1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/src/share/jaxws_classes/com/sun/xml/internal/fastinfoset/Encoder.java Wed Apr 27 01:27:09 2016 +0800
1.3 @@ -0,0 +1,2594 @@
1.4 +/*
1.5 + * Copyright (c) 2004, 2011, Oracle and/or its affiliates. All rights reserved.
1.6 + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
1.7 + *
1.8 + * This code is free software; you can redistribute it and/or modify it
1.9 + * under the terms of the GNU General Public License version 2 only, as
1.10 + * published by the Free Software Foundation. Oracle designates this
1.11 + * particular file as subject to the "Classpath" exception as provided
1.12 + * by Oracle in the LICENSE file that accompanied this code.
1.13 + *
1.14 + * This code is distributed in the hope that it will be useful, but WITHOUT
1.15 + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
1.16 + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
1.17 + * version 2 for more details (a copy is included in the LICENSE file that
1.18 + * accompanied this code).
1.19 + *
1.20 + * You should have received a copy of the GNU General Public License version
1.21 + * 2 along with this work; if not, write to the Free Software Foundation,
1.22 + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
1.23 + *
1.24 + * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
1.25 + * or visit www.oracle.com if you need additional information or have any
1.26 + * questions.
1.27 + *
1.28 + * THIS FILE WAS MODIFIED BY SUN MICROSYSTEMS, INC.
1.29 + */
1.30 +
1.31 +package com.sun.xml.internal.fastinfoset;
1.32 +
1.33 +import com.sun.xml.internal.fastinfoset.algorithm.BuiltInEncodingAlgorithmFactory;
1.34 +import com.sun.xml.internal.fastinfoset.org.apache.xerces.util.XMLChar;
1.35 +import com.sun.xml.internal.fastinfoset.util.CharArrayIntMap;
1.36 +import com.sun.xml.internal.fastinfoset.util.KeyIntMap;
1.37 +import com.sun.xml.internal.fastinfoset.util.LocalNameQualifiedNamesMap;
1.38 +import com.sun.xml.internal.fastinfoset.util.StringIntMap;
1.39 +import com.sun.xml.internal.fastinfoset.vocab.SerializerVocabulary;
1.40 +import java.io.IOException;
1.41 +import java.io.OutputStream;
1.42 +import java.util.HashMap;
1.43 +import java.util.Map;
1.44 +import com.sun.xml.internal.org.jvnet.fastinfoset.EncodingAlgorithm;
1.45 +import com.sun.xml.internal.org.jvnet.fastinfoset.EncodingAlgorithmException;
1.46 +import com.sun.xml.internal.org.jvnet.fastinfoset.EncodingAlgorithmIndexes;
1.47 +import com.sun.xml.internal.org.jvnet.fastinfoset.ExternalVocabulary;
1.48 +import com.sun.xml.internal.org.jvnet.fastinfoset.FastInfosetException;
1.49 +import com.sun.xml.internal.org.jvnet.fastinfoset.FastInfosetSerializer;
1.50 +import com.sun.xml.internal.org.jvnet.fastinfoset.RestrictedAlphabet;
1.51 +import com.sun.xml.internal.org.jvnet.fastinfoset.VocabularyApplicationData;
1.52 +import org.xml.sax.helpers.DefaultHandler;
1.53 +
1.54 +/**
1.55 + * Abstract encoder for developing concrete encoders.
1.56 + *
1.57 + * Concrete implementations extending Encoder will utilize methods on Encoder
1.58 + * to encode XML infoset according to the Fast Infoset standard. It is the
1.59 + * responsibility of the concrete implementation to ensure that methods are
1.60 + * invoked in the correct order to produce a valid fast infoset document.
1.61 + *
1.62 + * <p>
1.63 + * This class extends org.sax.xml.DefaultHandler so that concrete SAX
1.64 + * implementations can be used with javax.xml.parsers.SAXParser and the parse
1.65 + * methods that take org.sax.xml.DefaultHandler as a parameter.
1.66 + *
1.67 + * <p>
1.68 + * Buffering of octets that are written to an {@link java.io.OutputStream} is
1.69 + * supported in a similar manner to a {@link java.io.BufferedOutputStream}.
1.70 + * Combining buffering with encoding enables better performance.
1.71 + *
1.72 + * <p>
1.73 + * More than one fast infoset document may be encoded to the
1.74 + * {@link java.io.OutputStream}.
1.75 + *
1.76 + */
1.77 +public abstract class Encoder extends DefaultHandler implements FastInfosetSerializer {
1.78 +
1.79 + /**
1.80 + * Character encoding scheme system property for the encoding
1.81 + * of content and attribute values.
1.82 + */
1.83 + public static final String CHARACTER_ENCODING_SCHEME_SYSTEM_PROPERTY =
1.84 + "com.sun.xml.internal.fastinfoset.serializer.character-encoding-scheme";
1.85 +
1.86 + /**
1.87 + * Default character encoding scheme system property for the encoding
1.88 + * of content and attribute values.
1.89 + */
1.90 + protected static final String _characterEncodingSchemeSystemDefault = getDefaultEncodingScheme();
1.91 +
1.92 + private static String getDefaultEncodingScheme() {
1.93 + String p = System.getProperty(CHARACTER_ENCODING_SCHEME_SYSTEM_PROPERTY,
1.94 + UTF_8);
1.95 + if (p.equals(UTF_16BE)) {
1.96 + return UTF_16BE;
1.97 + } else {
1.98 + return UTF_8;
1.99 + }
1.100 + }
1.101 +
1.102 + private static int[] NUMERIC_CHARACTERS_TABLE;
1.103 +
1.104 + private static int[] DATE_TIME_CHARACTERS_TABLE;
1.105 +
1.106 + static {
1.107 + NUMERIC_CHARACTERS_TABLE = new int[maxCharacter(RestrictedAlphabet.NUMERIC_CHARACTERS) + 1];
1.108 + DATE_TIME_CHARACTERS_TABLE = new int[maxCharacter(RestrictedAlphabet.DATE_TIME_CHARACTERS) + 1];
1.109 +
1.110 + for (int i = 0; i < NUMERIC_CHARACTERS_TABLE.length ; i++) {
1.111 + NUMERIC_CHARACTERS_TABLE[i] = -1;
1.112 + }
1.113 + for (int i = 0; i < DATE_TIME_CHARACTERS_TABLE.length ; i++) {
1.114 + DATE_TIME_CHARACTERS_TABLE[i] = -1;
1.115 + }
1.116 +
1.117 + for (int i = 0; i < RestrictedAlphabet.NUMERIC_CHARACTERS.length() ; i++) {
1.118 + NUMERIC_CHARACTERS_TABLE[RestrictedAlphabet.NUMERIC_CHARACTERS.charAt(i)] = i;
1.119 + }
1.120 + for (int i = 0; i < RestrictedAlphabet.DATE_TIME_CHARACTERS.length() ; i++) {
1.121 + DATE_TIME_CHARACTERS_TABLE[RestrictedAlphabet.DATE_TIME_CHARACTERS.charAt(i)] = i;
1.122 + }
1.123 + }
1.124 +
1.125 + private static int maxCharacter(String alphabet) {
1.126 + int c = 0;
1.127 + for (int i = 0; i < alphabet.length() ; i++) {
1.128 + if (c < alphabet.charAt(i)) {
1.129 + c = alphabet.charAt(i);
1.130 + }
1.131 + }
1.132 +
1.133 + return c;
1.134 + }
1.135 +
1.136 + /**
1.137 + * True if DTD and internal subset shall be ignored.
1.138 + */
1.139 + private boolean _ignoreDTD;
1.140 +
1.141 + /**
1.142 + * True if comments shall be ignored.
1.143 + */
1.144 + private boolean _ignoreComments;
1.145 +
1.146 + /**
1.147 + * True if procesing instructions shall be ignored.
1.148 + */
1.149 + private boolean _ignoreProcessingInstructions;
1.150 +
1.151 + /**
1.152 + * True if white space characters for text content shall be ignored.
1.153 + */
1.154 + private boolean _ignoreWhiteSpaceTextContent;
1.155 +
1.156 + /**
1.157 + * True, if the local name string is used as the key to find the
1.158 + * associated set of qualified names.
1.159 + * <p>
1.160 + * False, if the <prefix>:<local name> string is used as the key
1.161 + * to find the associated set of qualified names.
1.162 + */
1.163 + private boolean _useLocalNameAsKeyForQualifiedNameLookup;
1.164 +
1.165 + /**
1.166 + * True if strings for text content and attribute values will be
1.167 + * UTF-8 encoded otherwise they will be UTF-16 encoded.
1.168 + */
1.169 + private boolean _encodingStringsAsUtf8 = true;
1.170 +
1.171 + /**
1.172 + * Encoding constant generated from the string encoding.
1.173 + */
1.174 + private int _nonIdentifyingStringOnThirdBitCES;
1.175 +
1.176 + /**
1.177 + * Encoding constant generated from the string encoding.
1.178 + */
1.179 + private int _nonIdentifyingStringOnFirstBitCES;
1.180 +
1.181 + /**
1.182 + * The map of URIs to algorithms.
1.183 + */
1.184 + private Map _registeredEncodingAlgorithms = new HashMap();
1.185 +
1.186 + /**
1.187 + * The vocabulary that is used by the encoder
1.188 + */
1.189 + protected SerializerVocabulary _v;
1.190 +
1.191 + /**
1.192 + * The vocabulary application data that is used by the encoder
1.193 + */
1.194 + protected VocabularyApplicationData _vData;
1.195 +
1.196 + /**
1.197 + * True if the vocubulary is internal to the encoder
1.198 + */
1.199 + private boolean _vIsInternal;
1.200 +
1.201 + /**
1.202 + * True if terminatation of an information item is required
1.203 + */
1.204 + protected boolean _terminate = false;
1.205 +
1.206 + /**
1.207 + * The current octet that is to be written.
1.208 + */
1.209 + protected int _b;
1.210 +
1.211 + /**
1.212 + * The {@link java.io.OutputStream} that the encoded XML infoset (the
1.213 + * fast infoset document) is written to.
1.214 + */
1.215 + protected OutputStream _s;
1.216 +
1.217 + /**
1.218 + * The internal buffer of characters used for the UTF-8 or UTF-16 encoding
1.219 + * of characters.
1.220 + */
1.221 + protected char[] _charBuffer = new char[512];
1.222 +
1.223 + /**
1.224 + * The internal buffer of bytes.
1.225 + */
1.226 + protected byte[] _octetBuffer = new byte[1024];
1.227 +
1.228 + /**
1.229 + * The current position in the internal buffer.
1.230 + */
1.231 + protected int _octetBufferIndex;
1.232 +
1.233 + /**
1.234 + * The current mark in the internal buffer.
1.235 + *
1.236 + * <p>
1.237 + * If the value of the mark is < 0 then the mark is not set.
1.238 + */
1.239 + protected int _markIndex = -1;
1.240 +
1.241 + /**
1.242 + * The minimum size of [normalized value] of Attribute Information
1.243 + * Items that will be indexed.
1.244 + */
1.245 + protected int minAttributeValueSize = FastInfosetSerializer.MIN_ATTRIBUTE_VALUE_SIZE;
1.246 +
1.247 + /**
1.248 + * The maximum size of [normalized value] of Attribute Information
1.249 + * Items that will be indexed.
1.250 + */
1.251 + protected int maxAttributeValueSize = FastInfosetSerializer.MAX_ATTRIBUTE_VALUE_SIZE;
1.252 +
1.253 + /**
1.254 + * The limit on the size of indexed Map for attribute values
1.255 + * Limit is measured in characters number
1.256 + */
1.257 + protected int attributeValueMapTotalCharactersConstraint = FastInfosetSerializer.ATTRIBUTE_VALUE_MAP_MEMORY_CONSTRAINT / 2;
1.258 +
1.259 + /**
1.260 + * The minimum size of character content chunks
1.261 + * of Character Information Items or Comment Information Items that
1.262 + * will be indexed.
1.263 + */
1.264 + protected int minCharacterContentChunkSize = FastInfosetSerializer.MIN_CHARACTER_CONTENT_CHUNK_SIZE;
1.265 +
1.266 + /**
1.267 + * The maximum size of character content chunks
1.268 + * of Character Information Items or Comment Information Items that
1.269 + * will be indexed.
1.270 + */
1.271 + protected int maxCharacterContentChunkSize = FastInfosetSerializer.MAX_CHARACTER_CONTENT_CHUNK_SIZE;
1.272 +
1.273 + /**
1.274 + * The limit on the size of indexed Map for character content chunks
1.275 + * Limit is measured in characters number
1.276 + */
1.277 + protected int characterContentChunkMapTotalCharactersConstraint = FastInfosetSerializer.CHARACTER_CONTENT_CHUNK_MAP_MEMORY_CONSTRAINT / 2;
1.278 +
1.279 + /**
1.280 + * Default constructor for the Encoder.
1.281 + */
1.282 + protected Encoder() {
1.283 + setCharacterEncodingScheme(_characterEncodingSchemeSystemDefault);
1.284 + }
1.285 +
1.286 + protected Encoder(boolean useLocalNameAsKeyForQualifiedNameLookup) {
1.287 + setCharacterEncodingScheme(_characterEncodingSchemeSystemDefault);
1.288 + _useLocalNameAsKeyForQualifiedNameLookup = useLocalNameAsKeyForQualifiedNameLookup;
1.289 + }
1.290 +
1.291 +
1.292 + // FastInfosetSerializer interface
1.293 +
1.294 + /**
1.295 + * {@inheritDoc}
1.296 + */
1.297 + public final void setIgnoreDTD(boolean ignoreDTD) {
1.298 + _ignoreDTD = ignoreDTD;
1.299 + }
1.300 +
1.301 + /**
1.302 + * {@inheritDoc}
1.303 + */
1.304 + public final boolean getIgnoreDTD() {
1.305 + return _ignoreDTD;
1.306 + }
1.307 +
1.308 + /**
1.309 + * {@inheritDoc}
1.310 + */
1.311 + public final void setIgnoreComments(boolean ignoreComments) {
1.312 + _ignoreComments = ignoreComments;
1.313 + }
1.314 +
1.315 + /**
1.316 + * {@inheritDoc}
1.317 + */
1.318 + public final boolean getIgnoreComments() {
1.319 + return _ignoreComments;
1.320 + }
1.321 +
1.322 + /**
1.323 + * {@inheritDoc}
1.324 + */
1.325 + public final void setIgnoreProcesingInstructions(boolean
1.326 + ignoreProcesingInstructions) {
1.327 + _ignoreProcessingInstructions = ignoreProcesingInstructions;
1.328 + }
1.329 +
1.330 + /**
1.331 + * {@inheritDoc}
1.332 + */
1.333 + public final boolean getIgnoreProcesingInstructions() {
1.334 + return _ignoreProcessingInstructions;
1.335 + }
1.336 +
1.337 + /**
1.338 + * {@inheritDoc}
1.339 + */
1.340 + public final void setIgnoreWhiteSpaceTextContent(boolean ignoreWhiteSpaceTextContent) {
1.341 + _ignoreWhiteSpaceTextContent = ignoreWhiteSpaceTextContent;
1.342 + }
1.343 +
1.344 + /**
1.345 + * {@inheritDoc}
1.346 + */
1.347 + public final boolean getIgnoreWhiteSpaceTextContent() {
1.348 + return _ignoreWhiteSpaceTextContent;
1.349 + }
1.350 +
1.351 + /**
1.352 + * {@inheritDoc}
1.353 + */
1.354 + public void setCharacterEncodingScheme(String characterEncodingScheme) {
1.355 + if (characterEncodingScheme.equals(UTF_16BE)) {
1.356 + _encodingStringsAsUtf8 = false;
1.357 + _nonIdentifyingStringOnThirdBitCES = EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_UTF_16_FLAG;
1.358 + _nonIdentifyingStringOnFirstBitCES = EncodingConstants.NISTRING_UTF_16_FLAG;
1.359 + } else {
1.360 + _encodingStringsAsUtf8 = true;
1.361 + _nonIdentifyingStringOnThirdBitCES = EncodingConstants.CHARACTER_CHUNK;
1.362 + _nonIdentifyingStringOnFirstBitCES = 0;
1.363 + }
1.364 + }
1.365 +
1.366 + /**
1.367 + * {@inheritDoc}
1.368 + */
1.369 + public String getCharacterEncodingScheme() {
1.370 + return (_encodingStringsAsUtf8) ? UTF_8 : UTF_16BE;
1.371 + }
1.372 +
1.373 + /**
1.374 + * {@inheritDoc}
1.375 + */
1.376 + public void setRegisteredEncodingAlgorithms(Map algorithms) {
1.377 + _registeredEncodingAlgorithms = algorithms;
1.378 + if (_registeredEncodingAlgorithms == null) {
1.379 + _registeredEncodingAlgorithms = new HashMap();
1.380 + }
1.381 + }
1.382 +
1.383 + /**
1.384 + * {@inheritDoc}
1.385 + */
1.386 + public Map getRegisteredEncodingAlgorithms() {
1.387 + return _registeredEncodingAlgorithms;
1.388 + }
1.389 +
1.390 + /**
1.391 + * {@inheritDoc}
1.392 + */
1.393 + public int getMinCharacterContentChunkSize() {
1.394 + return minCharacterContentChunkSize;
1.395 + }
1.396 +
1.397 + /**
1.398 + * {@inheritDoc}
1.399 + */
1.400 + public void setMinCharacterContentChunkSize(int size) {
1.401 + if (size < 0 ) {
1.402 + size = 0;
1.403 + }
1.404 +
1.405 + minCharacterContentChunkSize = size;
1.406 + }
1.407 +
1.408 + /**
1.409 + * {@inheritDoc}
1.410 + */
1.411 + public int getMaxCharacterContentChunkSize() {
1.412 + return maxCharacterContentChunkSize;
1.413 + }
1.414 +
1.415 + /**
1.416 + * {@inheritDoc}
1.417 + */
1.418 + public void setMaxCharacterContentChunkSize(int size) {
1.419 + if (size < 0 ) {
1.420 + size = 0;
1.421 + }
1.422 +
1.423 + maxCharacterContentChunkSize = size;
1.424 + }
1.425 +
1.426 + /**
1.427 + * {@inheritDoc}
1.428 + */
1.429 + public int getCharacterContentChunkMapMemoryLimit() {
1.430 + return characterContentChunkMapTotalCharactersConstraint * 2;
1.431 + }
1.432 +
1.433 + /**
1.434 + * {@inheritDoc}
1.435 + */
1.436 + public void setCharacterContentChunkMapMemoryLimit(int size) {
1.437 + if (size < 0 ) {
1.438 + size = 0;
1.439 + }
1.440 +
1.441 + characterContentChunkMapTotalCharactersConstraint = size / 2;
1.442 + }
1.443 +
1.444 + /**
1.445 + * Checks whether character content chunk (its length) matches length limit
1.446 + *
1.447 + * @param length the length of character content chunk is checking to be added to Map.
1.448 + * @return whether character content chunk length matches limit
1.449 + */
1.450 + public boolean isCharacterContentChunkLengthMatchesLimit(int length) {
1.451 + return length >= minCharacterContentChunkSize &&
1.452 + length < maxCharacterContentChunkSize;
1.453 + }
1.454 +
1.455 + /**
1.456 + * Checks whether character content table has enough memory to
1.457 + * store character content chunk with the given length
1.458 + *
1.459 + * @param length the length of character content chunk is checking to be added to Map.
1.460 + * @param map the custom CharArrayIntMap, which memory limits will be checked.
1.461 + * @return whether character content map has enough memory
1.462 + */
1.463 + public boolean canAddCharacterContentToTable(int length, CharArrayIntMap map) {
1.464 + return map.getTotalCharacterCount() + length <
1.465 + characterContentChunkMapTotalCharactersConstraint;
1.466 + }
1.467 +
1.468 + /**
1.469 + * {@inheritDoc}
1.470 + */
1.471 + public int getMinAttributeValueSize() {
1.472 + return minAttributeValueSize;
1.473 + }
1.474 +
1.475 + /**
1.476 + * {@inheritDoc}
1.477 + */
1.478 + public void setMinAttributeValueSize(int size) {
1.479 + if (size < 0 ) {
1.480 + size = 0;
1.481 + }
1.482 +
1.483 + minAttributeValueSize = size;
1.484 + }
1.485 +
1.486 + /**
1.487 + * {@inheritDoc}
1.488 + */
1.489 + public int getMaxAttributeValueSize() {
1.490 + return maxAttributeValueSize;
1.491 + }
1.492 +
1.493 + /**
1.494 + * {@inheritDoc}
1.495 + */
1.496 + public void setMaxAttributeValueSize(int size) {
1.497 + if (size < 0 ) {
1.498 + size = 0;
1.499 + }
1.500 +
1.501 + maxAttributeValueSize = size;
1.502 + }
1.503 +
1.504 + /**
1.505 + * {@inheritDoc}
1.506 + */
1.507 + public void setAttributeValueMapMemoryLimit(int size) {
1.508 + if (size < 0 ) {
1.509 + size = 0;
1.510 + }
1.511 +
1.512 + attributeValueMapTotalCharactersConstraint = size / 2;
1.513 +
1.514 + }
1.515 +
1.516 + /**
1.517 + * {@inheritDoc}
1.518 + */
1.519 + public int getAttributeValueMapMemoryLimit() {
1.520 + return attributeValueMapTotalCharactersConstraint * 2;
1.521 + }
1.522 +
1.523 + /**
1.524 + * Checks whether attribute value (its length) matches length limit
1.525 + *
1.526 + * @param length the length of attribute
1.527 + * @return whether attribute value matches limit
1.528 + */
1.529 + public boolean isAttributeValueLengthMatchesLimit(int length) {
1.530 + return length >= minAttributeValueSize &&
1.531 + length < maxAttributeValueSize;
1.532 + }
1.533 +
1.534 + /**
1.535 + * Checks whether attribute table has enough memory to
1.536 + * store attribute value with the given length
1.537 + *
1.538 + * @param length the length of attribute value is checking to be added to Map.
1.539 + * @return whether attribute map has enough memory
1.540 + */
1.541 + public boolean canAddAttributeToTable(int length) {
1.542 + return _v.attributeValue.getTotalCharacterCount() + length <
1.543 + attributeValueMapTotalCharactersConstraint;
1.544 + }
1.545 +
1.546 + /**
1.547 + * {@inheritDoc}
1.548 + */
1.549 + public void setExternalVocabulary(ExternalVocabulary v) {
1.550 + // Create internal serializer vocabulary
1.551 + _v = new SerializerVocabulary();
1.552 + // Set the external vocabulary
1.553 + SerializerVocabulary ev = new SerializerVocabulary(v.vocabulary,
1.554 + _useLocalNameAsKeyForQualifiedNameLookup);
1.555 + _v.setExternalVocabulary(v.URI,
1.556 + ev, false);
1.557 +
1.558 + _vIsInternal = true;
1.559 + }
1.560 +
1.561 + /**
1.562 + * {@inheritDoc}
1.563 + */
1.564 + public void setVocabularyApplicationData(VocabularyApplicationData data) {
1.565 + _vData = data;
1.566 + }
1.567 +
1.568 + /**
1.569 + * {@inheritDoc}
1.570 + */
1.571 + public VocabularyApplicationData getVocabularyApplicationData() {
1.572 + return _vData;
1.573 + }
1.574 +
1.575 + // End of FastInfosetSerializer interface
1.576 +
1.577 + /**
1.578 + * Reset the encoder for reuse encoding another XML infoset.
1.579 + */
1.580 + public void reset() {
1.581 + _terminate = false;
1.582 + }
1.583 +
1.584 + /**
1.585 + * Set the OutputStream to encode the XML infoset to a
1.586 + * fast infoset document.
1.587 + *
1.588 + * @param s the OutputStream where the fast infoset document is written to.
1.589 + */
1.590 + public void setOutputStream(OutputStream s) {
1.591 + _octetBufferIndex = 0;
1.592 + _markIndex = -1;
1.593 + _s = s;
1.594 + }
1.595 +
1.596 + /**
1.597 + * Set the SerializerVocabulary to be used for encoding.
1.598 + *
1.599 + * @param vocabulary the vocabulary to be used for encoding.
1.600 + */
1.601 + public void setVocabulary(SerializerVocabulary vocabulary) {
1.602 + _v = vocabulary;
1.603 + _vIsInternal = false;
1.604 + }
1.605 +
1.606 + /**
1.607 + * Encode the header of a fast infoset document.
1.608 + *
1.609 + * @param encodeXmlDecl true if the XML declaration should be encoded.
1.610 + */
1.611 + protected final void encodeHeader(boolean encodeXmlDecl) throws IOException {
1.612 + if (encodeXmlDecl) {
1.613 + _s.write(EncodingConstants.XML_DECLARATION_VALUES[0]);
1.614 + }
1.615 + _s.write(EncodingConstants.BINARY_HEADER);
1.616 + }
1.617 +
1.618 + /**
1.619 + * Encode the initial vocabulary of a fast infoset document.
1.620 + *
1.621 + */
1.622 + protected final void encodeInitialVocabulary() throws IOException {
1.623 + if (_v == null) {
1.624 + _v = new SerializerVocabulary();
1.625 + _vIsInternal = true;
1.626 + } else if (_vIsInternal) {
1.627 + _v.clear();
1.628 + if (_vData != null)
1.629 + _vData.clear();
1.630 + }
1.631 +
1.632 + if (!_v.hasInitialVocabulary() && !_v.hasExternalVocabulary()) {
1.633 + write(0);
1.634 + } else if (_v.hasInitialVocabulary()) {
1.635 + _b = EncodingConstants.DOCUMENT_INITIAL_VOCABULARY_FLAG;
1.636 + write(_b);
1.637 +
1.638 + SerializerVocabulary initialVocabulary = _v.getReadOnlyVocabulary();
1.639 +
1.640 + // TODO check for contents of vocabulary to assign bits
1.641 + if (initialVocabulary.hasExternalVocabulary()) {
1.642 + _b = EncodingConstants.INITIAL_VOCABULARY_EXTERNAL_VOCABULARY_FLAG;
1.643 + write(_b);
1.644 + write(0);
1.645 + }
1.646 +
1.647 + if (initialVocabulary.hasExternalVocabulary()) {
1.648 + encodeNonEmptyOctetStringOnSecondBit(_v.getExternalVocabularyURI());
1.649 + }
1.650 +
1.651 + // TODO check for contents of vocabulary to encode values
1.652 + } else if (_v.hasExternalVocabulary()) {
1.653 + _b = EncodingConstants.DOCUMENT_INITIAL_VOCABULARY_FLAG;
1.654 + write(_b);
1.655 +
1.656 + _b = EncodingConstants.INITIAL_VOCABULARY_EXTERNAL_VOCABULARY_FLAG;
1.657 + write(_b);
1.658 + write(0);
1.659 +
1.660 + encodeNonEmptyOctetStringOnSecondBit(_v.getExternalVocabularyURI());
1.661 + }
1.662 + }
1.663 +
1.664 + /**
1.665 + * Encode the termination of the Document Information Item.
1.666 + *
1.667 + */
1.668 + protected final void encodeDocumentTermination() throws IOException {
1.669 + encodeElementTermination();
1.670 + encodeTermination();
1.671 + _flush();
1.672 + _s.flush();
1.673 + }
1.674 +
1.675 + /**
1.676 + * Encode the termination of an Element Information Item.
1.677 + *
1.678 + */
1.679 + protected final void encodeElementTermination() throws IOException {
1.680 + _terminate = true;
1.681 + switch (_b) {
1.682 + case EncodingConstants.TERMINATOR:
1.683 + _b = EncodingConstants.DOUBLE_TERMINATOR;
1.684 + break;
1.685 + case EncodingConstants.DOUBLE_TERMINATOR:
1.686 + write(EncodingConstants.DOUBLE_TERMINATOR);
1.687 + default:
1.688 + _b = EncodingConstants.TERMINATOR;
1.689 + }
1.690 + }
1.691 +
1.692 + /**
1.693 + * Encode a termination if required.
1.694 + *
1.695 + */
1.696 + protected final void encodeTermination() throws IOException {
1.697 + if (_terminate) {
1.698 + write(_b);
1.699 + _b = 0;
1.700 + _terminate = false;
1.701 + }
1.702 + }
1.703 +
1.704 + /**
1.705 + * Encode a Attribute Information Item that is a namespace declaration.
1.706 + *
1.707 + * @param prefix the prefix of the namespace declaration,
1.708 + * if "" then there is no prefix for the namespace declaration.
1.709 + * @param uri the URI of the namespace declaration,
1.710 + * if "" then there is no URI for the namespace declaration.
1.711 + */
1.712 + protected final void encodeNamespaceAttribute(String prefix, String uri) throws IOException {
1.713 + _b = EncodingConstants.NAMESPACE_ATTRIBUTE;
1.714 + if (prefix.length() > 0) {
1.715 + _b |= EncodingConstants.NAMESPACE_ATTRIBUTE_PREFIX_FLAG;
1.716 + }
1.717 + if (uri.length() > 0) {
1.718 + _b |= EncodingConstants.NAMESPACE_ATTRIBUTE_NAME_FLAG;
1.719 + }
1.720 +
1.721 + // NOTE a prefix with out a namespace name is an undeclaration
1.722 + // of the namespace bound to the prefix
1.723 + // TODO needs to investigate how the startPrefixMapping works in
1.724 + // relation to undeclaration
1.725 +
1.726 + write(_b);
1.727 +
1.728 + if (prefix.length() > 0) {
1.729 + encodeIdentifyingNonEmptyStringOnFirstBit(prefix, _v.prefix);
1.730 + }
1.731 + if (uri.length() > 0) {
1.732 + encodeIdentifyingNonEmptyStringOnFirstBit(uri, _v.namespaceName);
1.733 + }
1.734 + }
1.735 +
1.736 + /**
1.737 + * Encode a chunk of Character Information Items.
1.738 + *
1.739 + * @param ch the array of characters.
1.740 + * @param offset the offset into the array of characters.
1.741 + * @param length the length of characters.
1.742 + * @throws ArrayIndexOutOfBoundsException.
1.743 + */
1.744 + protected final void encodeCharacters(char[] ch, int offset, int length) throws IOException {
1.745 + final boolean addToTable = isCharacterContentChunkLengthMatchesLimit(length);
1.746 + encodeNonIdentifyingStringOnThirdBit(ch, offset, length, _v.characterContentChunk, addToTable, true);
1.747 + }
1.748 +
1.749 + /**
1.750 + * Encode a chunk of Character Information Items.
1.751 + *
1.752 + * If the array of characters is to be indexed (as determined by
1.753 + * {@link Encoder#characterContentChunkSizeContraint}) then the array is not cloned
1.754 + * when adding the array to the vocabulary.
1.755 + *
1.756 + * @param ch the array of characters.
1.757 + * @param offset the offset into the array of characters.
1.758 + * @param length the length of characters.
1.759 + * @throws ArrayIndexOutOfBoundsException.
1.760 + */
1.761 + protected final void encodeCharactersNoClone(char[] ch, int offset, int length) throws IOException {
1.762 + final boolean addToTable = isCharacterContentChunkLengthMatchesLimit(length);
1.763 + encodeNonIdentifyingStringOnThirdBit(ch, offset, length, _v.characterContentChunk, addToTable, false);
1.764 + }
1.765 +
1.766 + /**
1.767 + * Encode a chunk of Character Information Items using a numeric
1.768 + * alphabet that results in the encoding of a character in 4 bits
1.769 + * (or two characters per octet).
1.770 + *
1.771 + * @param id the restricted alphabet identifier.
1.772 + * @param table the table mapping characters to 4 bit values.
1.773 + * @param ch the array of characters.
1.774 + * @param offset the offset into the array of characters.
1.775 + * @param length the length of characters.
1.776 + * @param addToTable if characters should be added to table.
1.777 + * @throws ArrayIndexOutOfBoundsException.
1.778 + */
1.779 + protected final void encodeNumericFourBitCharacters(char[] ch, int offset, int length,
1.780 + boolean addToTable) throws FastInfosetException, IOException {
1.781 + encodeFourBitCharacters(RestrictedAlphabet.NUMERIC_CHARACTERS_INDEX,
1.782 + NUMERIC_CHARACTERS_TABLE, ch, offset, length, addToTable);
1.783 + }
1.784 +
1.785 + /**
1.786 + * Encode a chunk of Character Information Items using a date-time
1.787 + * alphabet that results in the encoding of a character in 4 bits
1.788 + * (or two characters per octet).
1.789 + *
1.790 + * @param id the restricted alphabet identifier.
1.791 + * @param table the table mapping characters to 4 bit values.
1.792 + * @param ch the array of characters.
1.793 + * @param offset the offset into the array of characters.
1.794 + * @param length the length of characters.
1.795 + * @param addToTable if characters should be added to table.
1.796 + * @throws ArrayIndexOutOfBoundsException.
1.797 + */
1.798 + protected final void encodeDateTimeFourBitCharacters(char[] ch, int offset, int length,
1.799 + boolean addToTable) throws FastInfosetException, IOException {
1.800 + encodeFourBitCharacters(RestrictedAlphabet.DATE_TIME_CHARACTERS_INDEX,
1.801 + DATE_TIME_CHARACTERS_TABLE, ch, offset, length, addToTable);
1.802 + }
1.803 +
1.804 + /**
1.805 + * Encode a chunk of Character Information Items using a restricted
1.806 + * alphabet that results in the encoding of a character in 4 bits
1.807 + * (or two characters per octet).
1.808 + *
1.809 + * @param id the restricted alphabet identifier.
1.810 + * @param table the table mapping characters to 4 bit values.
1.811 + * @param ch the array of characters.
1.812 + * @param offset the offset into the array of characters.
1.813 + * @param length the length of characters.
1.814 + * @param addToTable if characters should be added to table.
1.815 + * @throws ArrayIndexOutOfBoundsException.
1.816 + */
1.817 + protected final void encodeFourBitCharacters(int id, int[] table, char[] ch, int offset, int length,
1.818 + boolean addToTable) throws FastInfosetException, IOException {
1.819 + if (addToTable) {
1.820 + // if char array could be added to table
1.821 + boolean canAddCharacterContentToTable =
1.822 + canAddCharacterContentToTable(length, _v.characterContentChunk);
1.823 +
1.824 + // obtain/get index
1.825 + int index = canAddCharacterContentToTable ?
1.826 + _v.characterContentChunk.obtainIndex(ch, offset, length, true) :
1.827 + _v.characterContentChunk.get(ch, offset, length);
1.828 +
1.829 + if (index != KeyIntMap.NOT_PRESENT) {
1.830 + // if char array is in table
1.831 + _b = EncodingConstants.CHARACTER_CHUNK | 0x20;
1.832 + encodeNonZeroIntegerOnFourthBit(index);
1.833 + return;
1.834 + } else if (canAddCharacterContentToTable) {
1.835 + // if char array is not in table, but could be added
1.836 + _b = EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_RESTRICTED_ALPHABET_FLAG | EncodingConstants.CHARACTER_CHUNK_ADD_TO_TABLE_FLAG;
1.837 + } else {
1.838 + // if char array is not in table and could not be added
1.839 + _b = EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_RESTRICTED_ALPHABET_FLAG;
1.840 + }
1.841 + } else {
1.842 + _b = EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_RESTRICTED_ALPHABET_FLAG;
1.843 + }
1.844 +
1.845 + write (_b);
1.846 +
1.847 + // Encode bottom 6 bits of enoding algorithm id
1.848 + _b = id << 2;
1.849 +
1.850 + encodeNonEmptyFourBitCharacterStringOnSeventhBit(table, ch, offset, length);
1.851 + }
1.852 +
1.853 + /**
1.854 + * Encode a chunk of Character Information Items using a restricted
1.855 + * alphabet table.
1.856 + *
1.857 + * @param alphabet the alphabet defining the mapping between characters and
1.858 + * integer values.
1.859 + * @param ch the array of characters.
1.860 + * @param offset the offset into the array of characters.
1.861 + * @param length the length of characters.
1.862 + * @param addToTable if characters should be added to table
1.863 + * @throws ArrayIndexOutOfBoundsException.
1.864 + * @throws FastInfosetException if the alphabet is not present in the
1.865 + * vocabulary.
1.866 + */
1.867 + protected final void encodeAlphabetCharacters(String alphabet, char[] ch, int offset, int length,
1.868 + boolean addToTable) throws FastInfosetException, IOException {
1.869 + if (addToTable) {
1.870 + // if char array could be added to table
1.871 + boolean canAddCharacterContentToTable =
1.872 + canAddCharacterContentToTable(length, _v.characterContentChunk);
1.873 +
1.874 + // obtain/get index
1.875 + int index = canAddCharacterContentToTable ?
1.876 + _v.characterContentChunk.obtainIndex(ch, offset, length, true) :
1.877 + _v.characterContentChunk.get(ch, offset, length);
1.878 +
1.879 + if (index != KeyIntMap.NOT_PRESENT) {
1.880 + // if char array is in table
1.881 + _b = EncodingConstants.CHARACTER_CHUNK | 0x20;
1.882 + encodeNonZeroIntegerOnFourthBit(index);
1.883 + return;
1.884 + } else if (canAddCharacterContentToTable) {
1.885 + // if char array is not in table, but could be added
1.886 + _b = EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_RESTRICTED_ALPHABET_FLAG | EncodingConstants.CHARACTER_CHUNK_ADD_TO_TABLE_FLAG;
1.887 + } else {
1.888 + // if char array is not in table and could not be added
1.889 + _b = EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_RESTRICTED_ALPHABET_FLAG;
1.890 + }
1.891 + } else {
1.892 + _b = EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_RESTRICTED_ALPHABET_FLAG;
1.893 + }
1.894 +
1.895 + int id = _v.restrictedAlphabet.get(alphabet);
1.896 + if (id == KeyIntMap.NOT_PRESENT) {
1.897 + throw new FastInfosetException(CommonResourceBundle.getInstance().getString("message.restrictedAlphabetNotPresent"));
1.898 + }
1.899 + id += EncodingConstants.RESTRICTED_ALPHABET_APPLICATION_START;
1.900 +
1.901 + _b |= (id & 0xC0) >> 6;
1.902 + write(_b);
1.903 +
1.904 + // Encode bottom 6 bits of enoding algorithm id
1.905 + _b = (id & 0x3F) << 2;
1.906 +
1.907 + encodeNonEmptyNBitCharacterStringOnSeventhBit(alphabet, ch, offset, length);
1.908 + }
1.909 +
1.910 + /**
1.911 + * Encode a Processing Instruction Information Item.
1.912 + *
1.913 + * @param target the target of the processing instruction.
1.914 + * @param data the data of the processing instruction.
1.915 + */
1.916 + protected final void encodeProcessingInstruction(String target, String data) throws IOException {
1.917 + write(EncodingConstants.PROCESSING_INSTRUCTION);
1.918 +
1.919 + // Target
1.920 + encodeIdentifyingNonEmptyStringOnFirstBit(target, _v.otherNCName);
1.921 +
1.922 + // Data
1.923 + boolean addToTable = isCharacterContentChunkLengthMatchesLimit(data.length());
1.924 + encodeNonIdentifyingStringOnFirstBit(data, _v.otherString, addToTable);
1.925 + }
1.926 +
1.927 + /**
1.928 + * Encode a Document Type Declaration.
1.929 + *
1.930 + * @param systemId the system identifier of the external subset.
1.931 + * @param publicId the public identifier of the external subset.
1.932 + */
1.933 + protected final void encodeDocumentTypeDeclaration(String systemId, String publicId) throws IOException {
1.934 + _b = EncodingConstants.DOCUMENT_TYPE_DECLARATION;
1.935 + if (systemId != null && systemId.length() > 0) {
1.936 + _b |= EncodingConstants.DOCUMENT_TYPE_SYSTEM_IDENTIFIER_FLAG;
1.937 + }
1.938 + if (publicId != null && publicId.length() > 0) {
1.939 + _b |= EncodingConstants.DOCUMENT_TYPE_PUBLIC_IDENTIFIER_FLAG;
1.940 + }
1.941 + write(_b);
1.942 +
1.943 + if (systemId != null && systemId.length() > 0) {
1.944 + encodeIdentifyingNonEmptyStringOnFirstBit(systemId, _v.otherURI);
1.945 + }
1.946 + if (publicId != null && publicId.length() > 0) {
1.947 + encodeIdentifyingNonEmptyStringOnFirstBit(publicId, _v.otherURI);
1.948 + }
1.949 + }
1.950 +
1.951 + /**
1.952 + * Encode a Comment Information Item.
1.953 + *
1.954 + * @param ch the array of characters that is as comment.
1.955 + * @param offset the offset into the array of characters.
1.956 + * @param length the length of characters.
1.957 + * @throws ArrayIndexOutOfBoundsException.
1.958 + */
1.959 + protected final void encodeComment(char[] ch, int offset, int length) throws IOException {
1.960 + write(EncodingConstants.COMMENT);
1.961 +
1.962 + boolean addToTable = isCharacterContentChunkLengthMatchesLimit(length);
1.963 + encodeNonIdentifyingStringOnFirstBit(ch, offset, length, _v.otherString, addToTable, true);
1.964 + }
1.965 +
1.966 + /**
1.967 + * Encode a Comment Information Item.
1.968 + *
1.969 + * If the array of characters that is a comment is to be indexed (as
1.970 + * determined by {@link Encoder#characterContentChunkSizeContraint}) then
1.971 + * the array is not cloned when adding the array to the vocabulary.
1.972 + *
1.973 + * @param ch the array of characters.
1.974 + * @param offset the offset into the array of characters.
1.975 + * @param length the length of characters.
1.976 + * @throws ArrayIndexOutOfBoundsException.
1.977 + */
1.978 + protected final void encodeCommentNoClone(char[] ch, int offset, int length) throws IOException {
1.979 + write(EncodingConstants.COMMENT);
1.980 +
1.981 + boolean addToTable = isCharacterContentChunkLengthMatchesLimit(length);
1.982 + encodeNonIdentifyingStringOnFirstBit(ch, offset, length, _v.otherString, addToTable, false);
1.983 + }
1.984 +
1.985 + /**
1.986 + * Encode a qualified name of an Element Informaiton Item on the third bit
1.987 + * of an octet.
1.988 + * Implementation of clause C.18 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.989 + *
1.990 + * <p>
1.991 + * The index of the qualified name will be encoded if the name is present
1.992 + * in the vocabulary otherwise the qualified name will be encoded literally
1.993 + * (see {@link #encodeLiteralElementQualifiedNameOnThirdBit}).
1.994 + *
1.995 + * @param namespaceURI the namespace URI of the qualified name.
1.996 + * @param prefix the prefix of the qualified name.
1.997 + * @param localName the local name of the qualified name.
1.998 + */
1.999 + protected final void encodeElementQualifiedNameOnThirdBit(String namespaceURI, String prefix, String localName) throws IOException {
1.1000 + LocalNameQualifiedNamesMap.Entry entry = _v.elementName.obtainEntry(localName);
1.1001 + if (entry._valueIndex > 0) {
1.1002 + QualifiedName[] names = entry._value;
1.1003 + for (int i = 0; i < entry._valueIndex; i++) {
1.1004 + if ((prefix == names[i].prefix || prefix.equals(names[i].prefix))
1.1005 + && (namespaceURI == names[i].namespaceName || namespaceURI.equals(names[i].namespaceName))) {
1.1006 + encodeNonZeroIntegerOnThirdBit(names[i].index);
1.1007 + return;
1.1008 + }
1.1009 + }
1.1010 + }
1.1011 +
1.1012 + encodeLiteralElementQualifiedNameOnThirdBit(namespaceURI, prefix,
1.1013 + localName, entry);
1.1014 + }
1.1015 +
1.1016 + /**
1.1017 + * Encode a literal qualified name of an Element Informaiton Item on the
1.1018 + * third bit of an octet.
1.1019 + * Implementation of clause C.18 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1020 + *
1.1021 + * @param namespaceURI the namespace URI of the qualified name.
1.1022 + * @param prefix the prefix of the qualified name.
1.1023 + * @param localName the local name of the qualified name.
1.1024 + */
1.1025 + protected final void encodeLiteralElementQualifiedNameOnThirdBit(String namespaceURI, String prefix, String localName,
1.1026 + LocalNameQualifiedNamesMap.Entry entry) throws IOException {
1.1027 + QualifiedName name = new QualifiedName(prefix, namespaceURI, localName, "", _v.elementName.getNextIndex());
1.1028 + entry.addQualifiedName(name);
1.1029 +
1.1030 + int namespaceURIIndex = KeyIntMap.NOT_PRESENT;
1.1031 + int prefixIndex = KeyIntMap.NOT_PRESENT;
1.1032 + if (namespaceURI.length() > 0) {
1.1033 + namespaceURIIndex = _v.namespaceName.get(namespaceURI);
1.1034 + if (namespaceURIIndex == KeyIntMap.NOT_PRESENT) {
1.1035 + throw new IOException(CommonResourceBundle.getInstance().getString("message.namespaceURINotIndexed", new Object[]{namespaceURI}));
1.1036 + }
1.1037 +
1.1038 + if (prefix.length() > 0) {
1.1039 + prefixIndex = _v.prefix.get(prefix);
1.1040 + if (prefixIndex == KeyIntMap.NOT_PRESENT) {
1.1041 + throw new IOException(CommonResourceBundle.getInstance().getString("message.prefixNotIndexed", new Object[]{prefix}));
1.1042 + }
1.1043 + }
1.1044 + }
1.1045 +
1.1046 + int localNameIndex = _v.localName.obtainIndex(localName);
1.1047 +
1.1048 + _b |= EncodingConstants.ELEMENT_LITERAL_QNAME_FLAG;
1.1049 + if (namespaceURIIndex >= 0) {
1.1050 + _b |= EncodingConstants.LITERAL_QNAME_NAMESPACE_NAME_FLAG;
1.1051 + if (prefixIndex >= 0) {
1.1052 + _b |= EncodingConstants.LITERAL_QNAME_PREFIX_FLAG;
1.1053 + }
1.1054 + }
1.1055 + write(_b);
1.1056 +
1.1057 + if (namespaceURIIndex >= 0) {
1.1058 + if (prefixIndex >= 0) {
1.1059 + encodeNonZeroIntegerOnSecondBitFirstBitOne(prefixIndex);
1.1060 + }
1.1061 + encodeNonZeroIntegerOnSecondBitFirstBitOne(namespaceURIIndex);
1.1062 + }
1.1063 +
1.1064 + if (localNameIndex >= 0) {
1.1065 + encodeNonZeroIntegerOnSecondBitFirstBitOne(localNameIndex);
1.1066 + } else {
1.1067 + encodeNonEmptyOctetStringOnSecondBit(localName);
1.1068 + }
1.1069 + }
1.1070 +
1.1071 + /**
1.1072 + * Encode a qualified name of an Attribute Informaiton Item on the third bit
1.1073 + * of an octet.
1.1074 + * Implementation of clause C.17 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1075 + *
1.1076 + * <p>
1.1077 + * The index of the qualified name will be encoded if the name is present
1.1078 + * in the vocabulary otherwise the qualified name will be encoded literally
1.1079 + * (see {@link #encodeLiteralAttributeQualifiedNameOnSecondBit}).
1.1080 + *
1.1081 + * @param namespaceURI the namespace URI of the qualified name.
1.1082 + * @param prefix the prefix of the qualified name.
1.1083 + * @param localName the local name of the qualified name.
1.1084 + */
1.1085 + protected final void encodeAttributeQualifiedNameOnSecondBit(String namespaceURI, String prefix, String localName) throws IOException {
1.1086 + LocalNameQualifiedNamesMap.Entry entry = _v.attributeName.obtainEntry(localName);
1.1087 + if (entry._valueIndex > 0) {
1.1088 + QualifiedName[] names = entry._value;
1.1089 + for (int i = 0; i < entry._valueIndex; i++) {
1.1090 + if ((prefix == names[i].prefix || prefix.equals(names[i].prefix))
1.1091 + && (namespaceURI == names[i].namespaceName || namespaceURI.equals(names[i].namespaceName))) {
1.1092 + encodeNonZeroIntegerOnSecondBitFirstBitZero(names[i].index);
1.1093 + return;
1.1094 + }
1.1095 + }
1.1096 + }
1.1097 +
1.1098 + encodeLiteralAttributeQualifiedNameOnSecondBit(namespaceURI, prefix,
1.1099 + localName, entry);
1.1100 + }
1.1101 +
1.1102 + /**
1.1103 + * Encode a literal qualified name of an Attribute Informaiton Item on the
1.1104 + * third bit of an octet.
1.1105 + * Implementation of clause C.17 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1106 + *
1.1107 + * @param namespaceURI the namespace URI of the qualified name.
1.1108 + * @param prefix the prefix of the qualified name.
1.1109 + * @param localName the local name of the qualified name.
1.1110 + */
1.1111 + protected final boolean encodeLiteralAttributeQualifiedNameOnSecondBit(String namespaceURI, String prefix, String localName,
1.1112 + LocalNameQualifiedNamesMap.Entry entry) throws IOException {
1.1113 + int namespaceURIIndex = KeyIntMap.NOT_PRESENT;
1.1114 + int prefixIndex = KeyIntMap.NOT_PRESENT;
1.1115 + if (namespaceURI.length() > 0) {
1.1116 + namespaceURIIndex = _v.namespaceName.get(namespaceURI);
1.1117 + if (namespaceURIIndex == KeyIntMap.NOT_PRESENT) {
1.1118 + if (namespaceURI == EncodingConstants.XMLNS_NAMESPACE_NAME ||
1.1119 + namespaceURI.equals(EncodingConstants.XMLNS_NAMESPACE_NAME)) {
1.1120 + return false;
1.1121 + } else {
1.1122 + throw new IOException(CommonResourceBundle.getInstance().getString("message.namespaceURINotIndexed", new Object[]{namespaceURI}));
1.1123 + }
1.1124 + }
1.1125 +
1.1126 + if (prefix.length() > 0) {
1.1127 + prefixIndex = _v.prefix.get(prefix);
1.1128 + if (prefixIndex == KeyIntMap.NOT_PRESENT) {
1.1129 + throw new IOException(CommonResourceBundle.getInstance().getString("message.prefixNotIndexed", new Object[]{prefix}));
1.1130 + }
1.1131 + }
1.1132 + }
1.1133 +
1.1134 + int localNameIndex = _v.localName.obtainIndex(localName);
1.1135 +
1.1136 + QualifiedName name = new QualifiedName(prefix, namespaceURI, localName, "", _v.attributeName.getNextIndex());
1.1137 + entry.addQualifiedName(name);
1.1138 +
1.1139 + _b = EncodingConstants.ATTRIBUTE_LITERAL_QNAME_FLAG;
1.1140 + if (namespaceURI.length() > 0) {
1.1141 + _b |= EncodingConstants.LITERAL_QNAME_NAMESPACE_NAME_FLAG;
1.1142 + if (prefix.length() > 0) {
1.1143 + _b |= EncodingConstants.LITERAL_QNAME_PREFIX_FLAG;
1.1144 + }
1.1145 + }
1.1146 +
1.1147 + write(_b);
1.1148 +
1.1149 + if (namespaceURIIndex >= 0) {
1.1150 + if (prefixIndex >= 0) {
1.1151 + encodeNonZeroIntegerOnSecondBitFirstBitOne(prefixIndex);
1.1152 + }
1.1153 + encodeNonZeroIntegerOnSecondBitFirstBitOne(namespaceURIIndex);
1.1154 + } else if (namespaceURI != "") {
1.1155 + // XML prefix and namespace name
1.1156 + encodeNonEmptyOctetStringOnSecondBit("xml");
1.1157 + encodeNonEmptyOctetStringOnSecondBit("http://www.w3.org/XML/1998/namespace");
1.1158 + }
1.1159 +
1.1160 + if (localNameIndex >= 0) {
1.1161 + encodeNonZeroIntegerOnSecondBitFirstBitOne(localNameIndex);
1.1162 + } else {
1.1163 + encodeNonEmptyOctetStringOnSecondBit(localName);
1.1164 + }
1.1165 +
1.1166 + return true;
1.1167 + }
1.1168 +
1.1169 + /**
1.1170 + * Encode a non identifying string on the first bit of an octet.
1.1171 + * Implementation of clause C.14 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1172 + *
1.1173 + * @param s the string to encode
1.1174 + * @param map the vocabulary table of strings to indexes.
1.1175 + * @param addToTable true if the string could be added to the vocabulary
1.1176 + * table (if table has enough memory)
1.1177 + * @param mustBeAddedToTable true if the string must be added to the vocabulary
1.1178 + * table (if not already present in the table).
1.1179 + */
1.1180 + protected final void encodeNonIdentifyingStringOnFirstBit(String s, StringIntMap map,
1.1181 + boolean addToTable, boolean mustBeAddedToTable) throws IOException {
1.1182 + if (s == null || s.length() == 0) {
1.1183 + // C.26 an index (first bit '1') with seven '1' bits for an empty string
1.1184 + write(0xFF);
1.1185 + } else {
1.1186 + if (addToTable || mustBeAddedToTable) {
1.1187 + // if attribute value could be added to table
1.1188 + boolean canAddAttributeToTable = mustBeAddedToTable ||
1.1189 + canAddAttributeToTable(s.length());
1.1190 +
1.1191 + // obtain/get index
1.1192 + int index = canAddAttributeToTable ?
1.1193 + map.obtainIndex(s) :
1.1194 + map.get(s);
1.1195 +
1.1196 + if (index != KeyIntMap.NOT_PRESENT) {
1.1197 + // if attribute value is in table
1.1198 + encodeNonZeroIntegerOnSecondBitFirstBitOne(index);
1.1199 + } else if (canAddAttributeToTable) {
1.1200 + // if attribute value is not in table, but could be added
1.1201 + _b = EncodingConstants.NISTRING_ADD_TO_TABLE_FLAG |
1.1202 + _nonIdentifyingStringOnFirstBitCES;
1.1203 + encodeNonEmptyCharacterStringOnFifthBit(s);
1.1204 + } else {
1.1205 + // if attribute value is not in table and could not be added
1.1206 + _b = _nonIdentifyingStringOnFirstBitCES;
1.1207 + encodeNonEmptyCharacterStringOnFifthBit(s);
1.1208 + }
1.1209 + } else {
1.1210 + _b = _nonIdentifyingStringOnFirstBitCES;
1.1211 + encodeNonEmptyCharacterStringOnFifthBit(s);
1.1212 + }
1.1213 + }
1.1214 + }
1.1215 +
1.1216 + /**
1.1217 + * Encode a non identifying string on the first bit of an octet.
1.1218 + * Implementation of clause C.14 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1219 + *
1.1220 + * @param s the string to encode
1.1221 + * @param map the vocabulary table of character arrays to indexes.
1.1222 + * @param addToTable true if the string should be added to the vocabulary
1.1223 + * table (if not already present in the table).
1.1224 + */
1.1225 + protected final void encodeNonIdentifyingStringOnFirstBit(String s, CharArrayIntMap map, boolean addToTable) throws IOException {
1.1226 + if (s == null || s.length() == 0) {
1.1227 + // C.26 an index (first bit '1') with seven '1' bits for an empty string
1.1228 + write(0xFF);
1.1229 + } else {
1.1230 + if (addToTable) {
1.1231 + final char[] ch = s.toCharArray();
1.1232 + final int length = s.length();
1.1233 +
1.1234 + // if char array could be added to table
1.1235 + boolean canAddCharacterContentToTable =
1.1236 + canAddCharacterContentToTable(length, map);
1.1237 +
1.1238 + // obtain/get index
1.1239 + int index = canAddCharacterContentToTable ?
1.1240 + map.obtainIndex(ch, 0, length, false) :
1.1241 + map.get(ch, 0, length);
1.1242 +
1.1243 + if (index != KeyIntMap.NOT_PRESENT) {
1.1244 + // if char array is in table
1.1245 + encodeNonZeroIntegerOnSecondBitFirstBitOne(index);
1.1246 + } else if (canAddCharacterContentToTable) {
1.1247 + // if char array is not in table, but could be added
1.1248 + _b = EncodingConstants.NISTRING_ADD_TO_TABLE_FLAG |
1.1249 + _nonIdentifyingStringOnFirstBitCES;
1.1250 + encodeNonEmptyCharacterStringOnFifthBit(ch, 0, length);
1.1251 + } else {
1.1252 + // if char array is not in table and could not be added
1.1253 + _b = _nonIdentifyingStringOnFirstBitCES;
1.1254 + encodeNonEmptyCharacterStringOnFifthBit(s);
1.1255 + }
1.1256 + } else {
1.1257 + _b = _nonIdentifyingStringOnFirstBitCES;
1.1258 + encodeNonEmptyCharacterStringOnFifthBit(s);
1.1259 + }
1.1260 + }
1.1261 + }
1.1262 +
1.1263 + /**
1.1264 + * Encode a non identifying string on the first bit of an octet.
1.1265 + * Implementation of clause C.14 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1266 + *
1.1267 + * @param ch the array of characters.
1.1268 + * @param offset the offset into the array of characters.
1.1269 + * @param length the length of characters.
1.1270 + * @param map the vocabulary table of character arrays to indexes.
1.1271 + * @param addToTable true if the string should be added to the vocabulary
1.1272 + * table (if not already present in the table).
1.1273 + * @param clone true if the array of characters should be cloned if added
1.1274 + * to the vocabulary table.
1.1275 + */
1.1276 + protected final void encodeNonIdentifyingStringOnFirstBit(char[] ch, int offset, int length, CharArrayIntMap map,
1.1277 + boolean addToTable, boolean clone) throws IOException {
1.1278 + if (length == 0) {
1.1279 + // C.26 an index (first bit '1') with seven '1' bits for an empty string
1.1280 + write(0xFF);
1.1281 + } else {
1.1282 + if (addToTable) {
1.1283 + // if char array could be added to table
1.1284 + boolean canAddCharacterContentToTable =
1.1285 + canAddCharacterContentToTable(length, map);
1.1286 +
1.1287 + // obtain/get index
1.1288 + int index = canAddCharacterContentToTable ?
1.1289 + map.obtainIndex(ch, offset, length, clone) :
1.1290 + map.get(ch, offset, length);
1.1291 +
1.1292 + if (index != KeyIntMap.NOT_PRESENT) {
1.1293 + // if char array is in table
1.1294 + encodeNonZeroIntegerOnSecondBitFirstBitOne(index);
1.1295 + } else if (canAddCharacterContentToTable) {
1.1296 + // if char array is not in table, but could be added
1.1297 + _b = EncodingConstants.NISTRING_ADD_TO_TABLE_FLAG |
1.1298 + _nonIdentifyingStringOnFirstBitCES;
1.1299 + encodeNonEmptyCharacterStringOnFifthBit(ch, offset, length);
1.1300 + } else {
1.1301 + // if char array is not in table and could not be added
1.1302 + _b = _nonIdentifyingStringOnFirstBitCES;
1.1303 + encodeNonEmptyCharacterStringOnFifthBit(ch, offset, length);
1.1304 + }
1.1305 + } else {
1.1306 + _b = _nonIdentifyingStringOnFirstBitCES;
1.1307 + encodeNonEmptyCharacterStringOnFifthBit(ch, offset, length);
1.1308 + }
1.1309 + }
1.1310 + }
1.1311 +
1.1312 + protected final void encodeNumericNonIdentifyingStringOnFirstBit(
1.1313 + String s, boolean addToTable, boolean mustBeAddedToTable)
1.1314 + throws IOException, FastInfosetException {
1.1315 + encodeNonIdentifyingStringOnFirstBit(
1.1316 + RestrictedAlphabet.NUMERIC_CHARACTERS_INDEX,
1.1317 + NUMERIC_CHARACTERS_TABLE, s, addToTable,
1.1318 + mustBeAddedToTable);
1.1319 + }
1.1320 +
1.1321 + protected final void encodeDateTimeNonIdentifyingStringOnFirstBit(
1.1322 + String s, boolean addToTable, boolean mustBeAddedToTable)
1.1323 + throws IOException, FastInfosetException {
1.1324 + encodeNonIdentifyingStringOnFirstBit(
1.1325 + RestrictedAlphabet.DATE_TIME_CHARACTERS_INDEX,
1.1326 + DATE_TIME_CHARACTERS_TABLE, s, addToTable,
1.1327 + mustBeAddedToTable);
1.1328 + }
1.1329 +
1.1330 + protected final void encodeNonIdentifyingStringOnFirstBit(int id, int[] table,
1.1331 + String s, boolean addToTable, boolean mustBeAddedToTable)
1.1332 + throws IOException, FastInfosetException {
1.1333 + if (s == null || s.length() == 0) {
1.1334 + // C.26 an index (first bit '1') with seven '1' bits for an empty string
1.1335 + write(0xFF);
1.1336 + return;
1.1337 + }
1.1338 +
1.1339 + if (addToTable || mustBeAddedToTable) {
1.1340 + // if attribute value could be added to table
1.1341 + boolean canAddAttributeToTable = mustBeAddedToTable ||
1.1342 + canAddAttributeToTable(s.length());
1.1343 +
1.1344 + // obtain/get index
1.1345 + int index = canAddAttributeToTable ?
1.1346 + _v.attributeValue.obtainIndex(s) :
1.1347 + _v.attributeValue.get(s);
1.1348 +
1.1349 + if (index != KeyIntMap.NOT_PRESENT) {
1.1350 + // if attribute value is in table
1.1351 + encodeNonZeroIntegerOnSecondBitFirstBitOne(index);
1.1352 + return;
1.1353 + } else if (canAddAttributeToTable) {
1.1354 + // if attribute value is not in table, but could be added
1.1355 + _b = EncodingConstants.NISTRING_RESTRICTED_ALPHABET_FLAG |
1.1356 + EncodingConstants.NISTRING_ADD_TO_TABLE_FLAG;
1.1357 + } else {
1.1358 + // if attribute value is not in table and could not be added
1.1359 + _b = EncodingConstants.NISTRING_RESTRICTED_ALPHABET_FLAG;
1.1360 + }
1.1361 + } else {
1.1362 + _b = EncodingConstants.NISTRING_RESTRICTED_ALPHABET_FLAG;
1.1363 + }
1.1364 +
1.1365 + // Encode identification and top four bits of alphabet id
1.1366 + write (_b | ((id & 0xF0) >> 4));
1.1367 + // Encode bottom 4 bits of alphabet id
1.1368 + _b = (id & 0x0F) << 4;
1.1369 +
1.1370 + final int length = s.length();
1.1371 + final int octetPairLength = length / 2;
1.1372 + final int octetSingleLength = length % 2;
1.1373 + encodeNonZeroOctetStringLengthOnFifthBit(octetPairLength + octetSingleLength);
1.1374 + encodeNonEmptyFourBitCharacterString(table, s.toCharArray(), 0, octetPairLength, octetSingleLength);
1.1375 + }
1.1376 +
1.1377 + /**
1.1378 + * Encode a non identifying string on the first bit of an octet as binary
1.1379 + * data using an encoding algorithm.
1.1380 + * Implementation of clause C.14 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1381 + *
1.1382 + * @param URI the encoding algorithm URI. If the URI == null then the
1.1383 + * encoding algorithm identifier takes precendence.
1.1384 + * @param id the encoding algorithm identifier.
1.1385 + * @param data the data to be encoded using an encoding algorithm.
1.1386 + * @throws EncodingAlgorithmException if the encoding algorithm URI is not
1.1387 + * present in the vocabulary, or the encoding algorithm identifier
1.1388 + * is not with the required range.
1.1389 + */
1.1390 + protected final void encodeNonIdentifyingStringOnFirstBit(String URI, int id, Object data) throws FastInfosetException, IOException {
1.1391 + if (URI != null) {
1.1392 + id = _v.encodingAlgorithm.get(URI);
1.1393 + if (id == KeyIntMap.NOT_PRESENT) {
1.1394 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.EncodingAlgorithmURI", new Object[]{URI}));
1.1395 + }
1.1396 + id += EncodingConstants.ENCODING_ALGORITHM_APPLICATION_START;
1.1397 +
1.1398 + EncodingAlgorithm ea = (EncodingAlgorithm)_registeredEncodingAlgorithms.get(URI);
1.1399 + if (ea != null) {
1.1400 + encodeAIIObjectAlgorithmData(id, data, ea);
1.1401 + } else {
1.1402 + if (data instanceof byte[]) {
1.1403 + byte[] d = (byte[])data;
1.1404 + encodeAIIOctetAlgorithmData(id, d, 0, d.length);
1.1405 + } else {
1.1406 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.nullEncodingAlgorithmURI"));
1.1407 + }
1.1408 + }
1.1409 + } else if (id <= EncodingConstants.ENCODING_ALGORITHM_BUILTIN_END) {
1.1410 + int length = 0;
1.1411 + switch(id) {
1.1412 + case EncodingAlgorithmIndexes.HEXADECIMAL:
1.1413 + case EncodingAlgorithmIndexes.BASE64:
1.1414 + length = ((byte[])data).length;
1.1415 + break;
1.1416 + case EncodingAlgorithmIndexes.SHORT:
1.1417 + length = ((short[])data).length;
1.1418 + break;
1.1419 + case EncodingAlgorithmIndexes.INT:
1.1420 + length = ((int[])data).length;
1.1421 + break;
1.1422 + case EncodingAlgorithmIndexes.LONG:
1.1423 + case EncodingAlgorithmIndexes.UUID:
1.1424 + length = ((long[])data).length;
1.1425 + break;
1.1426 + case EncodingAlgorithmIndexes.BOOLEAN:
1.1427 + length = ((boolean[])data).length;
1.1428 + break;
1.1429 + case EncodingAlgorithmIndexes.FLOAT:
1.1430 + length = ((float[])data).length;
1.1431 + break;
1.1432 + case EncodingAlgorithmIndexes.DOUBLE:
1.1433 + length = ((double[])data).length;
1.1434 + break;
1.1435 + case EncodingAlgorithmIndexes.CDATA:
1.1436 + throw new UnsupportedOperationException(CommonResourceBundle.getInstance().getString("message.CDATA"));
1.1437 + default:
1.1438 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.UnsupportedBuiltInAlgorithm", new Object[]{Integer.valueOf(id)}));
1.1439 + }
1.1440 + encodeAIIBuiltInAlgorithmData(id, data, 0, length);
1.1441 + } else if (id >= EncodingConstants.ENCODING_ALGORITHM_APPLICATION_START) {
1.1442 + if (data instanceof byte[]) {
1.1443 + byte[] d = (byte[])data;
1.1444 + encodeAIIOctetAlgorithmData(id, d, 0, d.length);
1.1445 + } else {
1.1446 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.nullEncodingAlgorithmURI"));
1.1447 + }
1.1448 + } else {
1.1449 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.identifiers10to31Reserved"));
1.1450 + }
1.1451 + }
1.1452 +
1.1453 + /**
1.1454 + * Encode the [normalized value] of an Attribute Information Item using
1.1455 + * using an encoding algorithm.
1.1456 + * Implementation of clause C.14 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1457 + *
1.1458 + * @param id the encoding algorithm identifier.
1.1459 + * @param d the data, as an array of bytes, to be encoded.
1.1460 + * @param offset the offset into the array of bytes.
1.1461 + * @param length the length of bytes.
1.1462 + */
1.1463 + protected final void encodeAIIOctetAlgorithmData(int id, byte[] d, int offset, int length) throws IOException {
1.1464 + // Encode identification and top four bits of encoding algorithm id
1.1465 + write (EncodingConstants.NISTRING_ENCODING_ALGORITHM_FLAG |
1.1466 + ((id & 0xF0) >> 4));
1.1467 +
1.1468 + // Encode bottom 4 bits of enoding algorithm id
1.1469 + _b = (id & 0x0F) << 4;
1.1470 +
1.1471 + // Encode the length
1.1472 + encodeNonZeroOctetStringLengthOnFifthBit(length);
1.1473 +
1.1474 + write(d, offset, length);
1.1475 + }
1.1476 +
1.1477 + /**
1.1478 + * Encode the [normalized value] of an Attribute Information Item using
1.1479 + * using an encoding algorithm.
1.1480 + * Implementation of clause C.14 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1481 + *
1.1482 + * @param id the encoding algorithm identifier.
1.1483 + * @param data the data to be encoded using an encoding algorithm.
1.1484 + * @param ea the encoding algorithm to use to encode the data into an
1.1485 + * array of bytes.
1.1486 + */
1.1487 + protected final void encodeAIIObjectAlgorithmData(int id, Object data, EncodingAlgorithm ea) throws FastInfosetException, IOException {
1.1488 + // Encode identification and top four bits of encoding algorithm id
1.1489 + write (EncodingConstants.NISTRING_ENCODING_ALGORITHM_FLAG |
1.1490 + ((id & 0xF0) >> 4));
1.1491 +
1.1492 + // Encode bottom 4 bits of enoding algorithm id
1.1493 + _b = (id & 0x0F) << 4;
1.1494 +
1.1495 + _encodingBufferOutputStream.reset();
1.1496 + ea.encodeToOutputStream(data, _encodingBufferOutputStream);
1.1497 + encodeNonZeroOctetStringLengthOnFifthBit(_encodingBufferIndex);
1.1498 + write(_encodingBuffer, _encodingBufferIndex);
1.1499 + }
1.1500 +
1.1501 + /**
1.1502 + * Encode the [normalized value] of an Attribute Information Item using
1.1503 + * using a built in encoding algorithm.
1.1504 + * Implementation of clause C.14 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1505 + *
1.1506 + * @param id the built in encoding algorithm identifier.
1.1507 + * @param data the data to be encoded using an encoding algorithm. The data
1.1508 + * represents an array of items specified by the encoding algorithm
1.1509 + * identifier
1.1510 + * @param offset the offset into the array of bytes.
1.1511 + * @param length the length of bytes.
1.1512 + */
1.1513 + protected final void encodeAIIBuiltInAlgorithmData(int id, Object data, int offset, int length) throws IOException {
1.1514 + // Encode identification and top four bits of encoding algorithm id
1.1515 + write (EncodingConstants.NISTRING_ENCODING_ALGORITHM_FLAG |
1.1516 + ((id & 0xF0) >> 4));
1.1517 +
1.1518 + // Encode bottom 4 bits of enoding algorithm id
1.1519 + _b = (id & 0x0F) << 4;
1.1520 +
1.1521 + final int octetLength = BuiltInEncodingAlgorithmFactory.getAlgorithm(id).
1.1522 + getOctetLengthFromPrimitiveLength(length);
1.1523 +
1.1524 + encodeNonZeroOctetStringLengthOnFifthBit(octetLength);
1.1525 +
1.1526 + ensureSize(octetLength);
1.1527 + BuiltInEncodingAlgorithmFactory.getAlgorithm(id).
1.1528 + encodeToBytes(data, offset, length, _octetBuffer, _octetBufferIndex);
1.1529 + _octetBufferIndex += octetLength;
1.1530 + }
1.1531 +
1.1532 + /**
1.1533 + * Encode a non identifying string on the third bit of an octet.
1.1534 + * Implementation of clause C.15 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1535 + *
1.1536 + * @param ch the array of characters.
1.1537 + * @param offset the offset into the array of characters.
1.1538 + * @param length the length of characters.
1.1539 + * @param map the vocabulary table of character arrays to indexes.
1.1540 + * @param addToTable true if the array of characters should be added to the vocabulary
1.1541 + * table (if not already present in the table).
1.1542 + * @param clone true if the array of characters should be cloned if added
1.1543 + * to the vocabulary table.
1.1544 + */
1.1545 + protected final void encodeNonIdentifyingStringOnThirdBit(char[] ch, int offset, int length,
1.1546 + CharArrayIntMap map, boolean addToTable, boolean clone) throws IOException {
1.1547 + // length cannot be zero since sequence of CIIs has to be > 0
1.1548 +
1.1549 + if (addToTable) {
1.1550 + // if char array could be added to table
1.1551 + boolean canAddCharacterContentToTable =
1.1552 + canAddCharacterContentToTable(length, map);
1.1553 +
1.1554 + // obtain/get index
1.1555 + int index = canAddCharacterContentToTable ?
1.1556 + map.obtainIndex(ch, offset, length, clone) :
1.1557 + map.get(ch, offset, length);
1.1558 +
1.1559 + if (index != KeyIntMap.NOT_PRESENT) {
1.1560 + // if char array is in table
1.1561 + _b = EncodingConstants.CHARACTER_CHUNK | 0x20;
1.1562 + encodeNonZeroIntegerOnFourthBit(index);
1.1563 + } else if (canAddCharacterContentToTable) {
1.1564 + // if char array is not in table, but could be added
1.1565 + _b = EncodingConstants.CHARACTER_CHUNK_ADD_TO_TABLE_FLAG |
1.1566 + _nonIdentifyingStringOnThirdBitCES;
1.1567 + encodeNonEmptyCharacterStringOnSeventhBit(ch, offset, length);
1.1568 + } else {
1.1569 + // if char array is not in table and could not be added
1.1570 + _b = _nonIdentifyingStringOnThirdBitCES;
1.1571 + encodeNonEmptyCharacterStringOnSeventhBit(ch, offset, length);
1.1572 + }
1.1573 + } else {
1.1574 + // char array will not be added to map
1.1575 + _b = _nonIdentifyingStringOnThirdBitCES;
1.1576 + encodeNonEmptyCharacterStringOnSeventhBit(ch, offset, length);
1.1577 + }
1.1578 + }
1.1579 +
1.1580 + /**
1.1581 + * Encode a non identifying string on the third bit of an octet as binary
1.1582 + * data using an encoding algorithm.
1.1583 + * Implementation of clause C.15 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1584 + *
1.1585 + * @param URI the encoding algorithm URI. If the URI == null then the
1.1586 + * encoding algorithm identifier takes precendence.
1.1587 + * @param id the encoding algorithm identifier.
1.1588 + * @param data the data to be encoded using an encoding algorithm.
1.1589 + * @throws EncodingAlgorithmException if the encoding algorithm URI is not
1.1590 + * present in the vocabulary, or the encoding algorithm identifier
1.1591 + * is not with the required range.
1.1592 + */
1.1593 + protected final void encodeNonIdentifyingStringOnThirdBit(String URI, int id, Object data) throws FastInfosetException, IOException {
1.1594 + if (URI != null) {
1.1595 + id = _v.encodingAlgorithm.get(URI);
1.1596 + if (id == KeyIntMap.NOT_PRESENT) {
1.1597 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.EncodingAlgorithmURI", new Object[]{URI}));
1.1598 + }
1.1599 + id += EncodingConstants.ENCODING_ALGORITHM_APPLICATION_START;
1.1600 +
1.1601 + EncodingAlgorithm ea = (EncodingAlgorithm)_registeredEncodingAlgorithms.get(URI);
1.1602 + if (ea != null) {
1.1603 + encodeCIIObjectAlgorithmData(id, data, ea);
1.1604 + } else {
1.1605 + if (data instanceof byte[]) {
1.1606 + byte[] d = (byte[])data;
1.1607 + encodeCIIOctetAlgorithmData(id, d, 0, d.length);
1.1608 + } else {
1.1609 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.nullEncodingAlgorithmURI"));
1.1610 + }
1.1611 + }
1.1612 + } else if (id <= EncodingConstants.ENCODING_ALGORITHM_BUILTIN_END) {
1.1613 + int length = 0;
1.1614 + switch(id) {
1.1615 + case EncodingAlgorithmIndexes.HEXADECIMAL:
1.1616 + case EncodingAlgorithmIndexes.BASE64:
1.1617 + length = ((byte[])data).length;
1.1618 + break;
1.1619 + case EncodingAlgorithmIndexes.SHORT:
1.1620 + length = ((short[])data).length;
1.1621 + break;
1.1622 + case EncodingAlgorithmIndexes.INT:
1.1623 + length = ((int[])data).length;
1.1624 + break;
1.1625 + case EncodingAlgorithmIndexes.LONG:
1.1626 + case EncodingAlgorithmIndexes.UUID:
1.1627 + length = ((long[])data).length;
1.1628 + break;
1.1629 + case EncodingAlgorithmIndexes.BOOLEAN:
1.1630 + length = ((boolean[])data).length;
1.1631 + break;
1.1632 + case EncodingAlgorithmIndexes.FLOAT:
1.1633 + length = ((float[])data).length;
1.1634 + break;
1.1635 + case EncodingAlgorithmIndexes.DOUBLE:
1.1636 + length = ((double[])data).length;
1.1637 + break;
1.1638 + case EncodingAlgorithmIndexes.CDATA:
1.1639 + throw new UnsupportedOperationException(CommonResourceBundle.getInstance().getString("message.CDATA"));
1.1640 + default:
1.1641 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.UnsupportedBuiltInAlgorithm", new Object[]{Integer.valueOf(id)}));
1.1642 + }
1.1643 + encodeCIIBuiltInAlgorithmData(id, data, 0, length);
1.1644 + } else if (id >= EncodingConstants.ENCODING_ALGORITHM_APPLICATION_START) {
1.1645 + if (data instanceof byte[]) {
1.1646 + byte[] d = (byte[])data;
1.1647 + encodeCIIOctetAlgorithmData(id, d, 0, d.length);
1.1648 + } else {
1.1649 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.nullEncodingAlgorithmURI"));
1.1650 + }
1.1651 + } else {
1.1652 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.identifiers10to31Reserved"));
1.1653 + }
1.1654 + }
1.1655 +
1.1656 + /**
1.1657 + * Encode a non identifying string on the third bit of an octet as binary
1.1658 + * data using an encoding algorithm.
1.1659 + * Implementation of clause C.15 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1660 + *
1.1661 + * @param URI the encoding algorithm URI. If the URI == null then the
1.1662 + * encoding algorithm identifier takes precendence.
1.1663 + * @param id the encoding algorithm identifier.
1.1664 + * @param d the data, as an array of bytes, to be encoded.
1.1665 + * @param offset the offset into the array of bytes.
1.1666 + * @param length the length of bytes.
1.1667 + * @throws EncodingAlgorithmException if the encoding algorithm URI is not
1.1668 + * present in the vocabulary.
1.1669 + */
1.1670 + protected final void encodeNonIdentifyingStringOnThirdBit(String URI, int id, byte[] d, int offset, int length) throws FastInfosetException, IOException {
1.1671 + if (URI != null) {
1.1672 + id = _v.encodingAlgorithm.get(URI);
1.1673 + if (id == KeyIntMap.NOT_PRESENT) {
1.1674 + throw new EncodingAlgorithmException(CommonResourceBundle.getInstance().getString("message.EncodingAlgorithmURI", new Object[]{URI}));
1.1675 + }
1.1676 + id += EncodingConstants.ENCODING_ALGORITHM_APPLICATION_START;
1.1677 + }
1.1678 +
1.1679 + encodeCIIOctetAlgorithmData(id, d, offset, length);
1.1680 + }
1.1681 +
1.1682 + /**
1.1683 + * Encode a chunk of Character Information Items using
1.1684 + * using an encoding algorithm.
1.1685 + * Implementation of clause C.15 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1686 + *
1.1687 + * @param id the encoding algorithm identifier.
1.1688 + * @param d the data, as an array of bytes, to be encoded.
1.1689 + * @param offset the offset into the array of bytes.
1.1690 + * @param length the length of bytes.
1.1691 + */
1.1692 + protected final void encodeCIIOctetAlgorithmData(int id, byte[] d, int offset, int length) throws IOException {
1.1693 + // Encode identification and top two bits of encoding algorithm id
1.1694 + write (EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_ENCODING_ALGORITHM_FLAG |
1.1695 + ((id & 0xC0) >> 6));
1.1696 +
1.1697 + // Encode bottom 6 bits of enoding algorithm id
1.1698 + _b = (id & 0x3F) << 2;
1.1699 +
1.1700 + // Encode the length
1.1701 + encodeNonZeroOctetStringLengthOnSenventhBit(length);
1.1702 +
1.1703 + write(d, offset, length);
1.1704 + }
1.1705 +
1.1706 + /**
1.1707 + * Encode a chunk of Character Information Items using
1.1708 + * using an encoding algorithm.
1.1709 + * Implementation of clause C.15 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1710 + *
1.1711 + * @param id the encoding algorithm identifier.
1.1712 + * @param data the data to be encoded using an encoding algorithm.
1.1713 + * @param ea the encoding algorithm to use to encode the data into an
1.1714 + * array of bytes.
1.1715 + */
1.1716 + protected final void encodeCIIObjectAlgorithmData(int id, Object data, EncodingAlgorithm ea) throws FastInfosetException, IOException {
1.1717 + // Encode identification and top two bits of encoding algorithm id
1.1718 + write (EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_ENCODING_ALGORITHM_FLAG |
1.1719 + ((id & 0xC0) >> 6));
1.1720 +
1.1721 + // Encode bottom 6 bits of enoding algorithm id
1.1722 + _b = (id & 0x3F) << 2;
1.1723 +
1.1724 + _encodingBufferOutputStream.reset();
1.1725 + ea.encodeToOutputStream(data, _encodingBufferOutputStream);
1.1726 + encodeNonZeroOctetStringLengthOnSenventhBit(_encodingBufferIndex);
1.1727 + write(_encodingBuffer, _encodingBufferIndex);
1.1728 + }
1.1729 +
1.1730 + /**
1.1731 + * Encode a chunk of Character Information Items using
1.1732 + * using an encoding algorithm.
1.1733 + * Implementation of clause C.15 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1734 + *
1.1735 + * @param id the built in encoding algorithm identifier.
1.1736 + * @param data the data to be encoded using an encoding algorithm. The data
1.1737 + * represents an array of items specified by the encoding algorithm
1.1738 + * identifier
1.1739 + * @param offset the offset into the array of bytes.
1.1740 + * @param length the length of bytes.
1.1741 + */
1.1742 + protected final void encodeCIIBuiltInAlgorithmData(int id, Object data, int offset, int length) throws FastInfosetException, IOException {
1.1743 + // Encode identification and top two bits of encoding algorithm id
1.1744 + write (EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_ENCODING_ALGORITHM_FLAG |
1.1745 + ((id & 0xC0) >> 6));
1.1746 +
1.1747 + // Encode bottom 6 bits of enoding algorithm id
1.1748 + _b = (id & 0x3F) << 2;
1.1749 +
1.1750 + final int octetLength = BuiltInEncodingAlgorithmFactory.getAlgorithm(id).
1.1751 + getOctetLengthFromPrimitiveLength(length);
1.1752 +
1.1753 + encodeNonZeroOctetStringLengthOnSenventhBit(octetLength);
1.1754 +
1.1755 + ensureSize(octetLength);
1.1756 + BuiltInEncodingAlgorithmFactory.getAlgorithm(id).
1.1757 + encodeToBytes(data, offset, length, _octetBuffer, _octetBufferIndex);
1.1758 + _octetBufferIndex += octetLength;
1.1759 + }
1.1760 +
1.1761 + /**
1.1762 + * Encode a chunk of Character Information Items using
1.1763 + * using the CDATA built in encoding algorithm.
1.1764 + * Implementation of clause C.15 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1765 + *
1.1766 + * @param ch the array of characters.
1.1767 + * @param offset the offset into the array of characters.
1.1768 + * @param length the length of characters.
1.1769 + */
1.1770 + protected final void encodeCIIBuiltInAlgorithmDataAsCDATA(char[] ch, int offset, int length) throws FastInfosetException, IOException {
1.1771 + // Encode identification and top two bits of encoding algorithm id
1.1772 + write (EncodingConstants.CHARACTER_CHUNK | EncodingConstants.CHARACTER_CHUNK_ENCODING_ALGORITHM_FLAG);
1.1773 +
1.1774 + // Encode bottom 6 bits of enoding algorithm id
1.1775 + _b = EncodingAlgorithmIndexes.CDATA << 2;
1.1776 +
1.1777 +
1.1778 + length = encodeUTF8String(ch, offset, length);
1.1779 + encodeNonZeroOctetStringLengthOnSenventhBit(length);
1.1780 + write(_encodingBuffer, length);
1.1781 + }
1.1782 +
1.1783 + /**
1.1784 + * Encode a non empty identifying string on the first bit of an octet.
1.1785 + * Implementation of clause C.13 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1786 + *
1.1787 + * @param s the identifying string.
1.1788 + * @param map the vocabulary table to use to determin the index of the
1.1789 + * identifying string
1.1790 + */
1.1791 + protected final void encodeIdentifyingNonEmptyStringOnFirstBit(String s, StringIntMap map) throws IOException {
1.1792 + int index = map.obtainIndex(s);
1.1793 + if (index == KeyIntMap.NOT_PRESENT) {
1.1794 + // _b = 0;
1.1795 + encodeNonEmptyOctetStringOnSecondBit(s);
1.1796 + } else {
1.1797 + // _b = 0x80;
1.1798 + encodeNonZeroIntegerOnSecondBitFirstBitOne(index);
1.1799 + }
1.1800 + }
1.1801 +
1.1802 + /**
1.1803 + * Encode a non empty string on the second bit of an octet using the UTF-8
1.1804 + * encoding.
1.1805 + * Implementation of clause C.22 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1806 + *
1.1807 + * @param s the string.
1.1808 + */
1.1809 + protected final void encodeNonEmptyOctetStringOnSecondBit(String s) throws IOException {
1.1810 + final int length = encodeUTF8String(s);
1.1811 + encodeNonZeroOctetStringLengthOnSecondBit(length);
1.1812 + write(_encodingBuffer, length);
1.1813 + }
1.1814 +
1.1815 + /**
1.1816 + * Encode the length of a UTF-8 encoded string on the second bit of an octet.
1.1817 + * Implementation of clause C.22 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1818 + *
1.1819 + * @param length the length to encode.
1.1820 + */
1.1821 + protected final void encodeNonZeroOctetStringLengthOnSecondBit(int length) throws IOException {
1.1822 + if (length < EncodingConstants.OCTET_STRING_LENGTH_2ND_BIT_SMALL_LIMIT) {
1.1823 + // [1, 64]
1.1824 + write(length - 1);
1.1825 + } else if (length < EncodingConstants.OCTET_STRING_LENGTH_2ND_BIT_MEDIUM_LIMIT) {
1.1826 + // [65, 320]
1.1827 + write(EncodingConstants.OCTET_STRING_LENGTH_2ND_BIT_MEDIUM_FLAG); // 010 00000
1.1828 + write(length - EncodingConstants.OCTET_STRING_LENGTH_2ND_BIT_SMALL_LIMIT);
1.1829 + } else {
1.1830 + // [321, 4294967296]
1.1831 + write(EncodingConstants.OCTET_STRING_LENGTH_2ND_BIT_LARGE_FLAG); // 0110 0000
1.1832 + length -= EncodingConstants.OCTET_STRING_LENGTH_2ND_BIT_MEDIUM_LIMIT;
1.1833 + write(length >>> 24);
1.1834 + write((length >> 16) & 0xFF);
1.1835 + write((length >> 8) & 0xFF);
1.1836 + write(length & 0xFF);
1.1837 + }
1.1838 + }
1.1839 +
1.1840 + /**
1.1841 + * Encode a non empty string on the fifth bit of an octet using the UTF-8
1.1842 + * or UTF-16 encoding.
1.1843 + * Implementation of clause C.23 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1844 + *
1.1845 + * @param s the string.
1.1846 + */
1.1847 + protected final void encodeNonEmptyCharacterStringOnFifthBit(String s) throws IOException {
1.1848 + final int length = (_encodingStringsAsUtf8) ? encodeUTF8String(s) : encodeUtf16String(s);
1.1849 + encodeNonZeroOctetStringLengthOnFifthBit(length);
1.1850 + write(_encodingBuffer, length);
1.1851 + }
1.1852 +
1.1853 + /**
1.1854 + * Encode a non empty string on the fifth bit of an octet using the UTF-8
1.1855 + * or UTF-16 encoding.
1.1856 + * Implementation of clause C.23 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1857 + *
1.1858 + * @param ch the array of characters.
1.1859 + * @param offset the offset into the array of characters.
1.1860 + * @param length the length of characters.
1.1861 + */
1.1862 + protected final void encodeNonEmptyCharacterStringOnFifthBit(char[] ch, int offset, int length) throws IOException {
1.1863 + length = (_encodingStringsAsUtf8) ? encodeUTF8String(ch, offset, length) : encodeUtf16String(ch, offset, length);
1.1864 + encodeNonZeroOctetStringLengthOnFifthBit(length);
1.1865 + write(_encodingBuffer, length);
1.1866 + }
1.1867 +
1.1868 + /**
1.1869 + * Encode the length of a UTF-8 or UTF-16 encoded string on the fifth bit
1.1870 + * of an octet.
1.1871 + * Implementation of clause C.23 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1872 + *
1.1873 + * @param length the length to encode.
1.1874 + */
1.1875 + protected final void encodeNonZeroOctetStringLengthOnFifthBit(int length) throws IOException {
1.1876 + if (length < EncodingConstants.OCTET_STRING_LENGTH_5TH_BIT_SMALL_LIMIT) {
1.1877 + // [1, 8]
1.1878 + write(_b | (length - 1));
1.1879 + } else if (length < EncodingConstants.OCTET_STRING_LENGTH_5TH_BIT_MEDIUM_LIMIT) {
1.1880 + // [9, 264]
1.1881 + write(_b | EncodingConstants.OCTET_STRING_LENGTH_5TH_BIT_MEDIUM_FLAG); // 000010 00
1.1882 + write(length - EncodingConstants.OCTET_STRING_LENGTH_5TH_BIT_SMALL_LIMIT);
1.1883 + } else {
1.1884 + // [265, 4294967296]
1.1885 + write(_b | EncodingConstants.OCTET_STRING_LENGTH_5TH_BIT_LARGE_FLAG); // 000011 00
1.1886 + length -= EncodingConstants.OCTET_STRING_LENGTH_5TH_BIT_MEDIUM_LIMIT;
1.1887 + write(length >>> 24);
1.1888 + write((length >> 16) & 0xFF);
1.1889 + write((length >> 8) & 0xFF);
1.1890 + write(length & 0xFF);
1.1891 + }
1.1892 + }
1.1893 +
1.1894 + /**
1.1895 + * Encode a non empty string on the seventh bit of an octet using the UTF-8
1.1896 + * or UTF-16 encoding.
1.1897 + * Implementation of clause C.24 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1898 + *
1.1899 + * @param ch the array of characters.
1.1900 + * @param offset the offset into the array of characters.
1.1901 + * @param length the length of characters.
1.1902 + */
1.1903 + protected final void encodeNonEmptyCharacterStringOnSeventhBit(char[] ch, int offset, int length) throws IOException {
1.1904 + length = (_encodingStringsAsUtf8) ? encodeUTF8String(ch, offset, length) : encodeUtf16String(ch, offset, length);
1.1905 + encodeNonZeroOctetStringLengthOnSenventhBit(length);
1.1906 + write(_encodingBuffer, length);
1.1907 + }
1.1908 +
1.1909 + /**
1.1910 + * Encode a non empty string on the seventh bit of an octet using a restricted
1.1911 + * alphabet that results in the encoding of a character in 4 bits
1.1912 + * (or two characters per octet).
1.1913 + * Implementation of clause C.24 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1914 + *
1.1915 + * @param table the table mapping characters to 4 bit values.
1.1916 + * @param ch the array of characters.
1.1917 + * @param offset the offset into the array of characters.
1.1918 + * @param length the length of characters.
1.1919 + */
1.1920 + protected final void encodeNonEmptyFourBitCharacterStringOnSeventhBit(int[] table, char[] ch, int offset, int length) throws FastInfosetException, IOException {
1.1921 + final int octetPairLength = length / 2;
1.1922 + final int octetSingleLength = length % 2;
1.1923 +
1.1924 + // Encode the length
1.1925 + encodeNonZeroOctetStringLengthOnSenventhBit(octetPairLength + octetSingleLength);
1.1926 + encodeNonEmptyFourBitCharacterString(table, ch, offset, octetPairLength, octetSingleLength);
1.1927 + }
1.1928 +
1.1929 + protected final void encodeNonEmptyFourBitCharacterString(int[] table, char[] ch, int offset,
1.1930 + int octetPairLength, int octetSingleLength) throws FastInfosetException, IOException {
1.1931 + ensureSize(octetPairLength + octetSingleLength);
1.1932 + // Encode all pairs
1.1933 + int v = 0;
1.1934 + for (int i = 0; i < octetPairLength; i++) {
1.1935 + v = (table[ch[offset++]] << 4) | table[ch[offset++]];
1.1936 + if (v < 0) {
1.1937 + throw new FastInfosetException(CommonResourceBundle.getInstance().getString("message.characterOutofAlphabetRange"));
1.1938 + }
1.1939 + _octetBuffer[_octetBufferIndex++] = (byte)v;
1.1940 + }
1.1941 + // Encode single character at end with termination bits
1.1942 + if (octetSingleLength == 1) {
1.1943 + v = (table[ch[offset]] << 4) | 0x0F;
1.1944 + if (v < 0) {
1.1945 + throw new FastInfosetException(CommonResourceBundle.getInstance().getString("message.characterOutofAlphabetRange"));
1.1946 + }
1.1947 + _octetBuffer[_octetBufferIndex++] = (byte)v;
1.1948 + }
1.1949 + }
1.1950 +
1.1951 + /**
1.1952 + * Encode a non empty string on the seventh bit of an octet using a restricted
1.1953 + * alphabet table.
1.1954 + * Implementation of clause C.24 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.1955 + *
1.1956 + * @param alphabet the alphabet defining the mapping between characters and
1.1957 + * integer values.
1.1958 + * @param ch the array of characters.
1.1959 + * @param offset the offset into the array of characters.
1.1960 + * @param length the length of characters.
1.1961 + */
1.1962 + protected final void encodeNonEmptyNBitCharacterStringOnSeventhBit(String alphabet, char[] ch, int offset, int length) throws FastInfosetException, IOException {
1.1963 + int bitsPerCharacter = 1;
1.1964 + while ((1 << bitsPerCharacter) <= alphabet.length()) {
1.1965 + bitsPerCharacter++;
1.1966 + }
1.1967 +
1.1968 + final int bits = length * bitsPerCharacter;
1.1969 + final int octets = bits / 8;
1.1970 + final int bitsOfLastOctet = bits % 8;
1.1971 + final int totalOctets = octets + ((bitsOfLastOctet > 0) ? 1 : 0);
1.1972 +
1.1973 + // Encode the length
1.1974 + encodeNonZeroOctetStringLengthOnSenventhBit(totalOctets);
1.1975 +
1.1976 + resetBits();
1.1977 + ensureSize(totalOctets);
1.1978 + int v = 0;
1.1979 + for (int i = 0; i < length; i++) {
1.1980 + final char c = ch[offset + i];
1.1981 + // This is grotesquely slow, need to use hash table of character to int value
1.1982 + for (v = 0; v < alphabet.length(); v++) {
1.1983 + if (c == alphabet.charAt(v)) {
1.1984 + break;
1.1985 + }
1.1986 + }
1.1987 + if (v == alphabet.length()) {
1.1988 + throw new FastInfosetException(CommonResourceBundle.getInstance().getString("message.characterOutofAlphabetRange"));
1.1989 + }
1.1990 + writeBits(bitsPerCharacter, v);
1.1991 + }
1.1992 +
1.1993 + if (bitsOfLastOctet > 0) {
1.1994 + _b |= (1 << (8 - bitsOfLastOctet)) - 1;
1.1995 + write(_b);
1.1996 + }
1.1997 + }
1.1998 +
1.1999 + private int _bitsLeftInOctet;
1.2000 +
1.2001 + private final void resetBits() {
1.2002 + _bitsLeftInOctet = 8;
1.2003 + _b = 0;
1.2004 + }
1.2005 +
1.2006 + private final void writeBits(int bits, int v) throws IOException {
1.2007 + while (bits > 0) {
1.2008 + final int bit = (v & (1 << --bits)) > 0 ? 1 : 0;
1.2009 + _b |= bit << (--_bitsLeftInOctet);
1.2010 + if (_bitsLeftInOctet == 0) {
1.2011 + write(_b);
1.2012 + _bitsLeftInOctet = 8;
1.2013 + _b = 0;
1.2014 + }
1.2015 + }
1.2016 + }
1.2017 +
1.2018 + /**
1.2019 + * Encode the length of a encoded string on the seventh bit
1.2020 + * of an octet.
1.2021 + * Implementation of clause C.24 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.2022 + *
1.2023 + * @param length the length to encode.
1.2024 + */
1.2025 + protected final void encodeNonZeroOctetStringLengthOnSenventhBit(int length) throws IOException {
1.2026 + if (length < EncodingConstants.OCTET_STRING_LENGTH_7TH_BIT_SMALL_LIMIT) {
1.2027 + // [1, 2]
1.2028 + write(_b | (length - 1));
1.2029 + } else if (length < EncodingConstants.OCTET_STRING_LENGTH_7TH_BIT_MEDIUM_LIMIT) {
1.2030 + // [3, 258]
1.2031 + write(_b | EncodingConstants.OCTET_STRING_LENGTH_7TH_BIT_MEDIUM_FLAG); // 00000010
1.2032 + write(length - EncodingConstants.OCTET_STRING_LENGTH_7TH_BIT_SMALL_LIMIT);
1.2033 + } else {
1.2034 + // [259, 4294967296]
1.2035 + write(_b | EncodingConstants.OCTET_STRING_LENGTH_7TH_BIT_LARGE_FLAG); // 00000011
1.2036 + length -= EncodingConstants.OCTET_STRING_LENGTH_7TH_BIT_MEDIUM_LIMIT;
1.2037 + write(length >>> 24);
1.2038 + write((length >> 16) & 0xFF);
1.2039 + write((length >> 8) & 0xFF);
1.2040 + write(length & 0xFF);
1.2041 + }
1.2042 + }
1.2043 +
1.2044 + /**
1.2045 + * Encode a non zero integer on the second bit of an octet, setting
1.2046 + * the first bit to 1.
1.2047 + * Implementation of clause C.24 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.2048 + *
1.2049 + * <p>
1.2050 + * The first bit of the first octet is set, as specified in clause C.13 of
1.2051 + * ITU-T Rec. X.891 | ISO/IEC 24824-1
1.2052 + *
1.2053 + * @param i The integer to encode, which is a member of the interval
1.2054 + * [0, 1048575]. In the specification the interval is [1, 1048576]
1.2055 + *
1.2056 + */
1.2057 + protected final void encodeNonZeroIntegerOnSecondBitFirstBitOne(int i) throws IOException {
1.2058 + if (i < EncodingConstants.INTEGER_2ND_BIT_SMALL_LIMIT) {
1.2059 + // [1, 64] ( [0, 63] ) 6 bits
1.2060 + write(0x80 | i);
1.2061 + } else if (i < EncodingConstants.INTEGER_2ND_BIT_MEDIUM_LIMIT) {
1.2062 + // [65, 8256] ( [64, 8255] ) 13 bits
1.2063 + i -= EncodingConstants.INTEGER_2ND_BIT_SMALL_LIMIT;
1.2064 + _b = (0x80 | EncodingConstants.INTEGER_2ND_BIT_MEDIUM_FLAG) | (i >> 8); // 010 00000
1.2065 + // _b = 0xC0 | (i >> 8); // 010 00000
1.2066 + write(_b);
1.2067 + write(i & 0xFF);
1.2068 + } else if (i < EncodingConstants.INTEGER_2ND_BIT_LARGE_LIMIT) {
1.2069 + // [8257, 1048576] ( [8256, 1048575] ) 20 bits
1.2070 + i -= EncodingConstants.INTEGER_2ND_BIT_MEDIUM_LIMIT;
1.2071 + _b = (0x80 | EncodingConstants.INTEGER_2ND_BIT_LARGE_FLAG) | (i >> 16); // 0110 0000
1.2072 + // _b = 0xE0 | (i >> 16); // 0110 0000
1.2073 + write(_b);
1.2074 + write((i >> 8) & 0xFF);
1.2075 + write(i & 0xFF);
1.2076 + } else {
1.2077 + throw new IOException(
1.2078 + CommonResourceBundle.getInstance().getString("message.integerMaxSize",
1.2079 + new Object[]{Integer.valueOf(EncodingConstants.INTEGER_2ND_BIT_LARGE_LIMIT)}));
1.2080 + }
1.2081 + }
1.2082 +
1.2083 + /**
1.2084 + * Encode a non zero integer on the second bit of an octet, setting
1.2085 + * the first bit to 0.
1.2086 + * Implementation of clause C.25 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.2087 + *
1.2088 + * <p>
1.2089 + * The first bit of the first octet is set, as specified in clause C.13 of
1.2090 + * ITU-T Rec. X.891 | ISO/IEC 24824-1
1.2091 + *
1.2092 + * @param i The integer to encode, which is a member of the interval
1.2093 + * [0, 1048575]. In the specification the interval is [1, 1048576]
1.2094 + *
1.2095 + */
1.2096 + protected final void encodeNonZeroIntegerOnSecondBitFirstBitZero(int i) throws IOException {
1.2097 + if (i < EncodingConstants.INTEGER_2ND_BIT_SMALL_LIMIT) {
1.2098 + // [1, 64] ( [0, 63] ) 6 bits
1.2099 + write(i);
1.2100 + } else if (i < EncodingConstants.INTEGER_2ND_BIT_MEDIUM_LIMIT) {
1.2101 + // [65, 8256] ( [64, 8255] ) 13 bits
1.2102 + i -= EncodingConstants.INTEGER_2ND_BIT_SMALL_LIMIT;
1.2103 + _b = EncodingConstants.INTEGER_2ND_BIT_MEDIUM_FLAG | (i >> 8); // 010 00000
1.2104 + write(_b);
1.2105 + write(i & 0xFF);
1.2106 + } else {
1.2107 + // [8257, 1048576] ( [8256, 1048575] ) 20 bits
1.2108 + i -= EncodingConstants.INTEGER_2ND_BIT_MEDIUM_LIMIT;
1.2109 + _b = EncodingConstants.INTEGER_2ND_BIT_LARGE_FLAG | (i >> 16); // 0110 0000
1.2110 + write(_b);
1.2111 + write((i >> 8) & 0xFF);
1.2112 + write(i & 0xFF);
1.2113 + }
1.2114 + }
1.2115 +
1.2116 + /**
1.2117 + * Encode a non zero integer on the third bit of an octet.
1.2118 + * Implementation of clause C.27 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.2119 + *
1.2120 + * @param i The integer to encode, which is a member of the interval
1.2121 + * [0, 1048575]. In the specification the interval is [1, 1048576]
1.2122 + *
1.2123 + */
1.2124 + protected final void encodeNonZeroIntegerOnThirdBit(int i) throws IOException {
1.2125 + if (i < EncodingConstants.INTEGER_3RD_BIT_SMALL_LIMIT) {
1.2126 + // [1, 32] ( [0, 31] ) 5 bits
1.2127 + write(_b | i);
1.2128 + } else if (i < EncodingConstants.INTEGER_3RD_BIT_MEDIUM_LIMIT) {
1.2129 + // [33, 2080] ( [32, 2079] ) 11 bits
1.2130 + i -= EncodingConstants.INTEGER_3RD_BIT_SMALL_LIMIT;
1.2131 + _b |= EncodingConstants.INTEGER_3RD_BIT_MEDIUM_FLAG | (i >> 8); // 00100 000
1.2132 + write(_b);
1.2133 + write(i & 0xFF);
1.2134 + } else if (i < EncodingConstants.INTEGER_3RD_BIT_LARGE_LIMIT) {
1.2135 + // [2081, 526368] ( [2080, 526367] ) 19 bits
1.2136 + i -= EncodingConstants.INTEGER_3RD_BIT_MEDIUM_LIMIT;
1.2137 + _b |= EncodingConstants.INTEGER_3RD_BIT_LARGE_FLAG | (i >> 16); // 00101 000
1.2138 + write(_b);
1.2139 + write((i >> 8) & 0xFF);
1.2140 + write(i & 0xFF);
1.2141 + } else {
1.2142 + // [526369, 1048576] ( [526368, 1048575] ) 20 bits
1.2143 + i -= EncodingConstants.INTEGER_3RD_BIT_LARGE_LIMIT;
1.2144 + _b |= EncodingConstants.INTEGER_3RD_BIT_LARGE_LARGE_FLAG; // 00110 000
1.2145 + write(_b);
1.2146 + write(i >> 16);
1.2147 + write((i >> 8) & 0xFF);
1.2148 + write(i & 0xFF);
1.2149 + }
1.2150 + }
1.2151 +
1.2152 + /**
1.2153 + * Encode a non zero integer on the fourth bit of an octet.
1.2154 + * Implementation of clause C.28 of ITU-T Rec. X.891 | ISO/IEC 24824-1.
1.2155 + *
1.2156 + * @param i The integer to encode, which is a member of the interval
1.2157 + * [0, 1048575]. In the specification the interval is [1, 1048576]
1.2158 + *
1.2159 + */
1.2160 + protected final void encodeNonZeroIntegerOnFourthBit(int i) throws IOException {
1.2161 + if (i < EncodingConstants.INTEGER_4TH_BIT_SMALL_LIMIT) {
1.2162 + // [1, 16] ( [0, 15] ) 4 bits
1.2163 + write(_b | i);
1.2164 + } else if (i < EncodingConstants.INTEGER_4TH_BIT_MEDIUM_LIMIT) {
1.2165 + // [17, 1040] ( [16, 1039] ) 10 bits
1.2166 + i -= EncodingConstants.INTEGER_4TH_BIT_SMALL_LIMIT;
1.2167 + _b |= EncodingConstants.INTEGER_4TH_BIT_MEDIUM_FLAG | (i >> 8); // 000 100 00
1.2168 + write(_b);
1.2169 + write(i & 0xFF);
1.2170 + } else if (i < EncodingConstants.INTEGER_4TH_BIT_LARGE_LIMIT) {
1.2171 + // [1041, 263184] ( [1040, 263183] ) 18 bits
1.2172 + i -= EncodingConstants.INTEGER_4TH_BIT_MEDIUM_LIMIT;
1.2173 + _b |= EncodingConstants.INTEGER_4TH_BIT_LARGE_FLAG | (i >> 16); // 000 101 00
1.2174 + write(_b);
1.2175 + write((i >> 8) & 0xFF);
1.2176 + write(i & 0xFF);
1.2177 + } else {
1.2178 + // [263185, 1048576] ( [263184, 1048575] ) 20 bits
1.2179 + i -= EncodingConstants.INTEGER_4TH_BIT_LARGE_LIMIT;
1.2180 + _b |= EncodingConstants.INTEGER_4TH_BIT_LARGE_LARGE_FLAG; // 000 110 00
1.2181 + write(_b);
1.2182 + write(i >> 16);
1.2183 + write((i >> 8) & 0xFF);
1.2184 + write(i & 0xFF);
1.2185 + }
1.2186 + }
1.2187 +
1.2188 + /**
1.2189 + * Encode a non empty string using the UTF-8 encoding.
1.2190 + *
1.2191 + * @param b the current octet that is being written.
1.2192 + * @param s the string to be UTF-8 encoded.
1.2193 + * @param constants the array of constants to use when encoding to determin
1.2194 + * how the length of the UTF-8 encoded string is encoded.
1.2195 + */
1.2196 + protected final void encodeNonEmptyUTF8StringAsOctetString(int b, String s, int[] constants) throws IOException {
1.2197 + final char[] ch = s.toCharArray();
1.2198 + encodeNonEmptyUTF8StringAsOctetString(b, ch, 0, ch.length, constants);
1.2199 + }
1.2200 +
1.2201 + /**
1.2202 + * Encode a non empty string using the UTF-8 encoding.
1.2203 + *
1.2204 + * @param b the current octet that is being written.
1.2205 + * @param ch the array of characters.
1.2206 + * @param offset the offset into the array of characters.
1.2207 + * @param length the length of characters.
1.2208 + * how the length of the UTF-8 encoded string is encoded.
1.2209 + * @param constants the array of constants to use when encoding to determin
1.2210 + * how the length of the UTF-8 encoded string is encoded.
1.2211 + */
1.2212 + protected final void encodeNonEmptyUTF8StringAsOctetString(int b, char ch[], int offset, int length, int[] constants) throws IOException {
1.2213 + length = encodeUTF8String(ch, offset, length);
1.2214 + encodeNonZeroOctetStringLength(b, length, constants);
1.2215 + write(_encodingBuffer, length);
1.2216 + }
1.2217 +
1.2218 + /**
1.2219 + * Encode the length of non empty UTF-8 encoded string.
1.2220 + *
1.2221 + * @param b the current octet that is being written.
1.2222 + * @param length the length of the UTF-8 encoded string.
1.2223 + * how the length of the UTF-8 encoded string is encoded.
1.2224 + * @param constants the array of constants to use when encoding to determin
1.2225 + * how the length of the UTF-8 encoded string is encoded.
1.2226 + */
1.2227 + protected final void encodeNonZeroOctetStringLength(int b, int length, int[] constants) throws IOException {
1.2228 + if (length < constants[EncodingConstants.OCTET_STRING_LENGTH_SMALL_LIMIT]) {
1.2229 + write(b | (length - 1));
1.2230 + } else if (length < constants[EncodingConstants.OCTET_STRING_LENGTH_MEDIUM_LIMIT]) {
1.2231 + write(b | constants[EncodingConstants.OCTET_STRING_LENGTH_MEDIUM_FLAG]);
1.2232 + write(length - constants[EncodingConstants.OCTET_STRING_LENGTH_SMALL_LIMIT]);
1.2233 + } else {
1.2234 + write(b | constants[EncodingConstants.OCTET_STRING_LENGTH_LARGE_FLAG]);
1.2235 + length -= constants[EncodingConstants.OCTET_STRING_LENGTH_MEDIUM_LIMIT];
1.2236 + write(length >>> 24);
1.2237 + write((length >> 16) & 0xFF);
1.2238 + write((length >> 8) & 0xFF);
1.2239 + write(length & 0xFF);
1.2240 + }
1.2241 + }
1.2242 +
1.2243 + /**
1.2244 + * Encode a non zero integer.
1.2245 + *
1.2246 + * @param b the current octet that is being written.
1.2247 + * @param i the non zero integer.
1.2248 + * @param constants the array of constants to use when encoding to determin
1.2249 + * how the non zero integer is encoded.
1.2250 + */
1.2251 + protected final void encodeNonZeroInteger(int b, int i, int[] constants) throws IOException {
1.2252 + if (i < constants[EncodingConstants.INTEGER_SMALL_LIMIT]) {
1.2253 + write(b | i);
1.2254 + } else if (i < constants[EncodingConstants.INTEGER_MEDIUM_LIMIT]) {
1.2255 + i -= constants[EncodingConstants.INTEGER_SMALL_LIMIT];
1.2256 + write(b | constants[EncodingConstants.INTEGER_MEDIUM_FLAG] | (i >> 8));
1.2257 + write(i & 0xFF);
1.2258 + } else if (i < constants[EncodingConstants.INTEGER_LARGE_LIMIT]) {
1.2259 + i -= constants[EncodingConstants.INTEGER_MEDIUM_LIMIT];
1.2260 + write(b | constants[EncodingConstants.INTEGER_LARGE_FLAG] | (i >> 16));
1.2261 + write((i >> 8) & 0xFF);
1.2262 + write(i & 0xFF);
1.2263 + } else if (i < EncodingConstants.INTEGER_MAXIMUM_SIZE) {
1.2264 + i -= constants[EncodingConstants.INTEGER_LARGE_LIMIT];
1.2265 + write(b | constants[EncodingConstants.INTEGER_LARGE_LARGE_FLAG]);
1.2266 + write(i >> 16);
1.2267 + write((i >> 8) & 0xFF);
1.2268 + write(i & 0xFF);
1.2269 + } else {
1.2270 + throw new IOException(CommonResourceBundle.getInstance().getString("message.integerMaxSize", new Object[]{Integer.valueOf(EncodingConstants.INTEGER_MAXIMUM_SIZE)}));
1.2271 + }
1.2272 + }
1.2273 +
1.2274 + /**
1.2275 + * Mark the current position in the buffered stream.
1.2276 + */
1.2277 + protected final void mark() {
1.2278 + _markIndex = _octetBufferIndex;
1.2279 + }
1.2280 +
1.2281 + /**
1.2282 + * Reset the marked position in the buffered stream.
1.2283 + */
1.2284 + protected final void resetMark() {
1.2285 + _markIndex = -1;
1.2286 + }
1.2287 +
1.2288 + /**
1.2289 + * @return true if the mark has been set, otherwise false if the mark
1.2290 + * has not been set.
1.2291 + */
1.2292 + protected final boolean hasMark() {
1.2293 + return _markIndex != -1;
1.2294 + }
1.2295 +
1.2296 + /**
1.2297 + * Write a byte to the buffered stream.
1.2298 + */
1.2299 + protected final void write(int i) throws IOException {
1.2300 + if (_octetBufferIndex < _octetBuffer.length) {
1.2301 + _octetBuffer[_octetBufferIndex++] = (byte)i;
1.2302 + } else {
1.2303 + if (_markIndex == -1) {
1.2304 + _s.write(_octetBuffer);
1.2305 + _octetBufferIndex = 1;
1.2306 + _octetBuffer[0] = (byte)i;
1.2307 + } else {
1.2308 + resize(_octetBuffer.length * 3 / 2);
1.2309 + _octetBuffer[_octetBufferIndex++] = (byte)i;
1.2310 + }
1.2311 + }
1.2312 + }
1.2313 +
1.2314 + /**
1.2315 + * Write an array of bytes to the buffered stream.
1.2316 + *
1.2317 + * @param b the array of bytes.
1.2318 + * @param length the length of bytes.
1.2319 + */
1.2320 + protected final void write(byte[] b, int length) throws IOException {
1.2321 + write(b, 0, length);
1.2322 + }
1.2323 +
1.2324 + /**
1.2325 + * Write an array of bytes to the buffered stream.
1.2326 + *
1.2327 + * @param b the array of bytes.
1.2328 + * @param offset the offset into the array of bytes.
1.2329 + * @param length the length of bytes.
1.2330 + */
1.2331 + protected final void write(byte[] b, int offset, int length) throws IOException {
1.2332 + if ((_octetBufferIndex + length) < _octetBuffer.length) {
1.2333 + System.arraycopy(b, offset, _octetBuffer, _octetBufferIndex, length);
1.2334 + _octetBufferIndex += length;
1.2335 + } else {
1.2336 + if (_markIndex == -1) {
1.2337 + _s.write(_octetBuffer, 0, _octetBufferIndex);
1.2338 + _s.write(b, offset, length);
1.2339 + _octetBufferIndex = 0;
1.2340 + } else {
1.2341 + resize((_octetBuffer.length + length) * 3 / 2 + 1);
1.2342 + System.arraycopy(b, offset, _octetBuffer, _octetBufferIndex, length);
1.2343 + _octetBufferIndex += length;
1.2344 + }
1.2345 + }
1.2346 + }
1.2347 +
1.2348 + private void ensureSize(int length) {
1.2349 + if ((_octetBufferIndex + length) > _octetBuffer.length) {
1.2350 + resize((_octetBufferIndex + length) * 3 / 2 + 1);
1.2351 + }
1.2352 + }
1.2353 +
1.2354 + private void resize(int length) {
1.2355 + byte[] b = new byte[length];
1.2356 + System.arraycopy(_octetBuffer, 0, b, 0, _octetBufferIndex);
1.2357 + _octetBuffer = b;
1.2358 + }
1.2359 +
1.2360 + private void _flush() throws IOException {
1.2361 + if (_octetBufferIndex > 0) {
1.2362 + _s.write(_octetBuffer, 0, _octetBufferIndex);
1.2363 + _octetBufferIndex = 0;
1.2364 + }
1.2365 + }
1.2366 +
1.2367 +
1.2368 + private EncodingBufferOutputStream _encodingBufferOutputStream = new EncodingBufferOutputStream();
1.2369 +
1.2370 + private byte[] _encodingBuffer = new byte[512];
1.2371 +
1.2372 + private int _encodingBufferIndex;
1.2373 +
1.2374 + private class EncodingBufferOutputStream extends OutputStream {
1.2375 +
1.2376 + public void write(int b) throws IOException {
1.2377 + if (_encodingBufferIndex < _encodingBuffer.length) {
1.2378 + _encodingBuffer[_encodingBufferIndex++] = (byte)b;
1.2379 + } else {
1.2380 + byte newbuf[] = new byte[Math.max(_encodingBuffer.length << 1, _encodingBufferIndex)];
1.2381 + System.arraycopy(_encodingBuffer, 0, newbuf, 0, _encodingBufferIndex);
1.2382 + _encodingBuffer = newbuf;
1.2383 +
1.2384 + _encodingBuffer[_encodingBufferIndex++] = (byte)b;
1.2385 + }
1.2386 + }
1.2387 +
1.2388 + public void write(byte b[], int off, int len) throws IOException {
1.2389 + if ((off < 0) || (off > b.length) || (len < 0) ||
1.2390 + ((off + len) > b.length) || ((off + len) < 0)) {
1.2391 + throw new IndexOutOfBoundsException();
1.2392 + } else if (len == 0) {
1.2393 + return;
1.2394 + }
1.2395 + final int newoffset = _encodingBufferIndex + len;
1.2396 + if (newoffset > _encodingBuffer.length) {
1.2397 + byte newbuf[] = new byte[Math.max(_encodingBuffer.length << 1, newoffset)];
1.2398 + System.arraycopy(_encodingBuffer, 0, newbuf, 0, _encodingBufferIndex);
1.2399 + _encodingBuffer = newbuf;
1.2400 + }
1.2401 + System.arraycopy(b, off, _encodingBuffer, _encodingBufferIndex, len);
1.2402 + _encodingBufferIndex = newoffset;
1.2403 + }
1.2404 +
1.2405 + public int getLength() {
1.2406 + return _encodingBufferIndex;
1.2407 + }
1.2408 +
1.2409 + public void reset() {
1.2410 + _encodingBufferIndex = 0;
1.2411 + }
1.2412 + }
1.2413 +
1.2414 + /**
1.2415 + * Encode a string using the UTF-8 encoding.
1.2416 + *
1.2417 + * @param s the string to encode.
1.2418 + */
1.2419 + protected final int encodeUTF8String(String s) throws IOException {
1.2420 + final int length = s.length();
1.2421 + if (length < _charBuffer.length) {
1.2422 + s.getChars(0, length, _charBuffer, 0);
1.2423 + return encodeUTF8String(_charBuffer, 0, length);
1.2424 + } else {
1.2425 + char[] ch = s.toCharArray();
1.2426 + return encodeUTF8String(ch, 0, length);
1.2427 + }
1.2428 + }
1.2429 +
1.2430 + private void ensureEncodingBufferSizeForUtf8String(int length) {
1.2431 + final int newLength = 4 * length;
1.2432 + if (_encodingBuffer.length < newLength) {
1.2433 + _encodingBuffer = new byte[newLength];
1.2434 + }
1.2435 + }
1.2436 +
1.2437 + /**
1.2438 + * Encode a string using the UTF-8 encoding.
1.2439 + *
1.2440 + * @param ch the array of characters.
1.2441 + * @param offset the offset into the array of characters.
1.2442 + * @param length the length of characters.
1.2443 + */
1.2444 + protected final int encodeUTF8String(char[] ch, int offset, int length) throws IOException {
1.2445 + int bpos = 0;
1.2446 +
1.2447 + // Make sure buffer is large enough
1.2448 + ensureEncodingBufferSizeForUtf8String(length);
1.2449 +
1.2450 + final int end = offset + length;
1.2451 + int c;
1.2452 + while (end != offset) {
1.2453 + c = ch[offset++];
1.2454 + if (c < 0x80) {
1.2455 + // 1 byte, 7 bits
1.2456 + _encodingBuffer[bpos++] = (byte) c;
1.2457 + } else if (c < 0x800) {
1.2458 + // 2 bytes, 11 bits
1.2459 + _encodingBuffer[bpos++] =
1.2460 + (byte) (0xC0 | (c >> 6)); // first 5
1.2461 + _encodingBuffer[bpos++] =
1.2462 + (byte) (0x80 | (c & 0x3F)); // second 6
1.2463 + } else if (c <= '\uFFFF') {
1.2464 + if (!XMLChar.isHighSurrogate(c) && !XMLChar.isLowSurrogate(c)) {
1.2465 + // 3 bytes, 16 bits
1.2466 + _encodingBuffer[bpos++] =
1.2467 + (byte) (0xE0 | (c >> 12)); // first 4
1.2468 + _encodingBuffer[bpos++] =
1.2469 + (byte) (0x80 | ((c >> 6) & 0x3F)); // second 6
1.2470 + _encodingBuffer[bpos++] =
1.2471 + (byte) (0x80 | (c & 0x3F)); // third 6
1.2472 + } else {
1.2473 + // 4 bytes, high and low surrogate
1.2474 + encodeCharacterAsUtf8FourByte(c, ch, offset, end, bpos);
1.2475 + bpos += 4;
1.2476 + offset++;
1.2477 + }
1.2478 + }
1.2479 + }
1.2480 +
1.2481 + return bpos;
1.2482 + }
1.2483 +
1.2484 + private void encodeCharacterAsUtf8FourByte(int c, char[] ch, int chpos, int chend, int bpos) throws IOException {
1.2485 + if (chpos == chend) {
1.2486 + throw new IOException("");
1.2487 + }
1.2488 +
1.2489 + final char d = ch[chpos];
1.2490 + if (!XMLChar.isLowSurrogate(d)) {
1.2491 + throw new IOException("");
1.2492 + }
1.2493 +
1.2494 + final int uc = (((c & 0x3ff) << 10) | (d & 0x3ff)) + 0x10000;
1.2495 + if (uc < 0 || uc >= 0x200000) {
1.2496 + throw new IOException("");
1.2497 + }
1.2498 +
1.2499 + _encodingBuffer[bpos++] = (byte)(0xF0 | ((uc >> 18)));
1.2500 + _encodingBuffer[bpos++] = (byte)(0x80 | ((uc >> 12) & 0x3F));
1.2501 + _encodingBuffer[bpos++] = (byte)(0x80 | ((uc >> 6) & 0x3F));
1.2502 + _encodingBuffer[bpos++] = (byte)(0x80 | (uc & 0x3F));
1.2503 + }
1.2504 +
1.2505 + /**
1.2506 + * Encode a string using the UTF-16 encoding.
1.2507 + *
1.2508 + * @param s the string to encode.
1.2509 + */
1.2510 + protected final int encodeUtf16String(String s) throws IOException {
1.2511 + final int length = s.length();
1.2512 + if (length < _charBuffer.length) {
1.2513 + s.getChars(0, length, _charBuffer, 0);
1.2514 + return encodeUtf16String(_charBuffer, 0, length);
1.2515 + } else {
1.2516 + char[] ch = s.toCharArray();
1.2517 + return encodeUtf16String(ch, 0, length);
1.2518 + }
1.2519 + }
1.2520 +
1.2521 + private void ensureEncodingBufferSizeForUtf16String(int length) {
1.2522 + final int newLength = 2 * length;
1.2523 + if (_encodingBuffer.length < newLength) {
1.2524 + _encodingBuffer = new byte[newLength];
1.2525 + }
1.2526 + }
1.2527 +
1.2528 + /**
1.2529 + * Encode a string using the UTF-16 encoding.
1.2530 + *
1.2531 + * @param ch the array of characters.
1.2532 + * @param offset the offset into the array of characters.
1.2533 + * @param length the length of characters.
1.2534 + */
1.2535 + protected final int encodeUtf16String(char[] ch, int offset, int length) throws IOException {
1.2536 + int byteLength = 0;
1.2537 +
1.2538 + // Make sure buffer is large enough
1.2539 + ensureEncodingBufferSizeForUtf16String(length);
1.2540 +
1.2541 + final int n = offset + length;
1.2542 + for (int i = offset; i < n; i++) {
1.2543 + final int c = (int) ch[i];
1.2544 + _encodingBuffer[byteLength++] = (byte)(c >> 8);
1.2545 + _encodingBuffer[byteLength++] = (byte)(c & 0xFF);
1.2546 + }
1.2547 +
1.2548 + return byteLength;
1.2549 + }
1.2550 +
1.2551 + /**
1.2552 + * Obtain the prefix from a qualified name.
1.2553 + *
1.2554 + * @param qName the qualified name
1.2555 + * @return the prefix, or "" if there is no prefix.
1.2556 + */
1.2557 + public static String getPrefixFromQualifiedName(String qName) {
1.2558 + int i = qName.indexOf(':');
1.2559 + String prefix = "";
1.2560 + if (i != -1) {
1.2561 + prefix = qName.substring(0, i);
1.2562 + }
1.2563 + return prefix;
1.2564 + }
1.2565 +
1.2566 + /**
1.2567 + * Check if character array contains characters that are all white space.
1.2568 + *
1.2569 + * @param ch the character array
1.2570 + * @param start the starting character index into the array to check from
1.2571 + * @param length the number of characters to check
1.2572 + * @return true if all characters are white space, false otherwise
1.2573 + */
1.2574 + public static boolean isWhiteSpace(final char[] ch, int start, final int length) {
1.2575 + if (!XMLChar.isSpace(ch[start])) return false;
1.2576 +
1.2577 + final int end = start + length;
1.2578 + while(++start < end && XMLChar.isSpace(ch[start]));
1.2579 +
1.2580 + return start == end;
1.2581 + }
1.2582 +
1.2583 + /**
1.2584 + * Check if a String contains characters that are all white space.
1.2585 + *
1.2586 + * @param s the string
1.2587 + * @return true if all characters are white space, false otherwise
1.2588 + */
1.2589 + public static boolean isWhiteSpace(String s) {
1.2590 + if (!XMLChar.isSpace(s.charAt(0))) return false;
1.2591 +
1.2592 + final int end = s.length();
1.2593 + int start = 1;
1.2594 + while(start < end && XMLChar.isSpace(s.charAt(start++)));
1.2595 + return start == end;
1.2596 + }
1.2597 +}
