/* * Licensed to the Apache Software Foundation (ASF) under one * or more contributor license agreements. See the NOTICE file * distributed with this work for additional information * regarding copyright ownership. The ASF licenses this file * to you 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. */ /* * $Id: XString.java 570108 2007-08-27 13:30:57Z zongaro $ */ package org.apache.xpath.objects; import java.util.Locale; import org.apache.xml.dtm.DTM; import org.apache.xml.utils.XMLCharacterRecognizer; import org.apache.xml.utils.XMLString; import org.apache.xml.utils.XMLStringFactory; import org.apache.xpath.ExpressionOwner; import org.apache.xpath.XPathContext; import org.apache.xpath.XPathVisitor; /** * This class represents an XPath string object, and is capable of * converting the string to other types, such as a number. * @xsl.usage general */ public class XString extends XObject implements XMLString { static final long serialVersionUID = 2020470518395094525L; /** Empty string XString object */ public static final XString EMPTYSTRING = new XString(""); /** * Construct a XString object. This constructor exists for derived classes. * * @param val String object this will wrap. */ protected XString(Object val) { super(val); } /** * Construct a XNodeSet object. * * @param val String object this will wrap. */ public XString(String val) { super(val); } /** * Tell that this is a CLASS_STRING. * * @return type CLASS_STRING */ public int getType() { return CLASS_STRING; } /** * Given a request type, return the equivalent string. * For diagnostic purposes. * * @return type string "#STRING" */ public String getTypeString() { return "#STRING"; } /** * Tell if this object contains a java String object. * * @return true if this XMLString can return a string without creating one. */ public boolean hasString() { return true; } /** * Cast result object to a number. * * @return 0.0 if this string is null, numeric value of this string * or NaN */ public double num() { return toDouble(); } /** * Convert a string to a double -- Allowed input is in fixed * notation ddd.fff. * * @return A double value representation of the string, or return Double.NaN * if the string can not be converted. */ public double toDouble() { /* XMLCharacterRecognizer.isWhiteSpace(char c) methods treats the following * characters as white space characters. * ht - horizontal tab, nl - newline , cr - carriage return and sp - space * trim() methods by default also takes care of these white space characters * So trim() method is used to remove leading and trailing white spaces. */ XMLString s = trim(); double result = Double.NaN; for (int i = 0; i < s.length(); i++) { char c = s.charAt(i); if (c != '-' && c != '.' && ( c < 0X30 || c > 0x39)) { // The character is not a '-' or a '.' or a digit // then return NaN because something is wrong. return result; } } try { result = Double.parseDouble(s.toString()); } catch (NumberFormatException e){} return result; } /** * Cast result object to a boolean. * * @return True if the length of this string object is greater * than 0. */ public boolean bool() { return str().length() > 0; } /** * Cast result object to a string. * * @return The string this wraps or the empty string if null */ public XMLString xstr() { return this; } /** * Cast result object to a string. * * @return The string this wraps or the empty string if null */ public String str() { return (null != m_obj) ? ((String) m_obj) : ""; } /** * Cast result object to a result tree fragment. * * @param support Xpath context to use for the conversion * * @return A document fragment with this string as a child node */ public int rtf(XPathContext support) { DTM frag = support.createDocumentFragment(); frag.appendTextChild(str()); return frag.getDocument(); } /** * Directly call the * characters method on the passed ContentHandler for the * string-value. Multiple calls to the * ContentHandler's characters methods may well occur for a single call to * this method. * * @param ch A non-null reference to a ContentHandler. * * @throws org.xml.sax.SAXException */ public void dispatchCharactersEvents(org.xml.sax.ContentHandler ch) throws org.xml.sax.SAXException { String str = str(); ch.characters(str.toCharArray(), 0, str.length()); } /** * Directly call the * comment method on the passed LexicalHandler for the * string-value. * * @param lh A non-null reference to a LexicalHandler. * * @throws org.xml.sax.SAXException */ public void dispatchAsComment(org.xml.sax.ext.LexicalHandler lh) throws org.xml.sax.SAXException { String str = str(); lh.comment(str.toCharArray(), 0, str.length()); } /** * Returns the length of this string. * * @return the length of the sequence of characters represented by this * object. */ public int length() { return str().length(); } /** * Returns the character at the specified index. An index ranges * from 0 to length() - 1. The first character * of the sequence is at index 0, the next at index * 1, and so on, as for array indexing. * * @param index the index of the character. * @return the character at the specified index of this string. * The first character is at index 0. * @exception IndexOutOfBoundsException if the index * argument is negative or not less than the length of this * string. */ public char charAt(int index) { return str().charAt(index); } /** * Copies characters from this string into the destination character * array. * * @param srcBegin index of the first character in the string * to copy. * @param srcEnd index after the last character in the string * to copy. * @param dst the destination array. * @param dstBegin the start offset in the destination array. * @exception IndexOutOfBoundsException If any of the following * is true: * * @exception NullPointerException if dst is null */ public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) { str().getChars(srcBegin, srcEnd, dst, dstBegin); } /** * Tell if two objects are functionally equal. * * @param obj2 Object to compare this to * * @return true if the two objects are equal * * @throws javax.xml.transform.TransformerException */ public boolean equals(XObject obj2) { // In order to handle the 'all' semantics of // nodeset comparisons, we always call the // nodeset function. int t = obj2.getType(); try { if (XObject.CLASS_NODESET == t) return obj2.equals(this); // If at least one object to be compared is a boolean, then each object // to be compared is converted to a boolean as if by applying the // boolean function. else if(XObject.CLASS_BOOLEAN == t) return obj2.bool() == bool(); // Otherwise, if at least one object to be compared is a number, then each object // to be compared is converted to a number as if by applying the number function. else if(XObject.CLASS_NUMBER == t) return obj2.num() == num(); } catch(javax.xml.transform.TransformerException te) { throw new org.apache.xml.utils.WrappedRuntimeException(te); } // Otherwise, both objects to be compared are converted to strings as // if by applying the string function. return xstr().equals(obj2.xstr()); } /** * Compares this string to the specified String. * The result is true if and only if the argument is not * null and is a String object that represents * the same sequence of characters as this object. * * @param obj2 the object to compare this String against. * @return true if the Strings are equal; * false otherwise. * @see java.lang.String#compareTo(java.lang.String) * @see java.lang.String#equalsIgnoreCase(java.lang.String) */ public boolean equals(String obj2) { return str().equals(obj2); } /** * Compares this string to the specified object. * The result is true if and only if the argument is not * null and is a String object that represents * the same sequence of characters as this object. * * @param obj2 the object to compare this String * against. * @return true if the String are equal; * false otherwise. * @see java.lang.String#compareTo(java.lang.String) * @see java.lang.String#equalsIgnoreCase(java.lang.String) */ public boolean equals(XMLString obj2) { if (obj2 != null) { if (!obj2.hasString()) { return obj2.equals(str()); } else { return str().equals(obj2.toString()); } } return false; } /** * Compares this string to the specified object. * The result is true if and only if the argument is not * null and is a String object that represents * the same sequence of characters as this object. * * @param obj2 the object to compare this String * against. * @return true if the String are equal; * false otherwise. * @see java.lang.String#compareTo(java.lang.String) * @see java.lang.String#equalsIgnoreCase(java.lang.String) */ public boolean equals(Object obj2) { if (null == obj2) return false; // In order to handle the 'all' semantics of // nodeset comparisons, we always call the // nodeset function. else if (obj2 instanceof XNodeSet) return obj2.equals(this); else if(obj2 instanceof XNumber) return obj2.equals(this); else return str().equals(obj2.toString()); } /** * Compares this String to another String, * ignoring case considerations. Two strings are considered equal * ignoring case if they are of the same length, and corresponding * characters in the two strings are equal ignoring case. * * @param anotherString the String to compare this * String against. * @return true if the argument is not null * and the Strings are equal, * ignoring case; false otherwise. * @see #equals(Object) * @see java.lang.Character#toLowerCase(char) * @see java.lang.Character#toUpperCase(char) */ public boolean equalsIgnoreCase(String anotherString) { return str().equalsIgnoreCase(anotherString); } /** * Compares two strings lexicographically. * * @param xstr the String to be compared. * * @return the value 0 if the argument string is equal to * this string; a value less than 0 if this string * is lexicographically less than the string argument; and a * value greater than 0 if this string is * lexicographically greater than the string argument. * @exception java.lang.NullPointerException if anotherString * is null. */ public int compareTo(XMLString xstr) { int len1 = this.length(); int len2 = xstr.length(); int n = Math.min(len1, len2); int i = 0; int j = 0; while (n-- != 0) { char c1 = this.charAt(i); char c2 = xstr.charAt(j); if (c1 != c2) { return c1 - c2; } i++; j++; } return len1 - len2; } /** * Compares two strings lexicographically, ignoring case considerations. * This method returns an integer whose sign is that of * this.toUpperCase().toLowerCase().compareTo( * str.toUpperCase().toLowerCase()). *

* Note that this method does not take locale into account, * and will result in an unsatisfactory ordering for certain locales. * The java.text package provides collators to allow * locale-sensitive ordering. * * @param str the String to be compared. * @return a negative integer, zero, or a positive integer as the * the specified String is greater than, equal to, or less * than this String, ignoring case considerations. * @see java.text.Collator#compare(String, String) * @since 1.2 */ public int compareToIgnoreCase(XMLString str) { // %REVIEW% Like it says, @since 1.2. Doesn't exist in earlier // versions of Java, hence we can't yet shell out to it. We can implement // it as character-by-character compare, but doing so efficiently // is likely to be (ahem) interesting. // // However, since nobody is actually _using_ this method yet: // return str().compareToIgnoreCase(str.toString()); throw new org.apache.xml.utils.WrappedRuntimeException( new java.lang.NoSuchMethodException( "Java 1.2 method, not yet implemented")); } /** * Tests if this string starts with the specified prefix beginning * a specified index. * * @param prefix the prefix. * @param toffset where to begin looking in the string. * @return true if the character sequence represented by the * argument is a prefix of the substring of this object starting * at index toffset; false otherwise. * The result is false if toffset is * negative or greater than the length of this * String object; otherwise the result is the same * as the result of the expression *

   *          this.subString(toffset).startsWith(prefix)
   *          
* @exception java.lang.NullPointerException if prefix is * null. */ public boolean startsWith(String prefix, int toffset) { return str().startsWith(prefix, toffset); } /** * Tests if this string starts with the specified prefix. * * @param prefix the prefix. * @return true if the character sequence represented by the * argument is a prefix of the character sequence represented by * this string; false otherwise. * Note also that true will be returned if the * argument is an empty string or is equal to this * String object as determined by the * {@link #equals(Object)} method. * @exception java.lang.NullPointerException if prefix is * null. */ public boolean startsWith(String prefix) { return startsWith(prefix, 0); } /** * Tests if this string starts with the specified prefix beginning * a specified index. * * @param prefix the prefix. * @param toffset where to begin looking in the string. * @return true if the character sequence represented by the * argument is a prefix of the substring of this object starting * at index toffset; false otherwise. * The result is false if toffset is * negative or greater than the length of this * String object; otherwise the result is the same * as the result of the expression *
   *          this.subString(toffset).startsWith(prefix)
   *          
* @exception java.lang.NullPointerException if prefix is * null. */ public boolean startsWith(XMLString prefix, int toffset) { int to = toffset; int tlim = this.length(); int po = 0; int pc = prefix.length(); // Note: toffset might be near -1>>>1. if ((toffset < 0) || (toffset > tlim - pc)) { return false; } while (--pc >= 0) { if (this.charAt(to) != prefix.charAt(po)) { return false; } to++; po++; } return true; } /** * Tests if this string starts with the specified prefix. * * @param prefix the prefix. * @return true if the character sequence represented by the * argument is a prefix of the character sequence represented by * this string; false otherwise. * Note also that true will be returned if the * argument is an empty string or is equal to this * String object as determined by the * {@link #equals(Object)} method. * @exception java.lang.NullPointerException if prefix is * null. */ public boolean startsWith(XMLString prefix) { return startsWith(prefix, 0); } /** * Tests if this string ends with the specified suffix. * * @param suffix the suffix. * @return true if the character sequence represented by the * argument is a suffix of the character sequence represented by * this object; false otherwise. Note that the * result will be true if the argument is the * empty string or is equal to this String object * as determined by the {@link #equals(Object)} method. * @exception java.lang.NullPointerException if suffix is * null. */ public boolean endsWith(String suffix) { return str().endsWith(suffix); } /** * Returns a hashcode for this string. The hashcode for a * String object is computed as *
   * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
   * 
* using int arithmetic, where s[i] is the * ith character of the string, n is the length of * the string, and ^ indicates exponentiation. * (The hash value of the empty string is zero.) * * @return a hash code value for this object. */ public int hashCode() { return str().hashCode(); } /** * Returns the index within this string of the first occurrence of the * specified character. If a character with value ch occurs * in the character sequence represented by this String * object, then the index of the first such occurrence is returned -- * that is, the smallest value k such that: *
   * this.charAt(k) == ch
   * 
* is true. If no such character occurs in this string, * then -1 is returned. * * @param ch a character. * @return the index of the first occurrence of the character in the * character sequence represented by this object, or * -1 if the character does not occur. */ public int indexOf(int ch) { return str().indexOf(ch); } /** * Returns the index within this string of the first occurrence of the * specified character, starting the search at the specified index. *

* If a character with value ch occurs in the character * sequence represented by this String object at an index * no smaller than fromIndex, then the index of the first * such occurrence is returned--that is, the smallest value k * such that: *

   * (this.charAt(k) == ch) && (k >= fromIndex)
   * 
* is true. If no such character occurs in this string at or after * position fromIndex, then -1 is returned. *

* There is no restriction on the value of fromIndex. If it * is negative, it has the same effect as if it were zero: this entire * string may be searched. If it is greater than the length of this * string, it has the same effect as if it were equal to the length of * this string: -1 is returned. * * @param ch a character. * @param fromIndex the index to start the search from. * @return the index of the first occurrence of the character in the * character sequence represented by this object that is greater * than or equal to fromIndex, or -1 * if the character does not occur. */ public int indexOf(int ch, int fromIndex) { return str().indexOf(ch, fromIndex); } /** * Returns the index within this string of the last occurrence of the * specified character. That is, the index returned is the largest * value k such that: *

   * this.charAt(k) == ch
   * 
* is true. * The String is searched backwards starting at the last character. * * @param ch a character. * @return the index of the last occurrence of the character in the * character sequence represented by this object, or * -1 if the character does not occur. */ public int lastIndexOf(int ch) { return str().lastIndexOf(ch); } /** * Returns the index within this string of the last occurrence of the * specified character, searching backward starting at the specified * index. That is, the index returned is the largest value k * such that: *
   * this.charAt(k) == ch) && (k <= fromIndex)
   * 
* is true. * * @param ch a character. * @param fromIndex the index to start the search from. There is no * restriction on the value of fromIndex. If it is * greater than or equal to the length of this string, it has * the same effect as if it were equal to one less than the * length of this string: this entire string may be searched. * If it is negative, it has the same effect as if it were -1: * -1 is returned. * @return the index of the last occurrence of the character in the * character sequence represented by this object that is less * than or equal to fromIndex, or -1 * if the character does not occur before that point. */ public int lastIndexOf(int ch, int fromIndex) { return str().lastIndexOf(ch, fromIndex); } /** * Returns the index within this string of the first occurrence of the * specified substring. The integer returned is the smallest value * k such that: *
   * this.startsWith(str, k)
   * 
* is true. * * @param str any string. * @return if the string argument occurs as a substring within this * object, then the index of the first character of the first * such substring is returned; if it does not occur as a * substring, -1 is returned. * @exception java.lang.NullPointerException if str is * null. */ public int indexOf(String str) { return str().indexOf(str); } /** * Returns the index within this string of the first occurrence of the * specified substring. The integer returned is the smallest value * k such that: *
   * this.startsWith(str, k)
   * 
* is true. * * @param str any string. * @return if the string argument occurs as a substring within this * object, then the index of the first character of the first * such substring is returned; if it does not occur as a * substring, -1 is returned. * @exception java.lang.NullPointerException if str is * null. */ public int indexOf(XMLString str) { return str().indexOf(str.toString()); } /** * Returns the index within this string of the first occurrence of the * specified substring, starting at the specified index. The integer * returned is the smallest value k such that: *
   * this.startsWith(str, k) && (k >= fromIndex)
   * 
* is true. *

* There is no restriction on the value of fromIndex. If * it is negative, it has the same effect as if it were zero: this entire * string may be searched. If it is greater than the length of this * string, it has the same effect as if it were equal to the length of * this string: -1 is returned. * * @param str the substring to search for. * @param fromIndex the index to start the search from. * @return If the string argument occurs as a substring within this * object at a starting index no smaller than * fromIndex, then the index of the first character * of the first such substring is returned. If it does not occur * as a substring starting at fromIndex or beyond, * -1 is returned. * @exception java.lang.NullPointerException if str is * null */ public int indexOf(String str, int fromIndex) { return str().indexOf(str, fromIndex); } /** * Returns the index within this string of the rightmost occurrence * of the specified substring. The rightmost empty string "" is * considered to occur at the index value this.length(). * The returned index is the largest value k such that *

   * this.startsWith(str, k)
   * 
* is true. * * @param str the substring to search for. * @return if the string argument occurs one or more times as a substring * within this object, then the index of the first character of * the last such substring is returned. If it does not occur as * a substring, -1 is returned. * @exception java.lang.NullPointerException if str is * null. */ public int lastIndexOf(String str) { return str().lastIndexOf(str); } /** * Returns the index within this string of the last occurrence of * the specified substring. * * @param str the substring to search for. * @param fromIndex the index to start the search from. There is no * restriction on the value of fromIndex. If it is greater than * the length of this string, it has the same effect as if it * were equal to the length of this string: this entire string * may be searched. If it is negative, it has the same effect * as if it were -1: -1 is returned. * @return If the string argument occurs one or more times as a substring * within this object at a starting index no greater than * fromIndex, then the index of the first character of * the last such substring is returned. If it does not occur as a * substring starting at fromIndex or earlier, * -1 is returned. * @exception java.lang.NullPointerException if str is * null. */ public int lastIndexOf(String str, int fromIndex) { return str().lastIndexOf(str, fromIndex); } /** * Returns a new string that is a substring of this string. The * substring begins with the character at the specified index and * extends to the end of this string.

* Examples: *

   * "unhappy".substring(2) returns "happy"
   * "Harbison".substring(3) returns "bison"
   * "emptiness".substring(9) returns "" (an empty string)
   * 
* * @param beginIndex the beginning index, inclusive. * @return the specified substring. * @exception IndexOutOfBoundsException if * beginIndex is negative or larger than the * length of this String object. */ public XMLString substring(int beginIndex) { return new XString(str().substring(beginIndex)); } /** * Returns a new string that is a substring of this string. The * substring begins at the specified beginIndex and * extends to the character at index endIndex - 1. * Thus the length of the substring is endIndex-beginIndex. * * @param beginIndex the beginning index, inclusive. * @param endIndex the ending index, exclusive. * @return the specified substring. * @exception IndexOutOfBoundsException if the * beginIndex is negative, or * endIndex is larger than the length of * this String object, or * beginIndex is larger than * endIndex. */ public XMLString substring(int beginIndex, int endIndex) { return new XString(str().substring(beginIndex, endIndex)); } /** * Concatenates the specified string to the end of this string. * * @param str the String that is concatenated to the end * of this String. * @return a string that represents the concatenation of this object's * characters followed by the string argument's characters. * @exception java.lang.NullPointerException if str is * null. */ public XMLString concat(String str) { // %REVIEW% Make an FSB here? return new XString(str().concat(str)); } /** * Converts all of the characters in this String to lower * case using the rules of the given Locale. * * @param locale use the case transformation rules for this locale * @return the String, converted to lowercase. * @see java.lang.Character#toLowerCase(char) * @see java.lang.String#toUpperCase(Locale) */ public XMLString toLowerCase(Locale locale) { return new XString(str().toLowerCase(locale)); } /** * Converts all of the characters in this String to lower * case using the rules of the default locale, which is returned * by Locale.getDefault. *

* * @return the string, converted to lowercase. * @see java.lang.Character#toLowerCase(char) * @see java.lang.String#toLowerCase(Locale) */ public XMLString toLowerCase() { return new XString(str().toLowerCase()); } /** * Converts all of the characters in this String to upper * case using the rules of the given locale. * @param locale use the case transformation rules for this locale * @return the String, converted to uppercase. * @see java.lang.Character#toUpperCase(char) * @see java.lang.String#toLowerCase(Locale) */ public XMLString toUpperCase(Locale locale) { return new XString(str().toUpperCase(locale)); } /** * Converts all of the characters in this String to upper * case using the rules of the default locale, which is returned * by Locale.getDefault. * *

* If no character in this string has a different uppercase version, * based on calling the toUpperCase method defined by * Character, then the original string is returned. *

* Otherwise, this method creates a new String object * representing a character sequence identical in length to the * character sequence represented by this String object and * with every character equal to the result of applying the method * Character.toUpperCase to the corresponding character of * this String object.

* Examples: *

   * "Fahrvergnügen".toUpperCase() returns "FAHRVERGNÜGEN"
   * "Visit Ljubinje!".toUpperCase() returns "VISIT LJUBINJE!"
   * 
* * @return the string, converted to uppercase. * @see java.lang.Character#toUpperCase(char) * @see java.lang.String#toUpperCase(Locale) */ public XMLString toUpperCase() { return new XString(str().toUpperCase()); } /** * Removes white space from both ends of this string. * * @return this string, with white space removed from the front and end. */ public XMLString trim() { return new XString(str().trim()); } /** * Returns whether the specified ch conforms to the XML 1.0 definition * of whitespace. Refer to * the definition of S for details. * @param ch Character to check as XML whitespace. * @return =true if ch is XML whitespace; otherwise =false. */ private static boolean isSpace(char ch) { return XMLCharacterRecognizer.isWhiteSpace(ch); // Take the easy way out for now. } /** * Conditionally trim all leading and trailing whitespace in the specified String. * All strings of white space are * replaced by a single space character (#x20), except spaces after punctuation which * receive double spaces if doublePunctuationSpaces is true. * This function may be useful to a formatter, but to get first class * results, the formatter should probably do it's own white space handling * based on the semantics of the formatting object. * * @param trimHead Trim leading whitespace? * @param trimTail Trim trailing whitespace? * @param doublePunctuationSpaces Use double spaces for punctuation? * @return The trimmed string. */ public XMLString fixWhiteSpace(boolean trimHead, boolean trimTail, boolean doublePunctuationSpaces) { // %OPT% !!!!!!! int len = this.length(); char[] buf = new char[len]; this.getChars(0, len, buf, 0); boolean edit = false; int s; for (s = 0; s < len; s++) { if (isSpace(buf[s])) { break; } } /* replace S to ' '. and ' '+ -> single ' '. */ int d = s; boolean pres = false; for (; s < len; s++) { char c = buf[s]; if (isSpace(c)) { if (!pres) { if (' ' != c) { edit = true; } buf[d++] = ' '; if (doublePunctuationSpaces && (s != 0)) { char prevChar = buf[s - 1]; if (!((prevChar == '.') || (prevChar == '!') || (prevChar == '?'))) { pres = true; } } else { pres = true; } } else { edit = true; pres = true; } } else { buf[d++] = c; pres = false; } } if (trimTail && 1 <= d && ' ' == buf[d - 1]) { edit = true; d--; } int start = 0; if (trimHead && 0 < d && ' ' == buf[0]) { edit = true; start++; } XMLStringFactory xsf = XMLStringFactoryImpl.getFactory(); return edit ? xsf.newstr(new String(buf, start, d - start)) : this; } /** * @see org.apache.xpath.XPathVisitable#callVisitors(ExpressionOwner, XPathVisitor) */ public void callVisitors(ExpressionOwner owner, XPathVisitor visitor) { visitor.visitStringLiteral(owner, this); } }