Java tutorial
//package com.java2s; /* * Copyright (c) 2013-2014 Josef Hardi <josef.hardi@gmail.com> * * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. * You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ public class Main { /** * Gets the longest NCName that is a suffix of a character sequence. * * @param cs * The character sequence. * @return Returns the string which is the longest suffix of the character * sequence <code>s</code> that is an NCName, or <code>null</code> if * the character sequence <code>s</code> does not have a suffix that * is an NCName. */ public static String getNCNameSuffix(CharSequence cs) { int localPartStartIndex = getNCNameSuffixIndex(cs); if (localPartStartIndex != -1) { return cs.toString().substring(localPartStartIndex); } else { return null; } } /** * Gets the index of the longest NCName that is the suffix of a character * sequence. * * @param cs * The character sequence. * @return Returns the index of the longest suffix of the specified character * sequence <code>cs</code> that is an NCName, or -1 if the character * sequence <code>cs</code> does not have a suffix that is an NCName. */ public static int getNCNameSuffixIndex(CharSequence cs) { int index = -1; for (int i = cs.length() - 1; i > -1; i--) { if (!Character.isLowSurrogate(cs.charAt(i))) { int c = Character.codePointAt(cs, i); if (isNCNameStartChar(c)) { index = i; } if (!isNCNameChar(c)) { break; } } } return index; } /** * Determines if the input character <code>c</code> is an NCName (Non-Colon * Name, i.e., an XML Name, minus the ":") start character. * * @param c * the input character value to test (according to UTF-8 or UTF-16) * @return Returns <code>true</code> if the input character is a NCName start * character, or <code>false</code> otherwise. */ public static boolean isNCNameStartChar(int c) { return c != ':' && isXmlNameStartChar(c); //$NON-NLS-1$ } /** * Determines if the input character <code>c</code> is a NCName (Non-Colon * Name, i.e., an XML Name, minus the ":") character. * * @param c * the input character value to test (according to UTF-8 or UTF-16) * @return Returns <code>true</code> if the input character is a NCName * character, or <code>false</code> otherwise. */ public static boolean isNCNameChar(int c) { return c != ':' && isXmlNameChar(c); //$NON-NLS-1$ } /** * Determines if the input character <code>c</code> is an XML name start * character. * * Source: http://www.w3.org/TR/xml/#NT-NameStartChar * * @param c * the input character value to test (according to UTF-8 or UTF-16) * @return Returns <code>true</code> if the input character is a name start * character, or <code>false</code> otherwise. */ public static boolean isXmlNameStartChar(int c) { return c == ':' //$NON-NLS-1$ || (c >= 'A' && c <= 'Z') //$NON-NLS-1$ //$NON-NLS-2$ || c == '_' //$NON-NLS-1$ || (c >= 'a' && c <= 'z') //$NON-NLS-1$ //$NON-NLS-2$ || (c >= 0xC0 && c <= 0xD6) || (c >= 0xD8 && c <= 0xF6) || (c >= 0xF8 && c <= 0x2FF) || (c >= 0x370 && c <= 0x37D) || (c >= 0x37F && c <= 0x1FFF) || (c >= 0x200C && c <= 0x200D) || (c >= 0x2070 && c <= 0x218F) || (c >= 0x2C00 && c <= 0x2FEF) || (c >= 0x3001 && c <= 0xD7FF) || (c >= 0xF900 && c <= 0xFDCF) || (c >= 0xFDF0 && c <= 0xFFFD) || (c >= 0x10000 && c <= 0xEFFFF); } /** * Determines if the input character <code>c</code> is an XML name character. * * Source: http://www.w3.org/TR/xml/#NT-NameChar * * @param c * the input character value to test (according to UTF-8 or UTF-16) * @return Returns <code>true</code> if the input character is a name * character, or <code>false</code> otherwise. */ public static boolean isXmlNameChar(int c) { return isXmlNameStartChar(c) || c == '-' //$NON-NLS-1$ || c == '.' //$NON-NLS-1$ || c >= '0' && c <= '9' //$NON-NLS-1$ //$NON-NLS-2$ || c == 0xB7 || c >= 0x0300 && c <= 0x036F || c >= 0x203F && c <= 0x2040; } }