Table clipper functionality (norma-0.7.0-alpha) and supporting analysis code

pom.xml

@@ -5,18 +5,29 @@
     <modelVersion>4.0.0</modelVersion>
 
     <properties>
-	    <norma.version>0.4.0</norma.version>
+		  <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
 	    <!-- upstream -->
-	    <cproject.version>0.4.0</cproject.version>
-	    <imageanalysis.version>1.1.0</imageanalysis.version>
-	    <!-- other -->
-	    <opennlp.version>1.6.0</opennlp.version>        
+	    <cproject.version>0.7.0-SNAPSHOT</cproject.version>
+
+	    <imageanalysis.version>1.3.0-SNAPSHOT</imageanalysis.version>
+	    <!--  this is the new PDFBox2 version -->
+	    <pdf2svg2.version>2.3.0-SNAPSHOT</pdf2svg2.version>
+	    <opennlp.version>1.6.0</opennlp.version>       
+	    <xml-apis.version>1.4.01</xml-apis.version>
+	    <Saxon-HE.version>9.6.0-3</Saxon-HE.version>
+	    <json-path.version>2.0.0</json-path.version>
+	    <jsoup.version>1.8.2</jsoup.version>
+	    <xmlunit.version>1.4</xmlunit.version>
+	    <jdeb.version>1.3</jdeb.version>
+
+
+
     </properties>
 
     <groupId>org.contentmine</groupId>
     <artifactId>norma</artifactId>
     <!-- to sync with new cproject-norma-ami versions -->
-    <version>${norma.version}</version>
+    <version>0.7.0-alpha</version>
     <packaging>jar</packaging>
     <name>norma</name>
     <description>A Java library for processing multiple legacy formats into normalized HTML5</description>
@@ -74,6 +85,7 @@
                     </execution>
                 </executions>
                 <configuration>
+          				<skip>true</skip>
                     <dataSet>
                         <data>
                             <src>${project.build.directory}/appassembler/</src>
@@ -135,20 +147,6 @@
                     <argLine>-Xmx1024m -XX:MaxPermSize=256m</argLine>
                 </configuration>
             </plugin>
-
-            <plugin>
-                <groupId>org.apache.maven.plugins</groupId>
-                <artifactId>maven-surefire-plugin</artifactId>
-            </plugin>
-            <plugin>
-                <groupId>org.apache.maven.plugins</groupId>
-                <artifactId>maven-compiler-plugin</artifactId>
-                <version>3.5</version>
-                <configuration>
-                    <source>1.5</source>
-                    <target>1.5</target>
-                </configuration>
-            </plugin>
             <!-- giant jar -->
             <plugin>
                 <groupId>org.apache.maven.plugins</groupId>
@@ -180,6 +178,13 @@
     </build>
 
     <dependencies>
+<!--     
+        <dependency>
+            <groupId>org.contentmine</groupId>
+            <artifactId>svghtml</artifactId>
+            <version>${svghtml.version}</version>
+        </dependency>
+        -->
         <dependency>
             <groupId>org.contentmine</groupId>
             <artifactId>cproject</artifactId>
@@ -190,10 +195,19 @@
             <artifactId>imageanalysis</artifactId>
             <version>${imageanalysis.version}</version>
         </dependency>
+        <!-- the new version -->
+        <!--  remove while refactoring -->
+        <!-- 
+        <dependency>
+            <groupId>org.contentmine</groupId>
+            <artifactId>pdf2svg</artifactId>
+            <version>${pdf2svg2.version}</version>
+        </dependency>
+        -->
         <dependency>
             <groupId>net.sf.saxon</groupId>
             <artifactId>Saxon-HE</artifactId>
-             <version>9.6.0-3</version>
+             <version>${Saxon-HE.version}</version>
         </dependency>        
         <dependency>
             <groupId>org.apache.opennlp</groupId>
@@ -205,34 +219,43 @@
         <dependency>
             <groupId>com.jayway.jsonpath</groupId>
             <artifactId>json-path</artifactId>
-            <version>2.0.0</version>
+            <version>${json-path.version}</version>
         </dependency>
         <!--  to avoid Xerces Hell? 
         http://stackoverflow.com/questions/17777821/maven-dependency-conflict-org-w3c-dom-elementtraversal
          -->
         <dependency>
             <groupId>org.jsoup</groupId>
             <artifactId>jsoup</artifactId>
-            <version>1.8.2</version>
+            <version>${jsoup.version}</version>
         </dependency>
         <dependency>
             <groupId>xmlunit</groupId>
             <artifactId>xmlunit</artifactId>
-            <version>1.4</version>
+            <version>${xmlunit.version}</version>
         </dependency>
         <dependency>
             <groupId>org.vafer</groupId>
             <artifactId>jdeb</artifactId>
-            <version>1.3</version>
+            <version>${jdeb.version}</version>
             <!-- Prevents jar bloat in final package -->
             <scope>provided</scope>
         </dependency>
 
-
+<!--        
         <dependency>
 	        <groupId>org.grobid</groupId>
 		    <artifactId>grobid-core</artifactId>
 		    <version>0.4.1</version>
 		</dependency>
+		-->
+
+        <dependency>
+            <groupId>xml-apis</groupId>
+            <artifactId>xml-apis</artifactId>
+		    <version>${xml-apis.version}</version>
+		</dependency>
+
+
     </dependencies>
 </project>

src/main/java/org/xmlcml/norma/Norma.java

@@ -1,8 +1,11 @@
 package org.xmlcml.norma;
 
+import java.io.File;
+
 import org.apache.log4j.Level;
 import org.apache.log4j.Logger;
 import org.xmlcml.cproject.args.DefaultArgProcessor;
+import org.xmlcml.cproject.util.Utils;
 
 public class Norma {
 
@@ -16,8 +19,17 @@ public class Norma {
 	private DefaultArgProcessor argProcessor;
 
 	public static void main(String[] args) {
+            try {
 		Norma norma = new Norma();
 		norma.run(args);
+            } catch (Exception ex) {
+                LOG.trace(ex.getMessage());
+                LOG.trace(ex.getStackTrace());
+                System.err.println(ex.getMessage());
+            }
+            // Ensure command prompt is on a new line
+            // after any runtime outputs
+            System.out.println();
 	}
 
 	public void run(String[] args) {
@@ -26,11 +38,32 @@ public void run(String[] args) {
 	}
 
 	public void run(String args) {
+		args = args == null ? null : args.trim();
 		argProcessor = new NormaArgProcessor(args.split("\\s+"));
 		argProcessor.runAndOutput();
 	}
 
 	public DefaultArgProcessor getArgProcessor() {
 		return argProcessor;
 	}
+
+	/** converts a projectDirectory to a project and the PDFs to SVG
+	 * 
+	 * @param projectDir
+	 */
+	public static void convertRawPDFToProjectToSVG(File projectDir) {
+                // Ensure fileFilter is cross-platform compatible
+                String fileFilterString = Utils.convertPathRegexToCurrentPlatform(".*/(.*)\\.pdf");
+		new Norma().run("--project "+projectDir+" --makeProject (\\1)/fulltext.pdf --fileFilter "+fileFilterString);
+		new Norma().run("--project " + projectDir + " --input fulltext.pdf "+ " --outputDir " + projectDir + " --transform pdf2svg ");
+	}
+
+	/** converts a projectDirectory to a project and the PDFs to SVG
+	 * 
+	 * @param projectDir
+	 */
+	public static void convertRawTEIXMLToProject(File projectDir) {
+		new Norma().run("--project "+projectDir+" --makeProject (\\1)/fulltext.xml --fileFilter .*\\/(.*)\\.xml");
+//		new Norma().run("--project " + projectDir + " --input fulltext.tei.xml "+ " --outputDir " + projectDir + " --transform tei2html ");
+	}
 }