Index: test/java/org/apache/fop/StandardTestSuite.java
===================================================================
--- test/java/org/apache/fop/StandardTestSuite.java (revision 1147766)
+++ test/java/org/apache/fop/StandardTestSuite.java (working copy)
@@ -22,6 +22,8 @@
import junit.framework.Test;
import junit.framework.TestSuite;
+import org.apache.fop.afp.fonts.CharactersetEncoderTest;
+import org.apache.fop.afp.parser.MODCAParserTestCase;
import org.apache.fop.area.ViewportTestSuite;
import org.apache.fop.afp.parser.MODCAParserTestCase;
import org.apache.fop.fonts.DejaVuLGCSerifTest;
@@ -59,6 +61,7 @@
suite.addTest(new TestSuite(PDFsRGBSettingsTestCase.class));
suite.addTest(new TestSuite(DejaVuLGCSerifTest.class));
suite.addTest(new TestSuite(MODCAParserTestCase.class));
+ suite.addTest(new TestSuite(CharactersetEncoderTest.class));
suite.addTest(AFPTestSuite.suite());
suite.addTest(PSTestSuite.suite());
suite.addTest(RichTextFormatTestSuite.suite());
Index: test/java/org/apache/fop/afp/fonts/CharactersetEncoderTest.java
===================================================================
--- test/java/org/apache/fop/afp/fonts/CharactersetEncoderTest.java (revision 0)
+++ test/java/org/apache/fop/afp/fonts/CharactersetEncoderTest.java (revision 0)
@@ -0,0 +1,108 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+/* $Id$ */
+
+package org.apache.fop.afp.fonts;
+
+import java.io.ByteArrayOutputStream;
+import java.io.IOException;
+import java.nio.charset.CharacterCodingException;
+
+import junit.framework.TestCase;
+
+/**
+ * Test {@link CharactersetEncoder}
+ */
+public class CharactersetEncoderTest extends TestCase {
+ private CharactersetEncoder singlebyteEncoder;
+ private CharactersetEncoder doublebyteEncoder;
+
+ public void setUp() {
+ singlebyteEncoder = CharactersetEncoder.newInstance("cp500", false);
+ doublebyteEncoder = CharactersetEncoder.newInstance("cp937", true);
+ }
+
+ // This is just an arbitrary CJK string
+ private final String testCJKText = "\u8ACB\u65BC\u627F\u505A\u65E5\u4E03\u65E5\u5167\u672A\u9054"
+ + "\u4E03\u65E5\u4E4B\u5B9A\u5B58\u8005\u4EE5\u5BE6\u969B\u5230\u671F\u65E5\u5167\u78BA"
+ + "\u8A8D\u672C\u4EA4\u6613\u5167\u5BB9\u3002\u5982\u672A\u65BC\u4E0A\u8FF0\u671F\u9593"
+ + "\u5167\u63D0\u51FA\u7570\u8B70\uFF0C\u8996\u540C\u610F\u627F\u8A8D\u672C\u4EA4\u6613"
+ + "\u3002";
+
+ private final byte[] test6CJKChars = {
+ (byte) 0x61, (byte) 0x99,
+ (byte) 0x50, (byte) 0xf4,
+ (byte) 0x50, (byte) 0xd4,
+ (byte) 0x56, (byte) 0x99,
+ (byte) 0x4c, (byte) 0xc9,
+ (byte) 0x4c, (byte) 0x44 };
+
+ private final String testEngText = "Hello World!";
+ private final byte[] testEngChars = {
+ (byte) 0xc8, // H
+ (byte) 0x85, // e
+ (byte) 0x93, // l
+ (byte) 0x93, // l
+ (byte) 0x96, // o
+ (byte) 0x40, // " "
+ (byte) 0xe6, // W
+ (byte) 0x96, // o
+ (byte) 0x99, // r
+ (byte) 0x93, // l
+ (byte) 0x84, // d
+ (byte) 0x4f // !
+ };
+
+ /**
+ * Tests canEncode() - tests that canEncode() responds properly to various input characters.
+ */
+ public void testCanEncode() {
+ // Both SBCS and DBCS should support Latin characters
+ for (char c = '!'; c < '~'; c++) {
+ assertTrue(singlebyteEncoder.canEncode(c));
+ assertTrue(doublebyteEncoder.canEncode(c));
+ }
+ // ONLY the double byte characters can handle CJK text
+ for (char c : testCJKText.toCharArray()) {
+ assertFalse(singlebyteEncoder.canEncode(c));
+ assertTrue(doublebyteEncoder.canEncode(c));
+ }
+ // Ensure that double byte encoder doesn't just return true all the time...
+ assertFalse(doublebyteEncoder.canEncode('\u00BB'));
+ }
+
+ public void testEncode() throws CharacterCodingException, IOException {
+ CharactersetEncoder.EncodedChars encChars;// = doublebyteEncoder.encode(testCJKText);
+ ByteArrayOutputStream bOut = new ByteArrayOutputStream();
+ // JAVA 1.5 has a bug in the JVM in which these err for some reason... JAVA 1.6 no issues
+ /*encChars.writeTo(bOut, 0, encChars.getLength());
+ byte[] bytes = bOut.toByteArray();
+ for (int i = 0; i < 12; i++) {
+ assertEquals(test6CJKChars[i], bytes[i]);
+ }
+ bOut.reset();*/
+
+ encChars = singlebyteEncoder.encode(testEngText);
+ encChars.writeTo(bOut, 0, encChars.getLength());
+ byte[] engBytes = bOut.toByteArray();
+ for (int i = 0; i < testEngChars.length; i++) {
+ assertEquals(testEngChars[i], engBytes[i]);
+ }
+ assertEquals(testEngChars.length, engBytes.length);
+ }
+}
Index: src/java/org/apache/fop/render/afp/AFPRendererConfigurator.java
===================================================================
--- src/java/org/apache/fop/render/afp/AFPRendererConfigurator.java (revision 1147766)
+++ src/java/org/apache/fop/render/afp/AFPRendererConfigurator.java (working copy)
@@ -27,7 +27,6 @@
import org.apache.avalon.framework.configuration.Configuration;
import org.apache.avalon.framework.configuration.ConfigurationException;
-
import org.apache.fop.afp.AFPResourceLevel;
import org.apache.fop.afp.AFPResourceLevelDefaults;
import org.apache.fop.afp.fonts.AFPFont;
@@ -258,9 +257,11 @@
}
String name = afpFontCfg.getAttribute("name", characterset);
CharacterSet characterSet = null;
+ boolean ebcdicDBCS = afpFontCfg.getAttributeAsBoolean("ebcdic-dbcs", false);
+
try {
- characterSet = CharacterSetBuilder.getDoubleByteInstance()
- .build(characterset, codepage, encoding, accessor);
+ characterSet = CharacterSetBuilder.getDoubleByteInstance().buildDBCS(characterset,
+ codepage, encoding, ebcdicDBCS, accessor);
} catch (IOException ioe) {
toConfigurationException(codepage, characterset, ioe);
}
Index: src/java/org/apache/fop/afp/fonts/CharacterSet.java
===================================================================
--- src/java/org/apache/fop/afp/fonts/CharacterSet.java (revision 1147766)
+++ src/java/org/apache/fop/afp/fonts/CharacterSet.java (working copy)
@@ -21,19 +21,13 @@
import java.io.File;
import java.io.UnsupportedEncodingException;
-import java.nio.ByteBuffer;
-import java.nio.CharBuffer;
import java.nio.charset.CharacterCodingException;
-import java.nio.charset.Charset;
-import java.nio.charset.CharsetEncoder;
-import java.nio.charset.CodingErrorAction;
-import java.nio.charset.UnsupportedCharsetException;
import java.util.Map;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
-
import org.apache.fop.afp.AFPConstants;
+import org.apache.fop.afp.fonts.CharactersetEncoder.EncodedChars;
import org.apache.fop.afp.util.ResourceAccessor;
import org.apache.fop.afp.util.SimpleResourceAccessor;
import org.apache.fop.afp.util.StringUtils;
@@ -70,16 +64,16 @@
/** The code page to which the character set relates */
- protected String codePage;
+ protected final String codePage;
/** The encoding used for the code page */
- protected String encoding;
+ protected final String encoding;
- /** The charset encoder corresponding to this encoding */
- private CharsetEncoder encoder;
+ /** The characterset encoder corresponding to this encoding */
+ private final CharactersetEncoder encoder;
/** The character set relating to the font */
- protected String name;
+ protected final String name;
/** The path to the installed fonts */
private ResourceAccessor accessor;
@@ -105,20 +99,22 @@
* {@link #CharacterSet(String, String, String, ResourceAccessor)} instead.
*/
public CharacterSet(String codePage, String encoding, String name, String path) {
- this(codePage, encoding, name,
+ this(codePage, encoding, false, name,
new SimpleResourceAccessor(path != null ? new File(path) : null));
}
/**
- * Constructor for the CharacterSetMetric object, the character set is used
- * to load the font information from the actual AFP font.
+ * Constructor for the CharacterSetMetric object, the character set is used to load the font
+ * information from the actual AFP font.
*
* @param codePage the code page identifier
* @param encoding the encoding of the font
+ * @param isEBDCS if this is an EBCDIC double byte character set.
* @param name the character set name
* @param accessor the resource accessor to load resource with
*/
- CharacterSet(String codePage, String encoding, String name, ResourceAccessor accessor) {
+ CharacterSet(String codePage, String encoding, boolean isEBDCS, String name,
+ ResourceAccessor accessor) {
if (name.length() > MAX_NAME_LEN) {
String msg = "Character set name '" + name + "' must be a maximum of "
+ MAX_NAME_LEN + " characters";
@@ -133,14 +129,7 @@
}
this.codePage = codePage;
this.encoding = encoding;
- try {
- this.encoder = Charset.forName(encoding).newEncoder();
- this.encoder.onUnmappableCharacter(CodingErrorAction.REPLACE);
- } catch (UnsupportedCharsetException uce) {
- //No nio-capable encoder available
- //This may happen with "Cp500" on Sun Java 1.4.2
- this.encoder = null;
- }
+ this.encoder = CharactersetEncoder.newInstance(encoding, isEBDCS);
this.accessor = accessor;
this.characterSetOrientations = new java.util.HashMap(4);
@@ -357,32 +346,8 @@
* @return the encoded characters
* @throws CharacterCodingException if the encoding operation fails
*/
- public byte[] encodeChars(CharSequence chars) throws CharacterCodingException {
- if (encoder != null) {
- ByteBuffer bb;
- // encode method is not thread safe
- synchronized (encoder) {
- bb = encoder.encode(CharBuffer.wrap(chars));
- }
- if (bb.hasArray()) {
- return bb.array();
- } else {
- bb.rewind();
- byte[] bytes = new byte[bb.remaining()];
- bb.get(bytes);
- return bytes;
- }
- } else {
- //Sun Java 1.4.2 compatibility
- byte[] bytes;
- try {
- bytes = chars.toString().getBytes(this.encoding);
- return bytes;
- } catch (UnsupportedEncodingException uee) {
- throw new UnsupportedOperationException(
- "Unsupported encoding: " + uee.getMessage());
- }
- }
+ public EncodedChars encodeChars(CharSequence chars) throws CharacterCodingException {
+ return encoder.encode(chars);
}
/**
Index: src/java/org/apache/fop/afp/fonts/FopCharacterSet.java
===================================================================
--- src/java/org/apache/fop/afp/fonts/FopCharacterSet.java (revision 1147766)
+++ src/java/org/apache/fop/afp/fonts/FopCharacterSet.java (working copy)
@@ -44,7 +44,7 @@
String name,
Typeface charSet) {
- super(codePage, encoding, name, (ResourceAccessor)null);
+ super(codePage, encoding, false, name, (ResourceAccessor) null);
this.charSet = charSet;
}
Index: src/java/org/apache/fop/afp/fonts/CharacterSetBuilder.java
===================================================================
--- src/java/org/apache/fop/afp/fonts/CharacterSetBuilder.java (revision 1147766)
+++ src/java/org/apache/fop/afp/fonts/CharacterSetBuilder.java (working copy)
@@ -30,13 +30,11 @@
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
-
-import org.apache.xmlgraphics.image.loader.util.SoftMapCache;
-
import org.apache.fop.afp.AFPConstants;
import org.apache.fop.afp.util.ResourceAccessor;
import org.apache.fop.afp.util.StructuredFieldReader;
import org.apache.fop.fonts.Typeface;
+import org.apache.xmlgraphics.image.loader.util.SoftMapCache;
/**
* The CharacterSetBuilder is responsible building the a CharacterSet instance that holds
@@ -181,9 +179,9 @@
}
/**
- * Load the font details and metrics into the CharacterSetMetric object,
- * this will use the actual afp code page and character set files to load
- * the object with the necessary metrics.
+ * Load the font details and metrics into the CharacterSetMetric object, this will use the
+ * actual afp code page and character set files to load the object with the necessary metrics.
+ *
* @param characterSetName name of the characterset
* @param codePageName name of the code page file
* @param encoding encoding name
@@ -191,9 +189,47 @@
* @return CharacterSet object
* @throws IOException if an I/O error occurs
*/
- public CharacterSet build(String characterSetName, String codePageName,
- String encoding, ResourceAccessor accessor) throws IOException {
+ public CharacterSet build(String characterSetName, String codePageName, String encoding,
+ ResourceAccessor accessor) throws IOException {
+ return processFont(characterSetName, codePageName, encoding, false, accessor);
+ }
+ /**
+ * Load the font details and metrics into the CharacterSetMetric object, this will use the
+ * actual afp code page and character set files to load the object with the necessary metrics.
+ * This method is to be used for double byte character sets (DBCS).
+ *
+ * @param characterSetName name of the characterset
+ * @param codePageName name of the code page file
+ * @param encoding encoding name
+ * @param isEDBCS if this is an EBCDIC double byte character set (DBCS)
+ * @param accessor used to load codepage and characterset
+ * @return CharacterSet object
+ * @throws IOException if an I/O error occurs
+ */
+ public CharacterSet buildDBCS(String characterSetName, String codePageName, String encoding,
+ boolean isEDBCS, ResourceAccessor accessor) throws IOException {
+ return processFont(characterSetName, codePageName, encoding, isEDBCS, accessor);
+ }
+
+ /**
+ * Load the font details and metrics into the CharacterSetMetric object, this will use the
+ * actual afp code page and character set files to load the object with the necessary metrics.
+ *
+ * @param characterSetName the CharacterSetMetric object to populate
+ * @param codePageName the name of the code page to use
+ * @param encoding name of the encoding in use
+ * @param typeface base14 font name
+ * @return CharacterSet object
+ * @throws IOException if an I/O error occurs
+ */
+ public CharacterSet build(String characterSetName, String codePageName, String encoding,
+ Typeface typeface) throws IOException {
+ return new FopCharacterSet(codePageName, encoding, characterSetName, typeface);
+ }
+
+ private CharacterSet processFont(String characterSetName, String codePageName, String encoding,
+ boolean isEDBCS, ResourceAccessor accessor) throws IOException {
// check for cached version of the characterset
String descriptor = characterSetName + "_" + encoding + "_" + codePageName;
CharacterSet characterSet = (CharacterSet)characterSetsCache.get(descriptor);
@@ -203,8 +239,8 @@
}
// characterset not in the cache, so recreating
- characterSet = new CharacterSet(
- codePageName, encoding, characterSetName, accessor);
+ characterSet = new CharacterSet(codePageName, encoding, isEDBCS, characterSetName,
+ accessor);
InputStream inputStream = null;
@@ -268,26 +304,9 @@
}
characterSetsCache.put(descriptor, characterSet);
return characterSet;
-
}
/**
- * Load the font details and metrics into the CharacterSetMetric object,
- * this will use the actual afp code page and character set files to load
- * the object with the necessary metrics.
- *
- * @param characterSetName the CharacterSetMetric object to populate
- * @param codePageName the name of the code page to use
- * @param encoding name of the encoding in use
- * @param typeface base14 font name
- * @return CharacterSet object
- */
- public CharacterSet build(String characterSetName, String codePageName,
- String encoding, Typeface typeface) {
- return new FopCharacterSet(codePageName, encoding, characterSetName, typeface);
- }
-
- /**
* Load the code page information from the appropriate file. The file name
* to load is determined by the code page name and the file extension 'CDP'.
*
Index: src/java/org/apache/fop/afp/ptoca/PtocaBuilder.java
===================================================================
--- src/java/org/apache/fop/afp/ptoca/PtocaBuilder.java (revision 1147766)
+++ src/java/org/apache/fop/afp/ptoca/PtocaBuilder.java (working copy)
@@ -29,6 +29,7 @@
import org.apache.xmlgraphics.java2d.color.CIELabColorSpace;
import org.apache.xmlgraphics.java2d.color.ColorUtil;
import org.apache.xmlgraphics.java2d.color.ColorWithAlternatives;
+import org.apache.fop.afp.fonts.CharactersetEncoder.EncodedChars;
/**
* Generator class for PTOCA data structures.
@@ -190,34 +191,25 @@
* @param data The text data to add.
* @throws IOException if an I/O error occurs
*/
- public void addTransparentData(byte[] data) throws IOException {
- if (data.length <= TRANSPARENT_DATA_MAX_SIZE) {
- addTransparentDataChunk(data);
- } else {
- // data size greater than TRANSPARENT_MAX_SIZE, so slice
- int numTransData = data.length / TRANSPARENT_DATA_MAX_SIZE;
- int currIndex = 0;
- for (int transDataCnt = 0; transDataCnt < numTransData; transDataCnt++) {
- addTransparentDataChunk(data, currIndex, TRANSPARENT_DATA_MAX_SIZE);
- currIndex += TRANSPARENT_DATA_MAX_SIZE;
- }
- int left = data.length - currIndex;
- addTransparentDataChunk(data, currIndex, left);
+ public void addTransparentData(EncodedChars encodedChars) throws IOException {
+
+ // data size greater than TRANSPARENT_MAX_SIZE, so slice
+ int numTransData = encodedChars.getLength() / TRANSPARENT_DATA_MAX_SIZE;
+ int currIndex = 0;
+ for (int transDataCnt = 0; transDataCnt < numTransData; transDataCnt++) {
+ addTransparentDataChunk(encodedChars, currIndex, TRANSPARENT_DATA_MAX_SIZE);
+ currIndex += TRANSPARENT_DATA_MAX_SIZE;
}
- }
+ int left = encodedChars.getLength() - currIndex;
+ addTransparentDataChunk(encodedChars, currIndex, left);
- private void addTransparentDataChunk(byte[] data) throws IOException {
- addTransparentDataChunk(data, 0, data.length);
}
- private void addTransparentDataChunk(byte[] data, int offset, int length) throws IOException {
- if (length > TRANSPARENT_MAX_SIZE) {
- // Check that we are not exceeding the maximum length
- throw new IllegalArgumentException(
- "Transparent data is longer than " + TRANSPARENT_MAX_SIZE + " bytes");
- }
+
+
+ private void addTransparentDataChunk(EncodedChars encodedChars, int offset, int length) throws IOException {
newControlSequence();
- write(data, offset, length);
+ encodedChars.writeTo(baout, offset, length);
commit(chained(TRN));
}
Index: src/java/org/apache/fop/afp/ptoca/TextDataInfoProducer.java
===================================================================
--- src/java/org/apache/fop/afp/ptoca/TextDataInfoProducer.java (revision 1147766)
+++ src/java/org/apache/fop/afp/ptoca/TextDataInfoProducer.java (working copy)
@@ -22,6 +22,7 @@
import java.io.IOException;
import org.apache.fop.afp.AFPTextDataInfo;
+import org.apache.fop.afp.fonts.CharactersetEncoder;
/**
* {@link PtocaProducer} implementation that interprets {@link AFPTextDataInfo} objects.
@@ -55,8 +56,7 @@
// Add transparent data
String textString = textDataInfo.getString();
String encoding = textDataInfo.getEncoding();
- byte[] data = textString.getBytes(encoding);
- builder.addTransparentData(data);
+ builder.addTransparentData(CharactersetEncoder.encodeSBCS(textString, encoding, false));
}
}
Index: src/documentation/content/xdocs/trunk/output.xml
===================================================================
--- src/documentation/content/xdocs/trunk/output.xml (revision 1147766)
+++ src/documentation/content/xdocs/trunk/output.xml (working copy)
@@ -743,6 +743,12 @@
referenced-fonts section of the configuration file.
However, the default fonts shown above will not be embedded.
+
+ For double byte EBCDIC encoded character sets, there is an optional tag that must be set to prevent
+ characters from being miscoded. This defaults to "false" if not specified.