) throws IOException {
//Set up the writeParam // Get tif writer and set output to file
TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.US);
tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED);
//Get tif writer and set output to file
ImageWriter writer = new TIFFImageWriterSpi().createWriterInstance(); ImageWriter writer = new TIFFImageWriterSpi().createWriterInstance();
//Get the stream metadata // Set up the writeParam
// We are using the old JAI ImageIO plugin, because for some reason, OCR don't work with TwelveMonkeys' plugin
ImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.US);
tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED);
// Get the stream metadata
IIOMetadata streamMetadata = writer.getDefaultStreamMetadata(tiffWriteParam); IIOMetadata streamMetadata = writer.getDefaultStreamMetadata(tiffWriteParam);
ByteArrayOutputStream outputStream = new ByteArrayOutputStream(); ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
ImageOutputStream ios = ImageIO.createImageOutputStream(outputStream); ImageOutputStream ios = ImageIO.createImageOutputStream(outputStream);
writer.setOutput(ios); writer.setOutput(ios);
writer.write(streamMetadata, new IIOImage(image.getRenderedImage(), null, null), tiffWriteParam); writer.write(streamMetadata, new IIOImage(oimage, null, null), tiffWriteParam);
writer.dispose(); writer.dispose();
// Read the writed image // Read the writed image

17
docs-core/src/main/java/com/sismics/tess4j/Tesseract.java
View File

@ -17,7 +17,6 @@ package com.sismics.tess4j;
import java.awt.Rectangle; import java.awt.Rectangle;
import java.awt.image.BufferedImage; import java.awt.image.BufferedImage;
import java.awt.image.RenderedImage;
import java.io.IOException; import java.io.IOException;
import java.nio.ByteBuffer; import java.nio.ByteBuffer;
import java.util.ArrayList; import java.util.ArrayList;
@ -25,8 +24,6 @@ import java.util.Enumeration;
import java.util.List; import java.util.List;
import java.util.Properties; import java.util.Properties;
import javax.imageio.IIOImage;
import com.sun.jna.Pointer; import com.sun.jna.Pointer;
/** /**
@ -169,9 +166,8 @@ public class Tesseract {
* @throws TesseractException * @throws TesseractException
*/ */
public String doOCR(BufferedImage bi, Rectangle rect) throws TesseractException { public String doOCR(BufferedImage bi, Rectangle rect) throws TesseractException {
IIOImage oimage = new IIOImage(bi, null, null); List<BufferedImage> imageList = new ArrayList<BufferedImage>();
List<IIOImage> imageList = new ArrayList<IIOImage>(); imageList.add(bi);
imageList.add(oimage);
return doOCR(imageList, rect); return doOCR(imageList, rect);
} }
@ -179,23 +175,22 @@ public class Tesseract {
* Performs OCR operation. * Performs OCR operation.
* *
* @param imageList a list of * @param imageList a list of
* <code>IIOImage</code> objects * <code>BufferedImage</code> objects
* @param rect the bounding rectangle defines the region of the image to be * @param rect the bounding rectangle defines the region of the image to be
* recognized. A rectangle of zero dimension or * recognized. A rectangle of zero dimension or
* <code>null</code> indicates the whole image. * <code>null</code> indicates the whole image.
* @return the recognized text * @return the recognized text
* @throws TesseractException * @throws TesseractException
*/ */
public String doOCR(List<IIOImage> imageList, Rectangle rect) throws TesseractException { public String doOCR(List<BufferedImage> imageList, Rectangle rect) throws TesseractException {
StringBuilder sb = new StringBuilder(); StringBuilder sb = new StringBuilder();
pageNum = 0; pageNum = 0;
for (IIOImage oimage : imageList) { for (BufferedImage oimage : imageList) {
pageNum++; pageNum++;
try { try {
ByteBuffer buf = ImageIOHelper.getImageByteBuffer(oimage); ByteBuffer buf = ImageIOHelper.getImageByteBuffer(oimage);
RenderedImage ri = oimage.getRenderedImage(); String pageText = doOCR(oimage.getWidth(), oimage.getHeight(), buf, rect, oimage.getColorModel().getPixelSize());
String pageText = doOCR(ri.getWidth(), ri.getHeight(), buf, rect, ri.getColorModel().getPixelSize());
sb.append(pageText); sb.append(pageText);
} catch (IOException ioe) { } catch (IOException ioe) {
//skip the problematic image //skip the problematic image

BIN
docs-parent/lib/jai_imageio.jar
View File

Binary file not shown.

BIN
docs-parent/lib/jna.jar
View File

Binary file not shown.

122
docs-parent/pom.xml
View File

@ -35,8 +35,11 @@
<joda-time.joda-time.version>2.9.1</joda-time.joda-time.version> <joda-time.joda-time.version>2.9.1</joda-time.joda-time.version>
<org.hibernate.hibernate.version>4.1.0.Final</org.hibernate.hibernate.version> <org.hibernate.hibernate.version>4.1.0.Final</org.hibernate.hibernate.version>
<javax.servlet.javax.servlet-api.version>3.1.0</javax.servlet.javax.servlet-api.version> <javax.servlet.javax.servlet-api.version>3.1.0</javax.servlet.javax.servlet-api.version>
<com.levigo.jbig2.levigo-jbig2-imageio.version>1.6.3</com.levigo.jbig2.levigo-jbig2-imageio.version>
<fr.opensagres.xdocreport.version>1.0.5</fr.opensagres.xdocreport.version> <fr.opensagres.xdocreport.version>1.0.5</fr.opensagres.xdocreport.version>
<net.java.dev.jna.jna.version>4.2.1</net.java.dev.jna.jna.version>
<com.twelvemonkeys.imageio.version>3.2.1</com.twelvemonkeys.imageio.version>
<com.levigo.jbig2.levigo-jbig2-imageio.version>1.6.5</com.levigo.jbig2.levigo-jbig2-imageio.version>
<com.github.jai-imageio.jai-imageio-core.version>1.3.1</com.github.jai-imageio.jai-imageio-core.version>
<org.eclipse.jetty.jetty-server.version>9.2.13.v20150730</org.eclipse.jetty.jetty-server.version> <org.eclipse.jetty.jetty-server.version>9.2.13.v20150730</org.eclipse.jetty.jetty-server.version>
<org.eclipse.jetty.jetty-webapp.version>9.2.13.v20150730</org.eclipse.jetty.jetty-webapp.version> <org.eclipse.jetty.jetty-webapp.version>9.2.13.v20150730</org.eclipse.jetty.jetty-webapp.version>
@ -69,14 +72,7 @@
<enabled>true</enabled> <enabled>true</enabled>
</snapshots> </snapshots>
</repository> </repository>
<repository>
<id>jbig2.googlecode</id>
<name>JBIG2 ImageIO-Plugin repository at googlecode.com</name>
<url>http://jbig2-imageio.googlecode.com/svn/maven-repository</url>
</repository>
</repositories> </repositories>
<build> <build>
<plugins> <plugins>
@ -369,90 +365,50 @@
</dependency> </dependency>
<dependency> <dependency>
<groupId>fr.opensagres.xdocreport</groupId> <groupId>fr.opensagres.xdocreport</groupId>
<artifactId>org.odftoolkit.odfdom.converter.pdf</artifactId> <artifactId>org.odftoolkit.odfdom.converter.pdf</artifactId>
<version>${fr.opensagres.xdocreport.version}</version> <version>${fr.opensagres.xdocreport.version}</version>
</dependency> </dependency>
<dependency>
<groupId>fr.opensagres.xdocreport</groupId>
<artifactId>org.apache.poi.xwpf.converter.pdf</artifactId>
<version>${fr.opensagres.xdocreport.version}</version>
</dependency>
<!-- Used to read JBIG2 images. See https://github.com/sismics/docs/issues/38 -->
<dependency> <dependency>
<groupId>fr.opensagres.xdocreport</groupId>
<artifactId>org.apache.poi.xwpf.converter.pdf</artifactId>
<version>${fr.opensagres.xdocreport.version}</version>
</dependency>
<dependency> <!-- Servlet listener to register SPI ImageIO plugins -->
<groupId>com.twelvemonkeys.servlet</groupId>
<artifactId>servlet</artifactId>
<version>${com.twelvemonkeys.imageio.version}</version>
</dependency>
<!-- JNA for Tesseract -->
<dependency>
<groupId>net.java.dev.jna</groupId>
<artifactId>jna</artifactId>
<version>${net.java.dev.jna.jna.version}</version>
</dependency>
<!-- ImageIO plugins -->
<dependency> <!-- Permissive JPEG plugin -->
<groupId>com.twelvemonkeys.imageio</groupId>
<artifactId>imageio-jpeg</artifactId>
<version>${com.twelvemonkeys.imageio.version}</version>
</dependency>
<dependency><!-- Only JBIG2 -->
<groupId>com.levigo.jbig2</groupId> <groupId>com.levigo.jbig2</groupId>
<artifactId>levigo-jbig2-imageio</artifactId> <artifactId>levigo-jbig2-imageio</artifactId>
<version>${com.levigo.jbig2.levigo-jbig2-imageio.version}</version> <version>${com.levigo.jbig2.levigo-jbig2-imageio.version}</version>
</dependency> </dependency>
<!-- OCR dependencies --> <dependency><!-- Essentially TIFF (for OCR) -->
<dependency> <groupId>com.github.jai-imageio</groupId>
<groupId>jna</groupId> <artifactId>jai-imageio-core</artifactId>
<artifactId>jna</artifactId> <version>${com.github.jai-imageio.jai-imageio-core.version}</version>
<version>1.0</version>
</dependency>
<dependency>
<groupId>jai</groupId>
<artifactId>imageio</artifactId>
<version>1.0</version>
</dependency> </dependency>
</dependencies> </dependencies>
</dependencyManagement> </dependencyManagement>
<profiles>
<profile>
<id>init</id>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-install-plugin</artifactId>
<version>2.3.1</version>
<executions>
<execution>
<id>install-jna</id>
<phase>validate</phase>
<configuration>
<file>${project.basedir}/lib/jna.jar</file>
<repositoryLayout>default</repositoryLayout>
<groupId>jna</groupId>
<artifactId>jna</artifactId>
<version>1.0</version>
<packaging>jar</packaging>
<generatePom>true</generatePom>
</configuration>
<goals>
<goal>install-file</goal>
</goals>
</execution>
<execution>
<id>install-jai-imageio</id>
<phase>validate</phase>
<configuration>
<file>${project.basedir}/lib/jai_imageio.jar</file>
<repositoryLayout>default</repositoryLayout>
<groupId>jai</groupId>
<artifactId>imageio</artifactId>
<version>1.0</version>
<packaging>jar</packaging>
<generatePom>true</generatePom>
</configuration>
<goals>
<goal>install-file</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
</profile>
</profiles>
</project> </project>

5
docs-web/pom.xml
View File

@ -83,6 +83,11 @@
<groupId>com.h2database</groupId> <groupId>com.h2database</groupId>
<artifactId>h2</artifactId> <artifactId>h2</artifactId>
</dependency> </dependency>
<dependency>
<groupId>com.twelvemonkeys.servlet</groupId>
<artifactId>servlet</artifactId>
</dependency>
<!-- Test dependencies --> <!-- Test dependencies -->
<dependency> <dependency>

6
docs-web/src/main/webapp/WEB-INF/web.xml
View File

@ -7,6 +7,12 @@
metadata-complete="true"> metadata-complete="true">
<display-name>Docs</display-name> <display-name>Docs</display-name>
<!-- Proper loader/unloader of ImageIO plugins -->
<listener>
<display-name>ImageIO service provider loader/unloader</display-name>
<listener-class>com.twelvemonkeys.servlet.image.IIOProviderContextListener</listener-class>
</listener>
<!-- This filter is used to process a couple things in the request context --> <!-- This filter is used to process a couple things in the request context -->
<filter> <filter>
<filter-name>requestContextFilter</filter-name> <filter-name>requestContextFilter</filter-name>