Java Tutorial/File/CSV — различия между версиями
Admin (обсуждение | вклад) м (1 версия) |
|
(нет различий)
| |
Текущая версия на 05:20, 1 июня 2010
Содержание
- 1 Builds a bracketed CSV list from the array
- 2 Builds a CSV list from the specified String[], separator string and quote string
- 3 Builds a CSV list from the specified two dimensional String[][], separator string and quote string.
- 4 CVS reader
- 5 Helper class to write table data to a csv-file (comma separated values).
- 6 The CSVQuoter is a helper class to encode a string for the CSV file format.
- 7 The csv tokenizer class allows an application to break a Comma Separated Value format into tokens.
Builds a bracketed CSV list from the array
import java.lang.reflect.Array;
/* Copyright (c) 2001-2009, The HSQL Development Group
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer.
*
* Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* Neither the name of the HSQL Development Group nor the names of its
* contributors may be used to endorse or promote products derived from this
* software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL HSQL DEVELOPMENT GROUP, HSQLDB.ORG,
* OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
/** Provides a collection of convenience methods for processing and
* creating objects with <code>String</code> value components.
*
* @author Campbell Boucher-Burnett (boucherb@users dot sourceforge.net)
* @author Fred Toussi (fredt@users dot sourceforge.net)
* @author Nitin Chauhan
* @version 1.9.0
* @since 1.7.0
*/
public class Main {
/**
* Builds a bracketed CSV list from the array
* @param array an array of Objects
* @return string
*/
public static String arrayToString(Object array) {
int len = Array.getLength(array);
int last = len - 1;
StringBuffer sb = new StringBuffer(2 * (len + 1));
sb.append("{");
for (int i = 0; i < len; i++) {
sb.append(Array.get(array, i));
if (i != last) {
sb.append(",");
}
}
sb.append("}");
return sb.toString();
}
}
Builds a CSV list from the specified String[], separator string and quote string
import java.lang.reflect.Array;
/* Copyright (c) 2001-2009, The HSQL Development Group
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer.
*
* Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* Neither the name of the HSQL Development Group nor the names of its
* contributors may be used to endorse or promote products derived from this
* software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL HSQL DEVELOPMENT GROUP, HSQLDB.ORG,
* OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
/** Provides a collection of convenience methods for processing and
* creating objects with <code>String</code> value components.
*
* @author Campbell Boucher-Burnett (boucherb@users dot sourceforge.net)
* @author Fred Toussi (fredt@users dot sourceforge.net)
* @author Nitin Chauhan
* @version 1.9.0
* @since 1.7.0
*/
public class Main {
/**
* Builds a CSV list from the specified String[], separator string and
* quote string.
*
* <ul>
* <li>All arguments are assumed to be non-null.
* <li>Separates each list element with the value of the
* <code>separator</code> argument.
* <li>Prepends and appends each element with the value of the
* <code>quote</code> argument.
* <li> No attempt is made to escape the quote character sequence if it is
* found internal to a list element.
* <ul>
* @return a CSV list
* @param separator the <code>String</code> to use as the list element separator
* @param quote the <code>String</code> with which to quote the list elements
* @param s array of <code>String</code> objects
*/
public static String getList(String[] s, String separator, String quote) {
int len = s.length;
StringBuffer sb = new StringBuffer(len * 16);
for (int i = 0; i < len; i++) {
sb.append(quote);
sb.append(s[i]);
sb.append(quote);
if (i + 1 < len) {
sb.append(separator);
}
}
return sb.toString();
}
}
Builds a CSV list from the specified two dimensional String[][], separator string and quote string.
import java.lang.reflect.Array;
/* Copyright (c) 2001-2009, The HSQL Development Group
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer.
*
* Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* Neither the name of the HSQL Development Group nor the names of its
* contributors may be used to endorse or promote products derived from this
* software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL HSQL DEVELOPMENT GROUP, HSQLDB.ORG,
* OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
/** Provides a collection of convenience methods for processing and
* creating objects with <code>String</code> value components.
*
* @author Campbell Boucher-Burnett (boucherb@users dot sourceforge.net)
* @author Fred Toussi (fredt@users dot sourceforge.net)
* @author Nitin Chauhan
* @version 1.9.0
* @since 1.7.0
*/
public class Main {
/**
* Builds a CSV list from the specified String[][], separator string and
* quote string.
*
* <ul>
* <li>All arguments are assumed to be non-null.
* <li>Uses only the first element in each subarray.
* <li>Separates each list element with the value of the
* <code>separator</code> argument.
* <li>Prepends and appends each element with the value of the
* <code>quote</code> argument.
* <li> No attempt is made to escape the quote character sequence if it is
* found internal to a list element.
* <ul>
* @return a CSV list
* @param separator the <code>String</code> to use as the list element separator
* @param quote the <code>String</code> with which to quote the list elements
* @param s the array of <code>String</code> array objects
*/
public static String getList(String[][] s, String separator,
String quote) {
int len = s.length;
StringBuffer sb = new StringBuffer(len * 16);
for (int i = 0; i < len; i++) {
sb.append(quote);
sb.append(s[i][0]);
sb.append(quote);
if (i + 1 < len) {
sb.append(separator);
}
}
return sb.toString();
}
}
CVS reader
package au.ru.bytecode.opencsv;
/**
Copyright 2005 Bytecode Pty Ltd.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
*/
import java.io.BufferedReader;
import java.io.IOException;
import java.io.Reader;
import java.util.ArrayList;
import java.util.List;
/**
* A very simple CSV reader released under a commercial-friendly license.
*
* @author Glen Smith
*
*/
public class CSVReader {
private BufferedReader br;
private boolean hasNext = true;
private char separator;
private char quotechar;
private int skipLines;
private boolean linesSkiped;
/** The default separator to use if none is supplied to the constructor. */
public static final char DEFAULT_SEPARATOR = ",";
/**
* The default quote character to use if none is supplied to the
* constructor.
*/
public static final char DEFAULT_QUOTE_CHARACTER = """;
/**
* The default line to start reading.
*/
public static final int DEFAULT_SKIP_LINES = 0;
/**
* Constructs CSVReader using a comma for the separator.
*
* @param reader
* the reader to an underlying CSV source.
*/
public CSVReader(Reader reader) {
this(reader, DEFAULT_SEPARATOR);
}
/**
* Constructs CSVReader with supplied separator.
*
* @param reader
* the reader to an underlying CSV source.
* @param separator
* the delimiter to use for separating entries.
*/
public CSVReader(Reader reader, char separator) {
this(reader, separator, DEFAULT_QUOTE_CHARACTER);
}
/**
* Constructs CSVReader with supplied separator and quote char.
*
* @param reader
* the reader to an underlying CSV source.
* @param separator
* the delimiter to use for separating entries
* @param quotechar
* the character to use for quoted elements
*/
public CSVReader(Reader reader, char separator, char quotechar) {
this(reader, separator, quotechar, DEFAULT_SKIP_LINES);
}
/**
* Constructs CSVReader with supplied separator and quote char.
*
* @param reader
* the reader to an underlying CSV source.
* @param separator
* the delimiter to use for separating entries
* @param quotechar
* the character to use for quoted elements
* @param line
* the line number to skip for start reading
*/
public CSVReader(Reader reader, char separator, char quotechar, int line) {
this.br = new BufferedReader(reader);
this.separator = separator;
this.quotechar = quotechar;
this.skipLines = line;
}
/**
* Reads the entire file into a List with each element being a String[] of
* tokens.
*
* @return a List of String[], with each String[] representing a line of the
* file.
*
* @throws IOException
* if bad things happen during the read
*/
public List readAll() throws IOException {
List allElements = new ArrayList();
while (hasNext) {
String[] nextLineAsTokens = readNext();
if (nextLineAsTokens != null)
allElements.add(nextLineAsTokens);
}
return allElements;
}
/**
* Reads the next line from the buffer and converts to a string array.
*
* @return a string array with each comma-separated element as a separate
* entry.
*
* @throws IOException
* if bad things happen during the read
*/
public String[] readNext() throws IOException {
String nextLine = getNextLine();
return hasNext ? parseLine(nextLine) : null;
}
/**
* Reads the next line from the file.
*
* @return the next line from the file without trailing newline
* @throws IOException
* if bad things happen during the read
*/
private String getNextLine() throws IOException {
if (!this.linesSkiped) {
for (int i = 0; i < skipLines; i++) {
br.readLine();
}
this.linesSkiped = true;
}
String nextLine = br.readLine();
if (nextLine == null) {
hasNext = false;
}
return hasNext ? nextLine : null;
}
/**
* Parses an incoming String and returns an array of elements.
*
* @param nextLine
* the string to parse
* @return the comma-tokenized list of elements, or null if nextLine is null
* @throws IOException if bad things happen during the read
*/
private String[] parseLine(String nextLine) throws IOException {
if (nextLine == null) {
return null;
}
List tokensOnThisLine = new ArrayList();
StringBuffer sb = new StringBuffer();
boolean inQuotes = false;
do {
if (inQuotes) {
// continuing a quoted section, reappend newline
sb.append("\n");
nextLine = getNextLine();
if (nextLine == null)
break;
}
for (int i = 0; i < nextLine.length(); i++) {
char c = nextLine.charAt(i);
if (c == quotechar) {
// this gets complex... the quote may end a quoted block, or escape another quote.
// do a 1-char lookahead:
if( inQuotes // we are in quotes, therefore there can be escaped quotes in here.
&& nextLine.length() > (i+1) // there is indeed another character to check.
&& nextLine.charAt(i+1) == quotechar ){ // ..and that char. is a quote also.
// we have two quote chars in a row == one quote char, so consume them both and
// put one on the token. we do *not* exit the quoted text.
sb.append(nextLine.charAt(i+1));
i++;
}else{
inQuotes = !inQuotes;
// the tricky case of an embedded quote in the middle: a,bc"d"ef,g
if(i>2 //not on the begining of the line
&& nextLine.charAt(i-1) != this.separator //not at the begining of an escape sequence
&& nextLine.length()>(i+1) &&
nextLine.charAt(i+1) != this.separator //not at the end of an escape sequence
){
sb.append(c);
}
}
} else if (c == separator && !inQuotes) {
tokensOnThisLine.add(sb.toString());
sb = new StringBuffer(); // start work on next token
} else {
sb.append(c);
}
}
} while (inQuotes);
tokensOnThisLine.add(sb.toString());
return (String[]) tokensOnThisLine.toArray(new String[0]);
}
/**
* Closes the underlying reader.
*
* @throws IOException if the close fails
*/
public void close() throws IOException{
br.close();
}
}
///////////////////////////////////////////
package au.ru.bytecode.opencsv;
/**
Copyright 2005 Bytecode Pty Ltd.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
*/
import java.io.IOException;
import java.io.StringReader;
import java.util.List;
import junit.framework.TestCase;
public class CSVReaderTest extends TestCase {
CSVReader csvr;
/**
* Setup the test.
*/
protected void setUp() throws Exception {
StringBuffer sb = new StringBuffer();
sb.append("a,b,c").append("\n"); // standard case
sb.append("a,\"b,b,b\",c").append("\n"); // quoted elements
sb.append(",,").append("\n"); // empty elements
sb.append("a,\"PO Box 123,\nKippax,ACT. 2615.\nAustralia\",d.\n");
sb.append("\"Glen \"\"The Man\"\" Smith\",Athlete,Developer\n"); // Test quoted quote chars
sb.append("\"\"\"\"\"\",\"test\"\n"); // """""","test" representing: "", test
sb.append("\"a\nb\",b,\"\nd\",e\n");
csvr = new CSVReader(new StringReader(sb.toString()));
}
/**
* Tests iterating over a reader.
*
* @throws IOException
* if the reader fails.
*/
public void testParseLine() throws IOException {
// test normal case
String[] nextLine = csvr.readNext();
assertEquals("a", nextLine[0]);
assertEquals("b", nextLine[1]);
assertEquals("c", nextLine[2]);
// test quoted commas
nextLine = csvr.readNext();
assertEquals("a", nextLine[0]);
assertEquals("b,b,b", nextLine[1]);
assertEquals("c", nextLine[2]);
// test empty elements
nextLine = csvr.readNext();
assertEquals(3, nextLine.length);
// test multiline quoted
nextLine = csvr.readNext();
assertEquals(3, nextLine.length);
// test quoted quote chars
nextLine = csvr.readNext();
assertEquals("Glen \"The Man\" Smith", nextLine[0]);
nextLine = csvr.readNext();
assertTrue(nextLine[0].equals("\"\"")); // check the tricky situation
assertTrue(nextLine[1].equals("test")); // make sure we didn"t ruin the next field..
nextLine = csvr.readNext();
assertEquals(4, nextLine.length);
//test end of stream
assertEquals(null, csvr.readNext());
}
/**
* Test parsing to a list.
*
* @throws IOException
* if the reader fails.
*/
public void testParseAll() throws IOException {
List allElements = csvr.readAll();
assertEquals(7, allElements.size());
}
/**
* Tests constructors with optional delimiters and optional quote char.
*
* @throws IOException if the reader fails.
*/
public void testOptionalConstructors() throws IOException {
StringBuffer sb = new StringBuffer();
sb.append("a\tb\tc").append("\n"); // tab separated case
sb.append("a\t"b\tb\tb"\tc").append("\n"); // single quoted elements
CSVReader c = new CSVReader(new StringReader(sb.toString()), "\t", "\"");
String[] nextLine = c.readNext();
assertEquals(3, nextLine.length);
nextLine = c.readNext();
assertEquals(3, nextLine.length);
}
/**
* Tests option to skip the first few lines of a file.
*
* @throws IOException if bad things happen
*/
public void testSkippingLines() throws IOException {
StringBuffer sb = new StringBuffer();
sb.append("Skip this line\t with tab").append("\n"); // should skip this
sb.append("And this line too").append("\n"); // and this
sb.append("a\t"b\tb\tb"\tc").append("\n"); // single quoted elements
CSVReader c = new CSVReader(new StringReader(sb.toString()), "\t", "\"", 2);
String[] nextLine = c.readNext();
assertEquals(3, nextLine.length);
assertEquals("a", nextLine[0]);
}
/**
* Tests quotes in the middle of an element.
*
* @throws IOException if bad things happen
*/
public void testParsedLineWithInternalQuota() throws IOException {
StringBuffer sb = new StringBuffer();
sb.append("a,123\"4\"567,c").append("\n");// a,123"4",c
CSVReader c = new CSVReader(new StringReader(sb.toString()));
String[] nextLine = c.readNext();
assertEquals(3, nextLine.length);
System.out.println(nextLine[1]);
assertEquals("123\"4\"567", nextLine[1]);
}
/**
* The Test Runner for commandline use.
*
* @param args
* no args required
*/
public static void main(String args[]) {
junit.textui.TestRunner.run(CSVReaderTest.class);
}
}
Helper class to write table data to a csv-file (comma separated values).
/* Copyright (c) 2001-2009, The HSQL Development Group
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* Redistributions of source code must retain the above copyright notice, this
* list of conditions and the following disclaimer.
*
* Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* Neither the name of the HSQL Development Group nor the names of its
* contributors may be used to endorse or promote products derived from this
* software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL HSQL DEVELOPMENT GROUP, HSQLDB.ORG,
* OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
/**
* helper class to write table data to a csv-file (comma separated values).
* the first line in file is a list of fieldnames, all following lines
* are data lines.
* a descptiontion of file format can be found on: http://www.wotsit.org/
* usage: create a object using the constructor. call writeHeader
* for writing the filename header then add data with writeData.
* at the end close() closes the file.
*
*@author jeberle@users
*/
public class CSVWriter {
private String newline = System.getProperty("line.separator");
private OutputStreamWriter writer = null;
private int nbrCols = 0;
private int nbrRows = 0;
/**
* constructor.
* creates a csv file for writing data to it
* @param file the file to write data to
* @param encoding encoding to use or null (=defualt)
*/
public CSVWriter(File file, String encoding) throws IOException {
if (encoding == null) {
encoding = System.getProperty("file.encoding");
}
FileOutputStream fout = new FileOutputStream(file);
writer = new OutputStreamWriter(fout, encoding);
}
/**
* writes the csv header (fieldnames). should be called after
* construction one time.
* @param header String[] with fieldnames
*/
public void writeHeader(String[] header) throws IOException {
this.nbrCols = header.length;
doWriteData(header);
}
/**
* writes a data-record to the file. note that data[] must have
* same number of elements as the header had.
*
* @param data data to write to csv-file
*/
public void writeData(String[] data) throws IOException {
doWriteData(data);
}
/**
* closes the csv file.
*/
public void close() throws IOException {
this.writer.close();
}
private void doWriteData(String[] values) throws IOException {
for (int i = 0; i < values.length; i++) {
if (i > 0) {
this.writer.write(";");
}
if (values[i] != null) {
this.writer.write("\"");
this.writer.write(this.toCsvValue(values[i]));
this.writer.write("\"");
}
}
this.writer.write(newline);
this.nbrRows++;
}
private String toCsvValue(String str) {
StringBuffer sb = new StringBuffer();
for (int i = 0; i < str.length(); i++) {
char c = str.charAt(i);
sb.append(c);
switch (c) {
case """ :
sb.append(""");
break;
}
}
return sb.toString();
}
}
The CSVQuoter is a helper class to encode a string for the CSV file format.
/**
*
* JFreeReport : a free Java reporting library
*
*
* Project Info: http://reporting.pentaho.org/
*
* (C) Copyright 2001-2007, by Object Refinery Ltd, Pentaho Corporation and Contributors.
*
* This library is free software; you can redistribute it and/or modify it under the terms
* of the GNU Lesser General Public License as published by the Free Software Foundation;
* either version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY;
* without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
* See the GNU Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License along with this
* library; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330,
* Boston, MA 02111-1307, USA.
*
* [Java is a trademark or registered trademark of Sun Microsystems, Inc.
* in the United States and other countries.]
*
* ------------
* CSVQuoter.java
* ------------
* (C) Copyright 2001-2007, by Object Refinery Ltd, Pentaho Corporation and Contributors.
*/
/**
* The <code>CSVQuoter</code> is a helper class to encode a string for the CSV file
* format.
*
* @author Thomas Morgner.
*/
public class CSVQuoter
{
/**
* The separator used in the CSV file.
*/
private char separator;
/**
* The quoting character or a single quote.
*/
private char quate;
/**
* The double quote. This is a string containing the quate two times.
*/
private String doubleQuate;
/**
* Creates a new CSVQuoter, which uses a comma as the default separator.
*/
public CSVQuoter ()
{
this(",", """);
}
/**
* Creates a new <code>CSVQuoter</code>, which uses the defined separator.
*
* @param separator the separator.
* @throws NullPointerException if the given separator is <code>null</code>.
*/
public CSVQuoter (final char separator)
{
this(separator, """);
}
/**
* Creates a new CSVQuoter with the given separator and quoting character.
*
* @param separator the separator
* @param quate the quoting character
*/
public CSVQuoter (final char separator, final char quate)
{
this.separator = separator;
this.quate = quate;
this.doubleQuate = String.valueOf(quate) + quate;
}
/**
* Encodes the string, so that the string can safely be used in CSV files. If the string
* does not need quoting, the original string is returned unchanged.
*
* @param original the unquoted string.
* @return The quoted string
*/
public String doQuoting (final String original)
{
if (isQuotingNeeded(original))
{
final StringBuffer retval = new StringBuffer();
retval.append(quate);
applyQuote(retval, original);
retval.append(quate);
return retval.toString();
}
else
{
return original;
}
}
/**
* Decodes the string, so that all escape sequences get removed. If the string was not
* quoted, then the string is returned unchanged.
*
* @param nativeString the quoted string.
* @return The unquoted string.
*/
public String undoQuoting (final String nativeString)
{
if (isQuotingNeeded(nativeString))
{
final StringBuffer b = new StringBuffer(nativeString.length());
final int length = nativeString.length() - 1;
int start = 1;
int pos = start;
while (pos != -1)
{
pos = nativeString.indexOf(doubleQuate, start);
if (pos == -1)
{
b.append(nativeString.substring(start, length));
}
else
{
b.append(nativeString.substring(start, pos));
start = pos + 1;
}
}
return b.toString();
}
else
{
return nativeString;
}
}
/**
* Tests, whether this string needs to be quoted. A string is encoded if the string
* contains a newline character, a quote character or the defined separator.
*
* @param str the string that should be tested.
* @return true, if quoting needs to be applied, false otherwise.
*/
private boolean isQuotingNeeded (final String str)
{
if (str.indexOf(separator) != -1)
{
return true;
}
if (str.indexOf("\n") != -1)
{
return true;
}
if (str.indexOf(quate, 1) != -1)
{
return true;
}
return false;
}
/**
* Applies the quoting to a given string, and stores the result in the StringBuffer
* <code>b</code>.
*
* @param b the result buffer
* @param original the string, that should be quoted.
*/
private void applyQuote (final StringBuffer b, final String original)
{
// This solution needs improvements. Copy blocks instead of single
// characters.
final int length = original.length();
for (int i = 0; i < length; i++)
{
final char c = original.charAt(i);
if (c == quate)
{
b.append(doubleQuate);
}
else
{
b.append(c);
}
}
}
/**
* Gets the separator used in this quoter and the CSV file.
*
* @return the separator (never <code>null</code>).
*/
public char getSeparator ()
{
return separator;
}
/**
* Returns the quoting character.
*
* @return the quote character.
*/
public char getQuate ()
{
return quate;
}
}
The csv tokenizer class allows an application to break a Comma Separated Value format into tokens.
/**
*
* JFreeReport : a free Java reporting library
*
*
* Project Info: http://reporting.pentaho.org/
*
* (C) Copyright 2001-2007, by Object Refinery Ltd, Pentaho Corporation and Contributors.
*
* This library is free software; you can redistribute it and/or modify it under the terms
* of the GNU Lesser General Public License as published by the Free Software Foundation;
* either version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY;
* without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
* See the GNU Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License along with this
* library; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330,
* Boston, MA 02111-1307, USA.
*
* [Java is a trademark or registered trademark of Sun Microsystems, Inc.
* in the United States and other countries.]
*
* ------------
* CSVTokenizer.java
* ------------
* (C) Copyright 2001-2007, by Object Refinery Ltd, Pentaho Corporation and Contributors.
*/
import java.util.Enumeration;
import java.util.NoSuchElementException;
/**
* The csv tokenizer class allows an application to break a Comma Separated Value format into tokens. The tokenization
* method is much simpler than the one used by the <code>StringTokenizer</code> class. The <code>CSVTokenizer</code>
* methods do not distinguish among identifiers, numbers, and quoted strings, nor do they recognize and skip comments.
*
* The set of separator (the characters that separate tokens) may be specified either at creation time or on a per-token
* basis.
*
* An instance of <code>CSVTokenizer</code> behaves in one of two ways, depending on whether it was created with the
* <code>returnSeparators</code> flag having the value <code>true</code> or <code>false</code>: <ul> <li>If the flag is
* <code>false</code>, delimiter characters serve to separate tokens. A token is a maximal sequence of consecutive
* characters that are not separator. <li>If the flag is <code>true</code>, delimiter characters are themselves
* considered to be tokens. A token is thus either one delimiter character, or a maximal sequence of consecutive
* characters that are not separator. </ul> A <tt>CSVTokenizer</tt> object internally maintains a current position
* within the string to be tokenized. Some operations advance this current position past the characters processed. A
* token is returned by taking a substring of the string that was used to create the <tt>CSVTokenizer</tt> object.
*
* The following is one example of the use of the tokenizer. The code:
* <blockquote><pre>
* CSVTokenizer csvt = new CSVTokenizer("this,is,a,test");
* while (csvt.hasMoreTokens()) {
* println(csvt.nextToken());
* }
* </pre></blockquote>
*
* prints the following output:
* <blockquote><pre>
* this
* is
* a
* test
* </pre></blockquote>
*
* @author abupon
*/
public class CSVTokenizer implements Enumeration
{
/**
* The complete record that should be separated into elements.
*/
private String record;
/**
* The separator.
*/
private String separator;
/**
* The quoting char.
*/
private String quate;
/**
* the current parsing position.
*/
private int currentIndex;
/**
* A flag indicating that the current parse position is before the start.
*/
private boolean beforeStart;
/**
* A possible separator constant.
*/
public static final String SEPARATOR_COMMA = ",";
/**
* A possible separator constant.
*/
public static final String SEPARATOR_TAB = "\t";
/**
* A possible separator constant.
*/
public static final String SEPARATOR_SPACE = " ";
/**
* A possible quote character constant.
*/
public static final String DOUBLE_QUATE = "\"";
/**
* A possible quote character constant.
*/
public static final String SINGLE_QUATE = """;
/**
* Constructs a csv tokenizer for the specified string. <code>theSeparator</code> argument is the separator for
* separating tokens.
*
* If the <code>returnSeparators</code> flag is <code>true</code>, then the separator string is also returned as
* tokens. separator is returned as a string. If the flag is <code>false</code>, the separator string is skipped and
* only serve as separator between tokens.
*
* @param aString a string to be parsed.
* @param theSeparator the separator (CSVTokenizer.SEPARATOR_COMMA, CSVTokenizer.TAB, CSVTokenizer.SPACE, etc.).
* @param theQuate the quate (CSVTokenizer.SINGLE_QUATE, CSVTokenizer.DOUBLE_QUATE, etc.).
*/
public CSVTokenizer(final String aString, final String theSeparator,
final String theQuate)
{
if (aString == null)
{
throw new NullPointerException("The given string is null");
}
if (theSeparator == null)
{
throw new NullPointerException("The given separator is null");
}
if (theQuate == null)
{
throw new NullPointerException("The given quate is null");
}
this.record = aString.trim();
this.separator = theSeparator;
this.quate = theQuate;
this.currentIndex = 0;
this.beforeStart = true;
}
/**
* Constructs a csv tokenizer for the specified string. The characters in the <code>theSeparator</code> argument are
* the separator for separating tokens. Separator string themselves will not be treated as tokens.
*
* @param aString a string to be parsed.
* @param theSeparator the separator (CSVTokenizer.SEPARATOR_COMMA, CSVTokenizer.TAB, CSVTokenizer.SPACE, etc.).
*/
public CSVTokenizer(final String aString, final String theSeparator)
{
this(aString, theSeparator, CSVTokenizer.DOUBLE_QUATE);
}
/**
* Constructs a string tokenizer for the specified string. The tokenizer uses the default separator set, which is
* <code>CSVTokenizer.SEPARATOR_COMMA</code>. Separator string themselves will not be treated as tokens.
*
* @param aString a string to be parsed.
*/
public CSVTokenizer(final String aString)
{
this(aString, CSVTokenizer.SEPARATOR_COMMA);
}
/**
* Tests if there are more tokens available from this tokenizer"s string. If this method returns <tt>true</tt>, then a
* subsequent call to <tt>nextToken</tt> with no argument will successfully return a token.
*
* @return <code>true</code> if and only if there is at least one token in the string after the current position;
* <code>false</code> otherwise.
*/
public boolean hasMoreTokens()
{
return (this.currentIndex < this.record.length());
}
/**
* Returns the next token from this string tokenizer.
*
* @return the next token from this string tokenizer.
* @throws NoSuchElementException if there are no more tokens in this tokenizer"s string.
* @throws IllegalArgumentException if given parameter string format was wrong
*/
public String nextToken()
throws NoSuchElementException, IllegalArgumentException
{
if (!this.hasMoreTokens())
{
throw new NoSuchElementException();
}
if (beforeStart == false)
{
currentIndex += this.separator.length();
}
else
{
beforeStart = false;
}
if (this.record.startsWith(this.quate, this.currentIndex))
{
final StringBuffer token = new StringBuffer();
String rec = this.record.substring(this.currentIndex + this.quate.length());
while (true)
{
final int end = rec.indexOf(this.quate);
if (end < 0)
{
throw new IllegalArgumentException("Illegal format");
}
if (!rec.startsWith(this.quate, end + 1))
{
token.append(rec.substring(0, end));
break;
}
token.append(rec.substring(0, end + 1));
rec = rec.substring(end + this.quate.length() * 2);
this.currentIndex++;
}
this.currentIndex += (token.length() + this.quate.length() * 2);
return token.toString();
}
final int end = this.record.indexOf(this.separator, this.currentIndex);
if (end >= 0)
{
final int start = this.currentIndex;
final String token = this.record.substring(start, end);
this.currentIndex = end;
return token;
}
else
{
final int start = this.currentIndex;
final String token = this.record.substring(start);
this.currentIndex = this.record.length();
return token;
}
}
/**
* Returns the next token in this string tokenizer"s string. First, the set of characters considered to be separator
* by this <tt>CSVTokenizer</tt> object is changed to be the characters in the string <tt>separator</tt>. Then the
* next token in the string after the current position is returned. The current position is advanced beyond the
* recognized token. The new delimiter set remains the default after this call.
*
* @param theSeparator the new separator.
* @return the next token, after switching to the new delimiter set.
* @throws java.util.NoSuchElementException
* if there are no more tokens in this tokenizer"s string.
*/
public String nextToken(final String theSeparator)
{
separator = theSeparator;
return nextToken();
}
/**
* Returns the same value as the <code>hasMoreTokens</code> method. It exists so that this class can implement the
* <code>Enumeration</code> interface.
*
* @return <code>true</code> if there are more tokens; <code>false</code> otherwise.
* @see java.util.Enumeration
* @see org.jfree.report.util.CSVTokenizer#hasMoreTokens()
*/
public boolean hasMoreElements()
{
return hasMoreTokens();
}
/**
* Returns the same value as the <code>nextToken</code> method, except that its declared return value is
* <code>Object</code> rather than <code>String</code>. It exists so that this class can implement the
* <code>Enumeration</code> interface.
*
* @return the next token in the string.
* @throws java.util.NoSuchElementException
* if there are no more tokens in this tokenizer"s string.
* @see java.util.Enumeration
* @see org.jfree.report.util.CSVTokenizer#nextToken()
*/
public Object nextElement()
{
return nextToken();
}
/**
* Calculates the number of times that this tokenizer"s <code>nextToken</code> method can be called before it
* generates an exception. The current position is not advanced.
*
* @return the number of tokens remaining in the string using the current delimiter set.
* @see org.jfree.report.util.CSVTokenizer#nextToken()
*/
public int countTokens()
{
int count = 0;
final int preserve = this.currentIndex;
final boolean preserveStart = this.beforeStart;
while (this.hasMoreTokens())
{
this.nextToken();
count++;
}
this.currentIndex = preserve;
this.beforeStart = preserveStart;
return count;
}
/**
* Returns the quate.
*
* @return char
*/
public String getQuate()
{
return this.quate;
}
/**
* Sets the quate.
*
* @param quate The quate to set
*/
public void setQuate(final String quate)
{
this.quate = quate;
}
}
