Repository: commons-text Updated Branches: refs/heads/master c0dd79eca -> 0b6a285bb
pulling back WordUtils as per Jira TEXT-55 Project: http://git-wip-us.apache.org/repos/asf/commons-text/repo Commit: http://git-wip-us.apache.org/repos/asf/commons-text/commit/5b89b382 Tree: http://git-wip-us.apache.org/repos/asf/commons-text/tree/5b89b382 Diff: http://git-wip-us.apache.org/repos/asf/commons-text/diff/5b89b382 Branch: refs/heads/master Commit: 5b89b382021600d2dac0ee2d06265fd4d9e08264 Parents: c0dd79e Author: Amey Jadiye <ameyjad...@gmail.com> Authored: Wed May 3 00:23:05 2017 +0530 Committer: Amey Jadiye <ameyjad...@gmail.com> Committed: Wed May 3 00:23:05 2017 +0530 ---------------------------------------------------------------------- .../java/org/apache/commons/text/WordUtils.java | 728 +++++++++++++++++++ .../org/apache/commons/text/WordUtilsTest.java | 420 +++++++++++ 2 files changed, 1148 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/commons-text/blob/5b89b382/src/main/java/org/apache/commons/text/WordUtils.java ---------------------------------------------------------------------- diff --git a/src/main/java/org/apache/commons/text/WordUtils.java b/src/main/java/org/apache/commons/text/WordUtils.java new file mode 100644 index 0000000..7292d89 --- /dev/null +++ b/src/main/java/org/apache/commons/text/WordUtils.java @@ -0,0 +1,728 @@ +/* + * 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.text; + +import java.lang.reflect.Array; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +/** + * <p>Operations on Strings that contain words.</p> + * + * <p>This class tries to handle <code>null</code> input gracefully. + * An exception will not be thrown for a <code>null</code> input. + * Each method documents its behaviour in more detail.</p> + * + * @since 1.0 + */ +public class WordUtils { + + /** + * <p><code>WordUtils</code> instances should NOT be constructed in + * standard programming. Instead, the class should be used as + * <code>WordUtils.wrap("foo bar", 20);</code>.</p> + * + * <p>This constructor is public to permit tools that require a JavaBean + * instance to operate.</p> + */ + public WordUtils() { + super(); + } + + // Wrapping + //-------------------------------------------------------------------------- + /** + * <p>Wraps a single line of text, identifying words by <code>' '</code>.</p> + * + * <p>New lines will be separated by the system property line separator. + * Very long words, such as URLs will <i>not</i> be wrapped.</p> + * + * <p>Leading spaces on a new line are stripped. + * Trailing spaces are not stripped.</p> + * + * <table border="1" summary="Wrap Results"> + * <tr> + * <th>input</th> + * <th>wrapLength</th> + * <th>result</th> + * </tr> + * <tr> + * <td>null</td> + * <td>*</td> + * <td>null</td> + * </tr> + * <tr> + * <td>""</td> + * <td>*</td> + * <td>""</td> + * </tr> + * <tr> + * <td>"Here is one line of text that is going to be wrapped after 20 columns."</td> + * <td>20</td> + * <td>"Here is one line of\ntext that is going\nto be wrapped after\n20 columns."</td> + * </tr> + * <tr> + * <td>"Click here to jump to the commons website - http://commons.apache.org";</td> + * <td>20</td> + * <td>"Click here to jump\nto the commons\nwebsite -\nhttp://commons.apache.org";</td> + * </tr> + * <tr> + * <td>"Click here, http://commons.apache.org, to jump to the commons website"</td> + * <td>20</td> + * <td>"Click here,\nhttp://commons.apache.org,\nto jump to the\ncommons website"</td> + * </tr> + * </table> + * + * (assuming that '\n' is the systems line separator) + * + * @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, <code>null</code> if null input + */ + public static String wrap(final String str, final int wrapLength) { + return wrap(str, wrapLength, null, false); + } + + /** + * <p>Wraps a single line of text, identifying words by <code>' '</code>.</p> + * + * <p>Leading spaces on a new line are stripped. + * Trailing spaces are not stripped.</p> + * + * <table border="1" summary="Wrap Results"> + * <tr> + * <th>input</th> + * <th>wrapLenght</th> + * <th>newLineString</th> + * <th>wrapLongWords</th> + * <th>result</th> + * </tr> + * <tr> + * <td>null</td> + * <td>*</td> + * <td>*</td> + * <td>true/false</td> + * <td>null</td> + * </tr> + * <tr> + * <td>""</td> + * <td>*</td> + * <td>*</td> + * <td>true/false</td> + * <td>""</td> + * </tr> + * <tr> + * <td>"Here is one line of text that is going to be wrapped after 20 columns."</td> + * <td>20</td> + * <td>"\n"</td> + * <td>true/false</td> + * <td>"Here is one line of\ntext that is going\nto be wrapped after\n20 columns."</td> + * </tr> + * <tr> + * <td>"Here is one line of text that is going to be wrapped after 20 columns."</td> + * <td>20</td> + * <td>"<br />"</td> + * <td>true/false</td> + * <td>"Here is one line of<br />text that is going<br />to be wrapped after<br />20 columns."</td> + * </tr> + * <tr> + * <td>"Here is one line of text that is going to be wrapped after 20 columns."</td> + * <td>20</td> + * <td>null</td> + * <td>true/false</td> + * <td>"Here is one line of" + systemNewLine + "text that is going" + systemNewLine + "to be wrapped after" + systemNewLine + "20 columns."</td> + * </tr> + * <tr> + * <td>"Click here to jump to the commons website - http://commons.apache.org";</td> + * <td>20</td> + * <td>"\n"</td> + * <td>false</td> + * <td>"Click here to jump\nto the commons\nwebsite -\nhttp://commons.apache.org";</td> + * </tr> + * <tr> + * <td>"Click here to jump to the commons website - http://commons.apache.org";</td> + * <td>20</td> + * <td>"\n"</td> + * <td>true</td> + * <td>"Click here to jump\nto the commons\nwebsite -\nhttp://commons.apach\ne.org";</td> + * </tr> + * </table> + * + * @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, + * <code>null</code> uses the system property line separator + * @param wrapLongWords true if long words (such as URLs) should be wrapped + * @return a line with newlines inserted, <code>null</code> if null input + */ + public static String wrap(final String str, final int wrapLength, final String newLineStr, final boolean wrapLongWords) { + return wrap(str, wrapLength, newLineStr, wrapLongWords, " "); + } + + /** + * <p>Wraps a single line of text, identifying words by <code>wrapOn</code>.</p> + * + * <p>Leading spaces on a new line are stripped. + * Trailing spaces are not stripped.</p> + * + * <table border="1" summary="Wrap Results"> + * <tr> + * <th>input</th> + * <th>wrapLenght</th> + * <th>newLineString</th> + * <th>wrapLongWords</th> + * <th>wrapOn</th> + * <th>result</th> + * </tr> + * <tr> + * <td>null</td> + * <td>*</td> + * <td>*</td> + * <td>true/false</td> + * <td>*</td> + * <td>null</td> + * </tr> + * <tr> + * <td>""</td> + * <td>*</td> + * <td>*</td> + * <td>true/false</td> + * <td>*</td> + * <td>""</td> + * </tr> + * <tr> + * <td>"Here is one line of text that is going to be wrapped after 20 columns."</td> + * <td>20</td> + * <td>"\n"</td> + * <td>true/false</td> + * <td>" "</td> + * <td>"Here is one line of\ntext that is going\nto be wrapped after\n20 columns."</td> + * </tr> + * <tr> + * <td>"Here is one line of text that is going to be wrapped after 20 columns."</td> + * <td>20</td> + * <td>"<br />"</td> + * <td>true/false</td> + * <td>" "</td> + * <td>"Here is one line of<br />text that is going<br />to be wrapped after<br />20 columns."</td> + * </tr> + * <tr> + * <td>"Here is one line of text that is going to be wrapped after 20 columns."</td> + * <td>20</td> + * <td>null</td> + * <td>true/false</td> + * <td>" "</td> + * <td>"Here is one line of" + systemNewLine + "text that is going" + systemNewLine + "to be wrapped after" + systemNewLine + "20 columns."</td> + * </tr> + * <tr> + * <td>"Click here to jump to the commons website - http://commons.apache.org";</td> + * <td>20</td> + * <td>"\n"</td> + * <td>false</td> + * <td>" "</td> + * <td>"Click here to jump\nto the commons\nwebsite -\nhttp://commons.apache.org";</td> + * </tr> + * <tr> + * <td>"Click here to jump to the commons website - http://commons.apache.org";</td> + * <td>20</td> + * <td>"\n"</td> + * <td>true</td> + * <td>" "</td> + * <td>"Click here to jump\nto the commons\nwebsite -\nhttp://commons.apach\ne.org";</td> + * </tr> + * <tr> + * <td>"flammable/inflammable"</td> + * <td>20</td> + * <td>"\n"</td> + * <td>true</td> + * <td>"/"</td> + * <td>"flammable\ninflammable"</td> + * </tr> + * </table> + * @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, + * <code>null</code> uses the system property line separator + * @param wrapLongWords true if long words (such as URLs) should be wrapped + * @param wrapOn regex expression to be used as a breakable characters, + * if blank string is provided a space character will be used + * @return a line with newlines inserted, <code>null</code> if null input + */ + public static String wrap(final String str, int wrapLength, String newLineStr, final boolean wrapLongWords, String wrapOn) { + if (str == null) { + return null; + } + if (newLineStr == null) { + newLineStr = System.getProperty("line.separator"); + } + if (wrapLength < 1) { + wrapLength = 1; + } + if (wrapOn == null || wrapOn.length() == 0 || wrapOn.trim().length() == 0) { + wrapOn = " "; + } + final Pattern patternToWrapOn = Pattern.compile(wrapOn); + final int inputLineLength = str.length(); + int offset = 0; + final StringBuilder wrappedLine = new StringBuilder(inputLineLength + 32); + + while (offset < inputLineLength) { + int spaceToWrapAt = -1; + Matcher matcher = patternToWrapOn.matcher(str.substring(offset, Math + .min(offset + wrapLength + 1, inputLineLength))); + if (matcher.find()) { + if (matcher.start() == 0) { + offset += matcher.end(); + continue; + } + spaceToWrapAt = matcher.start(); + } + + // only last line without leading spaces is left + if(inputLineLength - offset <= wrapLength) { + break; + } + + while(matcher.find()){ + spaceToWrapAt = matcher.start() + 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 + matcher = patternToWrapOn.matcher(str.substring(offset + wrapLength)); + if (matcher.find()) { + spaceToWrapAt = matcher.start() + offset + wrapLength; + } + + 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 + //----------------------------------------------------------------------- + /** + * <p>Capitalizes all the whitespace separated words in a String. + * Only the first character of each word is changed. To convert the + * rest of each word to lowercase at the same time, + * use {@link #capitalizeFully(String)}.</p> + * + * <p>Whitespace is defined by {@link Character#isWhitespace(char)}. + * A <code>null</code> input String returns <code>null</code>. + * Capitalization uses the Unicode title case, normally equivalent to + * upper case.</p> + * + * <pre> + * WordUtils.capitalize(null) = null + * WordUtils.capitalize("") = "" + * WordUtils.capitalize("i am FINE") = "I Am FINE" + * </pre> + * + * @param str the String to capitalize, may be null + * @return capitalized String, <code>null</code> if null String input + * @see #uncapitalize(String) + * @see #capitalizeFully(String) + */ + public static String capitalize(final String str) { + return capitalize(str, null); + } + + /** + * <p>Capitalizes all the delimiter separated words in a String. + * Only the first character of each word is changed. To convert the + * rest of each word to lowercase at the same time, + * use {@link #capitalizeFully(String, char[])}.</p> + * + * <p>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. </p> + * + * <p>A <code>null</code> input String returns <code>null</code>. + * Capitalization uses the Unicode title case, normally equivalent to + * upper case.</p> + * + * <pre> + * 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" + * </pre> + * + * @param str the String to capitalize, may be null + * @param delimiters set of characters to determine capitalization, null means whitespace + * @return capitalized String, <code>null</code> if null String input + * @see #uncapitalize(String) + * @see #capitalizeFully(String) + */ + public static String capitalize(final String str, final char... delimiters) { + final int delimLen = delimiters == null ? -1 : delimiters.length; + if (str == null || str.length() == 0 || delimLen == 0) { + return str; + } + final char[] buffer = str.toCharArray(); + boolean capitalizeNext = true; + for (int i = 0; i < buffer.length; i++) { + final char ch = buffer[i]; + if (isDelimiter(ch, delimiters)) { + capitalizeNext = true; + } else if (capitalizeNext) { + buffer[i] = Character.toTitleCase(ch); + capitalizeNext = false; + } + } + return new String(buffer); + } + + //----------------------------------------------------------------------- + /** + * <p>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. </p> + * + * <p>Whitespace is defined by {@link Character#isWhitespace(char)}. + * A <code>null</code> input String returns <code>null</code>. + * Capitalization uses the Unicode title case, normally equivalent to + * upper case.</p> + * + * <pre> + * WordUtils.capitalizeFully(null) = null + * WordUtils.capitalizeFully("") = "" + * WordUtils.capitalizeFully("i am FINE") = "I Am Fine" + * </pre> + * + * @param str the String to capitalize, may be null + * @return capitalized String, <code>null</code> if null String input + */ + public static String capitalizeFully(final String str) { + return capitalizeFully(str, null); + } + + /** + * <p>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. </p> + * + * <p>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. </p> + * + * <p>A <code>null</code> input String returns <code>null</code>. + * Capitalization uses the Unicode title case, normally equivalent to + * upper case.</p> + * + * <pre> + * WordUtils.capitalizeFully(null, *) = null + * WordUtils.capitalizeFully("", *) = "" + * WordUtils.capitalizeFully(*, null) = * + * WordUtils.capitalizeFully(*, new char[0]) = * + * WordUtils.capitalizeFully("i aM.fine", {'.'}) = "I am.Fine" + * </pre> + * + * @param str the String to capitalize, may be null + * @param delimiters set of characters to determine capitalization, null means whitespace + * @return capitalized String, <code>null</code> if null String input + */ + public static String capitalizeFully(String str, final char... delimiters) { + final int delimLen = delimiters == null ? -1 : delimiters.length; + if (str == null || str.length() == 0 || delimLen == 0) { + return str; + } + str = str.toLowerCase(); + return capitalize(str, delimiters); + } + + //----------------------------------------------------------------------- + /** + * <p>Uncapitalizes all the whitespace separated words in a String. + * Only the first character of each word is changed.</p> + * + * <p>Whitespace is defined by {@link Character#isWhitespace(char)}. + * A <code>null</code> input String returns <code>null</code>.</p> + * + * <pre> + * WordUtils.uncapitalize(null) = null + * WordUtils.uncapitalize("") = "" + * WordUtils.uncapitalize("I Am FINE") = "i am fINE" + * </pre> + * + * @param str the String to uncapitalize, may be null + * @return uncapitalized String, <code>null</code> if null String input + * @see #capitalize(String) + */ + public static String uncapitalize(final String str) { + return uncapitalize(str, null); + } + + /** + * <p>Uncapitalizes all the whitespace separated words in a String. + * Only the first character of each word is changed.</p> + * + * <p>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. </p> + * + * <p>Whitespace is defined by {@link Character#isWhitespace(char)}. + * A <code>null</code> input String returns <code>null</code>.</p> + * + * <pre> + * WordUtils.uncapitalize(null, *) = null + * WordUtils.uncapitalize("", *) = "" + * WordUtils.uncapitalize(*, null) = * + * WordUtils.uncapitalize(*, new char[0]) = * + * WordUtils.uncapitalize("I AM.FINE", {'.'}) = "i AM.fINE" + * </pre> + * + * @param str the String to uncapitalize, may be null + * @param delimiters set of characters to determine uncapitalization, null means whitespace + * @return uncapitalized String, <code>null</code> if null String input + * @see #capitalize(String) + */ + public static String uncapitalize(final String str, final char... delimiters) { + final int delimLen = delimiters == null ? -1 : delimiters.length; + if (str == null || str.length() == 0 || delimLen == 0) { + return str; + } + final char[] buffer = str.toCharArray(); + boolean uncapitalizeNext = true; + for (int i = 0; i < buffer.length; i++) { + final char ch = buffer[i]; + if (isDelimiter(ch, delimiters)) { + uncapitalizeNext = true; + } else if (uncapitalizeNext) { + buffer[i] = Character.toLowerCase(ch); + uncapitalizeNext = false; + } + } + return new String(buffer); + } + + //----------------------------------------------------------------------- + /** + * <p>Swaps the case of a String using a word based algorithm.</p> + * + * <ul> + * <li>Upper case character converts to Lower case</li> + * <li>Title case character converts to Lower case</li> + * <li>Lower case character after Whitespace or at start converts to Title case</li> + * <li>Other Lower case character converts to Upper case</li> + * </ul> + * + * <p>Whitespace is defined by {@link Character#isWhitespace(char)}. + * A <code>null</code> input String returns <code>null</code>.</p> + * + * <pre> + * StringUtils.swapCase(null) = null + * StringUtils.swapCase("") = "" + * StringUtils.swapCase("The dog has a BONE") = "tHE DOG HAS A bone" + * </pre> + * + * @param str the String to swap case, may be null + * @return the changed String, <code>null</code> if null String input + */ + public static String swapCase(final String str) { + if (str == null || str.length() == 0) { + return str; + } + final char[] buffer = str.toCharArray(); + + boolean whitespace = true; + + for (int i = 0; i < buffer.length; i++) { + final char ch = buffer[i]; + if (Character.isUpperCase(ch)) { + buffer[i] = Character.toLowerCase(ch); + whitespace = false; + } else if (Character.isTitleCase(ch)) { + buffer[i] = Character.toLowerCase(ch); + whitespace = false; + } else if (Character.isLowerCase(ch)) { + if (whitespace) { + buffer[i] = Character.toTitleCase(ch); + whitespace = false; + } else { + buffer[i] = Character.toUpperCase(ch); + } + } else { + whitespace = Character.isWhitespace(ch); + } + } + return new String(buffer); + } + + //----------------------------------------------------------------------- + /** + * <p>Extracts the initial characters from each word in the String.</p> + * + * <p>All first characters after whitespace are returned as a new string. + * Their case is not changed.</p> + * + * <p>Whitespace is defined by {@link Character#isWhitespace(char)}. + * A <code>null</code> input String returns <code>null</code>.</p> + * + * <pre> + * WordUtils.initials(null) = null + * WordUtils.initials("") = "" + * WordUtils.initials("Ben John Lee") = "BJL" + * WordUtils.initials("Ben J.Lee") = "BJ" + * </pre> + * + * @param str the String to get initials from, may be null + * @return String of initial letters, <code>null</code> if null String input + * @see #initials(String,char[]) + */ + public static String initials(final String str) { + return initials(str, null); + } + + /** + * <p>Extracts the initial characters from each word in the String.</p> + * + * <p>All first characters after the defined delimiters are returned as a new string. + * Their case is not changed.</p> + * + * <p>If the delimiters array is null, then Whitespace is used. + * Whitespace is defined by {@link Character#isWhitespace(char)}. + * A <code>null</code> input String returns <code>null</code>. + * An empty delimiter array returns an empty String.</p> + * + * <pre> + * 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]) = "" + * </pre> + * + * @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 characters, <code>null</code> if null String input + * @see #initials(String) + */ + public static String initials(final String str, final char... delimiters) { + if (str == null || str.length() == 0) { + return str; + } + if (delimiters != null && delimiters.length == 0) { + return ""; + } + final int strLen = str.length(); + final char[] buf = new char[strLen / 2 + 1]; + int count = 0; + boolean lastWasGap = true; + for (int i = 0; i < strLen; i++) { + final char ch = str.charAt(i); + + if (isDelimiter(ch, delimiters)) { + lastWasGap = true; + } else if (lastWasGap) { + buf[count++] = ch; + lastWasGap = false; + } else { + continue; // ignore ch + } + } + return new String(buf, 0, count); + } + + //----------------------------------------------------------------------- + /** + * <p>Checks if the String contains all words in the given array.</p> + * + * <p> + * A {@code null} String will return {@code false}. A {@code null}, zero + * length search array or if one element of array is null will return {@code false}. + * </p> + * + * <pre> + * WordUtils.containsAllWords(null, *) = false + * WordUtils.containsAllWords("", *) = false + * WordUtils.containsAllWords(*, null) = false + * WordUtils.containsAllWords(*, []) = false + * WordUtils.containsAllWords("abcd", "ab", "cd") = false + * WordUtils.containsAllWords("abc def", "def", "abc") = true + * </pre> + * + * + * @param word The CharSequence to check, may be null + * @param words The array of String words to search for, may be null + * @return {@code true} if all search words are found, {@code false} otherwise + */ + public static boolean containsAllWords(final CharSequence word, final CharSequence... words) { + if (word == null || word.length() == 0 || words == null || Array.getLength(words) == 0) { + return false; + } + for (final CharSequence w : words) { + if (w == null || w.length() == 0 || String.valueOf(w).trim().length() == 0 ) { + return false; + } + final Pattern p = Pattern.compile(".*\\b" + w + "\\b.*"); + if (!p.matcher(word).matches()) { + return false; + } + } + return true; + } + + //----------------------------------------------------------------------- + /** + * 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(final char ch, final char[] delimiters) { + if (delimiters == null) { + return Character.isWhitespace(ch); + } + for (final char delimiter : delimiters) { + if (ch == delimiter) { + return true; + } + } + return false; + } + +} http://git-wip-us.apache.org/repos/asf/commons-text/blob/5b89b382/src/test/java/org/apache/commons/text/WordUtilsTest.java ---------------------------------------------------------------------- diff --git a/src/test/java/org/apache/commons/text/WordUtilsTest.java b/src/test/java/org/apache/commons/text/WordUtilsTest.java new file mode 100644 index 0000000..0ab8b09 --- /dev/null +++ b/src/test/java/org/apache/commons/text/WordUtilsTest.java @@ -0,0 +1,420 @@ +/* + * 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.text; + +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertFalse; +import static org.junit.Assert.assertNotNull; +import static org.junit.Assert.assertTrue; + +import java.lang.reflect.Constructor; +import java.lang.reflect.Modifier; + +import org.junit.Test; + +/** + * Unit tests for {@link WordUtils} class. + */ +public class WordUtilsTest { + + //----------------------------------------------------------------------- + @Test + public void testConstructor() { + assertNotNull(new WordUtils()); + final Constructor<?>[] cons = WordUtils.class.getDeclaredConstructors(); + assertEquals(1, cons.length); + assertTrue(Modifier.isPublic(cons[0].getModifiers())); + assertTrue(Modifier.isPublic(WordUtils.class.getModifiers())); + assertFalse(Modifier.isFinal(WordUtils.class.getModifiers())); + } + + //----------------------------------------------------------------------- + @Test + public void testWrap_StringInt() { + assertEquals(null, WordUtils.wrap(null, 20)); + assertEquals(null, WordUtils.wrap(null, -1)); + + assertEquals("", WordUtils.wrap("", 20)); + assertEquals("", WordUtils.wrap("", -1)); + + // normal + final String systemNewLine = System.lineSeparator(); + String input = "Here is one line of text that is going to be wrapped after 20 columns."; + String expected = "Here is one line of" + systemNewLine + "text that is going" + + systemNewLine + "to be wrapped after" + systemNewLine + "20 columns."; + assertEquals(expected, WordUtils.wrap(input, 20)); + + // long word at end + input = "Click here to jump to the commons website - http://commons.apache.org";; + expected = "Click here to jump" + systemNewLine + "to the commons" + systemNewLine + + "website -" + systemNewLine + "http://commons.apache.org";; + assertEquals(expected, WordUtils.wrap(input, 20)); + + // long word in middle + input = "Click here, http://commons.apache.org, to jump to the commons website"; + expected = "Click here," + systemNewLine + "http://commons.apache.org,"; + systemNewLine + + "to jump to the" + systemNewLine + "commons website"; + assertEquals(expected, WordUtils.wrap(input, 20)); + + // leading spaces on a new line are stripped + // trailing spaces are not stripped + input = "word1 word2 word3"; + expected = "word1 " + systemNewLine + "word2 " + systemNewLine + "word3"; + assertEquals(expected, WordUtils.wrap(input, 7)); + } + + @Test + public void testWrap_StringIntStringBoolean() { + assertEquals(null, WordUtils.wrap(null, 20, "\n", false)); + assertEquals(null, WordUtils.wrap(null, 20, "\n", true)); + assertEquals(null, WordUtils.wrap(null, 20, null, true)); + assertEquals(null, WordUtils.wrap(null, 20, null, false)); + assertEquals(null, WordUtils.wrap(null, -1, null, true)); + assertEquals(null, WordUtils.wrap(null, -1, null, false)); + + assertEquals("", WordUtils.wrap("", 20, "\n", false)); + assertEquals("", WordUtils.wrap("", 20, "\n", true)); + assertEquals("", WordUtils.wrap("", 20, null, false)); + assertEquals("", WordUtils.wrap("", 20, null, true)); + assertEquals("", WordUtils.wrap("", -1, null, false)); + assertEquals("", WordUtils.wrap("", -1, null, true)); + + // normal + String input = "Here is one line of text that is going to be wrapped after 20 columns."; + String expected = "Here is one line of\ntext that is going\nto be wrapped after\n20 columns."; + assertEquals(expected, WordUtils.wrap(input, 20, "\n", false)); + assertEquals(expected, WordUtils.wrap(input, 20, "\n", true)); + + // unusual newline char + input = "Here is one line of text that is going to be wrapped after 20 columns."; + expected = "Here is one line of<br />text that is going<br />to be wrapped after<br />20 columns."; + assertEquals(expected, WordUtils.wrap(input, 20, "<br />", false)); + assertEquals(expected, WordUtils.wrap(input, 20, "<br />", true)); + + // short line length + input = "Here is one line"; + expected = "Here\nis one\nline"; + assertEquals(expected, WordUtils.wrap(input, 6, "\n", false)); + expected = "Here\nis\none\nline"; + assertEquals(expected, WordUtils.wrap(input, 2, "\n", false)); + assertEquals(expected, WordUtils.wrap(input, -1, "\n", false)); + + // system newline char + final String systemNewLine = System.lineSeparator(); + input = "Here is one line of text that is going to be wrapped after 20 columns."; + expected = "Here is one line of" + systemNewLine + "text that is going" + systemNewLine + + "to be wrapped after" + systemNewLine + "20 columns."; + assertEquals(expected, WordUtils.wrap(input, 20, null, false)); + assertEquals(expected, WordUtils.wrap(input, 20, null, true)); + + // with extra spaces + input = " Here: is one line of text that is going to be wrapped after 20 columns."; + expected = "Here: is one line\nof text that is \ngoing to be \nwrapped after 20 \ncolumns."; + assertEquals(expected, WordUtils.wrap(input, 20, "\n", false)); + assertEquals(expected, WordUtils.wrap(input, 20, "\n", true)); + + // with tab + input = "Here is\tone line of text that is going to be wrapped after 20 columns."; + expected = "Here is\tone line of\ntext that is going\nto be wrapped after\n20 columns."; + assertEquals(expected, WordUtils.wrap(input, 20, "\n", false)); + assertEquals(expected, WordUtils.wrap(input, 20, "\n", true)); + + // with tab at wrapColumn + input = "Here is one line of\ttext that is going to be wrapped after 20 columns."; + expected = "Here is one line\nof\ttext that is\ngoing to be wrapped\nafter 20 columns."; + assertEquals(expected, WordUtils.wrap(input, 20, "\n", false)); + assertEquals(expected, WordUtils.wrap(input, 20, "\n", true)); + + // difference because of long word + input = "Click here to jump to the commons website - http://commons.apache.org";; + expected = "Click here to jump\nto the commons\nwebsite -\nhttp://commons.apache.org";; + assertEquals(expected, WordUtils.wrap(input, 20, "\n", false)); + expected = "Click here to jump\nto the commons\nwebsite -\nhttp://commons.apach\ne.org";; + assertEquals(expected, WordUtils.wrap(input, 20, "\n", true)); + + // difference because of long word in middle + input = "Click here, http://commons.apache.org, to jump to the commons website"; + expected = "Click here,\nhttp://commons.apache.org,\nto jump to the\ncommons website"; + assertEquals(expected, WordUtils.wrap(input, 20, "\n", false)); + expected = "Click here,\nhttp://commons.apach\ne.org, to jump to\nthe commons website"; + assertEquals(expected, WordUtils.wrap(input, 20, "\n", true)); + } + + @Test + public void testWrap_StringIntStringBooleanString() { + + //no changes test + String input = "flammable/inflammable"; + String expected = "flammable/inflammable"; + assertEquals(expected, WordUtils.wrap(input, 30, "\n", false, "/")); + + // wrap on / and small width + expected = "flammable\ninflammable"; + assertEquals(expected, WordUtils.wrap(input, 2, "\n", false, "/")); + + // wrap long words on / 1 + expected = "flammable\ninflammab\nle"; + assertEquals(expected, WordUtils.wrap(input, 9, "\n", true, "/")); + + // wrap long words on / 2 + expected = "flammable\ninflammable"; + assertEquals(expected, WordUtils.wrap(input, 15, "\n", true, "/")); + + // wrap long words on / 3 + input = "flammableinflammable"; + expected = "flammableinflam\nmable"; + assertEquals(expected, WordUtils.wrap(input, 15, "\n", true, "/")); + } + + //----------------------------------------------------------------------- + @Test + public void testCapitalize_String() { + assertEquals(null, WordUtils.capitalize(null)); + assertEquals("", WordUtils.capitalize("")); + assertEquals(" ", WordUtils.capitalize(" ")); + + assertEquals("I", WordUtils.capitalize("I") ); + assertEquals("I", WordUtils.capitalize("i") ); + assertEquals("I Am Here 123", WordUtils.capitalize("i am here 123") ); + assertEquals("I Am Here 123", WordUtils.capitalize("I Am Here 123") ); + assertEquals("I Am HERE 123", WordUtils.capitalize("i am HERE 123") ); + assertEquals("I AM HERE 123", WordUtils.capitalize("I AM HERE 123") ); + } + + @Test + public void testCapitalizeWithDelimiters_String() { + assertEquals(null, WordUtils.capitalize(null, null)); + assertEquals("", WordUtils.capitalize("", new char[0])); + assertEquals(" ", WordUtils.capitalize(" ", new char[0])); + + char[] chars = new char[] { '-', '+', ' ', '@' }; + assertEquals("I", WordUtils.capitalize("I", chars) ); + assertEquals("I", WordUtils.capitalize("i", chars) ); + assertEquals("I-Am Here+123", WordUtils.capitalize("i-am here+123", chars) ); + assertEquals("I Am+Here-123", WordUtils.capitalize("I Am+Here-123", chars) ); + assertEquals("I+Am-HERE 123", WordUtils.capitalize("i+am-HERE 123", chars) ); + assertEquals("I-AM HERE+123", WordUtils.capitalize("I-AM HERE+123", chars) ); + chars = new char[] {'.'}; + assertEquals("I aM.Fine", WordUtils.capitalize("i aM.fine", chars) ); + assertEquals("I Am.fine", WordUtils.capitalize("i am.fine", null) ); + } + + @Test + public void testCapitalizeFully_String() { + assertEquals(null, WordUtils.capitalizeFully(null)); + assertEquals("", WordUtils.capitalizeFully("")); + assertEquals(" ", WordUtils.capitalizeFully(" ")); + + assertEquals("I", WordUtils.capitalizeFully("I") ); + assertEquals("I", WordUtils.capitalizeFully("i") ); + assertEquals("I Am Here 123", WordUtils.capitalizeFully("i am here 123") ); + assertEquals("I Am Here 123", WordUtils.capitalizeFully("I Am Here 123") ); + assertEquals("I Am Here 123", WordUtils.capitalizeFully("i am HERE 123") ); + assertEquals("I Am Here 123", WordUtils.capitalizeFully("I AM HERE 123") ); + } + + @Test + public void testCapitalizeFullyWithDelimiters_String() { + assertEquals(null, WordUtils.capitalizeFully(null, null)); + assertEquals("", WordUtils.capitalizeFully("", new char[0])); + assertEquals(" ", WordUtils.capitalizeFully(" ", new char[0])); + + char[] chars = new char[] { '-', '+', ' ', '@' }; + assertEquals("I", WordUtils.capitalizeFully("I", chars) ); + assertEquals("I", WordUtils.capitalizeFully("i", chars) ); + assertEquals("I-Am Here+123", WordUtils.capitalizeFully("i-am here+123", chars) ); + assertEquals("I Am+Here-123", WordUtils.capitalizeFully("I Am+Here-123", chars) ); + assertEquals("I+Am-Here 123", WordUtils.capitalizeFully("i+am-HERE 123", chars) ); + assertEquals("I-Am Here+123", WordUtils.capitalizeFully("I-AM HERE+123", chars) ); + chars = new char[] {'.'}; + assertEquals("I am.Fine", WordUtils.capitalizeFully("i aM.fine", chars) ); + assertEquals("I Am.fine", WordUtils.capitalizeFully("i am.fine", null) ); + } + + @Test + public void testContainsAllWords_StringString() { + assertFalse(WordUtils.containsAllWords(null, (String) null)); + assertFalse(WordUtils.containsAllWords(null, "")); + assertFalse(WordUtils.containsAllWords(null, "ab")); + + assertFalse(WordUtils.containsAllWords("", (String) null)); + assertFalse(WordUtils.containsAllWords("", "")); + assertFalse(WordUtils.containsAllWords("", "ab")); + + assertFalse(WordUtils.containsAllWords("foo", (String) null)); + assertFalse(WordUtils.containsAllWords("bar", "")); + assertFalse(WordUtils.containsAllWords("zzabyycdxx", "by")); + assertTrue(WordUtils.containsAllWords("lorem ipsum dolor sit amet", "ipsum", "lorem", "dolor")); + assertFalse(WordUtils.containsAllWords("lorem ipsum dolor sit amet", "ipsum", null, "lorem", "dolor")); + assertFalse(WordUtils.containsAllWords("lorem ipsum null dolor sit amet", "ipsum", null, "lorem", "dolor")); + assertFalse(WordUtils.containsAllWords("ab", "b")); + assertFalse(WordUtils.containsAllWords("ab", "z")); + } + + @Test + public void testUncapitalize_String() { + assertEquals(null, WordUtils.uncapitalize(null)); + assertEquals("", WordUtils.uncapitalize("")); + assertEquals(" ", WordUtils.uncapitalize(" ")); + + assertEquals("i", WordUtils.uncapitalize("I") ); + assertEquals("i", WordUtils.uncapitalize("i") ); + assertEquals("i am here 123", WordUtils.uncapitalize("i am here 123") ); + assertEquals("i am here 123", WordUtils.uncapitalize("I Am Here 123") ); + assertEquals("i am hERE 123", WordUtils.uncapitalize("i am HERE 123") ); + assertEquals("i aM hERE 123", WordUtils.uncapitalize("I AM HERE 123") ); + } + + @Test + public void testUncapitalizeWithDelimiters_String() { + assertEquals(null, WordUtils.uncapitalize(null, null)); + assertEquals("", WordUtils.uncapitalize("", new char[0])); + assertEquals(" ", WordUtils.uncapitalize(" ", new char[0])); + + char[] chars = new char[] { '-', '+', ' ', '@' }; + assertEquals("i", WordUtils.uncapitalize("I", chars) ); + assertEquals("i", WordUtils.uncapitalize("i", chars) ); + assertEquals("i am-here+123", WordUtils.uncapitalize("i am-here+123", chars) ); + assertEquals("i+am here-123", WordUtils.uncapitalize("I+Am Here-123", chars) ); + assertEquals("i-am+hERE 123", WordUtils.uncapitalize("i-am+HERE 123", chars) ); + assertEquals("i aM-hERE+123", WordUtils.uncapitalize("I AM-HERE+123", chars) ); + chars = new char[] {'.'}; + assertEquals("i AM.fINE", WordUtils.uncapitalize("I AM.FINE", chars) ); + assertEquals("i aM.FINE", WordUtils.uncapitalize("I AM.FINE", null) ); + } + + //----------------------------------------------------------------------- + @Test + public void testInitials_String() { + assertEquals(null, WordUtils.initials(null)); + assertEquals("", WordUtils.initials("")); + assertEquals("", WordUtils.initials(" ")); + + assertEquals("I", WordUtils.initials("I")); + assertEquals("i", WordUtils.initials("i")); + assertEquals("BJL", WordUtils.initials("Ben John Lee")); + assertEquals("BJL", WordUtils.initials(" Ben \n John\tLee\t")); + assertEquals("BJ", WordUtils.initials("Ben J.Lee")); + assertEquals("BJ.L", WordUtils.initials(" Ben John . Lee")); + assertEquals("iah1", WordUtils.initials("i am here 123")); + } + + // ----------------------------------------------------------------------- + @Test + public void testInitials_String_charArray() { + char[] array = null; + assertEquals(null, WordUtils.initials(null, array)); + assertEquals("", WordUtils.initials("", array)); + assertEquals("", WordUtils.initials(" ", array)); + assertEquals("I", WordUtils.initials("I", array)); + assertEquals("i", WordUtils.initials("i", array)); + assertEquals("S", WordUtils.initials("SJC", array)); + assertEquals("BJL", WordUtils.initials("Ben John Lee", array)); + assertEquals("BJL", WordUtils.initials(" Ben \n John\tLee\t", array)); + assertEquals("BJ", WordUtils.initials("Ben J.Lee", array)); + assertEquals("BJ.L", WordUtils.initials(" Ben John . Lee", array)); + assertEquals("KO", WordUtils.initials("Kay O'Murphy", array)); + assertEquals("iah1", WordUtils.initials("i am here 123", array)); + + array = new char[0]; + assertEquals(null, WordUtils.initials(null, array)); + assertEquals("", WordUtils.initials("", array)); + assertEquals("", WordUtils.initials(" ", array)); + assertEquals("", WordUtils.initials("I", array)); + assertEquals("", WordUtils.initials("i", array)); + assertEquals("", WordUtils.initials("SJC", array)); + assertEquals("", WordUtils.initials("Ben John Lee", array)); + assertEquals("", WordUtils.initials(" Ben \n John\tLee\t", array)); + assertEquals("", WordUtils.initials("Ben J.Lee", array)); + assertEquals("", WordUtils.initials(" Ben John . Lee", array)); + assertEquals("", WordUtils.initials("Kay O'Murphy", array)); + assertEquals("", WordUtils.initials("i am here 123", array)); + + array = " ".toCharArray(); + assertEquals(null, WordUtils.initials(null, array)); + assertEquals("", WordUtils.initials("", array)); + assertEquals("", WordUtils.initials(" ", array)); + assertEquals("I", WordUtils.initials("I", array)); + assertEquals("i", WordUtils.initials("i", array)); + assertEquals("S", WordUtils.initials("SJC", array)); + assertEquals("BJL", WordUtils.initials("Ben John Lee", array)); + assertEquals("BJ", WordUtils.initials("Ben J.Lee", array)); + assertEquals("B\nJ", WordUtils.initials(" Ben \n John\tLee\t", array)); + assertEquals("BJ.L", WordUtils.initials(" Ben John . Lee", array)); + assertEquals("KO", WordUtils.initials("Kay O'Murphy", array)); + assertEquals("iah1", WordUtils.initials("i am here 123", array)); + + array = " .".toCharArray(); + assertEquals(null, WordUtils.initials(null, array)); + assertEquals("", WordUtils.initials("", array)); + assertEquals("", WordUtils.initials(" ", array)); + assertEquals("I", WordUtils.initials("I", array)); + assertEquals("i", WordUtils.initials("i", array)); + assertEquals("S", WordUtils.initials("SJC", array)); + assertEquals("BJL", WordUtils.initials("Ben John Lee", array)); + assertEquals("BJL", WordUtils.initials("Ben J.Lee", array)); + assertEquals("BJL", WordUtils.initials(" Ben John . Lee", array)); + assertEquals("KO", WordUtils.initials("Kay O'Murphy", array)); + assertEquals("iah1", WordUtils.initials("i am here 123", array)); + + array = " .'".toCharArray(); + assertEquals(null, WordUtils.initials(null, array)); + assertEquals("", WordUtils.initials("", array)); + assertEquals("", WordUtils.initials(" ", array)); + assertEquals("I", WordUtils.initials("I", array)); + assertEquals("i", WordUtils.initials("i", array)); + assertEquals("S", WordUtils.initials("SJC", array)); + assertEquals("BJL", WordUtils.initials("Ben John Lee", array)); + assertEquals("BJL", WordUtils.initials("Ben J.Lee", array)); + assertEquals("BJL", WordUtils.initials(" Ben John . Lee", array)); + assertEquals("KOM", WordUtils.initials("Kay O'Murphy", array)); + assertEquals("iah1", WordUtils.initials("i am here 123", array)); + + array = "SIJo1".toCharArray(); + assertEquals(null, WordUtils.initials(null, array)); + assertEquals("", WordUtils.initials("", array)); + assertEquals(" ", WordUtils.initials(" ", array)); + assertEquals("", WordUtils.initials("I", array)); + assertEquals("i", WordUtils.initials("i", array)); + assertEquals("C", WordUtils.initials("SJC", array)); + assertEquals("Bh", WordUtils.initials("Ben John Lee", array)); + assertEquals("B.", WordUtils.initials("Ben J.Lee", array)); + assertEquals(" h", WordUtils.initials(" Ben John . Lee", array)); + assertEquals("K", WordUtils.initials("Kay O'Murphy", array)); + assertEquals("i2", WordUtils.initials("i am here 123", array)); + } + + // ----------------------------------------------------------------------- + @Test + public void testSwapCase_String() { + assertEquals(null, WordUtils.swapCase(null)); + assertEquals("", WordUtils.swapCase("")); + assertEquals(" ", WordUtils.swapCase(" ")); + + assertEquals("i", WordUtils.swapCase("I") ); + assertEquals("I", WordUtils.swapCase("i") ); + assertEquals("I AM HERE 123", WordUtils.swapCase("i am here 123") ); + assertEquals("i aM hERE 123", WordUtils.swapCase("I Am Here 123") ); + assertEquals("I AM here 123", WordUtils.swapCase("i am HERE 123") ); + assertEquals("i am here 123", WordUtils.swapCase("I AM HERE 123") ); + + final String test = "This String contains a TitleCase character: \u01C8"; + final String expect = "tHIS sTRING CONTAINS A tITLEcASE CHARACTER: \u01C9"; + assertEquals(expect, WordUtils.swapCase(test)); + } + +}
