org.elasticsearch.common.Strings Maven / Gradle / Ivy
/*
* Licensed to ElasticSearch and Shay Banon under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. ElasticSearch 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.elasticsearch.common;
import com.google.common.collect.ImmutableSet;
import com.google.common.collect.Iterables;
import gnu.trove.set.hash.THashSet;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.UnicodeUtil;
import org.elasticsearch.common.io.FastStringReader;
import java.io.BufferedReader;
import java.util.*;
/**
*
*/
public class Strings {
public static final String[] EMPTY_ARRAY = new String[0];
private static final String FOLDER_SEPARATOR = "/";
private static final String WINDOWS_FOLDER_SEPARATOR = "\\";
private static final String TOP_PATH = "src/test";
private static final String CURRENT_PATH = ".";
private static final char EXTENSION_SEPARATOR = '.';
public static void tabify(int tabs, String from, StringBuilder to) throws Exception {
BufferedReader reader = new BufferedReader(new FastStringReader(from));
String line;
while ((line = reader.readLine()) != null) {
for (int i = 0; i < tabs; i++) {
to.append('\t');
}
to.append(line).append('\n');
}
}
public static void spaceify(int spaces, String from, StringBuilder to) throws Exception {
BufferedReader reader = new BufferedReader(new FastStringReader(from));
String line;
while ((line = reader.readLine()) != null) {
for (int i = 0; i < spaces; i++) {
to.append(' ');
}
to.append(line).append('\n');
}
}
/**
* Splits a backslash escaped string on the separator.
*
* Current backslash escaping supported:
*
\n \t \r \b \f are escaped the same as a Java String
*
Other characters following a backslash are produced verbatim (\c => c)
*
* @param s the string to split
* @param separator the separator to split on
* @param decode decode backslash escaping
*/
public static List splitSmart(String s, String separator, boolean decode) {
ArrayList lst = new ArrayList(2);
StringBuilder sb = new StringBuilder();
int pos = 0, end = s.length();
while (pos < end) {
if (s.startsWith(separator, pos)) {
if (sb.length() > 0) {
lst.add(sb.toString());
sb = new StringBuilder();
}
pos += separator.length();
continue;
}
char ch = s.charAt(pos++);
if (ch == '\\') {
if (!decode) sb.append(ch);
if (pos >= end) break; // ERROR, or let it go?
ch = s.charAt(pos++);
if (decode) {
switch (ch) {
case 'n':
ch = '\n';
break;
case 't':
ch = '\t';
break;
case 'r':
ch = '\r';
break;
case 'b':
ch = '\b';
break;
case 'f':
ch = '\f';
break;
}
}
}
sb.append(ch);
}
if (sb.length() > 0) {
lst.add(sb.toString());
}
return lst;
}
public static List splitWS(String s, boolean decode) {
ArrayList lst = new ArrayList(2);
StringBuilder sb = new StringBuilder();
int pos = 0, end = s.length();
while (pos < end) {
char ch = s.charAt(pos++);
if (Character.isWhitespace(ch)) {
if (sb.length() > 0) {
lst.add(sb.toString());
sb = new StringBuilder();
}
continue;
}
if (ch == '\\') {
if (!decode) sb.append(ch);
if (pos >= end) break; // ERROR, or let it go?
ch = s.charAt(pos++);
if (decode) {
switch (ch) {
case 'n':
ch = '\n';
break;
case 't':
ch = '\t';
break;
case 'r':
ch = '\r';
break;
case 'b':
ch = '\b';
break;
case 'f':
ch = '\f';
break;
}
}
}
sb.append(ch);
}
if (sb.length() > 0) {
lst.add(sb.toString());
}
return lst;
}
//---------------------------------------------------------------------
// General convenience methods for working with Strings
//---------------------------------------------------------------------
/**
* Check that the given CharSequence is neither null nor of length 0.
* Note: Will return true for a CharSequence that purely consists of whitespace.
*
* StringUtils.hasLength(null) = false
* StringUtils.hasLength("") = false
* StringUtils.hasLength(" ") = true
* StringUtils.hasLength("Hello") = true
*
*
* @param str the CharSequence to check (may be null)
* @return true if the CharSequence is not null and has length
* @see #hasText(String)
*/
public static boolean hasLength(CharSequence str) {
return (str != null && str.length() > 0);
}
/**
* Check that the given String is neither null nor of length 0.
* Note: Will return true for a String that purely consists of whitespace.
*
* @param str the String to check (may be null)
* @return true if the String is not null and has length
* @see #hasLength(CharSequence)
*/
public static boolean hasLength(String str) {
return hasLength((CharSequence) str);
}
/**
* Check whether the given CharSequence has actual text.
* More specifically, returns true if the string not null,
* its length is greater than 0, and it contains at least one non-whitespace character.
*
* StringUtils.hasText(null) = false
* StringUtils.hasText("") = false
* StringUtils.hasText(" ") = false
* StringUtils.hasText("12345") = true
* StringUtils.hasText(" 12345 ") = true
*
*
* @param str the CharSequence to check (may be null)
* @return true if the CharSequence is not null,
* its length is greater than 0, and it does not contain whitespace only
* @see java.lang.Character#isWhitespace
*/
public static boolean hasText(CharSequence str) {
if (!hasLength(str)) {
return false;
}
int strLen = str.length();
for (int i = 0; i < strLen; i++) {
if (!Character.isWhitespace(str.charAt(i))) {
return true;
}
}
return false;
}
/**
* Check whether the given String has actual text.
* More specifically, returns true if the string not null,
* its length is greater than 0, and it contains at least one non-whitespace character.
*
* @param str the String to check (may be null)
* @return true if the String is not null, its length is
* greater than 0, and it does not contain whitespace only
* @see #hasText(CharSequence)
*/
public static boolean hasText(String str) {
return hasText((CharSequence) str);
}
/**
* Check whether the given CharSequence contains any whitespace characters.
*
* @param str the CharSequence to check (may be null)
* @return true if the CharSequence is not empty and
* contains at least 1 whitespace character
* @see java.lang.Character#isWhitespace
*/
public static boolean containsWhitespace(CharSequence str) {
if (!hasLength(str)) {
return false;
}
int strLen = str.length();
for (int i = 0; i < strLen; i++) {
if (Character.isWhitespace(str.charAt(i))) {
return true;
}
}
return false;
}
/**
* Check whether the given String contains any whitespace characters.
*
* @param str the String to check (may be null)
* @return true if the String is not empty and
* contains at least 1 whitespace character
* @see #containsWhitespace(CharSequence)
*/
public static boolean containsWhitespace(String str) {
return containsWhitespace((CharSequence) str);
}
/**
* Trim leading and trailing whitespace from the given String.
*
* @param str the String to check
* @return the trimmed String
* @see java.lang.Character#isWhitespace
*/
public static String trimWhitespace(String str) {
if (!hasLength(str)) {
return str;
}
StringBuilder sb = new StringBuilder(str);
while (sb.length() > 0 && Character.isWhitespace(sb.charAt(0))) {
sb.deleteCharAt(0);
}
while (sb.length() > 0 && Character.isWhitespace(sb.charAt(sb.length() - 1))) {
sb.deleteCharAt(sb.length() - 1);
}
return sb.toString();
}
/**
* Trim all whitespace from the given String:
* leading, trailing, and inbetween characters.
*
* @param str the String to check
* @return the trimmed String
* @see java.lang.Character#isWhitespace
*/
public static String trimAllWhitespace(String str) {
if (!hasLength(str)) {
return str;
}
StringBuilder sb = new StringBuilder(str);
int index = 0;
while (sb.length() > index) {
if (Character.isWhitespace(sb.charAt(index))) {
sb.deleteCharAt(index);
} else {
index++;
}
}
return sb.toString();
}
/**
* Trim leading whitespace from the given String.
*
* @param str the String to check
* @return the trimmed String
* @see java.lang.Character#isWhitespace
*/
public static String trimLeadingWhitespace(String str) {
if (!hasLength(str)) {
return str;
}
StringBuilder sb = new StringBuilder(str);
while (sb.length() > 0 && Character.isWhitespace(sb.charAt(0))) {
sb.deleteCharAt(0);
}
return sb.toString();
}
/**
* Trim trailing whitespace from the given String.
*
* @param str the String to check
* @return the trimmed String
* @see java.lang.Character#isWhitespace
*/
public static String trimTrailingWhitespace(String str) {
if (!hasLength(str)) {
return str;
}
StringBuilder sb = new StringBuilder(str);
while (sb.length() > 0 && Character.isWhitespace(sb.charAt(sb.length() - 1))) {
sb.deleteCharAt(sb.length() - 1);
}
return sb.toString();
}
/**
* Trim all occurences of the supplied leading character from the given String.
*
* @param str the String to check
* @param leadingCharacter the leading character to be trimmed
* @return the trimmed String
*/
public static String trimLeadingCharacter(String str, char leadingCharacter) {
if (!hasLength(str)) {
return str;
}
StringBuilder sb = new StringBuilder(str);
while (sb.length() > 0 && sb.charAt(0) == leadingCharacter) {
sb.deleteCharAt(0);
}
return sb.toString();
}
/**
* Trim all occurences of the supplied trailing character from the given String.
*
* @param str the String to check
* @param trailingCharacter the trailing character to be trimmed
* @return the trimmed String
*/
public static String trimTrailingCharacter(String str, char trailingCharacter) {
if (!hasLength(str)) {
return str;
}
StringBuilder sb = new StringBuilder(str);
while (sb.length() > 0 && sb.charAt(sb.length() - 1) == trailingCharacter) {
sb.deleteCharAt(sb.length() - 1);
}
return sb.toString();
}
/**
* Test if the given String starts with the specified prefix,
* ignoring upper/lower case.
*
* @param str the String to check
* @param prefix the prefix to look for
* @see java.lang.String#startsWith
*/
public static boolean startsWithIgnoreCase(String str, String prefix) {
if (str == null || prefix == null) {
return false;
}
if (str.startsWith(prefix)) {
return true;
}
if (str.length() < prefix.length()) {
return false;
}
String lcStr = str.substring(0, prefix.length()).toLowerCase(Locale.ROOT);
String lcPrefix = prefix.toLowerCase(Locale.ROOT);
return lcStr.equals(lcPrefix);
}
/**
* Test if the given String ends with the specified suffix,
* ignoring upper/lower case.
*
* @param str the String to check
* @param suffix the suffix to look for
* @see java.lang.String#endsWith
*/
public static boolean endsWithIgnoreCase(String str, String suffix) {
if (str == null || suffix == null) {
return false;
}
if (str.endsWith(suffix)) {
return true;
}
if (str.length() < suffix.length()) {
return false;
}
String lcStr = str.substring(str.length() - suffix.length()).toLowerCase(Locale.ROOT);
String lcSuffix = suffix.toLowerCase(Locale.ROOT);
return lcStr.equals(lcSuffix);
}
/**
* Test whether the given string matches the given substring
* at the given index.
*
* @param str the original string (or StringBuilder)
* @param index the index in the original string to start matching against
* @param substring the substring to match at the given index
*/
public static boolean substringMatch(CharSequence str, int index, CharSequence substring) {
for (int j = 0; j < substring.length(); j++) {
int i = index + j;
if (i >= str.length() || str.charAt(i) != substring.charAt(j)) {
return false;
}
}
return true;
}
/**
* Count the occurrences of the substring in string s.
*
* @param str string to search in. Return 0 if this is null.
* @param sub string to search for. Return 0 if this is null.
*/
public static int countOccurrencesOf(String str, String sub) {
if (str == null || sub == null || str.length() == 0 || sub.length() == 0) {
return 0;
}
int count = 0;
int pos = 0;
int idx;
while ((idx = str.indexOf(sub, pos)) != -1) {
++count;
pos = idx + sub.length();
}
return count;
}
/**
* Replace all occurences of a substring within a string with
* another string.
*
* @param inString String to examine
* @param oldPattern String to replace
* @param newPattern String to insert
* @return a String with the replacements
*/
public static String replace(String inString, String oldPattern, String newPattern) {
if (!hasLength(inString) || !hasLength(oldPattern) || newPattern == null) {
return inString;
}
StringBuilder sb = new StringBuilder();
int pos = 0; // our position in the old string
int index = inString.indexOf(oldPattern);
// the index of an occurrence we've found, or -1
int patLen = oldPattern.length();
while (index >= 0) {
sb.append(inString.substring(pos, index));
sb.append(newPattern);
pos = index + patLen;
index = inString.indexOf(oldPattern, pos);
}
sb.append(inString.substring(pos));
// remember to append any characters to the right of a match
return sb.toString();
}
/**
* Delete all occurrences of the given substring.
*
* @param inString the original String
* @param pattern the pattern to delete all occurrences of
* @return the resulting String
*/
public static String delete(String inString, String pattern) {
return replace(inString, pattern, "");
}
/**
* Delete any character in a given String.
*
* @param inString the original String
* @param charsToDelete a set of characters to delete.
* E.g. "az\n" will delete 'a's, 'z's and new lines.
* @return the resulting String
*/
public static String deleteAny(String inString, String charsToDelete) {
if (!hasLength(inString) || !hasLength(charsToDelete)) {
return inString;
}
StringBuilder sb = new StringBuilder();
for (int i = 0; i < inString.length(); i++) {
char c = inString.charAt(i);
if (charsToDelete.indexOf(c) == -1) {
sb.append(c);
}
}
return sb.toString();
}
//---------------------------------------------------------------------
// Convenience methods for working with formatted Strings
//---------------------------------------------------------------------
/**
* Quote the given String with single quotes.
*
* @param str the input String (e.g. "myString")
* @return the quoted String (e.g. "'myString'"),
* or null if the input was null
*/
public static String quote(String str) {
return (str != null ? "'" + str + "'" : null);
}
/**
* Turn the given Object into a String with single quotes
* if it is a String; keeping the Object as-is else.
*
* @param obj the input Object (e.g. "myString")
* @return the quoted String (e.g. "'myString'"),
* or the input object as-is if not a String
*/
public static Object quoteIfString(Object obj) {
return (obj instanceof String ? quote((String) obj) : obj);
}
/**
* Unqualify a string qualified by a '.' dot character. For example,
* "this.name.is.qualified", returns "qualified".
*
* @param qualifiedName the qualified name
*/
public static String unqualify(String qualifiedName) {
return unqualify(qualifiedName, '.');
}
/**
* Unqualify a string qualified by a separator character. For example,
* "this:name:is:qualified" returns "qualified" if using a ':' separator.
*
* @param qualifiedName the qualified name
* @param separator the separator
*/
public static String unqualify(String qualifiedName, char separator) {
return qualifiedName.substring(qualifiedName.lastIndexOf(separator) + 1);
}
/**
* Capitalize a String, changing the first letter to
* upper case as per {@link Character#toUpperCase(char)}.
* No other letters are changed.
*
* @param str the String to capitalize, may be null
* @return the capitalized String, null if null
*/
public static String capitalize(String str) {
return changeFirstCharacterCase(str, true);
}
/**
* Uncapitalize a String, changing the first letter to
* lower case as per {@link Character#toLowerCase(char)}.
* No other letters are changed.
*
* @param str the String to uncapitalize, may be null
* @return the uncapitalized String, null if null
*/
public static String uncapitalize(String str) {
return changeFirstCharacterCase(str, false);
}
private static String changeFirstCharacterCase(String str, boolean capitalize) {
if (str == null || str.length() == 0) {
return str;
}
StringBuilder sb = new StringBuilder(str.length());
if (capitalize) {
sb.append(Character.toUpperCase(str.charAt(0)));
} else {
sb.append(Character.toLowerCase(str.charAt(0)));
}
sb.append(str.substring(1));
return sb.toString();
}
public static final ImmutableSet INVALID_FILENAME_CHARS = ImmutableSet.of('\\', '/', '*', '?', '"', '<', '>', '|', ' ', ',');
public static boolean validFileName(String fileName) {
for (int i = 0; i < fileName.length(); i++) {
char c = fileName.charAt(i);
if (INVALID_FILENAME_CHARS.contains(c)) {
return false;
}
}
return true;
}
public static boolean validFileNameExcludingAstrix(String fileName) {
for (int i = 0; i < fileName.length(); i++) {
char c = fileName.charAt(i);
if (c != '*' && INVALID_FILENAME_CHARS.contains(c)) {
return false;
}
}
return true;
}
/**
* Extract the filename from the given path,
* e.g. "mypath/myfile.txt" -> "myfile.txt".
*
* @param path the file path (may be null)
* @return the extracted filename, or null if none
*/
public static String getFilename(String path) {
if (path == null) {
return null;
}
int separatorIndex = path.lastIndexOf(FOLDER_SEPARATOR);
return (separatorIndex != -1 ? path.substring(separatorIndex + 1) : path);
}
/**
* Extract the filename extension from the given path,
* e.g. "mypath/myfile.txt" -> "txt".
*
* @param path the file path (may be null)
* @return the extracted filename extension, or null if none
*/
public static String getFilenameExtension(String path) {
if (path == null) {
return null;
}
int sepIndex = path.lastIndexOf(EXTENSION_SEPARATOR);
return (sepIndex != -1 ? path.substring(sepIndex + 1) : null);
}
/**
* Strip the filename extension from the given path,
* e.g. "mypath/myfile.txt" -> "mypath/myfile".
*
* @param path the file path (may be null)
* @return the path with stripped filename extension,
* or null if none
*/
public static String stripFilenameExtension(String path) {
if (path == null) {
return null;
}
int sepIndex = path.lastIndexOf(EXTENSION_SEPARATOR);
return (sepIndex != -1 ? path.substring(0, sepIndex) : path);
}
/**
* Apply the given relative path to the given path,
* assuming standard Java folder separation (i.e. "/" separators);
*
* @param path the path to start from (usually a full file path)
* @param relativePath the relative path to apply
* (relative to the full file path above)
* @return the full file path that results from applying the relative path
*/
public static String applyRelativePath(String path, String relativePath) {
int separatorIndex = path.lastIndexOf(FOLDER_SEPARATOR);
if (separatorIndex != -1) {
String newPath = path.substring(0, separatorIndex);
if (!relativePath.startsWith(FOLDER_SEPARATOR)) {
newPath += FOLDER_SEPARATOR;
}
return newPath + relativePath;
} else {
return relativePath;
}
}
/**
* Normalize the path by suppressing sequences like "path/.." and
* inner simple dots.
* The result is convenient for path comparison. For other uses,
* notice that Windows separators ("\") are replaced by simple slashes.
*
* @param path the original path
* @return the normalized path
*/
public static String cleanPath(String path) {
if (path == null) {
return null;
}
String pathToUse = replace(path, WINDOWS_FOLDER_SEPARATOR, FOLDER_SEPARATOR);
// Strip prefix from path to analyze, to not treat it as part of the
// first path element. This is necessary to correctly parse paths like
// "file:core/../core/io/Resource.class", where the ".." should just
// strip the first "core" directory while keeping the "file:" prefix.
int prefixIndex = pathToUse.indexOf(":");
String prefix = "";
if (prefixIndex != -1) {
prefix = pathToUse.substring(0, prefixIndex + 1);
pathToUse = pathToUse.substring(prefixIndex + 1);
}
if (pathToUse.startsWith(FOLDER_SEPARATOR)) {
prefix = prefix + FOLDER_SEPARATOR;
pathToUse = pathToUse.substring(1);
}
String[] pathArray = delimitedListToStringArray(pathToUse, FOLDER_SEPARATOR);
List pathElements = new LinkedList();
int tops = 0;
for (int i = pathArray.length - 1; i >= 0; i--) {
String element = pathArray[i];
if (CURRENT_PATH.equals(element)) {
// Points to current directory - drop it.
} else if (TOP_PATH.equals(element)) {
// Registering top path found.
tops++;
} else {
if (tops > 0) {
// Merging path element with element corresponding to top path.
tops--;
} else {
// Normal path element found.
pathElements.add(0, element);
}
}
}
// Remaining top paths need to be retained.
for (int i = 0; i < tops; i++) {
pathElements.add(0, TOP_PATH);
}
return prefix + collectionToDelimitedString(pathElements, FOLDER_SEPARATOR);
}
/**
* Compare two paths after normalization of them.
*
* @param path1 first path for comparison
* @param path2 second path for comparison
* @return whether the two paths are equivalent after normalization
*/
public static boolean pathEquals(String path1, String path2) {
return cleanPath(path1).equals(cleanPath(path2));
}
/**
* Parse the given localeString into a {@link Locale}.
* This is the inverse operation of {@link Locale#toString Locale's toString}.
*
* @param localeString the locale string, following Locale's
* toString() format ("en", "en_UK", etc);
* also accepts spaces as separators, as an alternative to underscores
* @return a corresponding Locale instance
*/
public static Locale parseLocaleString(String localeString) {
String[] parts = tokenizeToStringArray(localeString, "_ ", false, false);
String language = (parts.length != 0 ? parts[0] : "");
String country = (parts.length > 1 ? parts[1] : "");
String variant = "";
if (parts.length >= 2) {
// There is definitely a variant, and it is everything after the country
// code sans the separator between the country code and the variant.
int endIndexOfCountryCode = localeString.indexOf(country) + country.length();
// Strip off any leading '_' and whitespace, what's left is the variant.
variant = trimLeadingWhitespace(localeString.substring(endIndexOfCountryCode));
if (variant.startsWith("_")) {
variant = trimLeadingCharacter(variant, '_');
}
}
return (language.length() > 0 ? new Locale(language, country, variant) : null);
}
/**
* Determine the RFC 3066 compliant language tag,
* as used for the HTTP "Accept-Language" header.
*
* @param locale the Locale to transform to a language tag
* @return the RFC 3066 compliant language tag as String
*/
public static String toLanguageTag(Locale locale) {
return locale.getLanguage() + (hasText(locale.getCountry()) ? "-" + locale.getCountry() : "");
}
//---------------------------------------------------------------------
// Convenience methods for working with String arrays
//---------------------------------------------------------------------
/**
* Append the given String to the given String array, returning a new array
* consisting of the input array contents plus the given String.
*
* @param array the array to append to (can be null)
* @param str the String to append
* @return the new array (never null)
*/
public static String[] addStringToArray(String[] array, String str) {
if (isEmpty(array)) {
return new String[]{str};
}
String[] newArr = new String[array.length + 1];
System.arraycopy(array, 0, newArr, 0, array.length);
newArr[array.length] = str;
return newArr;
}
/**
* Concatenate the given String arrays into one,
* with overlapping array elements included twice.
*
The order of elements in the original arrays is preserved.
*
* @param array1 the first array (can be null)
* @param array2 the second array (can be null)
* @return the new array (null if both given arrays were null)
*/
public static String[] concatenateStringArrays(String[] array1, String[] array2) {
if (isEmpty(array1)) {
return array2;
}
if (isEmpty(array2)) {
return array1;
}
String[] newArr = new String[array1.length + array2.length];
System.arraycopy(array1, 0, newArr, 0, array1.length);
System.arraycopy(array2, 0, newArr, array1.length, array2.length);
return newArr;
}
/**
* Merge the given String arrays into one, with overlapping
* array elements only included once.
*
The order of elements in the original arrays is preserved
* (with the exception of overlapping elements, which are only
* included on their first occurence).
*
* @param array1 the first array (can be null)
* @param array2 the second array (can be null)
* @return the new array (null if both given arrays were null)
*/
public static String[] mergeStringArrays(String[] array1, String[] array2) {
if (isEmpty(array1)) {
return array2;
}
if (isEmpty(array2)) {
return array1;
}
List result = new ArrayList();
result.addAll(Arrays.asList(array1));
for (String str : array2) {
if (!result.contains(str)) {
result.add(str);
}
}
return toStringArray(result);
}
/**
* Turn given source String array into sorted array.
*
* @param array the source array
* @return the sorted array (never null)
*/
public static String[] sortStringArray(String[] array) {
if (isEmpty(array)) {
return new String[0];
}
Arrays.sort(array);
return array;
}
/**
* Copy the given Collection into a String array.
* The Collection must contain String elements only.
*
* @param collection the Collection to copy
* @return the String array (null if the passed-in
* Collection was null)
*/
public static String[] toStringArray(Collection collection) {
if (collection == null) {
return null;
}
return collection.toArray(new String[collection.size()]);
}
/**
* Copy the given Enumeration into a String array.
* The Enumeration must contain String elements only.
*
* @param enumeration the Enumeration to copy
* @return the String array (null if the passed-in
* Enumeration was null)
*/
public static String[] toStringArray(Enumeration enumeration) {
if (enumeration == null) {
return null;
}
List list = Collections.list(enumeration);
return list.toArray(new String[list.size()]);
}
/**
* Trim the elements of the given String array,
* calling String.trim() on each of them.
*
* @param array the original String array
* @return the resulting array (of the same size) with trimmed elements
*/
public static String[] trimArrayElements(String[] array) {
if (isEmpty(array)) {
return new String[0];
}
String[] result = new String[array.length];
for (int i = 0; i < array.length; i++) {
String element = array[i];
result[i] = (element != null ? element.trim() : null);
}
return result;
}
/**
* Remove duplicate Strings from the given array.
* Also sorts the array, as it uses a TreeSet.
*
* @param array the String array
* @return an array without duplicates, in natural sort order
*/
public static String[] removeDuplicateStrings(String[] array) {
if (isEmpty(array)) {
return array;
}
Set set = new TreeSet();
set.addAll(Arrays.asList(array));
return toStringArray(set);
}
public static Set splitStringByCommaToSet(final String s) {
return splitStringToSet(s, ',');
}
public static String[] splitStringByCommaToArray(final String s) {
return splitStringToArray(s, ',');
}
public static Set splitStringToSet(final String s, final char c) {
final char[] chars = s.toCharArray();
int count = 1;
for (final char x : chars) {
if (x == c) {
count++;
}
}
final THashSet result = new THashSet(count);
final int len = chars.length;
int start = 0; // starting index in chars of the current substring.
int pos = 0; // current index in chars.
int i = 0; // number of the current substring.
for (; pos < len; pos++) {
if (chars[pos] == c) {
int size = pos - start;
if (size > 0) { // only add non empty strings
result.add(new String(chars, start, size));
}
start = pos + 1;
}
}
int size = pos - start;
if (size > 0) {
result.add(new String(chars, start, size));
}
return result;
}
public static String[] splitStringToArray(final CharSequence s, final char c) {
if (s.length() == 0) {
return Strings.EMPTY_ARRAY;
}
int count = 1;
for (int i = 0; i < s.length(); i++) {
if (s.charAt(i) == c) {
count++;
}
}
final String[] result = new String[count];
final StringBuilder builder = new StringBuilder();
int res = 0;
for (int i = 0; i < s.length(); i++) {
if (s.charAt(i) == c) {
if (builder.length() > 0) {
result[res++] = builder.toString();
builder.setLength(0);
}
} else {
builder.append(s.charAt(i));
}
}
if (builder.length() > 0) {
result[res++] = builder.toString();
}
if (res != count) {
// we have empty strings, copy over to a new array
String[] result1 = new String[res];
System.arraycopy(result, 0, result1, 0, res);
return result1;
}
return result;
}
/**
* Split a String at the first occurrence of the delimiter.
* Does not include the delimiter in the result.
*
* @param toSplit the string to split
* @param delimiter to split the string up with
* @return a two element array with index 0 being before the delimiter, and
* index 1 being after the delimiter (neither element includes the delimiter);
* or null if the delimiter wasn't found in the given input String
*/
public static String[] split(String toSplit, String delimiter) {
if (!hasLength(toSplit) || !hasLength(delimiter)) {
return null;
}
int offset = toSplit.indexOf(delimiter);
if (offset < 0) {
return null;
}
String beforeDelimiter = toSplit.substring(0, offset);
String afterDelimiter = toSplit.substring(offset + delimiter.length());
return new String[]{beforeDelimiter, afterDelimiter};
}
/**
* Take an array Strings and split each element based on the given delimiter.
* A Properties instance is then generated, with the left of the
* delimiter providing the key, and the right of the delimiter providing the value.
* Will trim both the key and value before adding them to the
* Properties instance.
*
* @param array the array to process
* @param delimiter to split each element using (typically the equals symbol)
* @return a Properties instance representing the array contents,
* or null if the array to process was null or empty
*/
public static Properties splitArrayElementsIntoProperties(String[] array, String delimiter) {
return splitArrayElementsIntoProperties(array, delimiter, null);
}
/**
* Take an array Strings and split each element based on the given delimiter.
* A Properties instance is then generated, with the left of the
* delimiter providing the key, and the right of the delimiter providing the value.
*
Will trim both the key and value before adding them to the
* Properties instance.
*
* @param array the array to process
* @param delimiter to split each element using (typically the equals symbol)
* @param charsToDelete one or more characters to remove from each element
* prior to attempting the split operation (typically the quotation mark
* symbol), or null if no removal should occur
* @return a Properties instance representing the array contents,
* or null if the array to process was null or empty
*/
public static Properties splitArrayElementsIntoProperties(
String[] array, String delimiter, String charsToDelete) {
if (isEmpty(array)) {
return null;
}
Properties result = new Properties();
for (String element : array) {
if (charsToDelete != null) {
element = deleteAny(element, charsToDelete);
}
String[] splittedElement = split(element, delimiter);
if (splittedElement == null) {
continue;
}
result.setProperty(splittedElement[0].trim(), splittedElement[1].trim());
}
return result;
}
/**
* Tokenize the given String into a String array via a StringTokenizer.
* Trims tokens and omits empty tokens.
*
The given delimiters string is supposed to consist of any number of
* delimiter characters. Each of those characters can be used to separate
* tokens. A delimiter is always a single character; for multi-character
* delimiters, consider using delimitedListToStringArray
*
* @param str the String to tokenize
* @param delimiters the delimiter characters, assembled as String
* (each of those characters is individually considered as delimiter).
* @return an array of the tokens
* @see java.util.StringTokenizer
* @see java.lang.String#trim()
* @see #delimitedListToStringArray
*/
public static String[] tokenizeToStringArray(String str, String delimiters) {
return tokenizeToStringArray(str, delimiters, true, true);
}
/**
* Tokenize the given String into a String array via a StringTokenizer.
*
The given delimiters string is supposed to consist of any number of
* delimiter characters. Each of those characters can be used to separate
* tokens. A delimiter is always a single character; for multi-character
* delimiters, consider using delimitedListToStringArray
*
* @param str the String to tokenize
* @param delimiters the delimiter characters, assembled as String
* (each of those characters is individually considered as delimiter)
* @param trimTokens trim the tokens via String's trim
* @param ignoreEmptyTokens omit empty tokens from the result array
* (only applies to tokens that are empty after trimming; StringTokenizer
* will not consider subsequent delimiters as token in the first place).
* @return an array of the tokens (null if the input String
* was null)
* @see java.util.StringTokenizer
* @see java.lang.String#trim()
* @see #delimitedListToStringArray
*/
public static String[] tokenizeToStringArray(
String str, String delimiters, boolean trimTokens, boolean ignoreEmptyTokens) {
if (str == null) {
return null;
}
StringTokenizer st = new StringTokenizer(str, delimiters);
List tokens = new ArrayList();
while (st.hasMoreTokens()) {
String token = st.nextToken();
if (trimTokens) {
token = token.trim();
}
if (!ignoreEmptyTokens || token.length() > 0) {
tokens.add(token);
}
}
return toStringArray(tokens);
}
/**
* Take a String which is a delimited list and convert it to a String array.
* A single delimiter can consists of more than one character: It will still
* be considered as single delimiter string, rather than as bunch of potential
* delimiter characters - in contrast to tokenizeToStringArray.
*
* @param str the input String
* @param delimiter the delimiter between elements (this is a single delimiter,
* rather than a bunch individual delimiter characters)
* @return an array of the tokens in the list
* @see #tokenizeToStringArray
*/
public static String[] delimitedListToStringArray(String str, String delimiter) {
return delimitedListToStringArray(str, delimiter, null);
}
/**
* Take a String which is a delimited list and convert it to a String array.
*
A single delimiter can consists of more than one character: It will still
* be considered as single delimiter string, rather than as bunch of potential
* delimiter characters - in contrast to tokenizeToStringArray.
*
* @param str the input String
* @param delimiter the delimiter between elements (this is a single delimiter,
* rather than a bunch individual delimiter characters)
* @param charsToDelete a set of characters to delete. Useful for deleting unwanted
* line breaks: e.g. "\r\n\f" will delete all new lines and line feeds in a String.
* @return an array of the tokens in the list
* @see #tokenizeToStringArray
*/
public static String[] delimitedListToStringArray(String str, String delimiter, String charsToDelete) {
if (str == null) {
return new String[0];
}
if (delimiter == null) {
return new String[]{str};
}
List result = new ArrayList();
if ("".equals(delimiter)) {
for (int i = 0; i < str.length(); i++) {
result.add(deleteAny(str.substring(i, i + 1), charsToDelete));
}
} else {
int pos = 0;
int delPos;
while ((delPos = str.indexOf(delimiter, pos)) != -1) {
result.add(deleteAny(str.substring(pos, delPos), charsToDelete));
pos = delPos + delimiter.length();
}
if (str.length() > 0 && pos <= str.length()) {
// Add rest of String, but not in case of empty input.
result.add(deleteAny(str.substring(pos), charsToDelete));
}
}
return toStringArray(result);
}
/**
* Convert a CSV list into an array of Strings.
*
* @param str the input String
* @return an array of Strings, or the empty array in case of empty input
*/
public static String[] commaDelimitedListToStringArray(String str) {
return delimitedListToStringArray(str, ",");
}
/**
* Convenience method to convert a CSV string list to a set.
* Note that this will suppress duplicates.
*
* @param str the input String
* @return a Set of String entries in the list
*/
public static Set commaDelimitedListToSet(String str) {
Set set = new TreeSet();
String[] tokens = commaDelimitedListToStringArray(str);
set.addAll(Arrays.asList(tokens));
return set;
}
/**
* Convenience method to return a Collection as a delimited (e.g. CSV)
* String. E.g. useful for toString() implementations.
*
* @param coll the Collection to display
* @param delim the delimiter to use (probably a ",")
* @param prefix the String to start each element with
* @param suffix the String to end each element with
* @return the delimited String
*/
public static String collectionToDelimitedString(Iterable coll, String delim, String prefix, String suffix) {
return collectionToDelimitedString(coll, delim, prefix, suffix, new StringBuilder());
}
public static String collectionToDelimitedString(Iterable coll, String delim, String prefix, String suffix, StringBuilder sb) {
if (Iterables.isEmpty(coll)) {
return "";
}
Iterator it = coll.iterator();
while (it.hasNext()) {
sb.append(prefix).append(it.next()).append(suffix);
if (it.hasNext()) {
sb.append(delim);
}
}
return sb.toString();
}
/**
* Convenience method to return a Collection as a delimited (e.g. CSV)
* String. E.g. useful for toString() implementations.
*
* @param coll the Collection to display
* @param delim the delimiter to use (probably a ",")
* @return the delimited String
*/
public static String collectionToDelimitedString(Iterable coll, String delim) {
return collectionToDelimitedString(coll, delim, "", "");
}
/**
* Convenience method to return a Collection as a CSV String.
* E.g. useful for toString() implementations.
*
* @param coll the Collection to display
* @return the delimited String
*/
public static String collectionToCommaDelimitedString(Iterable coll) {
return collectionToDelimitedString(coll, ",");
}
/**
* Convenience method to return a String array as a delimited (e.g. CSV)
* String. E.g. useful for toString() implementations.
*
* @param arr the array to display
* @param delim the delimiter to use (probably a ",")
* @return the delimited String
*/
public static String arrayToDelimitedString(Object[] arr, String delim) {
return arrayToDelimitedString(arr, delim, new StringBuilder());
}
public static String arrayToDelimitedString(Object[] arr, String delim, StringBuilder sb) {
if (isEmpty(arr)) {
return "";
}
for (int i = 0; i < arr.length; i++) {
if (i > 0) {
sb.append(delim);
}
sb.append(arr[i]);
}
return sb.toString();
}
/**
* Convenience method to return a String array as a CSV String.
* E.g. useful for toString() implementations.
*
* @param arr the array to display
* @return the delimited String
*/
public static String arrayToCommaDelimitedString(Object[] arr) {
return arrayToDelimitedString(arr, ",");
}
/**
* Format the double value with a single decimal points, trimming trailing '.0'.
*/
public static String format1Decimals(double value, String suffix) {
String p = String.valueOf(value);
int ix = p.indexOf('.') + 1;
int ex = p.indexOf('E');
char fraction = p.charAt(ix);
if (fraction == '0') {
if (ex != -1) {
return p.substring(0, ix - 1) + p.substring(ex) + suffix;
} else {
return p.substring(0, ix - 1) + suffix;
}
} else {
if (ex != -1) {
return p.substring(0, ix) + fraction + p.substring(ex) + suffix;
} else {
return p.substring(0, ix) + fraction + suffix;
}
}
}
public static String toCamelCase(String value) {
return toCamelCase(value, null);
}
public static String toCamelCase(String value, StringBuilder sb) {
boolean changed = false;
for (int i = 0; i < value.length(); i++) {
char c = value.charAt(i);
if (c == '_') {
if (!changed) {
if (sb != null) {
sb.setLength(0);
} else {
sb = new StringBuilder();
}
// copy it over here
for (int j = 0; j < i; j++) {
sb.append(value.charAt(j));
}
changed = true;
}
sb.append(Character.toUpperCase(value.charAt(++i)));
} else {
if (changed) {
sb.append(c);
}
}
}
if (!changed) {
return value;
}
return sb.toString();
}
public static String toUnderscoreCase(String value) {
return toUnderscoreCase(value, null);
}
public static String toUnderscoreCase(String value, StringBuilder sb) {
boolean changed = false;
for (int i = 0; i < value.length(); i++) {
char c = value.charAt(i);
if (Character.isUpperCase(c)) {
if (!changed) {
if (sb != null) {
sb.setLength(0);
} else {
sb = new StringBuilder();
}
// copy it over here
for (int j = 0; j < i; j++) {
sb.append(value.charAt(j));
}
changed = true;
if (i == 0) {
sb.append(Character.toLowerCase(c));
} else {
sb.append('_');
sb.append(Character.toLowerCase(c));
}
} else {
sb.append('_');
sb.append(Character.toLowerCase(c));
}
} else {
if (changed) {
sb.append(c);
}
}
}
if (!changed) {
return value;
}
return sb.toString();
}
/**
* Determine whether the given array is empty:
* i.e. null or of zero length.
*
* @param array the array to check
*/
private static boolean isEmpty(Object[] array) {
return (array == null || array.length == 0);
}
/**
* Return true if the supplied Collection is null
* or empty. Otherwise, return false.
*
* @param collection the Collection to check
* @return whether the given Collection is empty
*/
private static boolean isEmpty(Collection collection) {
return (collection == null || collection.isEmpty());
}
private Strings() {
}
public static byte[] toUTF8Bytes(CharSequence charSequence) {
return toUTF8Bytes(charSequence, new BytesRef());
}
public static byte[] toUTF8Bytes(CharSequence charSequence, BytesRef spare) {
UnicodeUtil.UTF16toUTF8(charSequence, 0, charSequence.length(), spare);
final byte[] bytes = new byte[spare.length];
System.arraycopy(spare.bytes, spare.offset, bytes, 0, bytes.length);
return bytes;
}
}