Main.java: Specify a password to decrypt PDFs with -p.

.classpath

@@ -5,5 +5,6 @@
 	<classpathentry kind="lib" path="lib/pdfbox-1.1.0.jar" sourcepath="lib/pdfbox-1.1.0-src.zip"/>
 	<classpathentry kind="lib" path="lib/commons-logging-1.1.1.jar"/>
 	<classpathentry kind="lib" path="lib/fontbox-1.1.0.jar"/>
+	<classpathentry kind="lib" path="lib/args4j-2.0.11.jar"/>
 	<classpathentry kind="output" path="bin"/>
 </classpath>

build.xml

@@ -23,6 +23,7 @@
       <zipfileset src="${lib.dir}/pdfbox-1.1.0.jar" excludes="META-INF"/>
       <zipfileset src="${lib.dir}/fontbox-1.1.0.jar" excludes="META-INF"/>
       <zipfileset src="${lib.dir}/commons-logging-1.1.1.jar" excludes="META-INF"/>
+      <zipfileset src="${lib.dir}/args4j-2.0.11.jar" excludes="META-INF"/>
       <manifest>
         <attribute name="Main-Class" 
                    value="org.crossref.pdf2xml.Main"/>

src/org/crossref/pdf2xml/Main.java

@@ -5,20 +5,43 @@
 import java.util.ArrayList;
 import java.util.List;
 
-import javax.swing.JFrame;
-import javax.swing.JScrollPane;
-
+import org.apache.pdfbox.exceptions.CryptographyException;
+import org.apache.pdfbox.exceptions.InvalidPasswordException;
+import org.apache.pdfbox.exceptions.WrappedIOException;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDDocumentCatalog;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.PDPageNode;
-import org.crossref.pdf2xml.visual.PageCanvas;
-
+import org.kohsuke.args4j.Argument;
+import org.kohsuke.args4j.CmdLineException;
+import org.kohsuke.args4j.CmdLineParser;
+import org.kohsuke.args4j.Option;
 
 public class Main {
+
+    @Option(name="-p", usage="Specify an optional decryption password.",
+            required=false, multiValued=false, metaVar="PASSWD")
+    private String password = "";
+
+    @Argument
+    private List<String> filenames = new ArrayList<String>();
 
-	private static TextExtractor parsePdf(File f) throws IOException {
+	private TextExtractor parsePdf(File f) throws IOException {
 		PDDocument doc = PDDocument.load(f);
+
+		if(doc.isEncrypted()) {
+            // Some documents are encrypted with the empty password. Try
+		    // to decrypt with this password, or the one passed in on the
+		    // command line (if any), and fail if we can't.
+            try {
+                doc.decrypt(password); // Defaults to the empty string.
+            } catch (CryptographyException e) {
+                throw new WrappedIOException("Can't decrypt document: ", e);
+            } catch (InvalidPasswordException e) {
+                throw new WrappedIOException("Document is encrypted: ", e);
+            }
+        }
+
 		PDDocumentCatalog docCat = doc.getDocumentCatalog();
 
 		PDPageNode root = docCat.getPages();
@@ -41,19 +64,36 @@ private static TextExtractor parsePdf(File f) throws IOException {
 		return te;
 	}
 
-	public static void main(String[] filenames) {
-		for (String filename : filenames) {
-			File inputFile = new File(filename);
-			TextExtractor te = null;
-
-			try {
-				te = parsePdf(inputFile);
-				System.out.println(te.toXml());
-			} catch (IOException e) {
-				System.err.println("Couldn't read file '" + inputFile +"'.");
-				System.exit(1);
-			}
-		}
+	private void doMain() {
+	    for (String filename : filenames) {
+            File inputFile = new File(filename);
+            TextExtractor te = null;
+
+            try {
+                te = parsePdf(inputFile);
+                System.out.println(te.toXml());
+            } catch (IOException e) {
+                System.err.println("Couldn't read file '" + inputFile +"'.");
+                System.exit(1);
+            }
+        }
+	}
+
+	public static void main(String[] args) {
+	    Main m = new Main();
+        CmdLineParser parser = new CmdLineParser(m);
+
+        if (args.length == 0) {
+            System.err.println("Usage: pdf2xml [options] <FILEs>");
+            parser.printUsage(System.err);
+        } else {
+            try {
+                parser.parseArgument(args);
+                m.doMain();
+            } catch (CmdLineException e) {
+                parser.printUsage(System.err);
+            }
+        }
 	}
 
 }

src/org/crossref/pdf2xml/TextExtractor.java

@@ -36,7 +36,7 @@
 
 /**
  * Extract text from a PDF document with position and style information.
- * This class attempts to coalease runs of text on the page; that is, 
+ * This class attempts to coalesce runs of text on the page; that is, 
  * 
  * @author Karl Ward
  */
@@ -67,9 +67,7 @@ public void processStream(PDPage aPage, PDResources resources,
 
 	protected void processTextPosition(TextPosition tp) {
 		PDGraphicsState gs = getGraphicsState();
-
-		Text newT = Text.newFor(tp, gs);
-		currentPage.addText(newT);
+        currentPage.addText(Text.newFor(tp, gs));
 	}
 
 	private void coalesceRows(Page page) {

src/org/crossref/pdf2xml/data/Text.java

@@ -2,6 +2,8 @@
 
 import java.io.IOException;
 
+import org.apache.fontbox.cmap.CMap;
+import org.apache.pdfbox.encoding.Encoding;
 import org.apache.pdfbox.pdmodel.font.PDCIDFont;
 import org.apache.pdfbox.pdmodel.font.PDFont;
 import org.apache.pdfbox.pdmodel.font.PDSimpleFont;
@@ -10,7 +12,9 @@
 import org.apache.pdfbox.util.TextPosition;
 
 public class Text implements Comparable<Text> {
-	private float x, baseline, width, height, pointSize, descent, ascent, fontSize;
+
+	private float x, baseline, width, height, pointSize, 
+	              descent, ascent, fontSize;
 	private String run;
 	private PDFont font;
 	private PDColorState strokeColor;