001: /*
002: * Licensed to the Apache Software Foundation (ASF) under one or more
003: * contributor license agreements. See the NOTICE file distributed with
004: * this work for additional information regarding copyright ownership.
005: * The ASF licenses this file to You under the Apache License, Version 2.0
006: * (the "License"); you may not use this file except in compliance with
007: * the License. You may obtain a copy of the License at
008: *
009: * http://www.apache.org/licenses/LICENSE-2.0
010: *
011: * Unless required by applicable law or agreed to in writing, software
012: * distributed under the License is distributed on an "AS IS" BASIS,
013: * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014: * See the License for the specific language governing permissions and
015: * limitations under the License.
016: */
017:
018: package org.apache.harmony.niochar.charset;
019:
020: import java.nio.charset.Charset;
021: import java.nio.charset.CoderResult;
022: import java.nio.charset.CharsetDecoder;
023: import java.nio.charset.CharsetEncoder;
024: import java.nio.CharBuffer;
025: import java.nio.ByteBuffer;
026:
027: import org.apache.harmony.nio.AddressUtil;
028:
029: public class ISO_8859_7 extends Charset {
030:
031: public ISO_8859_7(String csName, String[] aliases) {
032: super (csName, aliases);
033: }
034:
035: public boolean contains(Charset cs) {
036: return cs.name().equalsIgnoreCase("IBM367")
037: || cs.name().equalsIgnoreCase("iso-8859-7")
038: || cs.name().equalsIgnoreCase("US-ASCII");
039: }
040:
041: public CharsetDecoder newDecoder() {
042: return new Decoder(this );
043: }
044:
045: public CharsetEncoder newEncoder() {
046: return new Encoder(this );
047: }
048:
049: private static final class Decoder extends CharsetDecoder {
050: private Decoder(Charset cs) {
051: super (cs, 1, 1);
052:
053: }
054:
055: public native int nDecode(char[] array, int arrPosition,
056: int remaining, long outAddr, int absolutePos);
057:
058: protected CoderResult decodeLoop(ByteBuffer bb, CharBuffer cb) {
059: int cbRemaining = cb.remaining();
060: if (bb.isDirect() && bb.hasRemaining() && cb.hasArray()) {
061: int toProceed = bb.remaining();
062: int cbPos = cb.position();
063: int bbPos = bb.position();
064: boolean throwOverflow = false;
065: if (cbRemaining < toProceed) {
066: toProceed = cbRemaining;
067: throwOverflow = true;
068: }
069: int res = nDecode(cb.array(), cb.arrayOffset() + cbPos,
070: toProceed, AddressUtil
071: .getDirectBufferAddress(bb), bbPos);
072: if (res <= 0) {
073: bb.position(bbPos - res);
074: cb.position(cbPos - res);
075: return CoderResult.unmappableForLength(1);
076: } else {
077: cb.position(cbPos + res);
078: bb.position(bbPos + res);
079: if (throwOverflow)
080: return CoderResult.OVERFLOW;
081: }
082: } else {
083: if (bb.hasArray() && cb.hasArray()) {
084: int rem = bb.remaining();
085: rem = cbRemaining >= rem ? rem : cbRemaining;
086: byte[] bArr = bb.array();
087: char[] cArr = cb.array();
088: int bStart = bb.position();
089: int cStart = cb.position();
090: int i;
091: for (i = bStart; i < bStart + rem; i++) {
092: int in = (int) bArr[i];
093: if (in < 0 && in >= -95) {
094: int index = (int) in + 95;
095: if (arr[index] != 0x0000) {
096: cArr[cStart++] = (char) arr[index];
097: } else {
098: bb.position(i);
099: cb.position(cStart);
100: return CoderResult
101: .unmappableForLength(1);
102: }
103: } else {
104: cArr[cStart++] = (char) (in & 0xFF);
105: }
106: }
107: bb.position(i);
108: cb.position(cStart);
109: if (rem == cbRemaining && bb.hasRemaining())
110: return CoderResult.OVERFLOW;
111: } else {
112: while (bb.hasRemaining()) {
113: if (cbRemaining == 0)
114: return CoderResult.OVERFLOW;
115: int in = (int) bb.get();
116: if (in < 0 && in >= -95) {
117: int index = (int) in + 95;
118: if (arr[index] != 0x0000) {
119: cb.put(arr[index]);
120: } else {
121: bb.position(bb.position() - 1);
122: return CoderResult
123: .unmappableForLength(1);
124: }
125: } else {
126: cb.put((char) (in & 0xFF));
127: }
128: cbRemaining--;
129: }
130: }
131: }
132: return CoderResult.UNDERFLOW;
133: }
134:
135: final static char[] arr = { 0x2018, 0x2019, 0x00A3, 0x20AC,
136: 0x20AF, 0x00A6, 0x00A7, 0x00A8, 0x00A9, 0x037A, 0x00AB,
137: 0x00AC, 0x00AD, 0x0000, 0x2015, 0x00B0, 0x00B1, 0x00B2,
138: 0x00B3, 0x00B4, 0x0385, 0x0386, 0x0387, 0x0388, 0x0389,
139: 0x038A, 0x00BB, 0x038C, 0x00BD, 0x038E, 0x038F, 0x0390,
140: 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397,
141: 0x0398, 0x0399, 0x039A, 0x039B, 0x039C, 0x039D, 0x039E,
142: 0x039F, 0x03A0, 0x03A1, 0x0000, 0x03A3, 0x03A4, 0x03A5,
143: 0x03A6, 0x03A7, 0x03A8, 0x03A9, 0x03AA, 0x03AB, 0x03AC,
144: 0x03AD, 0x03AE, 0x03AF, 0x03B0, 0x03B1, 0x03B2, 0x03B3,
145: 0x03B4, 0x03B5, 0x03B6, 0x03B7, 0x03B8, 0x03B9, 0x03BA,
146: 0x03BB, 0x03BC, 0x03BD, 0x03BE, 0x03BF, 0x03C0, 0x03C1,
147: 0x03C2, 0x03C3, 0x03C4, 0x03C5, 0x03C6, 0x03C7, 0x03C8,
148: 0x03C9, 0x03CA, 0x03CB, 0x03CC, 0x03CD, 0x03CE, 0x0000 };
149: }
150:
151: private static final class Encoder extends CharsetEncoder {
152: private Encoder(Charset cs) {
153: super (cs, 1, 1);
154: }
155:
156: private native void nEncode(long outAddr, int absolutePos,
157: char[] array, int arrPosition, int[] res);
158:
159: protected CoderResult encodeLoop(CharBuffer cb, ByteBuffer bb) {
160: int bbRemaining = bb.remaining();
161: if (bb.isDirect() && cb.hasRemaining() && cb.hasArray()) {
162: int toProceed = cb.remaining();
163: int cbPos = cb.position();
164: int bbPos = bb.position();
165: boolean throwOverflow = false;
166: if (bbRemaining < toProceed) {
167: toProceed = bbRemaining;
168: throwOverflow = true;
169: }
170: int[] res = { toProceed, 0 };
171: nEncode(AddressUtil.getDirectBufferAddress(bb), bbPos,
172: cb.array(), cb.arrayOffset() + cbPos, res);
173: if (res[0] <= 0) {
174: bb.position(bbPos - res[0]);
175: cb.position(cbPos - res[0]);
176: if (res[1] != 0) {
177: if (res[1] < 0)
178: return CoderResult
179: .malformedForLength(-res[1]);
180: else
181: return CoderResult
182: .unmappableForLength(res[1]);
183: }
184: } else {
185: bb.position(bbPos + res[0]);
186: cb.position(cbPos + res[0]);
187: if (throwOverflow)
188: return CoderResult.OVERFLOW;
189: }
190: } else {
191: if (bb.hasArray() && cb.hasArray()) {
192: byte[] byteArr = bb.array();
193: char[] charArr = cb.array();
194: int rem = cb.remaining();
195: int byteArrStart = bb.position();
196: rem = bbRemaining <= rem ? bbRemaining : rem;
197: int x;
198: for (x = cb.position(); x < cb.position() + rem; x++) {
199: char c = charArr[x];
200: if (c > (char) 0x20AF) {
201: if (c >= 0xD800 && c <= 0xDFFF) {
202: if (x + 1 < cb.limit()) {
203: char c1 = charArr[x + 1];
204: if (c1 >= 0xD800 && c1 <= 0xDFFF) {
205: cb.position(x);
206: bb.position(byteArrStart);
207: return CoderResult
208: .unmappableForLength(2);
209: }
210: } else {
211: cb.position(x);
212: bb.position(byteArrStart);
213: return CoderResult.UNDERFLOW;
214: }
215: cb.position(x);
216: bb.position(byteArrStart);
217: return CoderResult
218: .malformedForLength(1);
219: }
220: cb.position(x);
221: bb.position(byteArrStart);
222: return CoderResult.unmappableForLength(1);
223: } else {
224: if (c < 0xA1) {
225: byteArr[byteArrStart++] = (byte) c;
226: } else {
227: int index = (int) c >> 8;
228: index = encodeIndex[index];
229: if (index < 0) {
230: cb.position(x);
231: bb.position(byteArrStart);
232: return CoderResult
233: .unmappableForLength(1);
234: }
235: index <<= 8;
236: index += (int) c & 0xFF;
237: if ((byte) arr[index] != 0) {
238: byteArr[byteArrStart++] = (byte) arr[index];
239: } else {
240: cb.position(x);
241: bb.position(byteArrStart);
242: return CoderResult
243: .unmappableForLength(1);
244: }
245: }
246: }
247: }
248: cb.position(x);
249: bb.position(byteArrStart);
250: if (rem == bbRemaining && cb.hasRemaining()) {
251: return CoderResult.OVERFLOW;
252: }
253: } else {
254: while (cb.hasRemaining()) {
255: if (bbRemaining == 0)
256: return CoderResult.OVERFLOW;
257: char c = cb.get();
258: if (c > (char) 0x20AF) {
259: if (c >= 0xD800 && c <= 0xDFFF) {
260: if (cb.hasRemaining()) {
261: char c1 = cb.get();
262: if (c1 >= 0xD800 && c1 <= 0xDFFF) {
263: cb.position(cb.position() - 2);
264: return CoderResult
265: .unmappableForLength(2);
266: } else {
267: cb.position(cb.position() - 1);
268: }
269: } else {
270: cb.position(cb.position() - 1);
271: return CoderResult.UNDERFLOW;
272: }
273: cb.position(cb.position() - 1);
274: return CoderResult
275: .malformedForLength(1);
276: }
277: cb.position(cb.position() - 1);
278: return CoderResult.unmappableForLength(1);
279: } else {
280: if (c < 0xA1) {
281: bb.put((byte) c);
282: } else {
283: int index = (int) c >> 8;
284: index = encodeIndex[index];
285: if (index < 0) {
286: cb.position(cb.position() - 1);
287: return CoderResult
288: .unmappableForLength(1);
289: }
290: index <<= 8;
291: index += (int) c & 0xFF;
292: if ((byte) arr[index] != 0) {
293: bb.put((byte) arr[index]);
294: } else {
295: cb.position(cb.position() - 1);
296: return CoderResult
297: .unmappableForLength(1);
298: }
299: }
300: bbRemaining--;
301: }
302: }
303: }
304: }
305: return CoderResult.UNDERFLOW;
306: }
307:
308: final static char arr[] = {
309:
310: 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09,
311: 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0x10, 0x11, 0x12,
312: 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1A, 0x1B,
313: 0x1C, 0x1D, 0x1E, 0x1F, 0x20, 0x21, 0x22, 0x23, 0x24,
314: 0x25, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D,
315: 0x2E, 0x2F, 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36,
316: 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
317: 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48,
318: 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51,
319: 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A,
320: 0x5B, 0x5C, 0x5D, 0x5E, 0x5F, 0x60, 0x61, 0x62, 0x63,
321: 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x6B, 0x6C,
322: 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0x73, 0x74, 0x75,
323: 0x76, 0x77, 0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E,
324: 0x7F, 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
325: 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F, 0x90,
326: 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99,
327: 0x9A, 0x9B, 0x9C, 0x9D, 0x9E, 0x9F, 0xA0, 0x00, 0x00,
328: 0xA3, 0x00, 0x00, 0xA6, 0xA7, 0xA8, 0xA9, 0x00, 0xAB,
329: 0xAC, 0xAD, 0x00, 0x00, 0xB0, 0xB1, 0xB2, 0xB3, 0xB4,
330: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xBB, 0x00, 0xBD,
331: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
332: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
333: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
334: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
335: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
336: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
337: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
338: 0x00, 0x00, 0x00,
339:
340: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
341: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
342: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
343: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
344: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
345: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
346: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
347: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
348: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
349: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
350: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
351: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
352: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
353: 0x00, 0x00, 0x00, 0x00, 0x00, 0xAA, 0x00, 0x00, 0x00,
354: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xB5, 0xB6,
355: 0xB7, 0xB8, 0xB9, 0xBA, 0x00, 0xBC, 0x00, 0xBE, 0xBF,
356: 0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8,
357: 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF, 0xD0, 0xD1,
358: 0x00, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7, 0xD8, 0xD9, 0xDA,
359: 0xDB, 0xDC, 0xDD, 0xDE, 0xDF, 0xE0, 0xE1, 0xE2, 0xE3,
360: 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC,
361: 0xED, 0xEE, 0xEF, 0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5,
362: 0xF6, 0xF7, 0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE,
363: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
364: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
365: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
366: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
367: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
368: 0x00, 0x00, 0x00, 0x00,
369:
370: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
371: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
372: 0x00, 0x00, 0x00, 0xAF, 0x00, 0x00, 0xA1, 0xA2, 0x00,
373: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
374: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
375: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
376: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
377: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
378: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
379: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
380: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
381: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
382: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
383: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
384: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
385: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
386: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
387: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
388: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
389: 0x00, 0xA4, 0x00, 0x00, 0xA5, 0x00, 0x00, 0x00, 0x00,
390: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
391: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
392: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
393: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
394: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
395: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
396: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
397: 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
398: 0x00, 0x00, 0x00, 0x00 };
399:
400: final static int[] encodeIndex = { 0, -1, -1, 1, -1, -1, -1,
401: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
402: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 2, -1, -1,
403: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
404: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
405: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
406: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
407: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
408: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
409: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
410: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
411: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
412: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
413: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
414: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
415: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
416: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
417: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
418: -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 };
419: }
420: }
|