Mathtype ole xml to mathml

README

@@ -1,16 +1 @@
-This is a library to parse MathType's MTEF binary format. Currently doesn't do very much at all.
-
-My intention is that it should read the MTEF stream and, as a bare minimum, output an XML serialisation of it with each
-MathType record mapping fairly directly to an XML element containing subrecords as subelements, and with record options
-represented by attributes. As an extension, it could make the XML a bit nicer (e.g. instead of outputting a TMPL element
-for the TMPL record, it could output a specific element based on the template selector).
-
-Ultimately, I'd like to be able to convert a binary MTEF stream into presentational MathML. My thinking is that once
-the binary MTEF is available in some kind of XML representation, it turns into a question of XSLT which personally I
-find more tractable (and it can be tested with XSpec tests).
-
-At the moment, this is my main project for working on in my spare time and on the train to / from where I work.
-Unfortunately, I don't have a lot of spare time currently! All contributions and suggestions are welcome, but
-my ability to respond is a bit limited at the moment.
-
-My intention is to put this under the Apache License, version 2.0, unless anyone has any serious objections.
+Moving forward the work done by Daniel Rendall towards the MathML target ...

code/output/expected-MathML/math1.xml

@@ -0,0 +1,5 @@
+<math>
+  <mi>x</mi>
+  <mo>=</mo>
+  <mi>α</mi>
+</math>

code/output/expected-MathML/math2.xml

@@ -0,0 +1,9 @@
+<math>
+  <mi>a</mi><msup><mi>x</mi><mn>2</mn></msup>
+  <mo>+</mo>
+  <mi>b</mi><mi>x</mi>
+  <mo>+</mo>
+  <mi>c</mi>
+  <mo>=</mo>
+  <mn>0</mn>
+</math>

code/output/expected-MathML/math3.xml

@@ -0,0 +1,8 @@
+<math>
+  <mi>x</mi>
+  <mo>=</mo>
+  <mfrac>
+    <mrow><mi>a</mi><mo>+</mo><mi>b</mi></mrow>
+    <mrow><mi>c</mi><mo>+</mo><mi>d</mi></mrow>
+  </mfrac>
+</math>

code/output/expected-MathML/math4.xml

@@ -0,0 +1,7 @@
+<math>
+  <msup><mi>x</mi><mn>2</mn></msup>
+  <mo>=</mo>
+  <msubsup><mi>y</mi><mn>2</mn><mn>3</mn></msubsup>
+  <mo>=</mo>
+  <mmultiscripts><mi>z</mi><mprescripts/><none/><mn>2</mn></mmultiscripts>
+</math>

code/output/expected-MathML/math5.xml

@@ -0,0 +1,12 @@
+<math>
+  <mi>x</mi>
+  <mo>=</mo>
+  <mrow>
+    <mo>(</mo>
+    <mtable>
+      <mtr><mtd><mi>a</mi></mtd><mtd><mi>b</mi></mtd><mtd><mi>c</mi></mtd></mtr>
+      <mtr><mtd><mi>d</mi></mtd><mtd><mi>e</mi></mtd><mtd><mi>f</mi></mtd></mtr>
+    </mtable>
+    <mo>)</mo>
+  </mrow>
+</math>

code/output/expected-MathML/math6.xml

@@ -0,0 +1,10 @@
+<math>
+  <mi>x</mi>
+  <mo>=</mo>
+  <munderover>
+    <mi>∑</mi>
+    <mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow>
+    <mi>N</mi>
+  </munderover>
+  <msub><mi>a</mi><mi>i</mi></msub>
+</math>

code/output/expected-MathML/math7.xml

@@ -0,0 +1,15 @@
+<math>
+  <mi>x</mi>
+  <mo>=</mo>
+  <msup>
+    <mrow>
+      <mo>[</mo>
+      <mfrac>
+	<mrow><mi>a</mi><mo>+</mo><mi>b</mi></mrow>
+	<mrow><mi>c</mi><mo>+</mo><mi>d</mi></mrow>
+      </mfrac>
+      <mo>]</mo>
+    </mrow>
+    <mn>2</mn>
+  </msup>
+</math>

code/pom.xml

@@ -16,22 +16,14 @@
 <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
          xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
     <modelVersion>4.0.0</modelVersion>
-
     <groupId>uk.co.danielrendall</groupId>
     <artifactId>metaphor</artifactId>
     <version>1.0-SNAPSHOT</version>
-    <packaging>jar</packaging>
-
+	<packaging>jar</packaging>
     <name>metaphor</name>
 	<description>A parser for MathType's MTEF binary format</description>
     <url>http://maven.apache.org</url>
-
-    <properties>
-        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
-    </properties>
-
     <dependencies>
-
         <dependency>
             <groupId>com.google.guava</groupId>
             <artifactId>guava</artifactId>
@@ -45,7 +37,6 @@
         </dependency>
 
         <!-- Logging -->
-
         <dependency>
             <groupId>ch.qos.logback</groupId>
             <artifactId>logback-classic</artifactId>
@@ -57,7 +48,19 @@
             <artifactId>jcl-over-slf4j</artifactId>
             <version>1.6.2</version>
         </dependency>
-
+
+        <dependency>
+			<groupId>commons-cli</groupId>
+			<artifactId>commons-cli</artifactId>
+			<version>1.2</version>
+		</dependency>
+
+		<dependency>
+			<groupId>net.sf.saxon</groupId>
+			<artifactId>saxon</artifactId>
+			<version>8.7</version>
+		</dependency>
+
         <dependency>
             <groupId>junit</groupId>
             <artifactId>junit</artifactId>

code/src/main/java/uk/co/danielrendall/metaphor/App.java

@@ -15,23 +15,86 @@
 
 package uk.co.danielrendall.metaphor;
 
-import uk.co.danielrendall.metaphor.parsers.MTEFParser;
-import uk.co.danielrendall.metaphor.records.MTEF;
-
+import java.io.File;
 import java.io.IOException;
-import java.io.InputStream;
-import java.io.PushbackInputStream;
+import java.net.URISyntaxException;
+import java.util.Map;
+import java.util.Properties;
 
-/**
- * Hello world!
- *
+import javax.xml.transform.TransformerConfigurationException;
+import javax.xml.transform.TransformerException;
+
+import org.apache.commons.cli.CommandLine;
+import org.apache.commons.cli.CommandLineParser;
+import org.apache.commons.cli.HelpFormatter;
+import org.apache.commons.cli.Options;
+import org.apache.commons.cli.PosixParser;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.google.common.io.Files;
+
+/*
+ * Entry Point to this Library
+ * @author Daniel Rendall
+ * @author Murugan Natarajan
  */
-public class App 
-{
-    public static MTEF parse(InputStream is) throws ParseException, IOException {
-        PushbackInputStream pis = new PushbackInputStream(is);
-        // hack - throw away 28 byte OLE header
-        pis.read(new byte[28]);
-        return new MTEFParser().parse(pis);
+public class App{
+	private static final Logger log = LoggerFactory.getLogger(App.class);
+	private Properties config = new Properties();
+	private File inputFile = null;
+	private File outputFile = null;
+
+	private App() throws IOException, TransformerConfigurationException{
+		this.config.load(App.class.getResourceAsStream("/cmdln/config.properties"));
+	}
+
+    private boolean doWithArgs(String[] args) throws ParseException, IOException, TransformerException, URISyntaxException{
+    	Options options = new Options();
+    	HelpFormatter formatter = new HelpFormatter();
+    	options.addOption(this.config.getProperty("mathMl.commandLine.input.option"), true, this.config.getProperty("mathMl.commandLine.input.desc"));
+    	options.addOption(this.config.getProperty("mathMl.commandLine.output.option"), true, this.config.getProperty("mathMl.commandLine.output.desc"));
+    	CommandLineParser parser = new PosixParser();
+    	CommandLine cmd = null;
+    	try {
+    		cmd = parser.parse(options, args);
+    	} catch (org.apache.commons.cli.ParseException e) {
+    		log.error(this.config.getProperty("mathMl.commandLine.invalid"));
+    		e.printStackTrace();
+     	}
+    	if (cmd == null || cmd != null && !cmd.hasOption(this.config.getProperty("mathMl.commandLine.input.option"))){
+    		formatter.printHelp(this.config.getProperty("mathMl.commandLine.help.desc"), options);
+    		return false;
+     	}
+    	String inputPath = cmd.getOptionValue(this.config.getProperty("mathMl.commandLine.input.option"));
+    	String outputPath = this.config.getProperty("mathMl.commandLine.output.default");
+    	if (cmd.hasOption(this.config.getProperty("mathMl.commandLine.output.option"))){
+    		outputPath = cmd.getOptionValue(this.config.getProperty("mathMl.commandLine.output.option"));
+  	   	}
+    	File inputFile = new File(inputPath);
+    	File outputFile = new File(outputPath);
+    	if(!inputFile.exists()){
+    		log.error(this.config.getProperty("mathMl.commandLine.input.invalid"));
+    		return false;
+    	}
+    	this.inputFile = inputFile;
+    	this.outputFile = outputFile;
+    	return true;
+    }
+
+    public static void main(String[] args)throws org.apache.commons.cli.ParseException, ParseException, IOException, TransformerException, URISyntaxException{
+    	App obj = new App();
+    	if(obj.doWithArgs(args)){
+    		FilesExplorer explorer = new FilesExplorer();
+    		BinFileHandler bin = new BinFileHandler();
+    		MMLConverter converter = new MMLConverter();
+    		explorer.setOutputExtention(".mml");
+        	explorer.setSearchPattern("^([^.]*)\\.bin$");
+    		explorer.collectFilePairs(obj.inputFile, obj.outputFile);
+    		for (Map.Entry<File, File> pair : explorer.getFilePairs().entrySet()){
+    			Files.write(converter.covertBin(bin.parseRequiredContent(Files.toByteArray(pair.getKey()))), pair.getValue());
+    		}
+    		log.info(obj.config.getProperty("mathMl.conversion.success"));
+    	}
     }
 }

code/src/main/java/uk/co/danielrendall/metaphor/BinFileHandler.java

@@ -0,0 +1,53 @@
+package uk.co.danielrendall.metaphor;
+
+import java.io.IOException;
+import java.util.Arrays;
+
+/*
+ * MTEF Bin parser to extract required and valid content from it
+ * @author Murugan Natarajan
+ */
+public class BinFileHandler {
+	public byte[] parseRequiredContent(byte[] bytes) throws ParseException, IOException {
+    	// To identify and throw away the unwanted contents until MathType OLE Header position for higher version greater than MathType5
+        Integer[] startKeys = new Integer[]{28, 0, 0, 0, 2, 0}; // Header Starting 6 byte values
+        int startIndex = identifyKeys(startKeys, bytes);
+        if(startIndex == -1){
+        	throw new ParseException("Expected Header Start Value \"1c00 0000 0200\" Not Found with this file.");
+        }
+        bytes = Arrays.copyOfRange(bytes, startIndex, bytes.length);
+
+       	// To throw away 28 bytes of MathType OLE Header
+       	if(28 >= bytes.length){
+       		throw new ParseException("Expected Header Start Value \"1c00 0000 0200\" Not Found with this file.");
+       	}
+       	bytes = Arrays.copyOfRange(bytes, 28, bytes.length);
+
+       	// To identify and throw away the unwanted contents within the body of the equation for higher version greater than MathType5
+       	Integer[] unwatedBodyKeys = new Integer[]{69, 0, 113, 0, 117, 0}; // Unwanted Body Content Starting 6 byte values
+       	int unwantedBodyIndex = identifyKeys(unwatedBodyKeys, bytes);
+       	if(unwantedBodyIndex >= 0 && unwantedBodyIndex + 512 <= bytes.length){
+       		byte[] frontBytes = Arrays.copyOfRange(bytes, 0, unwantedBodyIndex);
+       		byte[] backBytes = Arrays.copyOfRange(bytes, unwantedBodyIndex + 512, bytes.length);
+       		bytes = new byte[frontBytes.length + backBytes.length];
+       		System.arraycopy(frontBytes, 0, bytes, 0, frontBytes.length);
+       		System.arraycopy(backBytes, 0, bytes, frontBytes.length, backBytes.length);
+        }
+        return bytes;
+    }
+
+    private int identifyKeys(Integer[] keys, byte[] bytes) throws IOException{
+        int j = 0;
+       	for(int i = 0; i<keys.length && j<bytes.length; j++){
+       		if(keys[i] != (int)bytes[j]){
+       			i = 0;
+       		}else{
+       			i++;
+       		}
+       	}
+       	if(j < bytes.length){
+       		return j - keys.length;
+       	}
+        return -1;
+    }
+}