001: /*
002: * Copyright 1999-2004 The Apache Software Foundation.
003: *
004: * Licensed under the Apache License, Version 2.0 (the "License");
005: * you may not use this file except in compliance with the License.
006: * You may obtain a copy of the License at
007: *
008: * http://www.apache.org/licenses/LICENSE-2.0
009: *
010: * Unless required by applicable law or agreed to in writing, software
011: * distributed under the License is distributed on an "AS IS" BASIS,
012: * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
013: * See the License for the specific language governing permissions and
014: * limitations under the License.
015: */
016: /*
017: * $Id$
018: */
019:
020: package org.apache.xml.utils;
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: * @author Glenn Marcy, IBM
038: * @author Andy Clark, IBM
039: * @author Eric Ye, IBM
040: * @author Arnaud Le Hors, IBM
041: * @author Rahul Srivastava, Sun Microsystems Inc.
042: *
043: * @version $Id: XMLChar.java,v 1.7 2002/01/29 01:15:18 lehors Exp $
044: */
045: public class XMLChar {
046:
047: //
048: // Constants
049: //
050:
051: /** Character flags. */
052: private static final byte[] CHARS = new byte[1 << 16];
053:
054: /** Valid character mask. */
055: public static final int MASK_VALID = 0x01;
056:
057: /** Space character mask. */
058: public static final int MASK_SPACE = 0x02;
059:
060: /** Name start character mask. */
061: public static final int MASK_NAME_START = 0x04;
062:
063: /** Name character mask. */
064: public static final int MASK_NAME = 0x08;
065:
066: /** Pubid character mask. */
067: public static final int MASK_PUBID = 0x10;
068:
069: /**
070: * Content character mask. Special characters are those that can
071: * be considered the start of markup, such as '<' and '&'.
072: * The various newline characters are considered special as well.
073: * All other valid XML characters can be considered content.
074: * <p>
075: * This is an optimization for the inner loop of character scanning.
076: */
077: public static final int MASK_CONTENT = 0x20;
078:
079: /** NCName start character mask. */
080: public static final int MASK_NCNAME_START = 0x40;
081:
082: /** NCName character mask. */
083: public static final int MASK_NCNAME = 0x80;
084:
085: //
086: // Static initialization
087: //
088:
089: static {
090:
091: //
092: // [2] Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] |
093: // [#xE000-#xFFFD] | [#x10000-#x10FFFF]
094: //
095:
096: int charRange[] = { 0x0009, 0x000A, 0x000D, 0x000D, 0x0020,
097: 0xD7FF, 0xE000, 0xFFFD, };
098:
099: //
100: // [3] S ::= (#x20 | #x9 | #xD | #xA)+
101: //
102:
103: int spaceChar[] = { 0x0020, 0x0009, 0x000D, 0x000A, };
104:
105: //
106: // [4] NameChar ::= Letter | Digit | '.' | '-' | '_' | ':' |
107: // CombiningChar | Extender
108: //
109:
110: int nameChar[] = { 0x002D, 0x002E, // '-' and '.'
111: };
112:
113: //
114: // [5] Name ::= (Letter | '_' | ':') (NameChar)*
115: //
116:
117: int nameStartChar[] = { 0x003A, 0x005F, // ':' and '_'
118: };
119:
120: //
121: // [13] PubidChar ::= #x20 | 0xD | 0xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%]
122: //
123:
124: int pubidChar[] = { 0x000A, 0x000D, 0x0020, 0x0021, 0x0023,
125: 0x0024, 0x0025, 0x003D, 0x005F };
126:
127: int pubidRange[] = { 0x0027, 0x003B, 0x003F, 0x005A, 0x0061,
128: 0x007A };
129:
130: //
131: // [84] Letter ::= BaseChar | Ideographic
132: //
133:
134: int letterRange[] = {
135: // BaseChar
136: 0x0041, 0x005A, 0x0061, 0x007A, 0x00C0, 0x00D6, 0x00D8,
137: 0x00F6, 0x00F8, 0x0131, 0x0134, 0x013E, 0x0141, 0x0148,
138: 0x014A, 0x017E, 0x0180, 0x01C3, 0x01CD, 0x01F0, 0x01F4,
139: 0x01F5, 0x01FA, 0x0217, 0x0250, 0x02A8, 0x02BB, 0x02C1,
140: 0x0388, 0x038A, 0x038E, 0x03A1, 0x03A3, 0x03CE, 0x03D0,
141: 0x03D6, 0x03E2, 0x03F3, 0x0401, 0x040C, 0x040E, 0x044F,
142: 0x0451, 0x045C, 0x045E, 0x0481, 0x0490, 0x04C4, 0x04C7,
143: 0x04C8, 0x04CB, 0x04CC, 0x04D0, 0x04EB, 0x04EE, 0x04F5,
144: 0x04F8, 0x04F9, 0x0531, 0x0556, 0x0561, 0x0586, 0x05D0,
145: 0x05EA, 0x05F0, 0x05F2, 0x0621, 0x063A, 0x0641, 0x064A,
146: 0x0671, 0x06B7, 0x06BA, 0x06BE, 0x06C0, 0x06CE, 0x06D0,
147: 0x06D3, 0x06E5, 0x06E6, 0x0905, 0x0939, 0x0958, 0x0961,
148: 0x0985, 0x098C, 0x098F, 0x0990, 0x0993, 0x09A8, 0x09AA,
149: 0x09B0, 0x09B6, 0x09B9, 0x09DC, 0x09DD, 0x09DF, 0x09E1,
150: 0x09F0, 0x09F1, 0x0A05, 0x0A0A, 0x0A0F, 0x0A10, 0x0A13,
151: 0x0A28, 0x0A2A, 0x0A30, 0x0A32, 0x0A33, 0x0A35, 0x0A36,
152: 0x0A38, 0x0A39, 0x0A59, 0x0A5C, 0x0A72, 0x0A74, 0x0A85,
153: 0x0A8B, 0x0A8F, 0x0A91, 0x0A93, 0x0AA8, 0x0AAA, 0x0AB0,
154: 0x0AB2, 0x0AB3, 0x0AB5, 0x0AB9, 0x0B05, 0x0B0C, 0x0B0F,
155: 0x0B10, 0x0B13, 0x0B28, 0x0B2A, 0x0B30, 0x0B32, 0x0B33,
156: 0x0B36, 0x0B39, 0x0B5C, 0x0B5D, 0x0B5F, 0x0B61, 0x0B85,
157: 0x0B8A, 0x0B8E, 0x0B90, 0x0B92, 0x0B95, 0x0B99, 0x0B9A,
158: 0x0B9E, 0x0B9F, 0x0BA3, 0x0BA4, 0x0BA8, 0x0BAA, 0x0BAE,
159: 0x0BB5, 0x0BB7, 0x0BB9, 0x0C05, 0x0C0C, 0x0C0E, 0x0C10,
160: 0x0C12, 0x0C28, 0x0C2A, 0x0C33, 0x0C35, 0x0C39, 0x0C60,
161: 0x0C61, 0x0C85, 0x0C8C, 0x0C8E, 0x0C90, 0x0C92, 0x0CA8,
162: 0x0CAA, 0x0CB3, 0x0CB5, 0x0CB9, 0x0CE0, 0x0CE1, 0x0D05,
163: 0x0D0C, 0x0D0E, 0x0D10, 0x0D12, 0x0D28, 0x0D2A, 0x0D39,
164: 0x0D60, 0x0D61, 0x0E01, 0x0E2E, 0x0E32, 0x0E33, 0x0E40,
165: 0x0E45, 0x0E81, 0x0E82, 0x0E87, 0x0E88, 0x0E94, 0x0E97,
166: 0x0E99, 0x0E9F, 0x0EA1, 0x0EA3, 0x0EAA, 0x0EAB, 0x0EAD,
167: 0x0EAE, 0x0EB2, 0x0EB3, 0x0EC0, 0x0EC4, 0x0F40, 0x0F47,
168: 0x0F49, 0x0F69, 0x10A0, 0x10C5, 0x10D0, 0x10F6, 0x1102,
169: 0x1103, 0x1105, 0x1107, 0x110B, 0x110C, 0x110E, 0x1112,
170: 0x1154, 0x1155, 0x115F, 0x1161, 0x116D, 0x116E, 0x1172,
171: 0x1173, 0x11AE, 0x11AF, 0x11B7, 0x11B8, 0x11BC, 0x11C2,
172: 0x1E00, 0x1E9B, 0x1EA0, 0x1EF9, 0x1F00, 0x1F15, 0x1F18,
173: 0x1F1D, 0x1F20, 0x1F45, 0x1F48, 0x1F4D, 0x1F50, 0x1F57,
174: 0x1F5F, 0x1F7D, 0x1F80, 0x1FB4, 0x1FB6, 0x1FBC, 0x1FC2,
175: 0x1FC4, 0x1FC6, 0x1FCC, 0x1FD0, 0x1FD3, 0x1FD6, 0x1FDB,
176: 0x1FE0, 0x1FEC, 0x1FF2, 0x1FF4, 0x1FF6, 0x1FFC, 0x212A,
177: 0x212B, 0x2180, 0x2182, 0x3041, 0x3094, 0x30A1, 0x30FA,
178: 0x3105, 0x312C, 0xAC00, 0xD7A3,
179: // Ideographic
180: 0x3021, 0x3029, 0x4E00, 0x9FA5, };
181: int letterChar[] = {
182: // BaseChar
183: 0x0386, 0x038C, 0x03DA, 0x03DC, 0x03DE, 0x03E0, 0x0559,
184: 0x06D5, 0x093D, 0x09B2, 0x0A5E, 0x0A8D, 0x0ABD, 0x0AE0,
185: 0x0B3D, 0x0B9C, 0x0CDE, 0x0E30, 0x0E84, 0x0E8A, 0x0E8D,
186: 0x0EA5, 0x0EA7, 0x0EB0, 0x0EBD, 0x1100, 0x1109, 0x113C,
187: 0x113E, 0x1140, 0x114C, 0x114E, 0x1150, 0x1159, 0x1163,
188: 0x1165, 0x1167, 0x1169, 0x1175, 0x119E, 0x11A8, 0x11AB,
189: 0x11BA, 0x11EB, 0x11F0, 0x11F9, 0x1F59, 0x1F5B, 0x1F5D,
190: 0x1FBE, 0x2126, 0x212E,
191: // Ideographic
192: 0x3007, };
193:
194: //
195: // [87] CombiningChar ::= ...
196: //
197:
198: int combiningCharRange[] = { 0x0300, 0x0345, 0x0360, 0x0361,
199: 0x0483, 0x0486, 0x0591, 0x05A1, 0x05A3, 0x05B9, 0x05BB,
200: 0x05BD, 0x05C1, 0x05C2, 0x064B, 0x0652, 0x06D6, 0x06DC,
201: 0x06DD, 0x06DF, 0x06E0, 0x06E4, 0x06E7, 0x06E8, 0x06EA,
202: 0x06ED, 0x0901, 0x0903, 0x093E, 0x094C, 0x0951, 0x0954,
203: 0x0962, 0x0963, 0x0981, 0x0983, 0x09C0, 0x09C4, 0x09C7,
204: 0x09C8, 0x09CB, 0x09CD, 0x09E2, 0x09E3, 0x0A40, 0x0A42,
205: 0x0A47, 0x0A48, 0x0A4B, 0x0A4D, 0x0A70, 0x0A71, 0x0A81,
206: 0x0A83, 0x0ABE, 0x0AC5, 0x0AC7, 0x0AC9, 0x0ACB, 0x0ACD,
207: 0x0B01, 0x0B03, 0x0B3E, 0x0B43, 0x0B47, 0x0B48, 0x0B4B,
208: 0x0B4D, 0x0B56, 0x0B57, 0x0B82, 0x0B83, 0x0BBE, 0x0BC2,
209: 0x0BC6, 0x0BC8, 0x0BCA, 0x0BCD, 0x0C01, 0x0C03, 0x0C3E,
210: 0x0C44, 0x0C46, 0x0C48, 0x0C4A, 0x0C4D, 0x0C55, 0x0C56,
211: 0x0C82, 0x0C83, 0x0CBE, 0x0CC4, 0x0CC6, 0x0CC8, 0x0CCA,
212: 0x0CCD, 0x0CD5, 0x0CD6, 0x0D02, 0x0D03, 0x0D3E, 0x0D43,
213: 0x0D46, 0x0D48, 0x0D4A, 0x0D4D, 0x0E34, 0x0E3A, 0x0E47,
214: 0x0E4E, 0x0EB4, 0x0EB9, 0x0EBB, 0x0EBC, 0x0EC8, 0x0ECD,
215: 0x0F18, 0x0F19, 0x0F71, 0x0F84, 0x0F86, 0x0F8B, 0x0F90,
216: 0x0F95, 0x0F99, 0x0FAD, 0x0FB1, 0x0FB7, 0x20D0, 0x20DC,
217: 0x302A, 0x302F, };
218:
219: int combiningCharChar[] = { 0x05BF, 0x05C4, 0x0670, 0x093C,
220: 0x094D, 0x09BC, 0x09BE, 0x09BF, 0x09D7, 0x0A02, 0x0A3C,
221: 0x0A3E, 0x0A3F, 0x0ABC, 0x0B3C, 0x0BD7, 0x0D57, 0x0E31,
222: 0x0EB1, 0x0F35, 0x0F37, 0x0F39, 0x0F3E, 0x0F3F, 0x0F97,
223: 0x0FB9, 0x20E1, 0x3099, 0x309A, };
224:
225: //
226: // [88] Digit ::= ...
227: //
228:
229: int digitRange[] = { 0x0030, 0x0039, 0x0660, 0x0669, 0x06F0,
230: 0x06F9, 0x0966, 0x096F, 0x09E6, 0x09EF, 0x0A66, 0x0A6F,
231: 0x0AE6, 0x0AEF, 0x0B66, 0x0B6F, 0x0BE7, 0x0BEF, 0x0C66,
232: 0x0C6F, 0x0CE6, 0x0CEF, 0x0D66, 0x0D6F, 0x0E50, 0x0E59,
233: 0x0ED0, 0x0ED9, 0x0F20, 0x0F29, };
234:
235: //
236: // [89] Extender ::= ...
237: //
238:
239: int extenderRange[] = { 0x3031, 0x3035, 0x309D, 0x309E, 0x30FC,
240: 0x30FE, };
241:
242: int extenderChar[] = { 0x00B7, 0x02D0, 0x02D1, 0x0387, 0x0640,
243: 0x0E46, 0x0EC6, 0x3005, };
244:
245: //
246: // SpecialChar ::= '<', '&', '\n', '\r', ']'
247: //
248:
249: int specialChar[] = { '<', '&', '\n', '\r', ']', };
250:
251: //
252: // Initialize
253: //
254:
255: // set valid characters
256: for (int i = 0; i < charRange.length; i += 2) {
257: for (int j = charRange[i]; j <= charRange[i + 1]; j++) {
258: CHARS[j] |= MASK_VALID | MASK_CONTENT;
259: }
260: }
261:
262: // remove special characters
263: for (int i = 0; i < specialChar.length; i++) {
264: CHARS[specialChar[i]] = (byte) (CHARS[specialChar[i]] & ~MASK_CONTENT);
265: }
266:
267: // set space characters
268: for (int i = 0; i < spaceChar.length; i++) {
269: CHARS[spaceChar[i]] |= MASK_SPACE;
270: }
271:
272: // set name start characters
273: for (int i = 0; i < nameStartChar.length; i++) {
274: CHARS[nameStartChar[i]] |= MASK_NAME_START | MASK_NAME
275: | MASK_NCNAME_START | MASK_NCNAME;
276: }
277: for (int i = 0; i < letterRange.length; i += 2) {
278: for (int j = letterRange[i]; j <= letterRange[i + 1]; j++) {
279: CHARS[j] |= MASK_NAME_START | MASK_NAME
280: | MASK_NCNAME_START | MASK_NCNAME;
281: }
282: }
283: for (int i = 0; i < letterChar.length; i++) {
284: CHARS[letterChar[i]] |= MASK_NAME_START | MASK_NAME
285: | MASK_NCNAME_START | MASK_NCNAME;
286: }
287:
288: // set name characters
289: for (int i = 0; i < nameChar.length; i++) {
290: CHARS[nameChar[i]] |= MASK_NAME | MASK_NCNAME;
291: }
292: for (int i = 0; i < digitRange.length; i += 2) {
293: for (int j = digitRange[i]; j <= digitRange[i + 1]; j++) {
294: CHARS[j] |= MASK_NAME | MASK_NCNAME;
295: }
296: }
297: for (int i = 0; i < combiningCharRange.length; i += 2) {
298: for (int j = combiningCharRange[i]; j <= combiningCharRange[i + 1]; j++) {
299: CHARS[j] |= MASK_NAME | MASK_NCNAME;
300: }
301: }
302: for (int i = 0; i < combiningCharChar.length; i++) {
303: CHARS[combiningCharChar[i]] |= MASK_NAME | MASK_NCNAME;
304: }
305: for (int i = 0; i < extenderRange.length; i += 2) {
306: for (int j = extenderRange[i]; j <= extenderRange[i + 1]; j++) {
307: CHARS[j] |= MASK_NAME | MASK_NCNAME;
308: }
309: }
310: for (int i = 0; i < extenderChar.length; i++) {
311: CHARS[extenderChar[i]] |= MASK_NAME | MASK_NCNAME;
312: }
313:
314: // remove ':' from allowable MASK_NCNAME_START and MASK_NCNAME chars
315: CHARS[':'] &= ~(MASK_NCNAME_START | MASK_NCNAME);
316:
317: // set Pubid characters
318: for (int i = 0; i < pubidChar.length; i++) {
319: CHARS[pubidChar[i]] |= MASK_PUBID;
320: }
321: for (int i = 0; i < pubidRange.length; i += 2) {
322: for (int j = pubidRange[i]; j <= pubidRange[i + 1]; j++) {
323: CHARS[j] |= MASK_PUBID;
324: }
325: }
326:
327: } // <clinit>()
328:
329: //
330: // Public static methods
331: //
332:
333: /**
334: * Returns true if the specified character is a supplemental character.
335: *
336: * @param c The character to check.
337: */
338: public static boolean isSupplemental(int c) {
339: return (c >= 0x10000 && c <= 0x10FFFF);
340: }
341:
342: /**
343: * Returns true the supplemental character corresponding to the given
344: * surrogates.
345: *
346: * @param h The high surrogate.
347: * @param l The low surrogate.
348: */
349: public static int supplemental(char h, char l) {
350: return (h - 0xD800) * 0x400 + (l - 0xDC00) + 0x10000;
351: }
352:
353: /**
354: * Returns the high surrogate of a supplemental character
355: *
356: * @param c The supplemental character to "split".
357: */
358: public static char highSurrogate(int c) {
359: return (char) (((c - 0x00010000) >> 10) + 0xD800);
360: }
361:
362: /**
363: * Returns the low surrogate of a supplemental character
364: *
365: * @param c The supplemental character to "split".
366: */
367: public static char lowSurrogate(int c) {
368: return (char) (((c - 0x00010000) & 0x3FF) + 0xDC00);
369: }
370:
371: /**
372: * Returns whether the given character is a high surrogate
373: *
374: * @param c The character to check.
375: */
376: public static boolean isHighSurrogate(int c) {
377: return (0xD800 <= c && c <= 0xDBFF);
378: }
379:
380: /**
381: * Returns whether the given character is a low surrogate
382: *
383: * @param c The character to check.
384: */
385: public static boolean isLowSurrogate(int c) {
386: return (0xDC00 <= c && c <= 0xDFFF);
387: }
388:
389: /**
390: * Returns true if the specified character is valid. This method
391: * also checks the surrogate character range from 0x10000 to 0x10FFFF.
392: * <p>
393: * If the program chooses to apply the mask directly to the
394: * <code>CHARS</code> array, then they are responsible for checking
395: * the surrogate character range.
396: *
397: * @param c The character to check.
398: */
399: public static boolean isValid(int c) {
400: return (c < 0x10000 && (CHARS[c] & MASK_VALID) != 0)
401: || (0x10000 <= c && c <= 0x10FFFF);
402: } // isValid(int):boolean
403:
404: /**
405: * Returns true if the specified character is invalid.
406: *
407: * @param c The character to check.
408: */
409: public static boolean isInvalid(int c) {
410: return !isValid(c);
411: } // isInvalid(int):boolean
412:
413: /**
414: * Returns true if the specified character can be considered content.
415: *
416: * @param c The character to check.
417: */
418: public static boolean isContent(int c) {
419: return (c < 0x10000 && (CHARS[c] & MASK_CONTENT) != 0)
420: || (0x10000 <= c && c <= 0x10FFFF);
421: } // isContent(int):boolean
422:
423: /**
424: * Returns true if the specified character can be considered markup.
425: * Markup characters include '<', '&', and '%'.
426: *
427: * @param c The character to check.
428: */
429: public static boolean isMarkup(int c) {
430: return c == '<' || c == '&' || c == '%';
431: } // isMarkup(int):boolean
432:
433: /**
434: * Returns true if the specified character is a space character
435: * as defined by production [3] in the XML 1.0 specification.
436: *
437: * @param c The character to check.
438: */
439: public static boolean isSpace(int c) {
440: return c < 0x10000 && (CHARS[c] & MASK_SPACE) != 0;
441: } // isSpace(int):boolean
442:
443: /**
444: * Returns true if the specified character is a valid name start
445: * character as defined by production [5] in the XML 1.0
446: * specification.
447: *
448: * @param c The character to check.
449: */
450: public static boolean isNameStart(int c) {
451: return c < 0x10000 && (CHARS[c] & MASK_NAME_START) != 0;
452: } // isNameStart(int):boolean
453:
454: /**
455: * Returns true if the specified character is a valid name
456: * character as defined by production [4] in the XML 1.0
457: * specification.
458: *
459: * @param c The character to check.
460: */
461: public static boolean isName(int c) {
462: return c < 0x10000 && (CHARS[c] & MASK_NAME) != 0;
463: } // isName(int):boolean
464:
465: /**
466: * Returns true if the specified character is a valid NCName start
467: * character as defined by production [4] in Namespaces in XML
468: * recommendation.
469: *
470: * @param c The character to check.
471: */
472: public static boolean isNCNameStart(int c) {
473: return c < 0x10000 && (CHARS[c] & MASK_NCNAME_START) != 0;
474: } // isNCNameStart(int):boolean
475:
476: /**
477: * Returns true if the specified character is a valid NCName
478: * character as defined by production [5] in Namespaces in XML
479: * recommendation.
480: *
481: * @param c The character to check.
482: */
483: public static boolean isNCName(int c) {
484: return c < 0x10000 && (CHARS[c] & MASK_NCNAME) != 0;
485: } // isNCName(int):boolean
486:
487: /**
488: * Returns true if the specified character is a valid Pubid
489: * character as defined by production [13] in the XML 1.0
490: * specification.
491: *
492: * @param c The character to check.
493: */
494: public static boolean isPubid(int c) {
495: return c < 0x10000 && (CHARS[c] & MASK_PUBID) != 0;
496: } // isPubid(int):boolean
497:
498: /*
499: * [5] Name ::= (Letter | '_' | ':') (NameChar)*
500: */
501: /**
502: * Check to see if a string is a valid Name according to [5]
503: * in the XML 1.0 Recommendation
504: *
505: * @param name string to check
506: * @return true if name is a valid Name
507: */
508: public static boolean isValidName(String name) {
509: if (name.length() == 0)
510: return false;
511: char ch = name.charAt(0);
512: if (isNameStart(ch) == false)
513: return false;
514: for (int i = 1; i < name.length(); i++) {
515: ch = name.charAt(i);
516: if (isName(ch) == false) {
517: return false;
518: }
519: }
520: return true;
521: } // isValidName(String):boolean
522:
523: /*
524: * from the namespace rec
525: * [4] NCName ::= (Letter | '_') (NCNameChar)*
526: */
527: /**
528: * Check to see if a string is a valid NCName according to [4]
529: * from the XML Namespaces 1.0 Recommendation
530: *
531: * @param ncName string to check
532: * @return true if name is a valid NCName
533: */
534: public static boolean isValidNCName(String ncName) {
535: if (ncName.length() == 0)
536: return false;
537: char ch = ncName.charAt(0);
538: if (isNCNameStart(ch) == false)
539: return false;
540: for (int i = 1; i < ncName.length(); i++) {
541: ch = ncName.charAt(i);
542: if (isNCName(ch) == false) {
543: return false;
544: }
545: }
546: return true;
547: } // isValidNCName(String):boolean
548:
549: /*
550: * [7] Nmtoken ::= (NameChar)+
551: */
552: /**
553: * Check to see if a string is a valid Nmtoken according to [7]
554: * in the XML 1.0 Recommendation
555: *
556: * @param nmtoken string to check
557: * @return true if nmtoken is a valid Nmtoken
558: */
559: public static boolean isValidNmtoken(String nmtoken) {
560: if (nmtoken.length() == 0)
561: return false;
562: for (int i = 0; i < nmtoken.length(); i++) {
563: char ch = nmtoken.charAt(i);
564: if (!isName(ch)) {
565: return false;
566: }
567: }
568: return true;
569: } // isValidName(String):boolean
570:
571: // encodings
572:
573: /**
574: * Returns true if the encoding name is a valid IANA encoding.
575: * This method does not verify that there is a decoder available
576: * for this encoding, only that the characters are valid for an
577: * IANA encoding name.
578: *
579: * @param ianaEncoding The IANA encoding name.
580: */
581: public static boolean isValidIANAEncoding(String ianaEncoding) {
582: if (ianaEncoding != null) {
583: int length = ianaEncoding.length();
584: if (length > 0) {
585: char c = ianaEncoding.charAt(0);
586: if ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z')) {
587: for (int i = 1; i < length; i++) {
588: c = ianaEncoding.charAt(i);
589: if ((c < 'A' || c > 'Z')
590: && (c < 'a' || c > 'z')
591: && (c < '0' || c > '9') && c != '.'
592: && c != '_' && c != '-') {
593: return false;
594: }
595: }
596: return true;
597: }
598: }
599: }
600: return false;
601: } // isValidIANAEncoding(String):boolean
602:
603: /**
604: * Returns true if the encoding name is a valid Java encoding.
605: * This method does not verify that there is a decoder available
606: * for this encoding, only that the characters are valid for an
607: * Java encoding name.
608: *
609: * @param javaEncoding The Java encoding name.
610: */
611: public static boolean isValidJavaEncoding(String javaEncoding) {
612: if (javaEncoding != null) {
613: int length = javaEncoding.length();
614: if (length > 0) {
615: for (int i = 1; i < length; i++) {
616: char c = javaEncoding.charAt(i);
617: if ((c < 'A' || c > 'Z') && (c < 'a' || c > 'z')
618: && (c < '0' || c > '9') && c != '.'
619: && c != '_' && c != '-') {
620: return false;
621: }
622: }
623: return true;
624: }
625: }
626: return false;
627: } // isValidIANAEncoding(String):boolean
628:
629: /**
630: * Simple check to determine if qname is legal. If it returns false
631: * then <param>str</param> is illegal; if it returns true then
632: * <param>str</param> is legal.
633: */
634: public static boolean isValidQName(String str) {
635:
636: final int colon = str.indexOf(':');
637:
638: if (colon == 0 || colon == str.length() - 1) {
639: return false;
640: }
641:
642: if (colon > 0) {
643: final String prefix = str.substring(0, colon);
644: final String localPart = str.substring(colon + 1);
645: return isValidNCName(prefix) && isValidNCName(localPart);
646: } else {
647: return isValidNCName(str);
648: }
649: }
650:
651: } // class XMLChar
|