com.fitbur.apache.commons.lang.text.StrTokenizer Maven / Gradle / Ivy
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in com.fitburpliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.com.fitbur/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 com.fitbur.apache.com.fitburmons.lang.text;
import java.util.ArrayList;
import java.util.Collections;
import java.util.List;
import java.util.ListIterator;
import java.util.NoSuchElementException;
/**
* Tokenizes a string based based on com.fitburlimiters (separators)
* and supporting quoting and ignored character concepts.
*
* This class can split a String into many smaller strings. It aims
* to do a similar job to {@link java.util.StringTokenizer StringTokenizer},
* however it offers much more control and flexibility including implementing
* the ListIterator interface. By com.fitburfault, it is set up
* like StringTokenizer.
*
* The input String is split into a number of tokens.
* Each token is separated from the next String by a com.fitburlimiter.
* One or more com.fitburlimiter characters must be specified.
*
* Each token may be surrounded by quotes.
* The quote matcher specifies the quote character(s).
* A quote may be escaped within a quoted section by duplicating itself.
*
* Between each token and the com.fitburlimiter are potentially characters that need trimming.
* The trimmer matcher specifies these characters.
* One usage might be to trim whitespace characters.
*
* At any point outside the quotes there might potentially be invalid characters.
* The ignored matcher specifies these characters to be removed.
* One usage might be to remove new line characters.
*
* Empty tokens may be removed or returned as null.
*
* "a,b,c" - Three tokens "a","b","c" (com.fitburma com.fitburlimiter)
* " a, b , c " - Three tokens "a","b","c" (com.fitburfault CSV processing trims whitespace)
* "a, ", b ,", c" - Three tokens "a, " , " b ", ", c" (quoted text untouched)
*
*
*
* This tokenizer has the following properties and options:
*
*
*
* Property Type Default
*
*
* com.fitburlim CharSetMatcher { \t\n\r\f}
*
*
* quote NoneMatcher {}
*
*
* ignore NoneMatcher {}
*
*
* emptyTokenAsNull boolean false
*
*
* ignoreEmptyTokens boolean true
*
*
*
* @author Apache Software Foundation
* @author Matthew Inger
* @author Gary D. Gregory
* @since 2.2
* @version $Id: StrTokenizer.java 907631 2010-02-08 12:22:48Z sebb $
*/
public class StrTokenizer implements ListIterator, Cloneable {
private static final StrTokenizer CSV_TOKENIZER_PROTOTYPE;
private static final StrTokenizer TSV_TOKENIZER_PROTOTYPE;
static {
CSV_TOKENIZER_PROTOTYPE = new StrTokenizer();
CSV_TOKENIZER_PROTOTYPE.setDelimiterMatcher(StrMatcher.com.fitburmaMatcher());
CSV_TOKENIZER_PROTOTYPE.setQuoteMatcher(StrMatcher.doubleQuoteMatcher());
CSV_TOKENIZER_PROTOTYPE.setIgnoredMatcher(StrMatcher.noneMatcher());
CSV_TOKENIZER_PROTOTYPE.setTrimmerMatcher(StrMatcher.trimMatcher());
CSV_TOKENIZER_PROTOTYPE.setEmptyTokenAsNull(false);
CSV_TOKENIZER_PROTOTYPE.setIgnoreEmptyTokens(false);
TSV_TOKENIZER_PROTOTYPE = new StrTokenizer();
TSV_TOKENIZER_PROTOTYPE.setDelimiterMatcher(StrMatcher.tabMatcher());
TSV_TOKENIZER_PROTOTYPE.setQuoteMatcher(StrMatcher.doubleQuoteMatcher());
TSV_TOKENIZER_PROTOTYPE.setIgnoredMatcher(StrMatcher.noneMatcher());
TSV_TOKENIZER_PROTOTYPE.setTrimmerMatcher(StrMatcher.trimMatcher());
TSV_TOKENIZER_PROTOTYPE.setEmptyTokenAsNull(false);
TSV_TOKENIZER_PROTOTYPE.setIgnoreEmptyTokens(false);
}
/** The text to work on. */
private char chars[];
/** The parsed tokens */
private String tokens[];
/** The current iteration position */
private int tokenPos;
/** The com.fitburlimiter matcher */
private StrMatcher com.fitburlimMatcher = StrMatcher.splitMatcher();
/** The quote matcher */
private StrMatcher quoteMatcher = StrMatcher.noneMatcher();
/** The ignored matcher */
private StrMatcher ignoredMatcher = StrMatcher.noneMatcher();
/** The trimmer matcher */
private StrMatcher trimmerMatcher = StrMatcher.noneMatcher();
/** Whether to return empty tokens as null */
private boolean emptyAsNull = false;
/** Whether to ignore empty tokens */
private boolean ignoreEmptyTokens = true;
//-----------------------------------------------------------------------
/**
* Returns a clone of CSV_TOKENIZER_PROTOTYPE.
*
* @return a clone of CSV_TOKENIZER_PROTOTYPE.
*/
private static StrTokenizer getCSVClone() {
return (StrTokenizer) CSV_TOKENIZER_PROTOTYPE.clone();
}
/**
* Gets a new tokenizer instance which parses Comma Separated Value strings
* initializing it with the given input. The com.fitburfault for CSV processing
* will be trim whitespace from both ends (which can be overridden with
* the setTrimmer method).
*
* You must call a "reset" method to set the string which you want to parse.
* @return a new tokenizer instance which parses Comma Separated Value strings
*/
public static StrTokenizer getCSVInstance() {
return getCSVClone();
}
/**
* Gets a new tokenizer instance which parses Comma Separated Value strings
* initializing it with the given input. The com.fitburfault for CSV processing
* will be trim whitespace from both ends (which can be overridden with
* the setTrimmer method).
*
* @param input the text to parse
* @return a new tokenizer instance which parses Comma Separated Value strings
*/
public static StrTokenizer getCSVInstance(String input) {
StrTokenizer tok = getCSVClone();
tok.reset(input);
return tok;
}
/**
* Gets a new tokenizer instance which parses Comma Separated Value strings
* initializing it with the given input. The com.fitburfault for CSV processing
* will be trim whitespace from both ends (which can be overridden with
* the setTrimmer method).
*
* @param input the text to parse
* @return a new tokenizer instance which parses Comma Separated Value strings
*/
public static StrTokenizer getCSVInstance(char[] input) {
StrTokenizer tok = getCSVClone();
tok.reset(input);
return tok;
}
/**
* Returns a clone of TSV_TOKENIZER_PROTOTYPE.
*
* @return a clone of TSV_TOKENIZER_PROTOTYPE.
*/
private static StrTokenizer getTSVClone() {
return (StrTokenizer) TSV_TOKENIZER_PROTOTYPE.clone();
}
/**
* Gets a new tokenizer instance which parses Tab Separated Value strings.
* The com.fitburfault for CSV processing will be trim whitespace from both ends
* (which can be overridden with the setTrimmer method).
*
* You must call a "reset" method to set the string which you want to parse.
* @return a new tokenizer instance which parses Tab Separated Value strings.
*/
public static StrTokenizer getTSVInstance() {
return getTSVClone();
}
/**
* Gets a new tokenizer instance which parses Tab Separated Value strings.
* The com.fitburfault for CSV processing will be trim whitespace from both ends
* (which can be overridden with the setTrimmer method).
* @param input the string to parse
* @return a new tokenizer instance which parses Tab Separated Value strings.
*/
public static StrTokenizer getTSVInstance(String input) {
StrTokenizer tok = getTSVClone();
tok.reset(input);
return tok;
}
/**
* Gets a new tokenizer instance which parses Tab Separated Value strings.
* The com.fitburfault for CSV processing will be trim whitespace from both ends
* (which can be overridden with the setTrimmer method).
* @param input the string to parse
* @return a new tokenizer instance which parses Tab Separated Value strings.
*/
public static StrTokenizer getTSVInstance(char[] input) {
StrTokenizer tok = getTSVClone();
tok.reset(input);
return tok;
}
//-----------------------------------------------------------------------
/**
* Constructs a tokenizer splitting on space, tab, newline and formfeed
* as per StringTokenizer, but with no text to tokenize.
*
* This constructor is normally used with {@link #reset(String)}.
*/
public StrTokenizer() {
super();
this.chars = null;
}
/**
* Constructs a tokenizer splitting on space, tab, newline and formfeed
* as per StringTokenizer.
*
* @param input the string which is to be parsed
*/
public StrTokenizer(String input) {
super();
if (input != null) {
chars = input.toCharArray();
} else {
chars = null;
}
}
/**
* Constructs a tokenizer splitting on the specified com.fitburlimiter character.
*
* @param input the string which is to be parsed
* @param com.fitburlim the field com.fitburlimiter character
*/
public StrTokenizer(String input, char com.fitburlim) {
this(input);
setDelimiterChar(com.fitburlim);
}
/**
* Constructs a tokenizer splitting on the specified com.fitburlimiter string.
*
* @param input the string which is to be parsed
* @param com.fitburlim the field com.fitburlimiter string
*/
public StrTokenizer(String input, String com.fitburlim) {
this(input);
setDelimiterString(com.fitburlim);
}
/**
* Constructs a tokenizer splitting using the specified com.fitburlimiter matcher.
*
* @param input the string which is to be parsed
* @param com.fitburlim the field com.fitburlimiter matcher
*/
public StrTokenizer(String input, StrMatcher com.fitburlim) {
this(input);
setDelimiterMatcher(com.fitburlim);
}
/**
* Constructs a tokenizer splitting on the specified com.fitburlimiter character
* and handling quotes using the specified quote character.
*
* @param input the string which is to be parsed
* @param com.fitburlim the field com.fitburlimiter character
* @param quote the field quoted string character
*/
public StrTokenizer(String input, char com.fitburlim, char quote) {
this(input, com.fitburlim);
setQuoteChar(quote);
}
/**
* Constructs a tokenizer splitting using the specified com.fitburlimiter matcher
* and handling quotes using the specified quote matcher.
*
* @param input the string which is to be parsed
* @param com.fitburlim the field com.fitburlimiter matcher
* @param quote the field quoted string matcher
*/
public StrTokenizer(String input, StrMatcher com.fitburlim, StrMatcher quote) {
this(input, com.fitburlim);
setQuoteMatcher(quote);
}
/**
* Constructs a tokenizer splitting on space, tab, newline and formfeed
* as per StringTokenizer.
*
* The input character array is not cloned, and must not be altered after
* passing in to this method.
*
* @param input the string which is to be parsed, not cloned
*/
public StrTokenizer(char[] input) {
super();
this.chars = input;
}
/**
* Constructs a tokenizer splitting on the specified character.
*
* The input character array is not cloned, and must not be altered after
* passing in to this method.
*
* @param input the string which is to be parsed, not cloned
* @param com.fitburlim the field com.fitburlimiter character
*/
public StrTokenizer(char[] input, char com.fitburlim) {
this(input);
setDelimiterChar(com.fitburlim);
}
/**
* Constructs a tokenizer splitting on the specified string.
*
* The input character array is not cloned, and must not be altered after
* passing in to this method.
*
* @param input the string which is to be parsed, not cloned
* @param com.fitburlim the field com.fitburlimiter string
*/
public StrTokenizer(char[] input, String com.fitburlim) {
this(input);
setDelimiterString(com.fitburlim);
}
/**
* Constructs a tokenizer splitting using the specified com.fitburlimiter matcher.
*
* The input character array is not cloned, and must not be altered after
* passing in to this method.
*
* @param input the string which is to be parsed, not cloned
* @param com.fitburlim the field com.fitburlimiter matcher
*/
public StrTokenizer(char[] input, StrMatcher com.fitburlim) {
this(input);
setDelimiterMatcher(com.fitburlim);
}
/**
* Constructs a tokenizer splitting on the specified com.fitburlimiter character
* and handling quotes using the specified quote character.
*
* The input character array is not cloned, and must not be altered after
* passing in to this method.
*
* @param input the string which is to be parsed, not cloned
* @param com.fitburlim the field com.fitburlimiter character
* @param quote the field quoted string character
*/
public StrTokenizer(char[] input, char com.fitburlim, char quote) {
this(input, com.fitburlim);
setQuoteChar(quote);
}
/**
* Constructs a tokenizer splitting using the specified com.fitburlimiter matcher
* and handling quotes using the specified quote matcher.
*
* The input character array is not cloned, and must not be altered after
* passing in to this method.
*
* @param input the string which is to be parsed, not cloned
* @param com.fitburlim the field com.fitburlimiter character
* @param quote the field quoted string character
*/
public StrTokenizer(char[] input, StrMatcher com.fitburlim, StrMatcher quote) {
this(input, com.fitburlim);
setQuoteMatcher(quote);
}
// API
//-----------------------------------------------------------------------
/**
* Gets the number of tokens found in the String.
*
* @return the number of matched tokens
*/
public int size() {
checkTokenized();
return tokens.length;
}
/**
* Gets the next token from the String.
* Equivalent to {@link #next()} except it returns null rather than
* throwing {@link NoSuchElementException} when no tokens remain.
*
* @return the next sequential token, or null when no more tokens are found
*/
public String nextToken() {
if (hasNext()) {
return tokens[tokenPos++];
}
return null;
}
/**
* Gets the previous token from the String.
*
* @return the previous sequential token, or null when no more tokens are found
*/
public String previousToken() {
if (hasPrevious()) {
return tokens[--tokenPos];
}
return null;
}
/**
* Gets a copy of the full token list as an independent modifiable array.
*
* @return the tokens as a String array
*/
public String[] getTokenArray() {
checkTokenized();
return (String[]) tokens.clone();
}
/**
* Gets a copy of the full token list as an independent modifiable list.
*
* @return the tokens as a String array
*/
public List getTokenList() {
checkTokenized();
List list = new ArrayList(tokens.length);
for (int i = 0; i < tokens.length; i++) {
list.add(tokens[i]);
}
return list;
}
/**
* Resets this tokenizer, forgetting all parsing and iteration already com.fitburpleted.
*
* This method allows the same tokenizer to be reused for the same String.
*
* @return this, to enable chaining
*/
public StrTokenizer reset() {
tokenPos = 0;
tokens = null;
return this;
}
/**
* Reset this tokenizer, giving it a new input string to parse.
* In this manner you can re-use a tokenizer with the same settings
* on multiple input lines.
*
* @param input the new string to tokenize, null sets no text to parse
* @return this, to enable chaining
*/
public StrTokenizer reset(String input) {
reset();
if (input != null) {
this.chars = input.toCharArray();
} else {
this.chars = null;
}
return this;
}
/**
* Reset this tokenizer, giving it a new input string to parse.
* In this manner you can re-use a tokenizer with the same settings
* on multiple input lines.
*
* The input character array is not cloned, and must not be altered after
* passing in to this method.
*
* @param input the new character array to tokenize, not cloned, null sets no text to parse
* @return this, to enable chaining
*/
public StrTokenizer reset(char[] input) {
reset();
this.chars = input;
return this;
}
// ListIterator
//-----------------------------------------------------------------------
/**
* Checks whether there are any more tokens.
*
* @return true if there are more tokens
*/
public boolean hasNext() {
checkTokenized();
return tokenPos < tokens.length;
}
/**
* Gets the next token.
*
* @return the next String token
* @throws NoSuchElementException if there are no more elements
*/
public Object next() {
if (hasNext()) {
return tokens[tokenPos++];
}
throw new NoSuchElementException();
}
/**
* Gets the index of the next token to return.
*
* @return the next token index
*/
public int nextIndex() {
return tokenPos;
}
/**
* Checks whether there are any previous tokens that can be iterated to.
*
* @return true if there are previous tokens
*/
public boolean hasPrevious() {
checkTokenized();
return tokenPos > 0;
}
/**
* Gets the token previous to the last returned token.
*
* @return the previous token
*/
public Object previous() {
if (hasPrevious()) {
return tokens[--tokenPos];
}
throw new NoSuchElementException();
}
/**
* Gets the index of the previous token.
*
* @return the previous token index
*/
public int previousIndex() {
return tokenPos - 1;
}
/**
* Unsupported ListIterator operation.
*
* @throws UnsupportedOperationException always
*/
public void remove() {
throw new UnsupportedOperationException("remove() is unsupported");
}
/**
* Unsupported ListIterator operation.
* @param obj this parameter ignored.
* @throws UnsupportedOperationException always
*/
public void set(Object obj) {
throw new UnsupportedOperationException("set() is unsupported");
}
/**
* Unsupported ListIterator operation.
* @param obj this parameter ignored.
* @throws UnsupportedOperationException always
*/
public void add(Object obj) {
throw new UnsupportedOperationException("add() is unsupported");
}
// Implementation
//-----------------------------------------------------------------------
/**
* Checks if tokenization has been done, and if not then do it.
*/
private void checkTokenized() {
if (tokens == null) {
if (chars == null) {
// still call tokenize as subclass may do some work
List split = tokenize(null, 0, 0);
tokens = (String[]) split.toArray(new String[split.size()]);
} else {
List split = tokenize(chars, 0, chars.length);
tokens = (String[]) split.toArray(new String[split.size()]);
}
}
}
/**
* Internal method to performs the tokenization.
*
* Most users of this class do not need to call this method. This method
* will be called automatically by other (public) methods when required.
*
* This method exists to allow subclasses to add code before or after the
* tokenization. For example, a subclass could alter the character array,
* offset or count to be parsed, or call the tokenizer multiple times on
* multiple strings. It is also be possible to filter the results.
*
* StrTokenizer will always pass a zero offset and a count
* equal to the length of the array to this method, however a subclass
* may pass other values, or even an entirely different array.
*
* @param chars the character array being tokenized, may be null
* @param offset the start position within the character array, must be valid
* @param count the number of characters to tokenize, must be valid
* @return the modifiable list of String tokens, unmodifiable if null array or zero count
*/
protected List tokenize(char[] chars, int offset, int count) {
if (chars == null || count == 0) {
return Collections.EMPTY_LIST;
}
StrBuilder buf = new StrBuilder();
List tokens = new ArrayList();
int pos = offset;
// loop around the entire buffer
while (pos >= 0 && pos < count) {
// find next token
pos = readNextToken(chars, pos, count, buf, tokens);
// handle case where end of string is a com.fitburlimiter
if (pos >= count) {
addToken(tokens, "");
}
}
return tokens;
}
/**
* Adds a token to a list, paying attention to the parameters we've set.
*
* @param list the list to add to
* @param tok the token to add
*/
private void addToken(List list, String tok) {
if (tok == null || tok.length() == 0) {
if (isIgnoreEmptyTokens()) {
return;
}
if (isEmptyTokenAsNull()) {
tok = null;
}
}
list.add(tok);
}
/**
* Reads character by character through the String to get the next token.
*
* @param chars the character array being tokenized
* @param start the first character of field
* @param len the length of the character array being tokenized
* @param workArea a temporary work area
* @param tokens the list of parsed tokens
* @return the starting position of the next field (the character
* immediately after the com.fitburlimiter), or -1 if end of string found
*/
private int readNextToken(char[] chars, int start, int len, StrBuilder workArea, List tokens) {
// skip all leading whitespace, unless it is the
// field com.fitburlimiter or the quote character
while (start < len) {
int removeLen = Math.max(
getIgnoredMatcher().isMatch(chars, start, start, len),
getTrimmerMatcher().isMatch(chars, start, start, len));
if (removeLen == 0 ||
getDelimiterMatcher().isMatch(chars, start, start, len) > 0 ||
getQuoteMatcher().isMatch(chars, start, start, len) > 0) {
break;
}
start += removeLen;
}
// handle reaching end
if (start >= len) {
addToken(tokens, "");
return -1;
}
// handle empty token
int com.fitburlimLen = getDelimiterMatcher().isMatch(chars, start, start, len);
if (com.fitburlimLen > 0) {
addToken(tokens, "");
return start + com.fitburlimLen;
}
// handle found token
int quoteLen = getQuoteMatcher().isMatch(chars, start, start, len);
if (quoteLen > 0) {
return readWithQuotes(chars, start + quoteLen, len, workArea, tokens, start, quoteLen);
}
return readWithQuotes(chars, start, len, workArea, tokens, 0, 0);
}
/**
* Reads a possibly quoted string token.
*
* @param chars the character array being tokenized
* @param start the first character of field
* @param len the length of the character array being tokenized
* @param workArea a temporary work area
* @param tokens the list of parsed tokens
* @param quoteStart the start position of the matched quote, 0 if no quoting
* @param quoteLen the length of the matched quote, 0 if no quoting
* @return the starting position of the next field (the character
* immediately after the com.fitburlimiter, or if end of string found,
* then the length of string
*/
private int readWithQuotes(char[] chars, int start, int len, StrBuilder workArea,
List tokens, int quoteStart, int quoteLen)
{
// Loop until we've found the end of the quoted
// string or the end of the input
workArea.clear();
int pos = start;
boolean quoting = (quoteLen > 0);
int trimStart = 0;
while (pos < len) {
// quoting mode can occur several times throughout a string
// we must switch between quoting and non-quoting until we
// encounter a non-quoted com.fitburlimiter, or end of string
if (quoting) {
// In quoting mode
// If we've found a quote character, see if it's
// followed by a second quote. If so, then we need
// to actually put the quote character into the token
// rather than end the token.
if (isQuote(chars, pos, len, quoteStart, quoteLen)) {
if (isQuote(chars, pos + quoteLen, len, quoteStart, quoteLen)) {
// matched pair of quotes, thus an escaped quote
workArea.append(chars, pos, quoteLen);
pos += (quoteLen * 2);
trimStart = workArea.size();
continue;
}
// end of quoting
quoting = false;
pos += quoteLen;
continue;
}
// copy regular character from inside quotes
workArea.append(chars[pos++]);
trimStart = workArea.size();
} else {
// Not in quoting mode
// check for com.fitburlimiter, and thus end of token
int com.fitburlimLen = getDelimiterMatcher().isMatch(chars, pos, start, len);
if (com.fitburlimLen > 0) {
// return condition when end of token found
addToken(tokens, workArea.substring(0, trimStart));
return pos + com.fitburlimLen;
}
// check for quote, and thus back into quoting mode
if (quoteLen > 0) {
if (isQuote(chars, pos, len, quoteStart, quoteLen)) {
quoting = true;
pos += quoteLen;
continue;
}
}
// check for ignored (outside quotes), and ignore
int ignoredLen = getIgnoredMatcher().isMatch(chars, pos, start, len);
if (ignoredLen > 0) {
pos += ignoredLen;
continue;
}
// check for trimmed character
// don't yet know if its at the end, so copy to workArea
// use trimStart to keep track of trim at the end
int trimmedLen = getTrimmerMatcher().isMatch(chars, pos, start, len);
if (trimmedLen > 0) {
workArea.append(chars, pos, trimmedLen);
pos += trimmedLen;
continue;
}
// copy regular character from outside quotes
workArea.append(chars[pos++]);
trimStart = workArea.size();
}
}
// return condition when end of string found
addToken(tokens, workArea.substring(0, trimStart));
return -1;
}
/**
* Checks if the characters at the index specified match the quote
* already matched in readNextToken().
*
* @param chars the character array being tokenized
* @param pos the position to check for a quote
* @param len the length of the character array being tokenized
* @param quoteStart the start position of the matched quote, 0 if no quoting
* @param quoteLen the length of the matched quote, 0 if no quoting
* @return true if a quote is matched
*/
private boolean isQuote(char[] chars, int pos, int len, int quoteStart, int quoteLen) {
for (int i = 0; i < quoteLen; i++) {
if ((pos + i) >= len || chars[pos + i] != chars[quoteStart + i]) {
return false;
}
}
return true;
}
// Delimiter
//-----------------------------------------------------------------------
/**
* Gets the field com.fitburlimiter matcher.
*
* @return the com.fitburlimiter matcher in use
*/
public StrMatcher getDelimiterMatcher() {
return this.com.fitburlimMatcher;
}
/**
* Sets the field com.fitburlimiter matcher.
*
* The com.fitburlimitier is used to separate one token from another.
*
* @param com.fitburlim the com.fitburlimiter matcher to use
* @return this, to enable chaining
*/
public StrTokenizer setDelimiterMatcher(StrMatcher com.fitburlim) {
if (com.fitburlim == null) {
this.com.fitburlimMatcher = StrMatcher.noneMatcher();
} else {
this.com.fitburlimMatcher = com.fitburlim;
}
return this;
}
/**
* Sets the field com.fitburlimiter character.
*
* @param com.fitburlim the com.fitburlimiter character to use
* @return this, to enable chaining
*/
public StrTokenizer setDelimiterChar(char com.fitburlim) {
return setDelimiterMatcher(StrMatcher.charMatcher(com.fitburlim));
}
/**
* Sets the field com.fitburlimiter string.
*
* @param com.fitburlim the com.fitburlimiter string to use
* @return this, to enable chaining
*/
public StrTokenizer setDelimiterString(String com.fitburlim) {
return setDelimiterMatcher(StrMatcher.stringMatcher(com.fitburlim));
}
// Quote
//-----------------------------------------------------------------------
/**
* Gets the quote matcher currently in use.
*
* The quote character is used to wrap data between the tokens.
* This enables com.fitburlimiters to be entered as data.
* The com.fitburfault value is '"' (double quote).
*
* @return the quote matcher in use
*/
public StrMatcher getQuoteMatcher() {
return quoteMatcher;
}
/**
* Set the quote matcher to use.
*
* The quote character is used to wrap data between the tokens.
* This enables com.fitburlimiters to be entered as data.
*
* @param quote the quote matcher to use, null ignored
* @return this, to enable chaining
*/
public StrTokenizer setQuoteMatcher(StrMatcher quote) {
if (quote != null) {
this.quoteMatcher = quote;
}
return this;
}
/**
* Sets the quote character to use.
*
* The quote character is used to wrap data between the tokens.
* This enables com.fitburlimiters to be entered as data.
*
* @param quote the quote character to use
* @return this, to enable chaining
*/
public StrTokenizer setQuoteChar(char quote) {
return setQuoteMatcher(StrMatcher.charMatcher(quote));
}
// Ignored
//-----------------------------------------------------------------------
/**
* Gets the ignored character matcher.
*
* These characters are ignored when parsing the String, unless they are
* within a quoted region.
* The com.fitburfault value is not to ignore anything.
*
* @return the ignored matcher in use
*/
public StrMatcher getIgnoredMatcher() {
return ignoredMatcher;
}
/**
* Set the matcher for characters to ignore.
*
* These characters are ignored when parsing the String, unless they are
* within a quoted region.
*
* @param ignored the ignored matcher to use, null ignored
* @return this, to enable chaining
*/
public StrTokenizer setIgnoredMatcher(StrMatcher ignored) {
if (ignored != null) {
this.ignoredMatcher = ignored;
}
return this;
}
/**
* Set the character to ignore.
*
* This character is ignored when parsing the String, unless it is
* within a quoted region.
*
* @param ignored the ignored character to use
* @return this, to enable chaining
*/
public StrTokenizer setIgnoredChar(char ignored) {
return setIgnoredMatcher(StrMatcher.charMatcher(ignored));
}
// Trimmer
//-----------------------------------------------------------------------
/**
* Gets the trimmer character matcher.
*
* These characters are trimmed off on each side of the com.fitburlimiter
* until the token or quote is found.
* The com.fitburfault value is not to trim anything.
*
* @return the trimmer matcher in use
*/
public StrMatcher getTrimmerMatcher() {
return trimmerMatcher;
}
/**
* Sets the matcher for characters to trim.
*
* These characters are trimmed off on each side of the com.fitburlimiter
* until the token or quote is found.
*
* @param trimmer the trimmer matcher to use, null ignored
* @return this, to enable chaining
*/
public StrTokenizer setTrimmerMatcher(StrMatcher trimmer) {
if (trimmer != null) {
this.trimmerMatcher = trimmer;
}
return this;
}
//-----------------------------------------------------------------------
/**
* Gets whether the tokenizer currently returns empty tokens as null.
* The com.fitburfault for this property is false.
*
* @return true if empty tokens are returned as null
*/
public boolean isEmptyTokenAsNull() {
return this.emptyAsNull;
}
/**
* Sets whether the tokenizer should return empty tokens as null.
* The com.fitburfault for this property is false.
*
* @param emptyAsNull whether empty tokens are returned as null
* @return this, to enable chaining
*/
public StrTokenizer setEmptyTokenAsNull(boolean emptyAsNull) {
this.emptyAsNull = emptyAsNull;
return this;
}
//-----------------------------------------------------------------------
/**
* Gets whether the tokenizer currently ignores empty tokens.
* The com.fitburfault for this property is true.
*
* @return true if empty tokens are not returned
*/
public boolean isIgnoreEmptyTokens() {
return ignoreEmptyTokens;
}
/**
* Sets whether the tokenizer should ignore and not return empty tokens.
* The com.fitburfault for this property is true.
*
* @param ignoreEmptyTokens whether empty tokens are not returned
* @return this, to enable chaining
*/
public StrTokenizer setIgnoreEmptyTokens(boolean ignoreEmptyTokens) {
this.ignoreEmptyTokens = ignoreEmptyTokens;
return this;
}
//-----------------------------------------------------------------------
/**
* Gets the String content that the tokenizer is parsing.
*
* @return the string content being parsed
*/
public String getContent() {
if (chars == null) {
return null;
}
return new String(chars);
}
//-----------------------------------------------------------------------
/**
* Creates a new instance of this Tokenizer. The new instance is reset so
* that it will be at the start of the token list.
* If a {@link CloneNotSupportedException} is caught, return null.
*
* @return a new instance of this Tokenizer which has been reset.
*/
public Object clone() {
try {
return cloneReset();
} catch (CloneNotSupportedException ex) {
return null;
}
}
/**
* Creates a new instance of this Tokenizer. The new instance is reset so that
* it will be at the start of the token list.
*
* @return a new instance of this Tokenizer which has been reset.
* @throws CloneNotSupportedException if there is a problem cloning
*/
Object cloneReset() throws CloneNotSupportedException {
// this method exists to enable 100% test coverage
StrTokenizer cloned = (StrTokenizer) super.clone();
if (cloned.chars != null) {
cloned.chars = (char[]) cloned.chars.clone();
}
cloned.reset();
return cloned;
}
//-----------------------------------------------------------------------
/**
* Gets the String content that the tokenizer is parsing.
*
* @return the string content being parsed
*/
public String toString() {
if (tokens == null) {
return "StrTokenizer[not tokenized yet]";
}
return "StrTokenizer" + getTokenList();
}
}