001: /*
002: * Licensed to the Apache Software Foundation (ASF) under one
003: * or more contributor license agreements. See the NOTICE file
004: * distributed with this work for additional information
005: * regarding copyright ownership. The ASF licenses this file
006: * to you under the Apache License, Version 2.0 (the
007: * "License"); you may not use this file except in compliance
008: * with the License. You may obtain a copy of the License at
009: *
010: * http://www.apache.org/licenses/LICENSE-2.0
011: *
012: * Unless required by applicable law or agreed to in writing,
013: * software distributed under the License is distributed on an
014: * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
015: * KIND, either express or implied. See the License for the
016: * specific language governing permissions and limitations
017: * under the License.
018: */
019:
020: package org.apache.axis2.util;
021:
022: /**
023: * This class defines the basic XML character properties. The data
024: * in this class can be used to verify that a character is a valid
025: * XML character or if the character is a space, name start, or name
026: * character.
027: * <p/>
028: * A series of convenience methods are supplied to ease the burden
029: * of the developer. Because inlining the checks can improve per
030: * character performance, the tables of character properties are
031: * public. Using the character as an index into the <code>CHARS</code>
032: * array and applying the appropriate mask flag (e.g.
033: * <code>MASK_VALID</code>), yields the same results as calling the
034: * convenience methods. There is one exception: check the comments
035: * for the <code>isValid</code> method for details.
036: */
037: public class XMLChar {
038:
039: //
040: // Constants
041: //
042:
043: /**
044: * Character flags.
045: */
046: private static final byte[] CHARS = new byte[1 << 16];
047:
048: /**
049: * Valid character mask.
050: */
051: public static final int MASK_VALID = 0x01;
052:
053: /**
054: * Space character mask.
055: */
056: public static final int MASK_SPACE = 0x02;
057:
058: /**
059: * Name start character mask.
060: */
061: public static final int MASK_NAME_START = 0x04;
062:
063: /**
064: * Name character mask.
065: */
066: public static final int MASK_NAME = 0x08;
067:
068: /**
069: * Pubid character mask.
070: */
071: public static final int MASK_PUBID = 0x10;
072:
073: /**
074: * Content character mask. Special characters are those that can
075: * be considered the start of markup, such as '<' and '&'.
076: * The various newline characters are considered special as well.
077: * All other valid XML characters can be considered content.
078: * <p/>
079: * This is an optimization for the inner loop of character scanning.
080: */
081: public static final int MASK_CONTENT = 0x20;
082:
083: /**
084: * NCName start character mask.
085: */
086: public static final int MASK_NCNAME_START = 0x40;
087:
088: /**
089: * NCName character mask.
090: */
091: public static final int MASK_NCNAME = 0x80;
092:
093: //
094: // Static initialization
095: //
096:
097: static {
098:
099: //
100: // [2] Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] |
101: // [#xE000-#xFFFD] | [#x10000-#x10FFFF]
102: //
103:
104: int charRange[] = { 0x0009, 0x000A, 0x000D, 0x000D, 0x0020,
105: 0xD7FF, 0xE000, 0xFFFD, };
106:
107: //
108: // [3] S ::= (#x20 | #x9 | #xD | #xA)+
109: //
110:
111: int spaceChar[] = { 0x0020, 0x0009, 0x000D, 0x000A, };
112:
113: //
114: // [4] NameChar ::= Letter | Digit | '.' | '-' | '_' | ':' |
115: // CombiningChar | Extender
116: //
117:
118: int nameChar[] = { 0x002D, 0x002E, // '-' and '.'
119: };
120:
121: //
122: // [5] Name ::= (Letter | '_' | ':') (NameChar)*
123: //
124:
125: int nameStartChar[] = { 0x003A, 0x005F, // ':' and '_'
126: };
127:
128: //
129: // [13] PubidChar ::= #x20 | 0xD | 0xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%]
130: //
131:
132: int pubidChar[] = { 0x000A, 0x000D, 0x0020, 0x0021, 0x0023,
133: 0x0024, 0x0025, 0x003D, 0x005F };
134:
135: int pubidRange[] = { 0x0027, 0x003B, 0x003F, 0x005A, 0x0061,
136: 0x007A };
137:
138: //
139: // [84] Letter ::= BaseChar | Ideographic
140: //
141:
142: int letterRange[] = {
143: // BaseChar
144: 0x0041, 0x005A, 0x0061, 0x007A, 0x00C0, 0x00D6, 0x00D8,
145: 0x00F6, 0x00F8, 0x0131, 0x0134, 0x013E, 0x0141, 0x0148,
146: 0x014A, 0x017E, 0x0180, 0x01C3, 0x01CD, 0x01F0, 0x01F4,
147: 0x01F5, 0x01FA, 0x0217, 0x0250, 0x02A8, 0x02BB, 0x02C1,
148: 0x0388, 0x038A, 0x038E, 0x03A1, 0x03A3, 0x03CE, 0x03D0,
149: 0x03D6, 0x03E2, 0x03F3, 0x0401, 0x040C, 0x040E, 0x044F,
150: 0x0451, 0x045C, 0x045E, 0x0481, 0x0490, 0x04C4, 0x04C7,
151: 0x04C8, 0x04CB, 0x04CC, 0x04D0, 0x04EB, 0x04EE, 0x04F5,
152: 0x04F8, 0x04F9, 0x0531, 0x0556, 0x0561, 0x0586, 0x05D0,
153: 0x05EA, 0x05F0, 0x05F2, 0x0621, 0x063A, 0x0641, 0x064A,
154: 0x0671, 0x06B7, 0x06BA, 0x06BE, 0x06C0, 0x06CE, 0x06D0,
155: 0x06D3, 0x06E5, 0x06E6, 0x0905, 0x0939, 0x0958, 0x0961,
156: 0x0985, 0x098C, 0x098F, 0x0990, 0x0993, 0x09A8, 0x09AA,
157: 0x09B0, 0x09B6, 0x09B9, 0x09DC, 0x09DD, 0x09DF, 0x09E1,
158: 0x09F0, 0x09F1, 0x0A05, 0x0A0A, 0x0A0F, 0x0A10, 0x0A13,
159: 0x0A28, 0x0A2A, 0x0A30, 0x0A32, 0x0A33, 0x0A35, 0x0A36,
160: 0x0A38, 0x0A39, 0x0A59, 0x0A5C, 0x0A72, 0x0A74, 0x0A85,
161: 0x0A8B, 0x0A8F, 0x0A91, 0x0A93, 0x0AA8, 0x0AAA, 0x0AB0,
162: 0x0AB2, 0x0AB3, 0x0AB5, 0x0AB9, 0x0B05, 0x0B0C, 0x0B0F,
163: 0x0B10, 0x0B13, 0x0B28, 0x0B2A, 0x0B30, 0x0B32, 0x0B33,
164: 0x0B36, 0x0B39, 0x0B5C, 0x0B5D, 0x0B5F, 0x0B61, 0x0B85,
165: 0x0B8A, 0x0B8E, 0x0B90, 0x0B92, 0x0B95, 0x0B99, 0x0B9A,
166: 0x0B9E, 0x0B9F, 0x0BA3, 0x0BA4, 0x0BA8, 0x0BAA, 0x0BAE,
167: 0x0BB5, 0x0BB7, 0x0BB9, 0x0C05, 0x0C0C, 0x0C0E, 0x0C10,
168: 0x0C12, 0x0C28, 0x0C2A, 0x0C33, 0x0C35, 0x0C39, 0x0C60,
169: 0x0C61, 0x0C85, 0x0C8C, 0x0C8E, 0x0C90, 0x0C92, 0x0CA8,
170: 0x0CAA, 0x0CB3, 0x0CB5, 0x0CB9, 0x0CE0, 0x0CE1, 0x0D05,
171: 0x0D0C, 0x0D0E, 0x0D10, 0x0D12, 0x0D28, 0x0D2A, 0x0D39,
172: 0x0D60, 0x0D61, 0x0E01, 0x0E2E, 0x0E32, 0x0E33, 0x0E40,
173: 0x0E45, 0x0E81, 0x0E82, 0x0E87, 0x0E88, 0x0E94, 0x0E97,
174: 0x0E99, 0x0E9F, 0x0EA1, 0x0EA3, 0x0EAA, 0x0EAB, 0x0EAD,
175: 0x0EAE, 0x0EB2, 0x0EB3, 0x0EC0, 0x0EC4, 0x0F40, 0x0F47,
176: 0x0F49, 0x0F69, 0x10A0, 0x10C5, 0x10D0, 0x10F6, 0x1102,
177: 0x1103, 0x1105, 0x1107, 0x110B, 0x110C, 0x110E, 0x1112,
178: 0x1154, 0x1155, 0x115F, 0x1161, 0x116D, 0x116E, 0x1172,
179: 0x1173, 0x11AE, 0x11AF, 0x11B7, 0x11B8, 0x11BC, 0x11C2,
180: 0x1E00, 0x1E9B, 0x1EA0, 0x1EF9, 0x1F00, 0x1F15, 0x1F18,
181: 0x1F1D, 0x1F20, 0x1F45, 0x1F48, 0x1F4D, 0x1F50, 0x1F57,
182: 0x1F5F, 0x1F7D, 0x1F80, 0x1FB4, 0x1FB6, 0x1FBC, 0x1FC2,
183: 0x1FC4, 0x1FC6, 0x1FCC, 0x1FD0, 0x1FD3, 0x1FD6, 0x1FDB,
184: 0x1FE0, 0x1FEC, 0x1FF2, 0x1FF4, 0x1FF6, 0x1FFC, 0x212A,
185: 0x212B, 0x2180, 0x2182, 0x3041, 0x3094, 0x30A1, 0x30FA,
186: 0x3105, 0x312C, 0xAC00, 0xD7A3,
187: // Ideographic
188: 0x3021, 0x3029, 0x4E00, 0x9FA5, };
189: int letterChar[] = {
190: // BaseChar
191: 0x0386, 0x038C, 0x03DA, 0x03DC, 0x03DE, 0x03E0, 0x0559,
192: 0x06D5, 0x093D, 0x09B2, 0x0A5E, 0x0A8D, 0x0ABD, 0x0AE0,
193: 0x0B3D, 0x0B9C, 0x0CDE, 0x0E30, 0x0E84, 0x0E8A, 0x0E8D,
194: 0x0EA5, 0x0EA7, 0x0EB0, 0x0EBD, 0x1100, 0x1109, 0x113C,
195: 0x113E, 0x1140, 0x114C, 0x114E, 0x1150, 0x1159, 0x1163,
196: 0x1165, 0x1167, 0x1169, 0x1175, 0x119E, 0x11A8, 0x11AB,
197: 0x11BA, 0x11EB, 0x11F0, 0x11F9, 0x1F59, 0x1F5B, 0x1F5D,
198: 0x1FBE, 0x2126, 0x212E,
199: // Ideographic
200: 0x3007, };
201:
202: //
203: // [87] CombiningChar ::= ...
204: //
205:
206: int combiningCharRange[] = { 0x0300, 0x0345, 0x0360, 0x0361,
207: 0x0483, 0x0486, 0x0591, 0x05A1, 0x05A3, 0x05B9, 0x05BB,
208: 0x05BD, 0x05C1, 0x05C2, 0x064B, 0x0652, 0x06D6, 0x06DC,
209: 0x06DD, 0x06DF, 0x06E0, 0x06E4, 0x06E7, 0x06E8, 0x06EA,
210: 0x06ED, 0x0901, 0x0903, 0x093E, 0x094C, 0x0951, 0x0954,
211: 0x0962, 0x0963, 0x0981, 0x0983, 0x09C0, 0x09C4, 0x09C7,
212: 0x09C8, 0x09CB, 0x09CD, 0x09E2, 0x09E3, 0x0A40, 0x0A42,
213: 0x0A47, 0x0A48, 0x0A4B, 0x0A4D, 0x0A70, 0x0A71, 0x0A81,
214: 0x0A83, 0x0ABE, 0x0AC5, 0x0AC7, 0x0AC9, 0x0ACB, 0x0ACD,
215: 0x0B01, 0x0B03, 0x0B3E, 0x0B43, 0x0B47, 0x0B48, 0x0B4B,
216: 0x0B4D, 0x0B56, 0x0B57, 0x0B82, 0x0B83, 0x0BBE, 0x0BC2,
217: 0x0BC6, 0x0BC8, 0x0BCA, 0x0BCD, 0x0C01, 0x0C03, 0x0C3E,
218: 0x0C44, 0x0C46, 0x0C48, 0x0C4A, 0x0C4D, 0x0C55, 0x0C56,
219: 0x0C82, 0x0C83, 0x0CBE, 0x0CC4, 0x0CC6, 0x0CC8, 0x0CCA,
220: 0x0CCD, 0x0CD5, 0x0CD6, 0x0D02, 0x0D03, 0x0D3E, 0x0D43,
221: 0x0D46, 0x0D48, 0x0D4A, 0x0D4D, 0x0E34, 0x0E3A, 0x0E47,
222: 0x0E4E, 0x0EB4, 0x0EB9, 0x0EBB, 0x0EBC, 0x0EC8, 0x0ECD,
223: 0x0F18, 0x0F19, 0x0F71, 0x0F84, 0x0F86, 0x0F8B, 0x0F90,
224: 0x0F95, 0x0F99, 0x0FAD, 0x0FB1, 0x0FB7, 0x20D0, 0x20DC,
225: 0x302A, 0x302F, };
226:
227: int combiningCharChar[] = { 0x05BF, 0x05C4, 0x0670, 0x093C,
228: 0x094D, 0x09BC, 0x09BE, 0x09BF, 0x09D7, 0x0A02, 0x0A3C,
229: 0x0A3E, 0x0A3F, 0x0ABC, 0x0B3C, 0x0BD7, 0x0D57, 0x0E31,
230: 0x0EB1, 0x0F35, 0x0F37, 0x0F39, 0x0F3E, 0x0F3F, 0x0F97,
231: 0x0FB9, 0x20E1, 0x3099, 0x309A, };
232:
233: //
234: // [88] Digit ::= ...
235: //
236:
237: int digitRange[] = { 0x0030, 0x0039, 0x0660, 0x0669, 0x06F0,
238: 0x06F9, 0x0966, 0x096F, 0x09E6, 0x09EF, 0x0A66, 0x0A6F,
239: 0x0AE6, 0x0AEF, 0x0B66, 0x0B6F, 0x0BE7, 0x0BEF, 0x0C66,
240: 0x0C6F, 0x0CE6, 0x0CEF, 0x0D66, 0x0D6F, 0x0E50, 0x0E59,
241: 0x0ED0, 0x0ED9, 0x0F20, 0x0F29, };
242:
243: //
244: // [89] Extender ::= ...
245: //
246:
247: int extenderRange[] = { 0x3031, 0x3035, 0x309D, 0x309E, 0x30FC,
248: 0x30FE, };
249:
250: int extenderChar[] = { 0x00B7, 0x02D0, 0x02D1, 0x0387, 0x0640,
251: 0x0E46, 0x0EC6, 0x3005, };
252:
253: //
254: // SpecialChar ::= '<', '&', '\n', '\r', ']'
255: //
256:
257: int specialChar[] = { '<', '&', '\n', '\r', ']', };
258:
259: //
260: // Initialize
261: //
262:
263: // set valid characters
264: for (int i = 0; i < charRange.length; i += 2) {
265: for (int j = charRange[i]; j <= charRange[i + 1]; j++) {
266: CHARS[j] |= MASK_VALID | MASK_CONTENT;
267: }
268: }
269:
270: // remove special characters
271: for (int i = 0; i < specialChar.length; i++) {
272: CHARS[specialChar[i]] = (byte) (CHARS[specialChar[i]] & ~MASK_CONTENT);
273: }
274:
275: // set space characters
276: for (int i = 0; i < spaceChar.length; i++) {
277: CHARS[spaceChar[i]] |= MASK_SPACE;
278: }
279:
280: // set name start characters
281: for (int i = 0; i < nameStartChar.length; i++) {
282: CHARS[nameStartChar[i]] |= MASK_NAME_START | MASK_NAME
283: | MASK_NCNAME_START | MASK_NCNAME;
284: }
285: for (int i = 0; i < letterRange.length; i += 2) {
286: for (int j = letterRange[i]; j <= letterRange[i + 1]; j++) {
287: CHARS[j] |= MASK_NAME_START | MASK_NAME
288: | MASK_NCNAME_START | MASK_NCNAME;
289: }
290: }
291: for (int i = 0; i < letterChar.length; i++) {
292: CHARS[letterChar[i]] |= MASK_NAME_START | MASK_NAME
293: | MASK_NCNAME_START | MASK_NCNAME;
294: }
295:
296: // set name characters
297: for (int i = 0; i < nameChar.length; i++) {
298: CHARS[nameChar[i]] |= MASK_NAME | MASK_NCNAME;
299: }
300: for (int i = 0; i < digitRange.length; i += 2) {
301: for (int j = digitRange[i]; j <= digitRange[i + 1]; j++) {
302: CHARS[j] |= MASK_NAME | MASK_NCNAME;
303: }
304: }
305: for (int i = 0; i < combiningCharRange.length; i += 2) {
306: for (int j = combiningCharRange[i]; j <= combiningCharRange[i + 1]; j++) {
307: CHARS[j] |= MASK_NAME | MASK_NCNAME;
308: }
309: }
310: for (int i = 0; i < combiningCharChar.length; i++) {
311: CHARS[combiningCharChar[i]] |= MASK_NAME | MASK_NCNAME;
312: }
313: for (int i = 0; i < extenderRange.length; i += 2) {
314: for (int j = extenderRange[i]; j <= extenderRange[i + 1]; j++) {
315: CHARS[j] |= MASK_NAME | MASK_NCNAME;
316: }
317: }
318: for (int i = 0; i < extenderChar.length; i++) {
319: CHARS[extenderChar[i]] |= MASK_NAME | MASK_NCNAME;
320: }
321:
322: // remove ':' from allowable MASK_NCNAME_START and MASK_NCNAME chars
323: CHARS[':'] &= ~(MASK_NCNAME_START | MASK_NCNAME);
324:
325: // set Pubid characters
326: for (int i = 0; i < pubidChar.length; i++) {
327: CHARS[pubidChar[i]] |= MASK_PUBID;
328: }
329: for (int i = 0; i < pubidRange.length; i += 2) {
330: for (int j = pubidRange[i]; j <= pubidRange[i + 1]; j++) {
331: CHARS[j] |= MASK_PUBID;
332: }
333: }
334:
335: } // <clinit>()
336:
337: //
338: // Public static methods
339: //
340:
341: /**
342: * Returns true if the specified character is a supplemental character.
343: *
344: * @param c The character to check.
345: */
346: public static boolean isSupplemental(int c) {
347: return (c >= 0x10000 && c <= 0x10FFFF);
348: }
349:
350: /**
351: * Returns true the supplemental character corresponding to the given
352: * surrogates.
353: *
354: * @param h The high surrogate.
355: * @param l The low surrogate.
356: */
357: public static int supplemental(char h, char l) {
358: return (h - 0xD800) * 0x400 + (l - 0xDC00) + 0x10000;
359: }
360:
361: /**
362: * Returns the high surrogate of a supplemental character
363: *
364: * @param c The supplemental character to "split".
365: */
366: public static char highSurrogate(int c) {
367: return (char) (((c - 0x00010000) >> 10) + 0xD800);
368: }
369:
370: /**
371: * Returns the low surrogate of a supplemental character
372: *
373: * @param c The supplemental character to "split".
374: */
375: public static char lowSurrogate(int c) {
376: return (char) (((c - 0x00010000) & 0x3FF) + 0xDC00);
377: }
378:
379: /**
380: * Returns whether the given character is a high surrogate
381: *
382: * @param c The character to check.
383: */
384: public static boolean isHighSurrogate(int c) {
385: return (0xD800 <= c && c <= 0xDBFF);
386: }
387:
388: /**
389: * Returns whether the given character is a low surrogate
390: *
391: * @param c The character to check.
392: */
393: public static boolean isLowSurrogate(int c) {
394: return (0xDC00 <= c && c <= 0xDFFF);
395: }
396:
397: /**
398: * Returns true if the specified character is valid. This method
399: * also checks the surrogate character range from 0x10000 to 0x10FFFF.
400: * <p/>
401: * If the program chooses to apply the mask directly to the
402: * <code>CHARS</code> array, then they are responsible for checking
403: * the surrogate character range.
404: *
405: * @param c The character to check.
406: */
407: public static boolean isValid(int c) {
408: return (c < 0x10000 && (CHARS[c] & MASK_VALID) != 0)
409: || (0x10000 <= c && c <= 0x10FFFF);
410: } // isValid(int):boolean
411:
412: /**
413: * Returns true if the specified character is invalid.
414: *
415: * @param c The character to check.
416: */
417: public static boolean isInvalid(int c) {
418: return !isValid(c);
419: } // isInvalid(int):boolean
420:
421: /**
422: * Returns true if the specified character can be considered content.
423: *
424: * @param c The character to check.
425: */
426: public static boolean isContent(int c) {
427: return (c < 0x10000 && (CHARS[c] & MASK_CONTENT) != 0)
428: || (0x10000 <= c && c <= 0x10FFFF);
429: } // isContent(int):boolean
430:
431: /**
432: * Returns true if the specified character can be considered markup.
433: * Markup characters include '<', '&', and '%'.
434: *
435: * @param c The character to check.
436: */
437: public static boolean isMarkup(int c) {
438: return c == '<' || c == '&' || c == '%';
439: } // isMarkup(int):boolean
440:
441: /**
442: * Returns true if the specified character is a space character
443: * as defined by production [3] in the XML 1.0 specification.
444: *
445: * @param c The character to check.
446: */
447: public static boolean isSpace(int c) {
448: return c < 0x10000 && (CHARS[c] & MASK_SPACE) != 0;
449: } // isSpace(int):boolean
450:
451: /**
452: * Returns true if the specified character is a space character
453: * as amdended in the XML 1.1 specification.
454: *
455: * @param c The character to check.
456: */
457: public static boolean isXML11Space(int c) {
458: return (c < 0x10000 && (CHARS[c] & MASK_SPACE) != 0)
459: || c == 0x85 || c == 0x2028;
460: } // isXML11Space(int):boolean
461:
462: /**
463: * Returns true if the specified character is a valid name start
464: * character as defined by production [5] in the XML 1.0
465: * specification.
466: *
467: * @param c The character to check.
468: */
469: public static boolean isNameStart(int c) {
470: return c < 0x10000 && (CHARS[c] & MASK_NAME_START) != 0;
471: } // isNameStart(int):boolean
472:
473: /**
474: * Returns true if the specified character is a valid name
475: * character as defined by production [4] in the XML 1.0
476: * specification.
477: *
478: * @param c The character to check.
479: */
480: public static boolean isName(int c) {
481: return c < 0x10000 && (CHARS[c] & MASK_NAME) != 0;
482: } // isName(int):boolean
483:
484: /**
485: * Returns true if the specified character is a valid NCName start
486: * character as defined by production [4] in Namespaces in XML
487: * recommendation.
488: *
489: * @param c The character to check.
490: */
491: public static boolean isNCNameStart(int c) {
492: return c < 0x10000 && (CHARS[c] & MASK_NCNAME_START) != 0;
493: } // isNCNameStart(int):boolean
494:
495: /**
496: * Returns true if the specified character is a valid NCName
497: * character as defined by production [5] in Namespaces in XML
498: * recommendation.
499: *
500: * @param c The character to check.
501: */
502: public static boolean isNCName(int c) {
503: return c < 0x10000 && (CHARS[c] & MASK_NCNAME) != 0;
504: } // isNCName(int):boolean
505:
506: /**
507: * Returns true if the specified character is a valid Pubid
508: * character as defined by production [13] in the XML 1.0
509: * specification.
510: *
511: * @param c The character to check.
512: */
513: public static boolean isPubid(int c) {
514: return c < 0x10000 && (CHARS[c] & MASK_PUBID) != 0;
515: } // isPubid(int):boolean
516:
517: /*
518: * [5] Name ::= (Letter | '_' | ':') (NameChar)*
519: */
520: /**
521: * Check to see if a string is a valid Name according to [5]
522: * in the XML 1.0 Recommendation
523: *
524: * @param name string to check
525: * @return true if name is a valid Name
526: */
527: public static boolean isValidName(String name) {
528: if (name.length() == 0) {
529: return false;
530: }
531: char ch = name.charAt(0);
532: if (!isNameStart(ch)) {
533: return false;
534: }
535: for (int i = 1; i < name.length(); i++) {
536: ch = name.charAt(i);
537: if (!isName(ch)) {
538: return false;
539: }
540: }
541: return true;
542: } // isValidName(String):boolean
543:
544: /*
545: * from the namespace rec
546: * [4] NCName ::= (Letter | '_') (NCNameChar)*
547: */
548: /**
549: * Check to see if a string is a valid NCName according to [4]
550: * from the XML Namespaces 1.0 Recommendation
551: *
552: * @param ncName string to check
553: * @return true if name is a valid NCName
554: */
555: public static boolean isValidNCName(String ncName) {
556: if (ncName.length() == 0) {
557: return false;
558: }
559: char ch = ncName.charAt(0);
560: if (!isNCNameStart(ch)) {
561: return false;
562: }
563: for (int i = 1; i < ncName.length(); i++) {
564: ch = ncName.charAt(i);
565: if (!isNCName(ch)) {
566: return false;
567: }
568: }
569: return true;
570: } // isValidNCName(String):boolean
571:
572: /*
573: * [7] Nmtoken ::= (NameChar)+
574: */
575: /**
576: * Check to see if a string is a valid Nmtoken according to [7]
577: * in the XML 1.0 Recommendation
578: *
579: * @param nmtoken string to check
580: * @return true if nmtoken is a valid Nmtoken
581: */
582: public static boolean isValidNmtoken(String nmtoken) {
583: if (nmtoken.length() == 0) {
584: return false;
585: }
586: for (int i = 0; i < nmtoken.length(); i++) {
587: char ch = nmtoken.charAt(i);
588: if (!isName(ch)) {
589: return false;
590: }
591: }
592: return true;
593: } // isValidName(String):boolean
594:
595: // encodings
596:
597: /**
598: * Returns true if the encoding name is a valid IANA encoding.
599: * This method does not verify that there is a decoder available
600: * for this encoding, only that the characters are valid for an
601: * IANA encoding name.
602: *
603: * @param ianaEncoding The IANA encoding name.
604: */
605: public static boolean isValidIANAEncoding(String ianaEncoding) {
606: if (ianaEncoding != null) {
607: int length = ianaEncoding.length();
608: if (length > 0) {
609: char c = ianaEncoding.charAt(0);
610: if ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z')) {
611: for (int i = 1; i < length; i++) {
612: c = ianaEncoding.charAt(i);
613: if ((c < 'A' || c > 'Z')
614: && (c < 'a' || c > 'z')
615: && (c < '0' || c > '9') && c != '.'
616: && c != '_' && c != '-') {
617: return false;
618: }
619: }
620: return true;
621: }
622: }
623: }
624: return false;
625: } // isValidIANAEncoding(String):boolean
626:
627: /**
628: * Returns true if the encoding name is a valid Java encoding.
629: * This method does not verify that there is a decoder available
630: * for this encoding, only that the characters are valid for an
631: * Java encoding name.
632: *
633: * @param javaEncoding The Java encoding name.
634: */
635: public static boolean isValidJavaEncoding(String javaEncoding) {
636: if (javaEncoding != null) {
637: int length = javaEncoding.length();
638: if (length > 0) {
639: for (int i = 1; i < length; i++) {
640: char c = javaEncoding.charAt(i);
641: if ((c < 'A' || c > 'Z') && (c < 'a' || c > 'z')
642: && (c < '0' || c > '9') && c != '.'
643: && c != '_' && c != '-') {
644: return false;
645: }
646: }
647: return true;
648: }
649: }
650: return false;
651: } // isValidIANAEncoding(String):boolean
652:
653: } // class XMLChar
|