Merge pull request #261 from metanorma/image_extract

Image extract

Makefile

@@ -6,7 +6,7 @@ SHELL ?= /bin/bash
 endif
 
 #JAR_VERSION := $(shell mvn -q -Dexec.executable="echo" -Dexec.args='$${project.version}' --non-recursive exec:exec -DforceStdout)
-JAR_VERSION := 1.96
+JAR_VERSION := 1.97
 JAR_FILE := mn2pdf-$(JAR_VERSION).jar
 
 all: target/$(JAR_FILE)

README.adoc

@@ -17,14 +17,14 @@ You will need the Java Development Kit (JDK) version 8, Update 241 (8u241) or hi
 
 [source,sh]
 ----
-java -Xss5m -Xmx2048m -jar target/mn2pdf-1.96.jar --xml-file <XML-FileName> --xsl-file <XSLT-FileName> --pdf-file <Output-PDF-FileName> [--syntax-highlight]
+java -Xss5m -Xmx2048m -jar target/mn2pdf-1.97.jar --xml-file <XML-FileName> --xsl-file <XSLT-FileName> --pdf-file <Output-PDF-FileName> [--syntax-highlight]
 ----
 
 e.g.
 
 [source,sh]
 ----
-java -Xss5m -Xmx2048m -jar target/mn2pdf-1.96.jar --xml-file tests/G.191.xml --xsl-file tests/itu.recommendation.xsl --pdf-file tests/G.191.pdf
+java -Xss5m -Xmx2048m -jar target/mn2pdf-1.97.jar --xml-file tests/G.191.xml --xsl-file tests/itu.recommendation.xsl --pdf-file tests/G.191.pdf
 ----
 
 === PDF encryption features
@@ -100,7 +100,7 @@ Update version in `pom.xml`, e.g.:
 ----
 <groupId>org.metanorma.fop</groupId>
 <artifactId>mn2pdf</artifactId>
-<version>1.96</version>
+<version>1.97</version>
 <name>Metanorma XML to PDF converter</name>
 ----
 
@@ -111,8 +111,8 @@ Tag the same version in Git:
 
 [source,xml]
 ----
-git tag v1.96
-git push origin v1.96
+git tag v1.97
+git push origin v1.97
 ----
 
 Then the corresponding GitHub release will be automatically created at:

pom.xml

@@ -5,7 +5,7 @@
 	<modelVersion>4.0.0</modelVersion>
 	<groupId>org.metanorma.fop</groupId>
 	<artifactId>mn2pdf</artifactId>
-	<version>1.96</version>
+	<version>1.97</version>
 	<name>Metanorma XML to PDF converter</name>
 	<packaging>jar</packaging>
 	<url>https://www.metanorma.org</url>

src/main/java/org/metanorma/fop/PDFGenerator.java

@@ -265,7 +265,10 @@ public boolean process() {
             logger.info(String.format(OUTPUT_LOG, PDF_OUTPUT, fPDF));
             logger.info("");
 
-            File fPresentationPartXML = getPresentationPartXML(fXML, fPDF.getParent());
+            PDFResult pdfResult = PDFResult.PDFResult(fPDF);
+
+            //File fPresentationPartXML = getPresentationPartXML(fXML, fPDF.getParent());
+            File fPresentationPartXML = getPresentationPartXML(fXML, pdfResult.getOutFolder());
 
             sourceXMLDocument = new SourceXMLDocument(fPresentationPartXML);
 
@@ -341,6 +344,7 @@ public boolean process() {
                 }
                 xsltConverter.deleteTmpXSL();
                 fontcfg.deleteConfigFile();
+				pdfResult.flushOutTmpImagesFolder();
             }
 
             logger.info("Success!");

src/main/java/org/metanorma/fop/PDFResult.java

@@ -0,0 +1,64 @@
+package org.metanorma.fop;
+
+import java.io.File;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.nio.file.Paths;
+import java.util.Comparator;
+import java.util.UUID;
+
+public class PDFResult {
+
+    private static PDFResult PDFResultSingleInstance = null;
+
+    private String outFolder;
+
+    private Path outTmpImagesPath;
+
+    private PDFResult() {
+    }
+
+    private PDFResult(File pdfFile) {
+        String parentFolder = pdfFile.getParent();
+        if (parentFolder == null) {
+            parentFolder = pdfFile.getAbsoluteFile().getParent();
+        } else {
+            parentFolder = new File(parentFolder).getAbsolutePath();
+        }
+        outTmpImagesPath = Paths.get(parentFolder, "_tmp_images_" + UUID.randomUUID().toString());
+        outFolder = parentFolder;
+    }
+
+    public static PDFResult PDFResult(File pdfFile)
+    {
+        if (PDFResultSingleInstance == null) {
+            PDFResultSingleInstance = new PDFResult(pdfFile);
+        }
+        return PDFResultSingleInstance;
+    }
+
+    public String getOutFolder() {
+        return outFolder;
+    }
+
+    public Path getOutTmpImagesPath() {
+        return outTmpImagesPath;
+    }
+
+
+    public void flushOutTmpImagesFolder () {
+        if (Files.exists(outTmpImagesPath)) {
+            try {
+                Files.walk(outTmpImagesPath)
+                        .sorted(Comparator.reverseOrder())
+                        .map(Path::toFile)
+                        .forEach(File::delete);
+                Files.deleteIfExists(outTmpImagesPath);
+            } catch (Exception ex) {
+                ex.printStackTrace();
+            }
+        }
+
+    }
+
+}

src/main/java/org/metanorma/fop/ifhandler/FOPXMLPresentationHandler.java

@@ -1,6 +1,7 @@
 package org.metanorma.fop.ifhandler;
 
 import org.apache.commons.lang3.StringEscapeUtils;
+import org.metanorma.fop.PDFResult;
 import org.metanorma.fop.Util;
 import org.metanorma.utils.LoggerHelper;
 import org.w3c.dom.Document;
@@ -18,15 +19,20 @@
 import javax.xml.transform.TransformerFactory;
 import javax.xml.transform.stream.StreamResult;
 import javax.xml.transform.stream.StreamSource;
+import java.io.File;
+import java.io.IOException;
 import java.io.StringReader;
 import java.io.StringWriter;
-import java.util.HashMap;
-import java.util.Map;
-import java.util.Stack;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.nio.file.Paths;
+import java.util.*;
 import java.util.logging.Logger;
 
 /*
- * This class is intended for removing the semantic part from Metanorma XML
+ * This class is intended for:
+ * - removing the semantic part from Metanorma XML
+ * - extract embedded images in base64 to binary format into temporary folder on disk
  */
 
 public class FOPXMLPresentationHandler extends DefaultHandler {
@@ -39,6 +45,8 @@ public class FOPXMLPresentationHandler extends DefaultHandler {
 
     private StringBuilder sbResult = new StringBuilder();
 
+    private String currentElement;
+
     Stack<Character> stackChar = new Stack<>();
 
     Stack<Boolean> skipElements = new Stack<>();
@@ -51,6 +59,8 @@ public void startDocument() {
     @Override
     public void startElement(String uri, String lName, String qName, Attributes attr) throws SAXException {
 
+        currentElement = qName;
+
         if (qName.startsWith("semantic__") || qName.equals("emf")) {
             // skip
             skipElements.push(true);
@@ -82,11 +92,53 @@ private String copyAttributes(Attributes attr) {
         StringBuilder sbTmp = new StringBuilder();
         for (int i = 0; i < attr.getLength(); i++) {
             sbTmp.append(" ");
-            sbTmp.append(attr.getLocalName(i));
+            String attrName = attr.getLocalName(i);
+            String attrValue = attr.getValue(i);
+            sbTmp.append(attrName);
             sbTmp.append("=\"");
-            String value = StringEscapeUtils.escapeXml(attr.getValue(i));
+
+            String value = StringEscapeUtils.escapeXml(attrValue);;
+
+            boolean isExtractedImage = false;
+
+            if (currentElement.equals("image") && attrName.equals("src") &&
+                    (attrValue.startsWith("data:image/") || attrValue.startsWith("data:application/")) &&
+                    !(attrValue.startsWith("data:image/svg+xml;"))) {
+                String dataPrefix = "data:image/";
+                if (attrValue.startsWith("data:application/")) {
+                    dataPrefix = "data:application/";
+                }
+                // extract embedded images in base64 to binary format into temporary folder on disk
+                int startPos = attrValue.indexOf(";base64,") + 8;
+                String base64data = attrValue.substring(startPos);
+                byte[] decodedBytes = Base64.getDecoder().decode(base64data);
+
+                String imageFormat = attrValue.substring(attrValue.indexOf(dataPrefix) + dataPrefix.length(), attrValue.indexOf(";base64,"));
+                PDFResult pdfResult = PDFResult.PDFResult(null);
+                String imageTmpName = UUID.randomUUID().toString() + "." + imageFormat;
+                Path imagePath = Paths.get(pdfResult.getOutTmpImagesPath().toString(), imageTmpName);
+                try {
+                    Files.createDirectories(pdfResult.getOutTmpImagesPath());
+                    Files.write(imagePath, decodedBytes);
+                    // relative path to PDF out file
+                    //File imageFile = new File(imagePath.toString());
+                    //String imageFileParentFolder = imageFile.getParentFile().getName();
+                    //value = Paths.get(imageFileParentFolder, imageTmpName).toString();
+                    // absolutepath
+                    value = imagePath.toAbsolutePath().toString();
+                    isExtractedImage = true;
+                } catch (IOException ex) {
+                    logger.severe("Can't save the image on disk '" + imagePath.toString() + "':");
+                    logger.severe(ex.getMessage());
+                    ex.printStackTrace();
+                }
+            }
             sbTmp.append(value);
             sbTmp.append("\"");
+
+            if (isExtractedImage) {
+                sbTmp.append(" extracted=\"true\"");
+            }
         }
         return sbTmp.toString();
     }