001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 * 
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 * 
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.lang3.text;
018
019import org.apache.commons.lang3.StringUtils;
020import org.apache.commons.lang3.SystemUtils;
021
022/**
023 * <p>Operations on Strings that contain words.</p>
024 * 
025 * <p>This class tries to handle <code>null</code> input gracefully.
026 * An exception will not be thrown for a <code>null</code> input.
027 * Each method documents its behaviour in more detail.</p>
028 * 
029 * @since 2.0
030 * @version $Id: WordUtils.java 1561036 2014-01-24 15:42:19Z britter $
031 */
032public class WordUtils {
033
034    /**
035     * <p><code>WordUtils</code> instances should NOT be constructed in
036     * standard programming. Instead, the class should be used as
037     * <code>WordUtils.wrap("foo bar", 20);</code>.</p>
038     *
039     * <p>This constructor is public to permit tools that require a JavaBean
040     * instance to operate.</p>
041     */
042    public WordUtils() {
043      super();
044    }
045
046    // Wrapping
047    //--------------------------------------------------------------------------
048    /**
049     * <p>Wraps a single line of text, identifying words by <code>' '</code>.</p>
050     * 
051     * <p>New lines will be separated by the system property line separator.
052     * Very long words, such as URLs will <i>not</i> be wrapped.</p>
053     * 
054     * <p>Leading spaces on a new line are stripped.
055     * Trailing spaces are not stripped.</p>
056     *
057     * <table border="1">
058     *  <tr>
059     *   <th>input</th>
060     *   <th>wrapLenght</th>
061     *   <th>result</th>
062     *  </tr>
063     *  <tr>
064     *   <td>null</td>
065     *   <td>*</td>
066     *   <td>null</td>
067     *  </tr>
068     *  <tr>
069     *   <td>""</td>
070     *   <td>*</td>
071     *   <td>""</td>
072     *  </tr>
073     *  <tr>
074     *   <td>"Here is one line of text that is going to be wrapped after 20 columns."</td>
075     *   <td>20</td>
076     *   <td>"Here is one line of\ntext that is going\nto be wrapped after\n20 columns."</td>
077     *  </tr>
078     *  <tr>
079     *   <td>"Click here to jump to the commons website - http://commons.apache.org"</td>
080     *   <td>20</td>
081     *   <td>"Click here to jump\nto the commons\nwebsite -\nhttp://commons.apache.org"</td>
082     *  </tr>
083     *  <tr>
084     *   <td>"Click here, http://commons.apache.org, to jump to the commons website"</td>
085     *   <td>20</td>
086     *   <td>"Click here,\nhttp://commons.apache.org,\nto jump to the\ncommons website"</td>
087     *  </tr>
088     * </table>
089     *
090     * (assuming that '\n' is the systems line separator)
091     *
092     * @param str  the String to be word wrapped, may be null
093     * @param wrapLength  the column to wrap the words at, less than 1 is treated as 1
094     * @return a line with newlines inserted, <code>null</code> if null input
095     */
096    public static String wrap(final String str, final int wrapLength) {
097        return wrap(str, wrapLength, null, false);
098    }
099    
100    /**
101     * <p>Wraps a single line of text, identifying words by <code>' '</code>.</p>
102     * 
103     * <p>Leading spaces on a new line are stripped.
104     * Trailing spaces are not stripped.</p>
105     *
106     * <table border="1">
107     *  <tr>
108     *   <th>input</th>
109     *   <th>wrapLenght</th>
110     *   <th>newLineString</th>
111     *   <th>wrapLongWords</th>
112     *   <th>result</th>
113     *  </tr>
114     *  <tr>
115     *   <td>null</td>
116     *   <td>*</td>
117     *   <td>*</td>
118     *   <td>true/false</td>
119     *   <td>null</td>
120     *  </tr>
121     *  <tr>
122     *   <td>""</td>
123     *   <td>*</td>
124     *   <td>*</td>
125     *   <td>true/false</td>
126     *   <td>""</td>
127     *  </tr>
128     *  <tr>
129     *   <td>"Here is one line of text that is going to be wrapped after 20 columns."</td>
130     *   <td>20</td>
131     *   <td>"\n"</td>
132     *   <td>true/false</td>
133     *   <td>"Here is one line of\ntext that is going\nto be wrapped after\n20 columns."</td>
134     *  </tr>
135     *  <tr>
136     *   <td>"Here is one line of text that is going to be wrapped after 20 columns."</td>
137     *   <td>20</td>
138     *   <td>"&lt;br /&gt;"</td>
139     *   <td>true/false</td>
140     *   <td>"Here is one line of&lt;br /&gt;text that is going&lt;br /&gt;to be wrapped after&lt;br /&gt;20 columns."</td>
141     *  </tr>
142     *  <tr>
143     *   <td>"Here is one line of text that is going to be wrapped after 20 columns."</td>
144     *   <td>20</td>
145     *   <td>null</td>
146     *   <td>true/false</td>
147     *   <td>"Here is one line of" + systemNewLine + "text that is going" + systemNewLine + "to be wrapped after" + systemNewLine + "20 columns."</td>
148     *  </tr>
149     *  <tr>
150     *   <td>"Click here to jump to the commons website - http://commons.apache.org"</td>
151     *   <td>20</td>
152     *   <td>"\n"</td>
153     *   <td>false</td>
154     *   <td>"Click here to jump\nto the commons\nwebsite -\nhttp://commons.apache.org"</td>
155     *  </tr>
156     *  <tr>
157     *   <td>"Click here to jump to the commons website - http://commons.apache.org"</td>
158     *   <td>20</td>
159     *   <td>"\n"</td>
160     *   <td>true</td>
161     *   <td>"Click here to jump\nto the commons\nwebsite -\nhttp://commons.apach\ne.org"</td>
162     *  </tr>
163     * </table>
164     *
165     * @param str  the String to be word wrapped, may be null
166     * @param wrapLength  the column to wrap the words at, less than 1 is treated as 1
167     * @param newLineStr  the string to insert for a new line, 
168     *  <code>null</code> uses the system property line separator
169     * @param wrapLongWords  true if long words (such as URLs) should be wrapped
170     * @return a line with newlines inserted, <code>null</code> if null input
171     */
172    public static String wrap(final String str, int wrapLength, String newLineStr, final boolean wrapLongWords) {
173        if (str == null) {
174            return null;
175        }
176        if (newLineStr == null) {
177            newLineStr = SystemUtils.LINE_SEPARATOR;
178        }
179        if (wrapLength < 1) {
180            wrapLength = 1;
181        }
182        final int inputLineLength = str.length();
183        int offset = 0;
184        final StringBuilder wrappedLine = new StringBuilder(inputLineLength + 32);
185        
186        while (inputLineLength - offset > wrapLength) {
187            if (str.charAt(offset) == ' ') {
188                offset++;
189                continue;
190            }
191            int spaceToWrapAt = str.lastIndexOf(' ', wrapLength + offset);
192
193            if (spaceToWrapAt >= offset) {
194                // normal case
195                wrappedLine.append(str.substring(offset, spaceToWrapAt));
196                wrappedLine.append(newLineStr);
197                offset = spaceToWrapAt + 1;
198                
199            } else {
200                // really long word or URL
201                if (wrapLongWords) {
202                    // wrap really long word one line at a time
203                    wrappedLine.append(str.substring(offset, wrapLength + offset));
204                    wrappedLine.append(newLineStr);
205                    offset += wrapLength;
206                } else {
207                    // do not wrap really long word, just extend beyond limit
208                    spaceToWrapAt = str.indexOf(' ', wrapLength + offset);
209                    if (spaceToWrapAt >= 0) {
210                        wrappedLine.append(str.substring(offset, spaceToWrapAt));
211                        wrappedLine.append(newLineStr);
212                        offset = spaceToWrapAt + 1;
213                    } else {
214                        wrappedLine.append(str.substring(offset));
215                        offset = inputLineLength;
216                    }
217                }
218            }
219        }
220
221        // Whatever is left in line is short enough to just pass through
222        wrappedLine.append(str.substring(offset));
223
224        return wrappedLine.toString();
225    }
226
227    // Capitalizing
228    //-----------------------------------------------------------------------
229    /**
230     * <p>Capitalizes all the whitespace separated words in a String.
231     * Only the first letter of each word is changed. To convert the 
232     * rest of each word to lowercase at the same time, 
233     * use {@link #capitalizeFully(String)}.</p>
234     *
235     * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.
236     * A <code>null</code> input String returns <code>null</code>.
237     * Capitalization uses the Unicode title case, normally equivalent to
238     * upper case.</p>
239     *
240     * <pre>
241     * WordUtils.capitalize(null)        = null
242     * WordUtils.capitalize("")          = ""
243     * WordUtils.capitalize("i am FINE") = "I Am FINE"
244     * </pre>
245     * 
246     * @param str  the String to capitalize, may be null
247     * @return capitalized String, <code>null</code> if null String input
248     * @see #uncapitalize(String)
249     * @see #capitalizeFully(String)
250     */
251    public static String capitalize(final String str) {
252        return capitalize(str, null);
253    }
254
255    /**
256     * <p>Capitalizes all the delimiter separated words in a String.
257     * Only the first letter of each word is changed. To convert the 
258     * rest of each word to lowercase at the same time, 
259     * use {@link #capitalizeFully(String, char[])}.</p>
260     *
261     * <p>The delimiters represent a set of characters understood to separate words.
262     * The first string character and the first non-delimiter character after a
263     * delimiter will be capitalized. </p>
264     *
265     * <p>A <code>null</code> input String returns <code>null</code>.
266     * Capitalization uses the Unicode title case, normally equivalent to
267     * upper case.</p>
268     *
269     * <pre>
270     * WordUtils.capitalize(null, *)            = null
271     * WordUtils.capitalize("", *)              = ""
272     * WordUtils.capitalize(*, new char[0])     = *
273     * WordUtils.capitalize("i am fine", null)  = "I Am Fine"
274     * WordUtils.capitalize("i aM.fine", {'.'}) = "I aM.Fine"
275     * </pre>
276     * 
277     * @param str  the String to capitalize, may be null
278     * @param delimiters  set of characters to determine capitalization, null means whitespace
279     * @return capitalized String, <code>null</code> if null String input
280     * @see #uncapitalize(String)
281     * @see #capitalizeFully(String)
282     * @since 2.1
283     */
284    public static String capitalize(final String str, final char... delimiters) {
285        final int delimLen = delimiters == null ? -1 : delimiters.length;
286        if (StringUtils.isEmpty(str) || delimLen == 0) {
287            return str;
288        }
289        final char[] buffer = str.toCharArray();
290        boolean capitalizeNext = true;
291        for (int i = 0; i < buffer.length; i++) {
292            final char ch = buffer[i];
293            if (isDelimiter(ch, delimiters)) {
294                capitalizeNext = true;
295            } else if (capitalizeNext) {
296                buffer[i] = Character.toTitleCase(ch);
297                capitalizeNext = false;
298            }
299        }
300        return new String(buffer);
301    }
302
303    //-----------------------------------------------------------------------
304    /**
305     * <p>Converts all the whitespace separated words in a String into capitalized words, 
306     * that is each word is made up of a titlecase character and then a series of 
307     * lowercase characters.  </p>
308     *
309     * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.
310     * A <code>null</code> input String returns <code>null</code>.
311     * Capitalization uses the Unicode title case, normally equivalent to
312     * upper case.</p>
313     *
314     * <pre>
315     * WordUtils.capitalizeFully(null)        = null
316     * WordUtils.capitalizeFully("")          = ""
317     * WordUtils.capitalizeFully("i am FINE") = "I Am Fine"
318     * </pre>
319     * 
320     * @param str  the String to capitalize, may be null
321     * @return capitalized String, <code>null</code> if null String input
322     */
323    public static String capitalizeFully(final String str) {
324        return capitalizeFully(str, null);
325    }
326
327    /**
328     * <p>Converts all the delimiter separated words in a String into capitalized words, 
329     * that is each word is made up of a titlecase character and then a series of 
330     * lowercase characters. </p>
331     *
332     * <p>The delimiters represent a set of characters understood to separate words.
333     * The first string character and the first non-delimiter character after a
334     * delimiter will be capitalized. </p>
335     *
336     * <p>A <code>null</code> input String returns <code>null</code>.
337     * Capitalization uses the Unicode title case, normally equivalent to
338     * upper case.</p>
339     *
340     * <pre>
341     * WordUtils.capitalizeFully(null, *)            = null
342     * WordUtils.capitalizeFully("", *)              = ""
343     * WordUtils.capitalizeFully(*, null)            = *
344     * WordUtils.capitalizeFully(*, new char[0])     = *
345     * WordUtils.capitalizeFully("i aM.fine", {'.'}) = "I am.Fine"
346     * </pre>
347     * 
348     * @param str  the String to capitalize, may be null
349     * @param delimiters  set of characters to determine capitalization, null means whitespace
350     * @return capitalized String, <code>null</code> if null String input
351     * @since 2.1
352     */
353    public static String capitalizeFully(String str, final char... delimiters) {
354        final int delimLen = delimiters == null ? -1 : delimiters.length;
355        if (StringUtils.isEmpty(str) || delimLen == 0) {
356            return str;
357        }
358        str = str.toLowerCase();
359        return capitalize(str, delimiters);
360    }
361
362    //-----------------------------------------------------------------------
363    /**
364     * <p>Uncapitalizes all the whitespace separated words in a String.
365     * Only the first letter of each word is changed.</p>
366     *
367     * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.
368     * A <code>null</code> input String returns <code>null</code>.</p>
369     *
370     * <pre>
371     * WordUtils.uncapitalize(null)        = null
372     * WordUtils.uncapitalize("")          = ""
373     * WordUtils.uncapitalize("I Am FINE") = "i am fINE"
374     * </pre>
375     * 
376     * @param str  the String to uncapitalize, may be null
377     * @return uncapitalized String, <code>null</code> if null String input
378     * @see #capitalize(String)
379     */
380    public static String uncapitalize(final String str) {
381        return uncapitalize(str, null);
382    }
383
384    /**
385     * <p>Uncapitalizes all the whitespace separated words in a String.
386     * Only the first letter of each word is changed.</p>
387     *
388     * <p>The delimiters represent a set of characters understood to separate words.
389     * The first string character and the first non-delimiter character after a
390     * delimiter will be uncapitalized. </p>
391     *
392     * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.
393     * A <code>null</code> input String returns <code>null</code>.</p>
394     *
395     * <pre>
396     * WordUtils.uncapitalize(null, *)            = null
397     * WordUtils.uncapitalize("", *)              = ""
398     * WordUtils.uncapitalize(*, null)            = *
399     * WordUtils.uncapitalize(*, new char[0])     = *
400     * WordUtils.uncapitalize("I AM.FINE", {'.'}) = "i AM.fINE"
401     * </pre>
402     * 
403     * @param str  the String to uncapitalize, may be null
404     * @param delimiters  set of characters to determine uncapitalization, null means whitespace
405     * @return uncapitalized String, <code>null</code> if null String input
406     * @see #capitalize(String)
407     * @since 2.1
408     */
409    public static String uncapitalize(final String str, final char... delimiters) {
410        final int delimLen = delimiters == null ? -1 : delimiters.length;
411        if (StringUtils.isEmpty(str) || delimLen == 0) {
412            return str;
413        }
414        final char[] buffer = str.toCharArray();
415        boolean uncapitalizeNext = true;
416        for (int i = 0; i < buffer.length; i++) {
417            final char ch = buffer[i];
418            if (isDelimiter(ch, delimiters)) {
419                uncapitalizeNext = true;
420            } else if (uncapitalizeNext) {
421                buffer[i] = Character.toLowerCase(ch);
422                uncapitalizeNext = false;
423            }
424        }
425        return new String(buffer);
426    }
427
428    //-----------------------------------------------------------------------
429    /**
430     * <p>Swaps the case of a String using a word based algorithm.</p>
431     * 
432     * <ul>
433     *  <li>Upper case character converts to Lower case</li>
434     *  <li>Title case character converts to Lower case</li>
435     *  <li>Lower case character after Whitespace or at start converts to Title case</li>
436     *  <li>Other Lower case character converts to Upper case</li>
437     * </ul>
438     * 
439     * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.
440     * A <code>null</code> input String returns <code>null</code>.</p>
441     * 
442     * <pre>
443     * StringUtils.swapCase(null)                 = null
444     * StringUtils.swapCase("")                   = ""
445     * StringUtils.swapCase("The dog has a BONE") = "tHE DOG HAS A bone"
446     * </pre>
447     * 
448     * @param str  the String to swap case, may be null
449     * @return the changed String, <code>null</code> if null String input
450     */
451    public static String swapCase(final String str) {
452        if (StringUtils.isEmpty(str)) {
453            return str;
454        }
455        final char[] buffer = str.toCharArray();
456
457        boolean whitespace = true;
458
459        for (int i = 0; i < buffer.length; i++) {
460            final char ch = buffer[i];
461            if (Character.isUpperCase(ch)) {
462                buffer[i] = Character.toLowerCase(ch);
463                whitespace = false;
464            } else if (Character.isTitleCase(ch)) {
465                buffer[i] = Character.toLowerCase(ch);
466                whitespace = false;
467            } else if (Character.isLowerCase(ch)) {
468                if (whitespace) {
469                    buffer[i] = Character.toTitleCase(ch);
470                    whitespace = false;
471                } else {
472                    buffer[i] = Character.toUpperCase(ch);
473                }
474            } else {
475                whitespace = Character.isWhitespace(ch);
476            }
477        }
478        return new String(buffer);
479    }
480
481    //-----------------------------------------------------------------------
482    /**
483     * <p>Extracts the initial letters from each word in the String.</p>
484     * 
485     * <p>The first letter of the string and all first letters after
486     * whitespace are returned as a new string.
487     * Their case is not changed.</p>
488     *
489     * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.
490     * A <code>null</code> input String returns <code>null</code>.</p>
491     *
492     * <pre>
493     * WordUtils.initials(null)             = null
494     * WordUtils.initials("")               = ""
495     * WordUtils.initials("Ben John Lee")   = "BJL"
496     * WordUtils.initials("Ben J.Lee")      = "BJ"
497     * </pre>
498     *
499     * @param str  the String to get initials from, may be null
500     * @return String of initial letters, <code>null</code> if null String input
501     * @see #initials(String,char[])
502     * @since 2.2
503     */
504    public static String initials(final String str) {
505        return initials(str, null);
506    }
507
508    /**
509     * <p>Extracts the initial letters from each word in the String.</p>
510     * 
511     * <p>The first letter of the string and all first letters after the
512     * defined delimiters are returned as a new string.
513     * Their case is not changed.</p>
514     *
515     * <p>If the delimiters array is null, then Whitespace is used.
516     * Whitespace is defined by {@link Character#isWhitespace(char)}.
517     * A <code>null</code> input String returns <code>null</code>.
518     * An empty delimiter array returns an empty String.</p>
519     *
520     * <pre>
521     * WordUtils.initials(null, *)                = null
522     * WordUtils.initials("", *)                  = ""
523     * WordUtils.initials("Ben John Lee", null)   = "BJL"
524     * WordUtils.initials("Ben J.Lee", null)      = "BJ"
525     * WordUtils.initials("Ben J.Lee", [' ','.']) = "BJL"
526     * WordUtils.initials(*, new char[0])         = ""
527     * </pre>
528     * 
529     * @param str  the String to get initials from, may be null
530     * @param delimiters  set of characters to determine words, null means whitespace
531     * @return String of initial letters, <code>null</code> if null String input
532     * @see #initials(String)
533     * @since 2.2
534     */
535    public static String initials(final String str, final char... delimiters) {
536        if (StringUtils.isEmpty(str)) {
537            return str;
538        }
539        if (delimiters != null && delimiters.length == 0) {
540            return "";
541        }
542        final int strLen = str.length();
543        final char[] buf = new char[strLen / 2 + 1];
544        int count = 0;
545        boolean lastWasGap = true;
546        for (int i = 0; i < strLen; i++) {
547            final char ch = str.charAt(i);
548
549            if (isDelimiter(ch, delimiters)) {
550                lastWasGap = true;
551            } else if (lastWasGap) {
552                buf[count++] = ch;
553                lastWasGap = false;
554            } else {
555                continue; // ignore ch
556            }
557        }
558        return new String(buf, 0, count);
559    }
560
561    //-----------------------------------------------------------------------
562    /**
563     * Is the character a delimiter.
564     *
565     * @param ch  the character to check
566     * @param delimiters  the delimiters
567     * @return true if it is a delimiter
568     */
569    private static boolean isDelimiter(final char ch, final char[] delimiters) {
570        if (delimiters == null) {
571            return Character.isWhitespace(ch);
572        }
573        for (final char delimiter : delimiters) {
574            if (ch == delimiter) {
575                return true;
576            }
577        }
578        return false;
579    }
580
581}