org.cip4.jdflib.util

Class StringUtil

java.lang.Object

org.cip4.jdflib.util.StringUtil

public class StringUtil
extends java.lang.Object

collection of static string utilities

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	StringUtil.StringReplacer class that provides additional functionality for replacing string

Field Summary

Fields

Modifier and Type	Field and Description
static java.lang.String	m_URIEscape Deprecated. use UrlUtil.m_URIEscape
static java.lang.String	UTF8

Method Summary

Modifier and Type	Method and Description
static java.lang.String	addToken(java.lang.String strWork, java.lang.String delim, java.lang.String newToken) replace a token in a string
static int	compare(java.lang.String c0, java.lang.String c1, boolean ignoreCase) static implementation of compare for any comparable object that gracefully handles null null is always the smallest
static int	compareTo(double d1, double d2) return -1 if d1 < d2 , 0 if d1==d2 ; +1 if d1>d2 are within a range of epsilon or close enough to be serialized identically
static java.lang.String	concat(java.lang.String s1, java.lang.String s2, java.lang.String delim)
static void	concatStrings(VString vS, java.lang.String appendString) add the string appendString to all Strings in VString vs
static java.lang.String	createString(java.io.InputStream is) create a string from an input stream
static boolean	equals(java.lang.String a, java.lang.String b) return true if a equals b or both are null or ""
static boolean	equals(java.lang.String attribute, java.lang.String attribute2, double delta) simple comparison of strings with some heuristics
static byte[]	escape(byte[] a_toEscape, java.lang.String strCharSet, java.lang.String strEscapeChar, int iRadix, int iEscapeLen, int iEscapeBelow, int iEscapeAbove) escape a string by prepending escapeChar and a numerical representation of the string.
static java.lang.String	escape(java.lang.String strToEscape, java.lang.String strCharSet, java.lang.String strEscapeChar, int iRadix, int iEscapeLen, int iEscapeBelow, int iEscapeAbove) escape a string by prepending escapeChar and a numerical representation of the string.
static java.lang.String	extension(java.lang.String pathName) Deprecated. use URLUtil.extension
static java.lang.String	fileToUrl(java.io.File f, boolean b) Deprecated. use UrlUtil.fileToUrl(f, b);
static int	find_last_not_of(java.lang.String strWork, java.lang.String strNotList) find the last character in strwork that is not in strNotList
static java.lang.String	formatDouble(double d) returns a formatted double.
static java.lang.String	formatDouble(double value, int precision) returns a formatted double.
static java.lang.String	formatInteger(int i) returns a formatted integer, replaces string constants with according int constants
static java.lang.String	formatLong(long i) returns a formatted integer, replaces string constants with according int constants
static java.nio.charset.Charset	getCharset(java.lang.String csName)
static org.cip4.jdflib.util.StringUtil.EDataType	getDataType(java.lang.String s)
static java.lang.String	getDefaultNull(java.lang.String s, java.lang.String def) return null if s==null or s==def, else s used e.g.
static int	getDistance(java.lang.String s1, java.lang.String s2, boolean normalize, boolean ignoreCase, boolean ignoreEmpty) return the Levenschtein ditance where null is treated as ""
static int	getDistance(java.lang.String s1, java.lang.String s2, boolean normalize, boolean ignoreCase, boolean ignoreEmpty, boolean reduceSubstring)
static java.util.Vector<org.apache.commons.lang.enums.ValuedEnum>	getEnumsVector(java.lang.Class<? extends org.apache.commons.lang.enums.ValuedEnum> e) Deprecated. use @se EnumUtil.getEnumsVector
static byte[]	getHexBinaryBytes(byte[] unicodeArray) Decode a HexBinary encoded byte array back to Unicode
static VString	getNamesVector(java.lang.Class<? extends org.apache.commons.lang.enums.ValuedEnum> e) Deprecated. use @see EnumUtil.getNamesVector
static java.lang.String	getNonEmpty(java.lang.String s) return null if s==null or s=="", else s used e.g.
static java.lang.String	getRandomString() returns a random string for testing fun stuff - similar to unix fortune but biased towards monty python or the hitchhikers guide to the galaxy
static byte[]	getRawBytes(java.lang.String strUnicode) get the raw bytes specified in strUnicode, bypassing all transcoders any character values above 255 is truncated (c=c&0xff)
static java.lang.String	getRelativePath(java.io.File f, java.io.File fCWD) Deprecated. use URLUtil.getRelativePath(f, fCWD);
static java.lang.String	getRelativeURL(java.io.File f, java.io.File baseDir) Deprecated. use getRelativeURL(File f, File fCWD, boolean bEscape128)
static java.lang.String	getRelativeURL(java.io.File f, java.io.File baseDir, boolean bEscape128) Deprecated. use URLUtil.getRelativeURL
static byte[]	getUTF8Bytes(java.lang.String strUnicode) return the UTF8 String strUnicode as Unicode byte array
static java.lang.String	getUTF8String(byte[] utf8) get the unicode string representing the UTF8 representation of the byte buffer fall back on default encoding in case someone accidentally sends in non utf-8
static boolean	hasContent(java.lang.String s) return false if s==null or s has only whotespace
static boolean	hasToken(java.lang.String[] strWork, java.lang.String token, int iSkip) check whether a vector of Strings contains a given token
static boolean	hasToken(java.lang.String strWork, java.lang.String token, java.lang.String delim) Deprecated. use the 4 parameter version
static boolean	hasToken(java.lang.String strWork, java.lang.String token, java.lang.String delim, int iSkip) check whether a String contains a given token
static int	indexOfToken(java.lang.String strWork, java.lang.String token, java.lang.String delim, int start) index of a token in a string
static boolean	isBoolean(java.lang.String strWork) checks whether a string matches the boolean values "true" or "false"
static boolean	isDate(java.lang.String strWork) checks whether a string matches the boolean values "true" or "false"
static boolean	isEmpty(java.util.Collection<java.lang.String> v) are we null or empty or contain only an empty JDFAttributeMap
static boolean	isEmpty(java.lang.String s) return true if s==null or s==""
static boolean	isEqual(double d1, double d2) return true if d1 and d2 are within a range of epsilon or close enough to be serialized identically
static boolean	isEqual(double d1, double d2, double delta) return true if d1 and d2 are within a range of epsilon or close enough to be serialized identically
static boolean	isID(java.lang.String strWork) checks whether a string is an ID
static boolean	isInteger(java.lang.String str) checks whether str reprents an integer
static boolean	isLong(java.lang.String str) checks whether str reprents an integer
static boolean	isNMTOKEN(java.lang.String strWork) checks whether a string is a NMTOKEN
static boolean	isNMTOKENS(java.lang.String strWork) Deprecated. 060309 use isNMTOKENS(strWork,false)
static boolean	isNMTOKENS(java.lang.String strWork, boolean bID) checks whether a string is a NMTOKENS list
static boolean	isNumber(java.lang.String str) checks whether a string is a number
static boolean	isNumberList(java.lang.String strWork) checks whether a string matches the boolean values "true" or "false"
static boolean	isUNC(java.lang.String pathName) Deprecated. use URLUtil.isUNC(pathName)
static boolean	isWindowsLocalPath(java.lang.String pathName) Deprecated. use UrlUtil.isWindowsLocalPath(pathName);
static java.lang.String	leftStr(java.lang.String strWork, int n) n > 0 substring(0, n) take the first n chars (leftmost) n < 0 substring(0, s.length()+n) take the string and cut n chars on the right example: string = "abcdefgh" string.leftStr( 2) = "ab" string.leftStr(-3) = "abcde"
static int	length(java.lang.String s1)
static boolean	matches(java.lang.String str, java.lang.String regExp) match a regular expression using String.matches(), but also catch exceptions does NOT handle simplified regexp.
static boolean	matchesIgnoreCase(java.lang.String str, java.lang.String regExp) match a regular expression using ignoring cases using String.matches(), but also catch exceptions and handle simplified regexp.
static boolean	matchesIgnoreCase(java.lang.String str, java.lang.String regExp, boolean alwaysSimple) match a regular expression using ignoring cases using String.matches(), but also catch exceptions and handle simplified regexp.
static boolean	matchesSimple(java.lang.String str, java.lang.String regExp) match a regular expression using String.matches(), but also catch exceptions and handle simplified regexp.
static boolean	matchesSimple(java.lang.String str, java.lang.String regExp, boolean alwaysSimple) match a regular expression using String.matches(), but also catch exceptions and handle simplified regexp.
static java.lang.String	mime(java.lang.String strWork) Deprecated. use MimeUtil.getMimeTypeFromExt(strWork);
static java.lang.String	newExtension(java.lang.String strWork, java.lang.String newExt) Deprecated. use UrlUtil.newExtension
static java.lang.String	normalize(java.lang.String strWork) normalize a string by stripping and converting any internal whitespace to a single blank
static java.lang.String	normalize(java.lang.String strWork, boolean toLower) normalize a string by stripping and converting any internal whitespace to a single blank
static java.lang.String	normalize(java.lang.String strWork, boolean toLower, java.lang.String replace) normalize a string by stripping and converting any internal whitespace to the value of replace
static int	numSubstrings(java.lang.String strWork, java.lang.String subString) counts the number of occurrences of subString in String the total number of occurrences is counted, e.g "aaa" contains "aa" twice
static boolean	parseBoolean(java.lang.String s, boolean def) parses a string to boolean and catches any format exception "1" and "0" are treated as true and false respectively
static double	parseDouble(java.lang.String s, double def) parses a string to double and catches any format exception
static int	parseInt(java.lang.String s, int def) parses a string to integer and catches any format exception
static long	parseLong(java.lang.String s, long def) parses a string to long and catches any format exception
static java.lang.String	pathToName(java.lang.String pathName) gets the file name from a path - regardless of the OS syntax that the path is declared in
static int	posOfToken(java.lang.String strWork, java.lang.String name, java.lang.String separator, int iSkip) returns the position of the token, if it is in the String. The separator is excluded from the tokens.
static java.lang.String	prefix(java.lang.String strWork) Deprecated. use UrlUtil.prefix(strWork);
static java.lang.String	removeToken(java.lang.String strWork, int index, java.lang.String delim) replace a token in a string
static java.lang.String	removeToken(java.lang.String strWork, java.lang.String oldToken, java.lang.String delim)
static java.lang.String	replaceChar(java.lang.String strWork, char c, java.lang.String replaceString, int offset) replace multiple occurrences of a character in a given String
static java.lang.String	replaceCharSet(java.lang.String strWork, java.lang.String charSet, java.lang.String replaceString, int offset) replace any of a set of characters in a given String
static java.lang.String	replaceString(java.lang.String strWork, java.lang.String toReplace, java.lang.String replaceBy) replace a string in a given String if the replacement string is contained by the string to replace, recursively replace until no ocurrences of the original remain thus replaceString("a000000", "00", "0") will return "a0" rather than "a000"
static java.lang.String	replaceToken(java.lang.String strWork, int index, java.lang.String delim, java.lang.String newToken) replace a token in a string
static java.lang.String	replaceToken(java.lang.String strWork, java.lang.String oldToken, java.lang.String delim, java.lang.String newToken)
static java.lang.String	rightStr(java.lang.String strWork, int n) get the end of a string n > 0 str.substring(str.length() - n) take the rightmost n chars n < 0 substring(-n) take the string and cut n chars on the left example: string = "abcdefgh" string.rightStr( 2) = "gh" string.rightStr(-3) = "defgh"
static java.lang.String	setHexBinaryBytes(byte[] buffer, int len) get buffer as HexBinary any character values above 255 is truncated
static java.lang.String	setRawBytes(byte[] buffer, int len) set a string to the raw bytes specified in buffer, bypassing all transcoders
static byte[]	setUTF8String(java.lang.String strUnicode) Deprecated. use getUTF8Bytes instead
static java.lang.String	setvString(java.util.List<?> v) create a string from a vector of tokens
static java.lang.String	setvString(java.util.List<?> v, java.lang.String sep, java.lang.String front, java.lang.String back) create a string from a vector of tokens
static java.lang.String	setvString(java.lang.String[] a, java.lang.String sep, java.lang.String front, java.lang.String back) create a string from an array of tokens
static java.lang.String	simpleRegExptoRegExp(java.lang.String simpleRegExp) converts a simple regexp to a real regexp * --> (.*) (any # of chars) .
static java.lang.String	simpleRegExptoRegExp(java.lang.String simpleRegExp, boolean alwaysSimple) converts a simple regexp to a real regexp * --> (.*) (any # of chars) .
static java.lang.String	sprintf(java.lang.String format, java.lang.Object[] objects) format a string using C++ sprintf functionality
static java.lang.String	sprintf(java.lang.String format, java.lang.String template) format a string using C++ sprintf functionality
static java.lang.String	stripNot(java.lang.String work, java.lang.String keepChars) returns a new string that has all characters stripped from work that are not in keepChars
static java.lang.String	stripPrefix(java.lang.String str, java.lang.String prefix, boolean bIgnoreCase) strip a prefix, if it is there else return the string
static java.lang.String	stripQuote(java.lang.String str, java.lang.String quote, boolean bTrim) strip leading and trailing quotes from a string
static java.lang.String	substring(java.lang.String strWork, int first, int last) similar to substring but also null safe and allowing negative numbers to count backwards
static java.lang.String	token(java.lang.String strWork, int index, java.lang.String delim) get a single token from a String default: Token(strWork, index," \t\n")
static VString	tokenize(java.lang.String strWork, java.lang.String delim, boolean delim2token) return a vector of individual tokens Multiple consecutive delimitors are treated as one (similar to whitespace handling).
static VString	tokenizeBrackets(java.lang.String strWork, char delimIn, char delimOut) tokenize while counting the referenced in and out so that internal tokens are skipped used e.g for "?:" of "()"
static java.lang.String	trim(java.lang.String work, java.lang.String trimChars) returns a new string that has all characters trimmed from the front and back of work that are not in trimChars
static java.lang.String	uncToUrl(java.lang.String unc, boolean bEscape128) Convert a UNC path to a valid file URL or IRL note that some internal functions use network protocol and therefor performance may be non-optimal
static java.lang.String	underToCamel(java.lang.String toConvert)
static byte[]	unEscape(byte[] byteUnEscape, java.lang.String strEscapeChar, int iRadix, int escapeLen) unescape a String which was escaped with the Java StringUtil.escape method
static java.lang.String	unEscape(java.lang.String strToUnescape, java.lang.String strEscapeChar, int iRadix, int escapeLen) unescape a String which was escaped with the Java StringUtil.escape method
static java.lang.String	vStringToString(VString vs) Deprecated. use vs.getString(" ",null,null)
static java.lang.String	wipeInvalidXML10Chars(java.lang.String strText, java.lang.String replace) replaces all chars that are not compatible with xml1.0
static java.lang.String	write2String(IStreamWriter w) write to a file
static java.lang.String	xmlNameEscape(java.lang.String strWork)
static java.lang.String	xmlNameSpace(java.lang.String strWork) Deprecated. 060314 use KElement.xmlnsprefix
static java.lang.String	zappTokenWS(java.lang.String str, java.lang.String delim) Returns a string with deleted whitespaces near 'delim' and from the both ends of the string (if they were there) tokenizes a given string 'str' into tokens without separators.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

UTF8

public static final java.lang.String UTF8

m_URIEscape

@Deprecated
public static final java.lang.String m_URIEscape

Deprecated. use UrlUtil.m_URIEscape

See Also:

Constant Field Values

Method Detail

getRandomString

public static java.lang.String getRandomString()

returns a random string for testing fun stuff - similar to unix fortune but biased towards monty python or the hitchhikers guide to the galaxy

Returns:

a random string

zappTokenWS

public static java.lang.String zappTokenWS(java.lang.String str,
                                           java.lang.String delim)

Returns a string with deleted whitespaces near 'delim' and from the both ends of the string (if they were there)
tokenizes a given string 'str' into tokens without separators. Trims every token from both sides to remove the whitespaces and builds a new string from these tokens separated by 'delim'.

Parameters:

str - working string

delim - the delimiter

Returns:

String - the modified string

write2String

public static java.lang.String write2String(IStreamWriter w)

write to a file

Parameters:

file - the file to write

w - the writer to write to

Returns:

the file that was created, null if snafu

sprintf

public static java.lang.String sprintf(java.lang.String format,
                                       java.lang.String template)

format a string using C++ sprintf functionality

Parameters:

format - the format to print, see C++ spec for details

template - - comma separated string - the values are parsed and the appropriate objects are created more objects exist in template than the number of '%' tokens in format, the remainder of objects is ignored duplicate '\\,' is taken as literal ','

Returns:

String the formatted string

Throws:

java.lang.IllegalArgumentException - in case format and o do not match, i.e. not enough objects are passed to fill format

sprintf

public static java.lang.String sprintf(java.lang.String format,
                                       java.lang.Object[] objects)

format a string using C++ sprintf functionality

Parameters:

format - the format to print, see C++ spec for details

objects - the array of objects, either String, Double, Integer or ValuedEnum, if objects is longer than the number of '%' tokens in format, the remainder of objects is ignored The method works fairly loosely typed, thus doubles are printed as integers, Strings are converted to numbers, if possible etc.

Returns:

String the formatted string

Throws:

java.lang.IllegalArgumentException - in case format and o do not match, i.e. not eough objects are passed to fill format

setvString

public static java.lang.String setvString(java.lang.String[] a,
                                          java.lang.String sep,
                                          java.lang.String front,
                                          java.lang.String back)

create a string from an array of tokens

Parameters:

a - the token array

sep - the separator between the tokens

front - the front end of the string

back - the back end of the string

Returns:

String - the vector as String default: setvString(v, JDFConstants.BLANK, null, null)

setvString

public static java.lang.String setvString(java.util.List<?> v)

create a string from a vector of tokens

default: setvString(v, JDFConstants.BLANK, null, null)

Parameters:

v - the token vector

Returns:

String - the vector as String

setvString

public static java.lang.String setvString(java.util.List<?> v,
                                          java.lang.String sep,
                                          java.lang.String front,
                                          java.lang.String back)

create a string from a vector of tokens

Parameters:

v - the token vector

sep - the separator between the tokens

front - the front end of the string

back - the back end of the string

Returns:

String - the vector as String default: setvString(v, JDFConstants.BLANK, null, null)

leftStr

public static java.lang.String leftStr(java.lang.String strWork,
                                       int n)

n > 0 substring(0, n) take the first n chars (leftmost) n < 0 substring(0, s.length()+n) take the string and cut n chars on the right example: string = "abcdefgh" string.leftStr( 2) = "ab" string.leftStr(-3) = "abcde"

Parameters:

strWork - the string to work on

n - number of characters to cut (negative) or retain (positive)

Returns:

the modified string

substring

public static java.lang.String substring(java.lang.String strWork,
                                         int first,
                                         int last)

similar to substring but also null safe and allowing negative numbers to count backwards

Parameters:

strWork - the string to work on

first - the position of the starting character 0=first

last - the position of the end character 0=last

Returns:

the modified string

rightStr

public static java.lang.String rightStr(java.lang.String strWork,
                                        int n)

get the end of a string n > 0 str.substring(str.length() - n) take the rightmost n chars n < 0 substring(-n) take the string and cut n chars on the left example: string = "abcdefgh" string.rightStr( 2) = "gh" string.rightStr(-3) = "defgh"

Parameters:

strWork - the string to work on

n - number of characters to cut (negative) or retain (positive)

Returns:

the modified string

tokenize

public static VString tokenize(java.lang.String strWork,
                               java.lang.String delim,
                               boolean delim2token)

return a vector of individual tokens
Multiple consecutive delimitors are treated as one (similar to whitespace handling).

default: tokenize(strWork, delim, false)

Parameters:

strWork - the string to tokenize

delim - the delimiter, if null use whitespace

delim2token - should a delimiter be a token?

Returns:

the vector of strings - never null

tokenizeBrackets

public static VString tokenizeBrackets(java.lang.String strWork,
                                       char delimIn,
                                       char delimOut)

tokenize while counting the referenced in and out so that internal tokens are skipped used e.g for "?:" of "()"

Parameters:

strWork -

delimIn - the

delimOut -

Returns:

hasToken

public static boolean hasToken(java.lang.String strWork,
                               java.lang.String token,
                               java.lang.String delim,
                               int iSkip)

check whether a String contains a given token

default: hasToken(strWork, token, delim, 0)

Parameters:

strWork - the string to work on

token - the token to search for

delim - the delimiter of the tokens

iSkip - the number of matching tokens to skip before returning true

Returns:

boolean - true if strWork contains token

hasToken

public static boolean hasToken(java.lang.String[] strWork,
                               java.lang.String token,
                               int iSkip)

check whether a vector of Strings contains a given token

default: hasToken(strWork, token, 0)

Parameters:

strWork - the vector of strings string to work on

token - the token to search for

iSkip - the number of matching tokens to skip before returning true

Returns:

true, if strWork contains token

addToken

public static java.lang.String addToken(java.lang.String strWork,
                                        java.lang.String delim,
                                        java.lang.String newToken)

replace a token in a string

Parameters:

strWork - the String to work on

delim - the delimiter

newToken - the new token, if null said token is removed

Returns:

the modified string

removeToken

public static java.lang.String removeToken(java.lang.String strWork,
                                           int index,
                                           java.lang.String delim)

replace a token in a string

Parameters:

strWork - the String to work on

index - index of the token to replace if<0 return from end (e.g. -1 is the last token)

delim - the delimiter

Returns:

the modified string, null if last token was removed

replaceToken

public static java.lang.String replaceToken(java.lang.String strWork,
                                            java.lang.String oldToken,
                                            java.lang.String delim,
                                            java.lang.String newToken)

Parameters:

strWork -

oldToken -

delim -

newToken -

Returns:

removeToken

public static java.lang.String removeToken(java.lang.String strWork,
                                           java.lang.String oldToken,
                                           java.lang.String delim)

Parameters:

strWork -

oldToken -

delim -

newToken -

Returns:

replaceToken

public static java.lang.String replaceToken(java.lang.String strWork,
                                            int index,
                                            java.lang.String delim,
                                            java.lang.String newToken)

replace a token in a string

Parameters:

strWork - the String to work on

index - index of the token to replace if<0 return from end (e.g. -1 is the last token)

delim - the delimiter

newToken - the new token, if null said token is removed

Returns:

the modified string - never null

token

public static java.lang.String token(java.lang.String strWork,
                                     int index,
                                     java.lang.String delim)

get a single token from a String

default: Token(strWork, index," \t\n")

Parameters:

strWork - the String to work on

index - index of the token to return
if<0 return from end (e.g. -1 is the last token)

delim - the delimiter

Returns:

the single token (null if no token found)

replaceCharSet

public static java.lang.String replaceCharSet(java.lang.String strWork,
                                              java.lang.String charSet,
                                              java.lang.String replaceString,
                                              int offset)

replace any of a set of characters in a given String

default: replaceCharSet(strWork, c, s, 0)

Parameters:

strWork - String to work on

charSet - characters to replace

replaceString - String to insert for any character in charSet, if null simply remove all occurrences of any char in charSet

offset - where to start replacing

Returns:

the String with replaced characters

replaceChar

public static java.lang.String replaceChar(java.lang.String strWork,
                                           char c,
                                           java.lang.String replaceString,
                                           int offset)

replace multiple occurrences of a character in a given String

default: replaceChar(strWork, c, s, 0)

Parameters:

strWork - String to work on

c - character to replace

replaceString - String to insert for c, if null simply remove c

offset -

Returns:

the String with replaced characters

replaceString

public static java.lang.String replaceString(java.lang.String strWork,
                                             java.lang.String toReplace,
                                             java.lang.String replaceBy)

replace a string in a given String if the replacement string is contained by the string to replace, recursively replace until no ocurrences of the original remain thus replaceString("a000000", "00", "0") will return "a0" rather than "a000"

Parameters:

strWork - String to work on

toReplace - String to match and replace

replaceBy - String to insert for toReplace, null if nothing should be inserted

Returns:

the String with replaced characters

xmlNameEscape

public static java.lang.String xmlNameEscape(java.lang.String strWork)

Parameters:

strWork -

Returns:

the escaped string

extension

@Deprecated
public static java.lang.String extension(java.lang.String pathName)

Deprecated. use URLUtil.extension

the filename extension of pathName

Parameters:

pathName -

Returns:

prefix

@Deprecated
public static java.lang.String prefix(java.lang.String strWork)

Deprecated. use UrlUtil.prefix(strWork);

inverse of extension

Parameters:

strWork - the string to work on

Returns:

the prefix

normalize

public static java.lang.String normalize(java.lang.String strWork,
                                         boolean toLower)

normalize a string by stripping and converting any internal whitespace to a single blank

Parameters:

strWork - the input

toLower - if true return all lower case

Returns:

the output; null if all characters were removed

normalize

public static java.lang.String normalize(java.lang.String strWork)

normalize a string by stripping and converting any internal whitespace to a single blank

Parameters:

strWork - the input

Returns:

the output; null if all characters were removed

normalize

public static java.lang.String normalize(java.lang.String strWork,
                                         boolean toLower,
                                         java.lang.String replace)

normalize a string by stripping and converting any internal whitespace to the value of replace

Parameters:

strWork - the input

toLower - if true return all lower case

replace - the replace character, if null remove all whitespace

Returns:

the output; null if all characters were removed

getDefaultNull

public static java.lang.String getDefaultNull(java.lang.String s,
                                              java.lang.String def)

return null if s==null or s==def, else s
used e.g. to zapp "" strings

Parameters:

s - the String to test

def - the default that is converted to null

Returns:

the converted String

getDistance

public static int getDistance(java.lang.String s1,
                              java.lang.String s2,
                              boolean normalize,
                              boolean ignoreCase,
                              boolean ignoreEmpty,
                              boolean reduceSubstring)

Parameters:

s1 -

s2 -

normalize -

ignoreCase -

ignoreEmpty -

reduceSubstring - if true slide over the string and check only the substring

Returns:

length

public static int length(java.lang.String s1)

getDistance

public static int getDistance(java.lang.String s1,
                              java.lang.String s2,
                              boolean normalize,
                              boolean ignoreCase,
                              boolean ignoreEmpty)

return the Levenschtein ditance where null is treated as ""

Parameters:

s1 -

s2 -

normalize - if true, normalize strings prior to calculating

ignoreCase - if true, ignore case strings when calculating

ignoreEmpty - if true, the result is 0 if one of the two strings is null or ""

Returns:

the Levenshtein distance

getNonEmpty

public static java.lang.String getNonEmpty(java.lang.String s)

return null if s==null or s=="", else s
used e.g. to zapp "" strings

Parameters:

s - the String to test

Returns:

the converted String

isEmpty

public static boolean isEmpty(java.lang.String s)

return true if s==null or s==""

Parameters:

s -

Returns:

isEmpty

public static boolean isEmpty(java.util.Collection<java.lang.String> v)

are we null or empty or contain only an empty JDFAttributeMap

Parameters:

v -

Returns:

hasContent

public static boolean hasContent(java.lang.String s)

return false if s==null or s has only whotespace

Parameters:

s -

Returns:

newExtension

@Deprecated
public static java.lang.String newExtension(java.lang.String strWork,
                                                        java.lang.String newExt)

Deprecated. use UrlUtil.newExtension

replace the .extension of a file name

Parameters:

strWork - the file path

newExt - the new extension (works with or without the initial "."

Returns:

the strWork with a replaced extension

xmlNameSpace

@Deprecated
public static java.lang.String xmlNameSpace(java.lang.String strWork)

Deprecated. 060314 use KElement.xmlnsprefix

Parameters:

strWork -

Returns:

String

mime

@Deprecated
public static java.lang.String mime(java.lang.String strWork)

Deprecated. use MimeUtil.getMimeTypeFromExt(strWork);

get the mime type for a given extension

Parameters:

strWork - String to work in

Returns:

the mime type

isNMTOKEN

public static boolean isNMTOKEN(java.lang.String strWork)

checks whether a string is a NMTOKEN

Parameters:

strWork - the string to check

Returns:

boolean - true if strWork is a NMTOKEN

isID

public static boolean isID(java.lang.String strWork)

checks whether a string is an ID

Parameters:

strWork - the string to check

Returns:

boolean - true if strWork is an ID

isEqual

public static boolean isEqual(double d1,
                              double d2)

return true if d1 and d2 are within a range of epsilon or close enough to be serialized identically

Parameters:

d1 -

d2 -

Returns:

true if (almost) identical

isEqual

public static boolean isEqual(double d1,
                              double d2,
                              double delta)

return true if d1 and d2 are within a range of epsilon or close enough to be serialized identically

Parameters:

d1 -

d2 -

Returns:

true if (almost) identical

compareTo

public static int compareTo(double d1,
                            double d2)

return -1 if d1 < d2 , 0 if d1==d2 ; +1 if d1>d2 are within a range of epsilon or close enough to be serialized identically

Parameters:

d1 -

d2 -

Returns:

int 1,0 or -1

compare

public static int compare(java.lang.String c0,
                          java.lang.String c1,
                          boolean ignoreCase)

static implementation of compare for any comparable object that gracefully handles null
null is always the smallest

Parameters:

c0 -

c1 -

Returns:

-1 if c0 < c1, 0 if equal, 1 if c0 > c1;

isNMTOKENS

@Deprecated
public static boolean isNMTOKENS(java.lang.String strWork)

Deprecated. 060309 use isNMTOKENS(strWork,false)

checks whether a string is matches an NMTOKENS list

Parameters:

strWork - the string to check

Returns:

boolean - true if strWork is an NMTOKENS list

isNMTOKENS

public static boolean isNMTOKENS(java.lang.String strWork,
                                 boolean bID)

checks whether a string is a NMTOKENS list

Parameters:

strWork - the string to check

bID - if true, also check that each individual token matches the pattern for an ID

Returns:

boolean true if strWork is a NMTOKENS list

isBoolean

public static boolean isBoolean(java.lang.String strWork)

checks whether a string matches the boolean values "true" or "false"

Parameters:

strWork - the string to check

Returns:

boolean true if strWork is represents boolean value

isDate

public static boolean isDate(java.lang.String strWork)

checks whether a string matches the boolean values "true" or "false"

Parameters:

strWork - the string to check

Returns:

boolean true if strWork is represents boolean value

isNumberList

public static boolean isNumberList(java.lang.String strWork)

checks whether a string matches the boolean values "true" or "false"

Parameters:

strWork - the string to check

Returns:

boolean true if strWork is represents boolean value

getCharset

public static java.nio.charset.Charset getCharset(java.lang.String csName)

Parameters:

csName -

Returns:

getDataType

public static org.cip4.jdflib.util.StringUtil.EDataType getDataType(java.lang.String s)

Parameters:

s -

Returns:

null if nulkl, else the datatype

isNumber

public static boolean isNumber(java.lang.String str)

checks whether a string is a number

Parameters:

str - the string to check

Returns:

boolean true if strWork is a number

wipeInvalidXML10Chars

public static java.lang.String wipeInvalidXML10Chars(java.lang.String strText,
                                                     java.lang.String replace)

replaces all chars that are not compatible with xml1.0

Parameters:

strText - the text to check

replace - the single char string to replace non xml chars with; if null the non-xml char is simply omitted

Returns:

the clean string, may be the same string

find_last_not_of

public static int find_last_not_of(java.lang.String strWork,
                                   java.lang.String strNotList)

find the last character in strwork that is not in strNotList

Parameters:

strWork - the string to search

strNotList - the list of characters to ignore

Returns:

position of the last matching char, -1 if all strWork only contains chars from strNotList

posOfToken

public static int posOfToken(java.lang.String strWork,
                             java.lang.String name,
                             java.lang.String separator,
                             int iSkip)

returns the position of the token, if it is in the String.
The separator is excluded from the tokens. Multiple consecutive separators are treated as one (similar to whitespace handling).

Parameters:

strWork - the string to work on

name - the token to search

separator - separator

iSkip - number of tokens to skip before accepting (if 0 -> take the first etc., -1 -> first as well)

Returns:

int - 0 based position if the token exists, else -1

hasToken

@Deprecated
public static boolean hasToken(java.lang.String strWork,
                                           java.lang.String token,
                                           java.lang.String delim)

Deprecated. use the 4 parameter version

check whether a string contains a complete token

default: hasToken(strWork, token, delim)

Parameters:

strWork - the string to work on

token - the token to search for

delim - the delimiter of the tokens

Returns:

boolean -

indexOfToken

public static int indexOfToken(java.lang.String strWork,
                               java.lang.String token,
                               java.lang.String delim,
                               int start)

index of a token in a string

Parameters:

strWork - the string to work on

token - the token to search for

delim - the delimiter of the tokens

start - position to search in the string

Returns:

numSubstrings

public static int numSubstrings(java.lang.String strWork,
                                java.lang.String subString)

counts the number of occurrences of subString in String the total number of occurrences is counted, e.g "aaa" contains "aa" twice

Parameters:

strWork -

subString -

Returns:

the number of occurrences

setRawBytes

public static java.lang.String setRawBytes(byte[] buffer,
                                           int len)

set a string to the raw bytes specified in buffer, bypassing all transcoders

Parameters:

buffer - the buffer to assign to this

len -

Returns:

the raw string

getRawBytes

public static byte[] getRawBytes(java.lang.String strUnicode)

get the raw bytes specified in strUnicode, bypassing all transcoders
any character values above 255 is truncated (c=c&0xff)

Parameters:

strUnicode - the unicode string

Returns:

char array of the raw bytes assigned to this

setHexBinaryBytes

public static java.lang.String setHexBinaryBytes(byte[] buffer,
                                                 int len)

get buffer as HexBinary
any character values above 255 is truncated

Parameters:

buffer - the String which you want to encode to HexBinary

len - the length of the buffer.
If<0, default is -1. In this case the length of the char array will be used.

Returns:

the hexbinary representation

getHexBinaryBytes

public static byte[] getHexBinaryBytes(byte[] unicodeArray)

Decode a HexBinary encoded byte array back to Unicode

Parameters:

unicodeArray - array which stores the HexBinary

Returns:

array of byte holding the unicode chars

getUTF8Bytes

public static byte[] getUTF8Bytes(java.lang.String strUnicode)

return the UTF8 String strUnicode as Unicode byte array

Parameters:

strUnicode - the unicode string to transcode to utf8

Returns:

a byte array[] representing the utf-8 code of the input string, null if an error occurred

setUTF8String

@Deprecated
public static byte[] setUTF8String(java.lang.String strUnicode)

Deprecated. use getUTF8Bytes instead

Parameters:

strUnicode -

Returns:

getUTF8String

public static java.lang.String getUTF8String(byte[] utf8)

get the unicode string representing the UTF8 representation of the byte buffer fall back on default encoding in case someone accidentally sends in non utf-8

Parameters:

utf8 - the utf-8 encoded byte array

Returns:

String - the unicode string representation of the utf8 bytes assigned to this, null if an error occurrred

formatDouble

public static java.lang.String formatDouble(double d)

returns a formatted double. Truncates to 8 digits after the "."
If the double is representable as an integer, any ".0" is stripped.

Parameters:

d - the double to format

Returns:

the formatted string that represents d TBD handle exp format

formatInteger

public static java.lang.String formatInteger(int i)

returns a formatted integer, replaces string constants with according int constants

Parameters:

i - the integer to format

Returns:

the formatted string that represents i

formatLong

public static java.lang.String formatLong(long i)

returns a formatted integer, replaces string constants with according int constants

Parameters:

i - the integer to format

Returns:

the formatted string that represents i

isInteger

public static boolean isInteger(java.lang.String str)

checks whether str reprents an integer

Parameters:

str - the String to check

Returns:

boolean - true if the string represents an integer number

isLong

public static boolean isLong(java.lang.String str)

checks whether str reprents an integer

Parameters:

str - the String to check

Returns:

boolean - true if the string represents an integer number

escape

public static java.lang.String escape(java.lang.String strToEscape,
                                      java.lang.String strCharSet,
                                      java.lang.String strEscapeChar,
                                      int iRadix,
                                      int iEscapeLen,
                                      int iEscapeBelow,
                                      int iEscapeAbove)

escape a string by prepending escapeChar and a numerical representation of the string. Characters to be escaped are defined by toEscape, escapeBelow and escapeAbove

default: escape(String toEscape, null, 0, 0, 0, 256); //Note that an escaped character can't be unescaped without the knowledge of the escapelength

Parameters:

strToEscape - the String to escape

strCharSet - the set of characters that should be escaped eg "äöüß$€"

strEscapeChar - the character sequence that marks an escape sequence. If null, "\\" is used

iRadix - the numerical representation base of the escaped chars, e.g. 8 for octal, 16 for hex
if radix == 0 the escape char is merely inserted in front of the char to escape
if radix <0 the escape char is replaced by the prefix
valid radix: -1,0,2,8,10,16

iEscapeLen - the number of digits per escaped char, not including escapeChar

iEscapeBelow - all characters with an encoding below escapeBelow should also be escaped, if negative, no lower limit applies

iEscapeAbove - all characters with an encoding above escapeAbove should also be escaped, if negative, no upper limit applies

Returns:

the string where all required sequences have been replaced by their escaped representation

equals

public static boolean equals(java.lang.String a,
                             java.lang.String b)

return true if a equals b or both are null or ""

Parameters:

a - String to compare

b - String to compare

Returns:

boolean true if a equals b or both are one of null or ""

escape

public static byte[] escape(byte[] a_toEscape,
                            java.lang.String strCharSet,
                            java.lang.String strEscapeChar,
                            int iRadix,
                            int iEscapeLen,
                            int iEscapeBelow,
                            int iEscapeAbove)

escape a string by prepending escapeChar and a numerical representation of the string. Characters to be escaped are defined by toEscape, escapeBelow and escapeAbove

default: escape(String toEscape, null, 0, 0, 0, 256); //Note that an escaped character can't be unescaped without the knowledge of the escapelength

Parameters:

a_toEscape - the bytes to escape

strCharSet - the set of characters that should be escaped eg "äöüß$€"

strEscapeChar - the character sequence that marks an escape sequence. If null, "\\" is used

iRadix - the numerical representation base of the escaped chars, e.g. 8 for octal, 16 for hex
if radix == 0 the escape char is merely inserted in front of the char to escape
if radix <0 the escape char is replaced by the prefix
valid radix: -1,0,2,8,10,16

iEscapeLen - the number of digits per escaped char, not including escapeChar

iEscapeBelow - all characters with an encoding below escapeBelow should also be escaped, if negative, no lower limit applies

iEscapeAbove - all characters with an encoding above escapeAbove should also be escaped, if negative, no upper limit applies

Returns:

the string where all illegal sequences have been replaced by their escaped representation

unEscape

public static java.lang.String unEscape(java.lang.String strToUnescape,
                                        java.lang.String strEscapeChar,
                                        int iRadix,
                                        int escapeLen)

unescape a String which was escaped with the Java StringUtil.escape method

Parameters:

strToUnescape - the String to unescape. For example zz\d6\zzz\c4\\dc\z\d6\\24\\3f\zz@z

strEscapeChar - the char which indicates a escape sequence "\\" in this case (thats also the default)

iRadix - the radix of the escape sequenze. 16 in this example.

escapeLen - the number of digits per escaped char, not including strEscapeChar

Returns:

the unescaped String.

unEscape

public static byte[] unEscape(byte[] byteUnEscape,
                              java.lang.String strEscapeChar,
                              int iRadix,
                              int escapeLen)

unescape a String which was escaped with the Java StringUtil.escape method

Parameters:

byteUnEscape - the bytes to unescape. For example zz\d6\zzz\c4\\dc\z\d6\\24\\3f\zz�z

strEscapeChar - the char which indicates a escape sequence "\\" in this case (thats also the default)

iRadix - the radix of the escape sequenze. 16 in this example.

escapeLen - the number of digits per escaped char, not including strEscapeChar

Returns:

the unescaped byte array. zz�zzz��z�$?zz�z in this example

vStringToString

@Deprecated
public static java.lang.String vStringToString(VString vs)

Deprecated. use vs.getString(" ",null,null)

converts a VString to a single string represents all members of the VString concatenated together

Parameters:

vs -

Returns:

String - the unicode string representation of the utf8 bytes assigned to this, null if an error occurrred

parseDouble

public static double parseDouble(java.lang.String s,
                                 double def)

parses a string to double and catches any format exception

Parameters:

s - the string to parse

def - the default to return in case of error

Returns:

the parsed double of s

Since:

080404 handles "" gracefully

parseBoolean

public static boolean parseBoolean(java.lang.String s,
                                   boolean def)

parses a string to boolean and catches any format exception "1" and "0" are treated as true and false respectively

Parameters:

s - the string to parse

def - the default to return in case of error

Returns:

the parsed boolean of s

Since:

080404 handles "" gracefully

parseInt

public static int parseInt(java.lang.String s,
                           int def)

parses a string to integer and catches any format exception

Parameters:

s - the string to parse

def - the default to return in case of error

Returns:

the parsed double of s

Since:

080404 handles "" gracefully

parseLong

public static long parseLong(java.lang.String s,
                             long def)

parses a string to long and catches any format exception

Parameters:

s - the string to parse

def - the default to return in case of error

Returns:

the parsed double of s

Since:

080404 handles "" gracefully

uncToUrl

public static java.lang.String uncToUrl(java.lang.String unc,
                                        boolean bEscape128)

Convert a UNC path to a valid file URL or IRL note that some internal functions use network protocol and therefor performance may be non-optimal

Parameters:

unc - The UNC string to parse, may also be used for local characters

bEscape128 - if true, escape non -ascii chars (URI), if false, don't (IRI)

Returns:

the URL string

pathToName

public static java.lang.String pathToName(java.lang.String pathName)

gets the file name from a path - regardless of the OS syntax that the path is declared in

Parameters:

pathName -

Returns:

underToCamel

public static java.lang.String underToCamel(java.lang.String toConvert)

isWindowsLocalPath

@Deprecated
public static boolean isWindowsLocalPath(java.lang.String pathName)

Deprecated. use UrlUtil.isWindowsLocalPath(pathName);

Parameters:

pathName -

Returns:

isUNC

@Deprecated
public static boolean isUNC(java.lang.String pathName)

Deprecated. use URLUtil.isUNC(pathName)

Parameters:

pathName -

Returns:

simpleRegExptoRegExp

public static java.lang.String simpleRegExptoRegExp(java.lang.String simpleRegExp)

converts a simple regexp to a real regexp
* --> (.*) (any # of chars)
. --> \. (literal ".")
? --> . (exactly one character) if one of ([|\ is found in the expression we assume it is a real regexp that has already been converted

Parameters:

simpleRegExp - the simple regexp

Returns:

the converted real regexp

simpleRegExptoRegExp

public static java.lang.String simpleRegExptoRegExp(java.lang.String simpleRegExp,
                                                    boolean alwaysSimple)

converts a simple regexp to a real regexp
* --> (.*) (any # of chars)
. --> \. (literal ".")
? --> . (exactly one character) if not alwaysSimple one of ([|\ is found in the expression we assume it is a real regexp that has already been converted

Parameters:

simpleRegExp - the simple regexp

alwaysSimple -

Returns:

the converted real regexp

matchesSimple

public static boolean matchesSimple(java.lang.String str,
                                    java.lang.String regExp)

match a regular expression using String.matches(), but also catch exceptions and handle simplified regexp. The null expression is assumed to match anything.

Parameters:

str - the string to match

regExp - the expression to match against

Returns:

true, if str matches regExp or regexp is empty

matchesSimple

public static boolean matchesSimple(java.lang.String str,
                                    java.lang.String regExp,
                                    boolean alwaysSimple)

match a regular expression using String.matches(), but also catch exceptions and handle simplified regexp. The null expression is assumed to match anything.

Parameters:

str - the string to match

regExp - the expression to match against

alwaysSimple - if true - always escape

Returns:

true, if str matches regExp or regexp is empty

equals

public static boolean equals(java.lang.String attribute,
                             java.lang.String attribute2,
                             double delta)

simple comparison of strings with some heuristics

Parameters:

attribute -

attribute2 -

delta - absolute delta of numeric values to be considered equal

Returns:

matches

public static boolean matches(java.lang.String str,
                              java.lang.String regExp)

match a regular expression using String.matches(), but also catch exceptions
does NOT handle simplified regexp. The null expression is assumed to match anything.

Parameters:

str - the string to match

regExp - the expression to match against

Returns:

true, if str matches regExp or regexp is empty

matchesIgnoreCase

public static boolean matchesIgnoreCase(java.lang.String str,
                                        java.lang.String regExp)

match a regular expression using ignoring cases using String.matches(), but also catch exceptions and handle simplified regexp. The null expression is assumed to match anything.

Parameters:

str - the string to match

regExp - the simplified expression to match against

Returns:

true, if str matches regExp or regexp is empty

matchesIgnoreCase

public static boolean matchesIgnoreCase(java.lang.String str,
                                        java.lang.String regExp,
                                        boolean alwaysSimple)

match a regular expression using ignoring cases using String.matches(), but also catch exceptions and handle simplified regexp. The null expression is assumed to match anything.

Parameters:

str - the string to match

regExp - the simplified expression to match against

alwaysSimple - TODO

Returns:

true, if str matches regExp or regexp is empty

concatStrings

public static void concatStrings(VString vS,
                                 java.lang.String appendString)

add the string appendString to all Strings in VString vs

Parameters:

vS - the string vector

appendString - the string to append

concat

public static java.lang.String concat(java.lang.String s1,
                                      java.lang.String s2,
                                      java.lang.String delim)

Parameters:

s1 -

s2 -

delim -

Returns:

createString

public static java.lang.String createString(java.io.InputStream is)

create a string from an input stream

Parameters:

is - the input stream

Returns:

the string representation

getRelativeURL

@Deprecated
public static java.lang.String getRelativeURL(java.io.File f,
                                                          java.io.File baseDir)

Deprecated. use getRelativeURL(File f, File fCWD, boolean bEscape128)

returns the relative URL of a file relative to the current working directory

Parameters:

f - the file to get the relative url for

baseDir - the file that describes cwd, if null cwd is calculated

Returns:

getRelativeURL

@Deprecated
public static java.lang.String getRelativeURL(java.io.File f,
                                                          java.io.File baseDir,
                                                          boolean bEscape128)

Deprecated. use URLUtil.getRelativeURL

returns the relative URL of a file relative to the current workin directory

Parameters:

f - the file to get the relative url for

baseDir - the file that describes cwd, if null cwd is calculated

bEscape128 - if true, escape > 128 (URL) else retain (IRL)

Returns:

getRelativePath

@Deprecated
public static java.lang.String getRelativePath(java.io.File f,
                                                           java.io.File fCWD)

Deprecated. use URLUtil.getRelativePath(f, fCWD);

returns the relative URL of a file relative to the current working directory
this includes escaping of %20 etc.

Parameters:

f - the file to get the relative path for

fCWD - the file that describes cwd, if null cwd is calculated

Returns:

getNamesVector

@Deprecated
public static VString getNamesVector(java.lang.Class<? extends org.apache.commons.lang.enums.ValuedEnum> e)

Deprecated. use @see EnumUtil.getNamesVector

get a vector of names in an iteration

Parameters:

e - any member of the enum to iterate over

Returns:

VString - the vector of enum names

getEnumsVector

@Deprecated
public static java.util.Vector<org.apache.commons.lang.enums.ValuedEnum> getEnumsVector(java.lang.Class<? extends org.apache.commons.lang.enums.ValuedEnum> e)

Deprecated. use @se EnumUtil.getEnumsVector

get a vector of elements in an iteration

Parameters:

e - any member of the enum to iterate over

Returns:

Vector - the vector of enum instances

fileToUrl

@Deprecated
public static java.lang.String fileToUrl(java.io.File f,
                                                     boolean b)

Deprecated. use UrlUtil.fileToUrl(f, b);

Parameters:

f -

b -

Returns:

stripPrefix

public static java.lang.String stripPrefix(java.lang.String str,
                                           java.lang.String prefix,
                                           boolean bIgnoreCase)

strip a prefix, if it is there else return the string

Parameters:

str - the string to strip

prefix - the prefix to strip

bIgnoreCase - if true ignore the case of the prefix

Returns:

stripQuote

public static java.lang.String stripQuote(java.lang.String str,
                                          java.lang.String quote,
                                          boolean bTrim)

strip leading and trailing quotes from a string

Parameters:

str - the work string

quote - the quote character

bTrim - if true, trim whitespace prior to trimming quotes

Returns:

the work string trimmed and trailing + leading quote chars removed

stripNot

public static java.lang.String stripNot(java.lang.String work,
                                        java.lang.String keepChars)

returns a new string that has all characters stripped from work that are not in keepChars

Parameters:

work -

keepChars -

Returns:

trim

public static java.lang.String trim(java.lang.String work,
                                    java.lang.String trimChars)

returns a new string that has all characters trimmed from the front and back of work that are not in trimChars

Parameters:

work -

trimChars - if null - use standard whitespace

Returns:

null if no chars left

formatDouble

public static java.lang.String formatDouble(double value,
                                            int precision)

returns a formatted double. Truncates to @param precision digits after the "."
If the double is representable as an integer, any ".0" is stripped.

Parameters:

value -

precision - number of digits after the "."

Returns: