org.apache.commons.lang.WordUtils Maven / Gradle / Ivy
Show all versions of commons-lang Show documentation
/*
* 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.
*/
package org.apache.commons.lang;
/**
* Operations on Strings that contain words.
*
* This class tries to handle null input gracefully.
* An exception will not be thrown for a null input.
* Each method documents its behaviour in more detail.
*
* @author Apache Jakarta Velocity
* @author Henri Yandell
* @author Stephen Colebourne
* @author Henning P. Schmiedehausen
* @author Gary Gregory
* @since 2.0
* @version $Id: WordUtils.java 437554 2006-08-28 06:21:41Z bayard $
*/
public class WordUtils {
/**
* WordUtils instances should NOT be constructed in
* standard programming. Instead, the class should be used as
* WordUtils.wrap("foo bar", 20);.
*
* This constructor is public to permit tools that require a JavaBean
* instance to operate.
*/
public WordUtils() {
super();
}
// Wrapping
//--------------------------------------------------------------------------
// /**
// * Wraps a block of text to a specified line length using '\n' as
// * a newline.
// *
// * This method takes a block of text, which might have long lines in it
// * and wraps the long lines based on the supplied lineLength parameter.
// *
// * If a single word is longer than the line length (eg. a URL), it will
// * not be broken, and will display beyond the expected width.
// *
// * If there are tabs in inString, you are going to get results that are
// * a bit strange. Tabs are a single character but are displayed as 4 or 8
// * spaces. Remove the tabs.
// *
// * @param str text which is in need of word-wrapping, may be null
// * @param lineLength the column to wrap the words at
// * @return the text with all the long lines word-wrapped
// * null if null string input
// */
// public static String wrapText(String str, int lineLength) {
// return wrap(str, null, lineLength);
// }
// /**
// * Wraps a block of text to a specified line length.
// *
// * This method takes a block of text, which might have long lines in it
// * and wraps the long lines based on the supplied lineLength parameter.
// *
// * If a single word is longer than the wrapColumn (eg. a URL), it will
// * not be broken, and will display beyond the expected width.
// *
// * If there are tabs in inString, you are going to get results that are
// * a bit strange. Tabs are a single character but are displayed as 4 or 8
// * spaces. Remove the tabs.
// *
// * @param str text which is in need of word-wrapping, may be null
// * @param newLineChars the characters that define a newline, null treated as \n
// * @param lineLength the column to wrap the words at
// * @return the text with all the long lines word-wrapped
// * null if null string input
// */
// public static String wrapText(String str, String newLineChars, int lineLength) {
// if (str == null) {
// return null;
// }
// if (newLineChars == null) {
// newLineChars = "\n";
// }
// StringTokenizer lineTokenizer = new StringTokenizer(str, newLineChars, true);
// StringBuffer stringBuffer = new StringBuffer();
//
// while (lineTokenizer.hasMoreTokens()) {
// try {
// String nextLine = lineTokenizer.nextToken();
//
// if (nextLine.length() > lineLength) {
// // This line is long enough to be wrapped.
// nextLine = wrapLine(nextLine, null, lineLength, false);
// }
//
// stringBuffer.append(nextLine);
//
// } catch (NoSuchElementException nsee) {
// // thrown by nextToken(), but I don't know why it would
// break;
// }
// }
//
// return stringBuffer.toString();
// }
// Wrapping
//-----------------------------------------------------------------------
/**
* Wraps a single line of text, identifying words by ' '.
*
* New lines will be separated by the system property line separator.
* Very long words, such as URLs will not be wrapped.
*
* Leading spaces on a new line are stripped.
* Trailing spaces are not stripped.
*
*
* WordUtils.wrap(null, *) = null
* WordUtils.wrap("", *) = ""
*
*
* @param str the String to be word wrapped, may be null
* @param wrapLength the column to wrap the words at, less than 1 is treated as 1
* @return a line with newlines inserted, null if null input
*/
public static String wrap(String str, int wrapLength) {
return wrap(str, wrapLength, null, false);
}
/**
* Wraps a single line of text, identifying words by ' '.
*
* Leading spaces on a new line are stripped.
* Trailing spaces are not stripped.
*
*
* WordUtils.wrap(null, *, *, *) = null
* WordUtils.wrap("", *, *, *) = ""
*
*
* @param str the String to be word wrapped, may be null
* @param wrapLength the column to wrap the words at, less than 1 is treated as 1
* @param newLineStr the string to insert for a new line,
* null uses the system property line separator
* @param wrapLongWords true if long words (such as URLs) should be wrapped
* @return a line with newlines inserted, null if null input
*/
public static String wrap(String str, int wrapLength, String newLineStr, boolean wrapLongWords) {
if (str == null) {
return null;
}
if (newLineStr == null) {
newLineStr = SystemUtils.LINE_SEPARATOR;
}
if (wrapLength < 1) {
wrapLength = 1;
}
int inputLineLength = str.length();
int offset = 0;
StringBuffer wrappedLine = new StringBuffer(inputLineLength + 32);
while ((inputLineLength - offset) > wrapLength) {
if (str.charAt(offset) == ' ') {
offset++;
continue;
}
int spaceToWrapAt = str.lastIndexOf(' ', wrapLength + offset);
if (spaceToWrapAt >= offset) {
// normal case
wrappedLine.append(str.substring(offset, spaceToWrapAt));
wrappedLine.append(newLineStr);
offset = spaceToWrapAt + 1;
} else {
// really long word or URL
if (wrapLongWords) {
// wrap really long word one line at a time
wrappedLine.append(str.substring(offset, wrapLength + offset));
wrappedLine.append(newLineStr);
offset += wrapLength;
} else {
// do not wrap really long word, just extend beyond limit
spaceToWrapAt = str.indexOf(' ', wrapLength + offset);
if (spaceToWrapAt >= 0) {
wrappedLine.append(str.substring(offset, spaceToWrapAt));
wrappedLine.append(newLineStr);
offset = spaceToWrapAt + 1;
} else {
wrappedLine.append(str.substring(offset));
offset = inputLineLength;
}
}
}
}
// Whatever is left in line is short enough to just pass through
wrappedLine.append(str.substring(offset));
return wrappedLine.toString();
}
// Capitalizing
//-----------------------------------------------------------------------
/**
* Capitalizes all the whitespace separated words in a String.
* Only the first letter of each word is changed. To convert the
* rest of each word to lowercase at the same time,
* use {@link #capitalizeFully(String)}.
*
* Whitespace is defined by {@link Character#isWhitespace(char)}.
* A null input String returns null.
* Capitalization uses the unicode title case, normally equivalent to
* upper case.
*
*
* WordUtils.capitalize(null) = null
* WordUtils.capitalize("") = ""
* WordUtils.capitalize("i am FINE") = "I Am FINE"
*
*
* @param str the String to capitalize, may be null
* @return capitalized String, null if null String input
* @see #uncapitalize(String)
* @see #capitalizeFully(String)
*/
public static String capitalize(String str) {
return capitalize(str, null);
}
/**
* Capitalizes all the delimiter separated words in a String.
* Only the first letter of each word is changed. To convert the
* rest of each word to lowercase at the same time,
* use {@link #capitalizeFully(String, char[])}.
*
* The delimiters represent a set of characters understood to separate words.
* The first string character and the first non-delimiter character after a
* delimiter will be capitalized.
*
* A null input String returns null.
* Capitalization uses the unicode title case, normally equivalent to
* upper case.
*
*
* WordUtils.capitalize(null, *) = null
* WordUtils.capitalize("", *) = ""
* WordUtils.capitalize(*, new char[0]) = *
* WordUtils.capitalize("i am fine", null) = "I Am Fine"
* WordUtils.capitalize("i aM.fine", {'.'}) = "I aM.Fine"
*
*
* @param str the String to capitalize, may be null
* @param delimiters set of characters to determine capitalization, null means whitespace
* @return capitalized String, null if null String input
* @see #uncapitalize(String)
* @see #capitalizeFully(String)
* @since 2.1
*/
public static String capitalize(String str, char[] delimiters) {
int delimLen = (delimiters == null ? -1 : delimiters.length);
if (str == null || str.length() == 0 || delimLen == 0) {
return str;
}
int strLen = str.length();
StringBuffer buffer = new StringBuffer(strLen);
boolean capitalizeNext = true;
for (int i = 0; i < strLen; i++) {
char ch = str.charAt(i);
if (isDelimiter(ch, delimiters)) {
buffer.append(ch);
capitalizeNext = true;
} else if (capitalizeNext) {
buffer.append(Character.toTitleCase(ch));
capitalizeNext = false;
} else {
buffer.append(ch);
}
}
return buffer.toString();
}
//-----------------------------------------------------------------------
/**
* Converts all the whitespace separated words in a String into capitalized words,
* that is each word is made up of a titlecase character and then a series of
* lowercase characters.
*
* Whitespace is defined by {@link Character#isWhitespace(char)}.
* A null input String returns null.
* Capitalization uses the unicode title case, normally equivalent to
* upper case.
*
*
* WordUtils.capitalizeFully(null) = null
* WordUtils.capitalizeFully("") = ""
* WordUtils.capitalizeFully("i am FINE") = "I Am Fine"
*
*
* @param str the String to capitalize, may be null
* @return capitalized String, null if null String input
*/
public static String capitalizeFully(String str) {
return capitalizeFully(str, null);
}
/**
* Converts all the delimiter separated words in a String into capitalized words,
* that is each word is made up of a titlecase character and then a series of
* lowercase characters.
*
* The delimiters represent a set of characters understood to separate words.
* The first string character and the first non-delimiter character after a
* delimiter will be capitalized.
*
* A null input String returns null.
* Capitalization uses the unicode title case, normally equivalent to
* upper case.
*
*
* WordUtils.capitalizeFully(null, *) = null
* WordUtils.capitalizeFully("", *) = ""
* WordUtils.capitalizeFully(*, null) = *
* WordUtils.capitalizeFully(*, new char[0]) = *
* WordUtils.capitalizeFully("i aM.fine", {'.'}) = "I am.Fine"
*
*
* @param str the String to capitalize, may be null
* @param delimiters set of characters to determine capitalization, null means whitespace
* @return capitalized String, null if null String input
* @since 2.1
*/
public static String capitalizeFully(String str, char[] delimiters) {
int delimLen = (delimiters == null ? -1 : delimiters.length);
if (str == null || str.length() == 0 || delimLen == 0) {
return str;
}
str = str.toLowerCase();
return capitalize(str, delimiters);
}
//-----------------------------------------------------------------------
/**
* Uncapitalizes all the whitespace separated words in a String.
* Only the first letter of each word is changed.
*
* Whitespace is defined by {@link Character#isWhitespace(char)}.
* A null input String returns null.
*
*
* WordUtils.uncapitalize(null) = null
* WordUtils.uncapitalize("") = ""
* WordUtils.uncapitalize("I Am FINE") = "i am fINE"
*
*
* @param str the String to uncapitalize, may be null
* @return uncapitalized String, null if null String input
* @see #capitalize(String)
*/
public static String uncapitalize(String str) {
return uncapitalize(str, null);
}
/**
* Uncapitalizes all the whitespace separated words in a String.
* Only the first letter of each word is changed.
*
* The delimiters represent a set of characters understood to separate words.
* The first string character and the first non-delimiter character after a
* delimiter will be uncapitalized.
*
* Whitespace is defined by {@link Character#isWhitespace(char)}.
* A null input String returns null.
*
*
* WordUtils.uncapitalize(null, *) = null
* WordUtils.uncapitalize("", *) = ""
* WordUtils.uncapitalize(*, null) = *
* WordUtils.uncapitalize(*, new char[0]) = *
* WordUtils.uncapitalize("I AM.FINE", {'.'}) = "i AM.fINE"
*
*
* @param str the String to uncapitalize, may be null
* @param delimiters set of characters to determine uncapitalization, null means whitespace
* @return uncapitalized String, null if null String input
* @see #capitalize(String)
* @since 2.1
*/
public static String uncapitalize(String str, char[] delimiters) {
int delimLen = (delimiters == null ? -1 : delimiters.length);
if (str == null || str.length() == 0 || delimLen == 0) {
return str;
}
int strLen = str.length();
StringBuffer buffer = new StringBuffer(strLen);
boolean uncapitalizeNext = true;
for (int i = 0; i < strLen; i++) {
char ch = str.charAt(i);
if (isDelimiter(ch, delimiters)) {
buffer.append(ch);
uncapitalizeNext = true;
} else if (uncapitalizeNext) {
buffer.append(Character.toLowerCase(ch));
uncapitalizeNext = false;
} else {
buffer.append(ch);
}
}
return buffer.toString();
}
//-----------------------------------------------------------------------
/**
* Swaps the case of a String using a word based algorithm.
*
*
* - Upper case character converts to Lower case
* - Title case character converts to Lower case
* - Lower case character after Whitespace or at start converts to Title case
* - Other Lower case character converts to Upper case
*
*
* Whitespace is defined by {@link Character#isWhitespace(char)}.
* A null input String returns null.
*
*
* StringUtils.swapCase(null) = null
* StringUtils.swapCase("") = ""
* StringUtils.swapCase("The dog has a BONE") = "tHE DOG HAS A bone"
*
*
* @param str the String to swap case, may be null
* @return the changed String, null if null String input
*/
public static String swapCase(String str) {
int strLen;
if (str == null || (strLen = str.length()) == 0) {
return str;
}
StringBuffer buffer = new StringBuffer(strLen);
boolean whitespace = true;
char ch = 0;
char tmp = 0;
for (int i = 0; i < strLen; i++) {
ch = str.charAt(i);
if (Character.isUpperCase(ch)) {
tmp = Character.toLowerCase(ch);
} else if (Character.isTitleCase(ch)) {
tmp = Character.toLowerCase(ch);
} else if (Character.isLowerCase(ch)) {
if (whitespace) {
tmp = Character.toTitleCase(ch);
} else {
tmp = Character.toUpperCase(ch);
}
} else {
tmp = ch;
}
buffer.append(tmp);
whitespace = Character.isWhitespace(ch);
}
return buffer.toString();
}
//-----------------------------------------------------------------------
/**
* Extracts the initial letters from each word in the String.
*
* The first letter of the string and all first letters after
* whitespace are returned as a new string.
* Their case is not changed.
*
* Whitespace is defined by {@link Character#isWhitespace(char)}.
* A null input String returns null.
*
*
* WordUtils.initials(null) = null
* WordUtils.initials("") = ""
* WordUtils.initials("Ben John Lee") = "BJL"
* WordUtils.initials("Ben J.Lee") = "BJ"
*
*
* @param str the String to get initials from, may be null
* @return String of initial letters, null if null String input
* @see #initials(String,char[])
* @since 2.2
*/
public static String initials(String str) {
return initials(str, null);
}
/**
* Extracts the initial letters from each word in the String.
*
* The first letter of the string and all first letters after the
* defined delimiters are returned as a new string.
* Their case is not changed.
*
* If the delimiters array is null, then Whitespace is used.
* Whitespace is defined by {@link Character#isWhitespace(char)}.
* A null input String returns null.
* An empty delimiter array returns an empty String.
*
*
* WordUtils.initials(null, *) = null
* WordUtils.initials("", *) = ""
* WordUtils.initials("Ben John Lee", null) = "BJL"
* WordUtils.initials("Ben J.Lee", null) = "BJ"
* WordUtils.initials("Ben J.Lee", [' ','.']) = "BJL"
* WordUtils.initials(*, new char[0]) = ""
*
*
* @param str the String to get initials from, may be null
* @param delimiters set of characters to determine words, null means whitespace
* @return String of initial letters, null if null String input
* @see #initials(String)
* @since 2.2
*/
public static String initials(String str, char[] delimiters) {
if (str == null || str.length() == 0) {
return str;
}
if (delimiters != null && delimiters.length == 0) {
return "";
}
int strLen = str.length();
char[] buf = new char[strLen / 2 + 1];
int count = 0;
boolean lastWasGap = true;
for (int i = 0; i < strLen; i++) {
char ch = str.charAt(i);
if (isDelimiter(ch, delimiters)) {
lastWasGap = true;
} else if (lastWasGap) {
buf[count++] = ch;
lastWasGap = false;
} else {
// ignore ch
}
}
return new String(buf, 0, count);
}
//-----------------------------------------------------------------------
/**
* Is the character a delimiter.
*
* @param ch the character to check
* @param delimiters the delimiters
* @return true if it is a delimiter
*/
private static boolean isDelimiter(char ch, char[] delimiters) {
if (delimiters == null) {
return Character.isWhitespace(ch);
}
for (int i = 0, isize = delimiters.length; i < isize; i++) {
if (ch == delimiters[i]) {
return true;
}
}
return false;
}
}