de.tudarmstadt.ukp.jwktl.parser.ru.wikokit.base.wikipedia.util
Class StringUtil

java.lang.Object
  extended by de.tudarmstadt.ukp.jwktl.parser.ru.wikokit.base.wikipedia.util.StringUtil

public class StringUtil
extends Object


Method Summary
static List<String> addOR(List<String> a, List<String> b)
          Adds two lists to one, i.e. creates the list of unique strings (case insensitive).
static String[] addORCaseSensitive(String[] a, String[] b)
          Adds two arrays to one, i.e. creates the array of unique strings (case sensitive).
static boolean containsIgnoreCase(String[] ar, String wanted)
          Returns true if array 'ar' contains string 'wanted', ignore case.
static StringBuffer escapeCharDollarAndBackslash(String text)
          Doubles slashes before dollar sign "$" and backslash "\", skip two slashes "\\".
static String escapeChars(String text)
          Doubles slashes before quotes.
static String getTextAfterFirstColumn(String s)
           
static String getTextAfterFirstSpace(String s)
           
static String getTextAfterFirstVerticalPipe(String s)
           
static String getTextBeforeFirstAndSecondColumns(String s)
           
static String getTextBeforeFirstColumn(String s)
           
static String getTextBeforeFirstVerticalPipe(String s)
           
static String getTextTillSpaceOrPuctuationMark(int pos, String s)
          Gets text from position 'pos' till the space or punctuation mark.
static List<String> getUnique(List<String> l)
          Gets list of unique strings (case insensitive).
static String[] intersect(String[] list1, String[] list2)
          Returns intersections of two list.
static boolean isInterWiki(String title)
          Returns true if third character is column, e.g.
static String join(String token, int[] source)
           
static String join(String token, String[] strings)
           
static String replaceSpecialChars(String str)
          Replace special characters (e.g.
static String spaceToUnderscore(String text)
          Substitutes spaces by underscore character
static String[] split(String token, String s)
           
static String[] trim(String[] s)
          Trims each element of array.
static String underscoreToSpace(String text)
          Substitutes all underscores by space character
static String UpperFirstLetter(String s)
          Converts first letter to upper-case (capitalization - good for WP, bad for Wiktionary).
static String UpperFirstLowerSecondLetter(String s)
          Converts two letters word: first letter to Upper, second letter to Lower case.
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Method Detail

join

public static String join(String token,
                          String[] strings)

join

public static String join(String token,
                          int[] source)

split

public static String[] split(String token,
                             String s)

escapeChars

public static String escapeChars(String text)
Doubles slashes before quotes.


escapeCharDollarAndBackslash

public static StringBuffer escapeCharDollarAndBackslash(String text)
Doubles slashes before dollar sign "$" and backslash "\", skip two slashes "\\". slash1 (true if prev prev is "\") slash2 (previous) slash3 (current character)
$ -> \\$ if !slash1 && !slash2 then + "\\"
\\ -> \\ if slash1 && slash2 then skip
\\$ -> \\$


spaceToUnderscore

public static String spaceToUnderscore(String text)
Substitutes spaces by underscore character


underscoreToSpace

public static String underscoreToSpace(String text)
Substitutes all underscores by space character


getUnique

public static List<String> getUnique(List<String> l)
Gets list of unique strings (case insensitive).


addOR

public static List<String> addOR(List<String> a,
                                 List<String> b)
Adds two lists to one, i.e. creates the list of unique strings (case insensitive).


addORCaseSensitive

public static String[] addORCaseSensitive(String[] a,
                                          String[] b)
Adds two arrays to one, i.e. creates the array of unique strings (case sensitive).


containsIgnoreCase

public static boolean containsIgnoreCase(String[] ar,
                                         String wanted)
Returns true if array 'ar' contains string 'wanted', ignore case.


intersect

public static String[] intersect(String[] list1,
                                 String[] list2)
Returns intersections of two list. Return null if input String[] is null.


getTextBeforeFirstColumn

public static String getTextBeforeFirstColumn(String s)

getTextBeforeFirstVerticalPipe

public static String getTextBeforeFirstVerticalPipe(String s)

getTextAfterFirstColumn

public static String getTextAfterFirstColumn(String s)

getTextAfterFirstVerticalPipe

public static String getTextAfterFirstVerticalPipe(String s)

getTextAfterFirstSpace

public static String getTextAfterFirstSpace(String s)

getTextBeforeFirstAndSecondColumns

public static String getTextBeforeFirstAndSecondColumns(String s)

getTextTillSpaceOrPuctuationMark

public static String getTextTillSpaceOrPuctuationMark(int pos,
                                                      String s)
Gets text from position 'pos' till the space or punctuation mark.


isInterWiki

public static boolean isInterWiki(String title)
Returns true if third character is column, e.g. "ru:test"


UpperFirstLowerSecondLetter

public static String UpperFirstLowerSecondLetter(String s)
Converts two letters word: first letter to Upper, second letter to Lower case.


UpperFirstLetter

public static String UpperFirstLetter(String s)
Converts first letter to upper-case (capitalization - good for WP, bad for Wiktionary).


trim

public static String[] trim(String[] s)
Trims each element of array.


replaceSpecialChars

public static String replaceSpecialChars(String str)
Replace special characters (e.g.  ,   by spaces).



Copyright © 2011-2013 Ubiquitous Knowledge Processing (UKP) Lab. All Rights Reserved.