Changed PDFText.escapeText() so it doesn't output 7bit ASCII texts in hex mode. This makes it easier to read the PDF in a text editor in most cases.

Fixed the property names for xmp:CreatorTool and xmp:CreateDate (case mistake on my side).
Changed XMP-generation to output the creation date including the time zone to keep Acrobat's preflight check for PDF/A-1b happy. Found that only after more than 3 hours of trial&error.

git-svn-id: https://svn.apache.org/repos/asf/xmlgraphics/fop/trunk@390051 13f79535-47bb-0310-9956-ffa450edef68

3 files changed, 60 insertions, 25 deletions

diff --git a/src/java/org/apache/fop/pdf/PDFMetadata.java b/src/java/org/apache/fop/pdf/PDFMetadata.java
index 13774c026..1dad2b5a5 100644
--- a/src/java/org/apache/fop/pdf/PDFMetadata.java
+++ b/src/java/org/apache/fop/pdf/PDFMetadata.java
@@ -23,7 +23,6 @@ import java.io.OutputStream;
 import java.text.DateFormat;
 import java.text.SimpleDateFormat;
 import java.util.Date;
-import java.util.TimeZone;
 
 import javax.xml.transform.OutputKeys;
 import javax.xml.transform.Transformer;
@@ -35,6 +34,7 @@ import javax.xml.transform.stream.StreamResult;
 
 import org.apache.fop.fo.ElementMapping;
 import org.apache.fop.fo.extensions.xmp.XMPConstants;
+
 import org.w3c.dom.DOMImplementation;
 import org.w3c.dom.Document;
 import org.w3c.dom.Element;
@@ -47,6 +47,9 @@ public class PDFMetadata extends PDFStream {
     
     private static final String XMLNS = "http://www.w3.org/2000/xmlns/";
 
+    private static DateFormat pseudoISO8601DateFormat = new SimpleDateFormat(
+        "yyyy'-'MM'-'dd'T'HH':'mm':'ssZ");
+
     private Document xmpMetadata;
     private boolean readOnly = true;
 
@@ -145,6 +148,16 @@ public class PDFMetadata extends PDFStream {
         return sb.toString();
     }
 
+    private static String formatDate(Date dt) {
+        String s = pseudoISO8601DateFormat.format(dt);
+        
+        //Now insert the colon that's not possible using SimpleDateFormat
+        int tzpos = s.length() - 4;
+        String tz = s.substring(tzpos);
+        s = s.substring(0, tzpos) + tz.substring(0, 2) + ":" + tz.substring(2);
+        return s;
+    }
+    
     /**
      * Creates an XMP document based on the settings on the PDF Document.
      * @param pdfDoc the PDF Document
@@ -159,15 +172,16 @@ public class PDFMetadata extends PDFStream {
         
         Element desc, el;
         PDFInfo info = pdfDoc.getInfo();
-        DateFormat pseudoISO8601DateFormat = new SimpleDateFormat(
-            "yyyy'-'MM'-'dd'T'HH':'mm':'ss'.'SSS'Z'");
-        pseudoISO8601DateFormat.setTimeZone(TimeZone.getTimeZone("GMT+00"));
         
         //Set creation date if not available, yet
         if (info.getCreationDate() == null) {
             Date d = new Date();
             info.setCreationDate(d);
         }
+        
+        //Important: Acrobat's preflight check for PDF/A-1b wants the creation date in the Info
+        //object and in the XMP metadata to have the same timezone or else it shows a validation
+        //error even if the times are essentially equal.
 
         //Dublin Core
         desc = doc.createElementNS(XMPConstants.RDF_NAMESPACE, "rdf:Description");
@@ -195,18 +209,18 @@ public class PDFMetadata extends PDFStream {
         }
         el = doc.createElementNS(XMPConstants.DUBLIN_CORE_NAMESPACE, "dc:date");
         desc.appendChild(el);
-        el.appendChild(doc.createTextNode(pseudoISO8601DateFormat.format(info.getCreationDate())));
+        el.appendChild(doc.createTextNode(formatDate(info.getCreationDate())));
         
         //XMP Basic Schema
         desc = doc.createElementNS(XMPConstants.RDF_NAMESPACE, "rdf:Description");
         desc.setAttributeNS(XMPConstants.RDF_NAMESPACE, "rdf:about", "");
         desc.setAttributeNS(XMLNS, "xmlns:xmp", XMPConstants.XMP_BASIC_NAMESPACE);
         rdf.appendChild(desc);
-        el = doc.createElementNS(XMPConstants.XMP_BASIC_NAMESPACE, "xmp:createDate");
+        el = doc.createElementNS(XMPConstants.XMP_BASIC_NAMESPACE, "xmp:CreateDate");
         desc.appendChild(el);
-        el.appendChild(doc.createTextNode(pseudoISO8601DateFormat.format(info.getCreationDate())));
+        el.appendChild(doc.createTextNode(formatDate(info.getCreationDate())));
         if (info.getCreator() != null) {
-            el = doc.createElementNS(XMPConstants.XMP_BASIC_NAMESPACE, "xmp:creatorTool");
+            el = doc.createElementNS(XMPConstants.XMP_BASIC_NAMESPACE, "xmp:CreatorTool");
             desc.appendChild(el);
             el.appendChild(doc.createTextNode(info.getCreator()));
         }
diff --git a/src/java/org/apache/fop/pdf/PDFObject.java b/src/java/org/apache/fop/pdf/PDFObject.java
index 6d312b25f..9ccd59bfc 100644
--- a/src/java/org/apache/fop/pdf/PDFObject.java
+++ b/src/java/org/apache/fop/pdf/PDFObject.java
@@ -1,5 +1,5 @@
 /*
- * Copyright 1999-2004 The Apache Software Foundation.
+ * Copyright 1999-2004,2006 The Apache Software Foundation.
  * 
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -198,7 +198,7 @@ public abstract class PDFObject {
             return PDFText.escapeByteArray(
                 getDocument().getEncryption().encrypt(buf, this));
         } else {
-            return encode(PDFText.escapeText(text, true));
+            return encode(PDFText.escapeText(text, false));
         }
     }
     
diff --git a/src/java/org/apache/fop/pdf/PDFText.java b/src/java/org/apache/fop/pdf/PDFText.java
index e21b078a7..16fccb97e 100644
--- a/src/java/org/apache/fop/pdf/PDFText.java
+++ b/src/java/org/apache/fop/pdf/PDFText.java
@@ -1,5 +1,5 @@
 /*
- * Copyright 1999-2004 The Apache Software Foundation.
+ * Copyright 1999-2004,2006 The Apache Software Foundation.
  * 
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -73,20 +73,34 @@ public class PDFText extends PDFObject {
      * @return encoded text
      */
     public static final String escapeText(final String text) {
-        return escapeText(text, true);
+        return escapeText(text, false);
     }
     /**
      * Escape text (see 4.4.1 in PDF 1.3 specs)
      * @param text the text to encode
-     * @param hexMode true if the output should follow the hex encoding rules
+     * @param forceHexMode true if the output should follow the hex encoding rules
      * @return encoded text
      */
-    public static final String escapeText(final String text, boolean hexMode) {
+    public static final String escapeText(final String text, boolean forceHexMode) {
         if (text != null && text.length() > 0) {
+            boolean unicode = false;
+            boolean hexMode = false;
+            if (forceHexMode) {
+                hexMode = true;
+            } else {
+                for (int i = 0, c = text.length(); i < c; i++) {
+                    if (text.charAt(i) >= 128) {
+                        unicode = true;
+                        hexMode = true;
+                        break;
+                    }
+                }
+            }
+            
             if (hexMode) {
                 final byte[] uniBytes;
                 try {
-                    uniBytes = text.getBytes("UnicodeBig");
+                    uniBytes = text.getBytes("UTF-16");
                 } catch (java.io.UnsupportedEncodingException uee) {
                     throw new CascadingRuntimeException("Incompatible VM", uee);
                 }
@@ -96,22 +110,29 @@ public class PDFText extends PDFObject {
                 result.append("(");
                 final int l = text.length();
 
-                // byte order marker (0xfeff)
-                result.append("\\376\\377");
-                
-                for (int i = 0; i < l; i++) {
-                    final char ch = text.charAt(i);
-                    //if (ch < 128) {
-                    //    result.append('\u0000');
-                    //    result.append(ch);
-                    //} else {
+                if (unicode) {
+                    // byte order marker (0xfeff)
+                    result.append("\\376\\377");
+                    
+                    for (int i = 0; i < l; i++) {
+                        final char ch = text.charAt(i);
                         final int high = (ch & 0xff00) >>> 8;
                         final int low = ch & 0xff;
                         result.append("\\");
                         result.append(Integer.toOctalString(high));
                         result.append("\\");
                         result.append(Integer.toOctalString(low));
-                    //}
+                    }
+                } else {
+                    for (int i = 0; i < l; i++) {
+                        final char ch = text.charAt(i);
+                        if (ch < 256) {
+                            escapeStringChar(ch, result);
+                        } else {
+                            throw new IllegalStateException(
+                            "Can only treat text in 8-bit ASCII/PDFEncoding");
+                        }
+                    }
                 }
                 result.append(")");
                 return result.toString();