Apache
/
commons-csv
mirror of https://github.com/apache/commons-csv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Remove trailing spaces. 

git-svn-id: https://svn.apache.org/repos/asf/commons/proper/csv/trunk@1383577 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Gary D. Gregory 2012-09-11 19:40:37 +00:00
parent 0638a37368
commit bf06bed9b8
21 changed files with 199 additions and 199 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

82
src/main/java/org/apache/commons/csv/CSVFormat.java
View File

@ -33,7 +33,7 @@ public class CSVFormat implements Serializable {
/** According to RFC 4180, line breaks are delimited by CRLF */ /** According to RFC 4180, line breaks are delimited by CRLF */
public static final String CRLF = "\r\n"; public static final String CRLF = "\r\n";
private final char delimiter; private final char delimiter;
private final char encapsulator; private final char encapsulator;
private final char commentStart; private final char commentStart;
@ -60,14 +60,14 @@ public class CSVFormat implements Serializable {
*/ */
static final CSVFormat PRISTINE = new CSVFormat(DISABLED, DISABLED, DISABLED, DISABLED, false, false, null, null); static final CSVFormat PRISTINE = new CSVFormat(DISABLED, DISABLED, DISABLED, DISABLED, false, false, null, null);
/** /**
* Standard comma separated format, as for {@link #RFC4180} but allowing blank lines. * Standard comma separated format, as for {@link #RFC4180} but allowing blank lines.
* <ul> * <ul>
* <li>withDelimiter(',')</li> * <li>withDelimiter(',')</li>
* <li>withEncapsulator('"')</li> * <li>withEncapsulator('"')</li>
* <li>withEmptyLinesIgnored(true)</li> * <li>withEmptyLinesIgnored(true)</li>
* <li>withLineSeparator(CRLF)</li> * <li>withLineSeparator(CRLF)</li>
* </ul> * </ul>
*/ */
public static final CSVFormat DEFAULT = public static final CSVFormat DEFAULT =
PRISTINE. PRISTINE.
@ -83,7 +83,7 @@ public class CSVFormat implements Serializable {
* <li>withEncapsulator('"')</li> * <li>withEncapsulator('"')</li>
* <li>withLineSeparator(CRLF)</li> * <li>withLineSeparator(CRLF)</li>
* <li></li> * <li></li>
* </ul> * </ul>
*/ */
public static final CSVFormat RFC4180 = public static final CSVFormat RFC4180 =
PRISTINE. PRISTINE.
@ -99,7 +99,7 @@ public class CSVFormat implements Serializable {
* <p/> * <p/>
* For example for parsing or generating a CSV file on a French system * For example for parsing or generating a CSV file on a French system
* the following format will be used: * the following format will be used:
* *
* <pre>CSVFormat fmt = CSVFormat.EXCEL.withDelimiter(';');</pre> * <pre>CSVFormat fmt = CSVFormat.EXCEL.withDelimiter(';');</pre>
*/ */
public static final CSVFormat EXCEL = public static final CSVFormat EXCEL =
@ -122,7 +122,7 @@ public class CSVFormat implements Serializable {
* <tt>LOAD DATA INFILE</tt> operations. This is a tab-delimited * <tt>LOAD DATA INFILE</tt> operations. This is a tab-delimited
* format with a LF character as the line separator. Values are not quoted * format with a LF character as the line separator. Values are not quoted
* and special characters are escaped with '\'. * and special characters are escaped with '\'.
* *
* @see <a href="http://dev.mysql.com/doc/refman/5.1/en/load-data.html">http://dev.mysql.com/doc/refman/5.1/en/load-data.html</a> * @see <a href="http://dev.mysql.com/doc/refman/5.1/en/load-data.html">http://dev.mysql.com/doc/refman/5.1/en/load-data.html</a>
*/ */
public static final CSVFormat MYSQL = public static final CSVFormat MYSQL =
@ -168,9 +168,9 @@ public class CSVFormat implements Serializable {
/** /**
* Returns true if the given character is a line break character. * Returns true if the given character is a line break character.
* *
* @param c the character to check * @param c the character to check
* *
* @return true if <code>c</code> is a line break character * @return true if <code>c</code> is a line break character
*/ */
private static boolean isLineBreak(char c) { private static boolean isLineBreak(char c) {
@ -184,19 +184,19 @@ public class CSVFormat implements Serializable {
if (delimiter == encapsulator) { if (delimiter == encapsulator) {
throw new IllegalArgumentException("The encapsulator character and the delimiter cannot be the same (\"" + encapsulator + "\")"); throw new IllegalArgumentException("The encapsulator character and the delimiter cannot be the same (\"" + encapsulator + "\")");
} }
if (delimiter == escape) { if (delimiter == escape) {
throw new IllegalArgumentException("The escape character and the delimiter cannot be the same (\"" + escape + "\")"); throw new IllegalArgumentException("The escape character and the delimiter cannot be the same (\"" + escape + "\")");
} }
if (delimiter == commentStart) { if (delimiter == commentStart) {
throw new IllegalArgumentException("The comment start character and the delimiter cannot be the same (\"" + commentStart + "\")"); throw new IllegalArgumentException("The comment start character and the delimiter cannot be the same (\"" + commentStart + "\")");
} }
if (encapsulator != DISABLED && encapsulator == commentStart) { if (encapsulator != DISABLED && encapsulator == commentStart) {
throw new IllegalArgumentException("The comment start character and the encapsulator cannot be the same (\"" + commentStart + "\")"); throw new IllegalArgumentException("The comment start character and the encapsulator cannot be the same (\"" + commentStart + "\")");
} }
if (escape != DISABLED && escape == commentStart) { if (escape != DISABLED && escape == commentStart) {
throw new IllegalArgumentException("The comment start and the escape character cannot be the same (\"" + commentStart + "\")"); throw new IllegalArgumentException("The comment start and the escape character cannot be the same (\"" + commentStart + "\")");
} }
@ -204,7 +204,7 @@ public class CSVFormat implements Serializable {
/** /**
* Returns the character delimiting the values (typically ';', ',' or '\t'). * Returns the character delimiting the values (typically ';', ',' or '\t').
* *
* @return the delimiter character * @return the delimiter character
*/ */
public char getDelimiter() { public char getDelimiter() {
@ -213,7 +213,7 @@ public class CSVFormat implements Serializable {
/** /**
* Returns a copy of this format using the specified delimiter character. * Returns a copy of this format using the specified delimiter character.
* *
* @param delimiter the delimiter character * @param delimiter the delimiter character
* @return A copy of this format using the specified delimiter character * @return A copy of this format using the specified delimiter character
* @throws IllegalArgumentException thrown if the specified character is a line break * @throws IllegalArgumentException thrown if the specified character is a line break
@ -228,7 +228,7 @@ public class CSVFormat implements Serializable {
/** /**
* Returns the character used to encapsulate values containing special characters. * Returns the character used to encapsulate values containing special characters.
* *
* @return the encapsulator character * @return the encapsulator character
*/ */
public char getEncapsulator() { public char getEncapsulator() {
@ -237,7 +237,7 @@ public class CSVFormat implements Serializable {
/** /**
* Returns a copy of this format using the specified encapsulator character. * Returns a copy of this format using the specified encapsulator character.
* *
* @param encapsulator the encapsulator character * @param encapsulator the encapsulator character
* @return A copy of this format using the specified encapsulator character * @return A copy of this format using the specified encapsulator character
* @throws IllegalArgumentException thrown if the specified character is a line break * @throws IllegalArgumentException thrown if the specified character is a line break
@ -246,13 +246,13 @@ public class CSVFormat implements Serializable {
if (isLineBreak(encapsulator)) { if (isLineBreak(encapsulator)) {
throw new IllegalArgumentException("The encapsulator cannot be a line break"); throw new IllegalArgumentException("The encapsulator cannot be a line break");
} }
return new CSVFormat(delimiter, encapsulator, commentStart, escape, surroundingSpacesIgnored, emptyLinesIgnored, lineSeparator, header); return new CSVFormat(delimiter, encapsulator, commentStart, escape, surroundingSpacesIgnored, emptyLinesIgnored, lineSeparator, header);
} }
/** /**
* Returns whether an encapsulator has been defined. * Returns whether an encapsulator has been defined.
* *
* @return {@code true} if an encapsulator is defined * @return {@code true} if an encapsulator is defined
*/ */
public boolean isEncapsulating() { public boolean isEncapsulating() {
@ -261,7 +261,7 @@ public class CSVFormat implements Serializable {
/** /**
* Returns the character marking the start of a line comment. * Returns the character marking the start of a line comment.
* *
* @return the comment start marker. * @return the comment start marker.
*/ */
public char getCommentStart() { public char getCommentStart() {
@ -270,10 +270,10 @@ public class CSVFormat implements Serializable {
/** /**
* Returns a copy of this format using the specified character as the comment start marker. * Returns a copy of this format using the specified character as the comment start marker.
* *
* Note that the comment introducer character is only recognised * Note that the comment introducer character is only recognised
* at the start of a line. * at the start of a line.
* *
* @param commentStart the comment start marker * @param commentStart the comment start marker
* @return A copy of this format using the specified character as the comment start marker * @return A copy of this format using the specified character as the comment start marker
* @throws IllegalArgumentException thrown if the specified character is a line break * @throws IllegalArgumentException thrown if the specified character is a line break
@ -282,16 +282,16 @@ public class CSVFormat implements Serializable {
if (isLineBreak(commentStart)) { if (isLineBreak(commentStart)) {
throw new IllegalArgumentException("The comment start character cannot be a line break"); throw new IllegalArgumentException("The comment start character cannot be a line break");
} }
return new CSVFormat(delimiter, encapsulator, commentStart, escape, surroundingSpacesIgnored, emptyLinesIgnored, lineSeparator, header); return new CSVFormat(delimiter, encapsulator, commentStart, escape, surroundingSpacesIgnored, emptyLinesIgnored, lineSeparator, header);
} }
/** /**
* Specifies whether comments are supported by this format. * Specifies whether comments are supported by this format.
* *
* Note that the comment introducer character is only recognised * Note that the comment introducer character is only recognised
* at the start of a line. * at the start of a line.
* *
* @return <tt>true</tt> is comments are supported, <tt>false</tt> otherwise * @return <tt>true</tt> is comments are supported, <tt>false</tt> otherwise
*/ */
public boolean isCommentingEnabled() { public boolean isCommentingEnabled() {
@ -300,7 +300,7 @@ public class CSVFormat implements Serializable {
/** /**
* Returns the escape character. * Returns the escape character.
* *
* @return the escape character * @return the escape character
*/ */
public char getEscape() { public char getEscape() {
@ -309,7 +309,7 @@ public class CSVFormat implements Serializable {
/** /**
* Returns a copy of this format using the specified escape character. * Returns a copy of this format using the specified escape character.
* *
* @param escape the escape character * @param escape the escape character
* @return A copy of this format using the specified escape character * @return A copy of this format using the specified escape character
* @throws IllegalArgumentException thrown if the specified character is a line break * @throws IllegalArgumentException thrown if the specified character is a line break
@ -318,13 +318,13 @@ public class CSVFormat implements Serializable {
if (isLineBreak(escape)) { if (isLineBreak(escape)) {
throw new IllegalArgumentException("The escape character cannot be a line break"); throw new IllegalArgumentException("The escape character cannot be a line break");
} }
return new CSVFormat(delimiter, encapsulator, commentStart, escape, surroundingSpacesIgnored, emptyLinesIgnored, lineSeparator, header); return new CSVFormat(delimiter, encapsulator, commentStart, escape, surroundingSpacesIgnored, emptyLinesIgnored, lineSeparator, header);
} }
/** /**
* Returns whether escape are being processed. * Returns whether escape are being processed.
* *
* @return {@code true} if escapes are processed * @return {@code true} if escapes are processed
*/ */
public boolean isEscaping() { public boolean isEscaping() {
@ -333,7 +333,7 @@ public class CSVFormat implements Serializable {
/** /**
* Specifies whether spaces around values are ignored when parsing input. * Specifies whether spaces around values are ignored when parsing input.
* *
* @return <tt>true</tt> if spaces around values are ignored, <tt>false</tt> if they are treated as part of the value. * @return <tt>true</tt> if spaces around values are ignored, <tt>false</tt> if they are treated as part of the value.
*/ */
public boolean isSurroundingSpacesIgnored() { public boolean isSurroundingSpacesIgnored() {
@ -353,7 +353,7 @@ public class CSVFormat implements Serializable {
/** /**
* Specifies whether empty lines between records are ignored when parsing input. * Specifies whether empty lines between records are ignored when parsing input.
* *
* @return <tt>true</tt> if empty lines between records are ignored, <tt>false</tt> if they are turned into empty records. * @return <tt>true</tt> if empty lines between records are ignored, <tt>false</tt> if they are turned into empty records.
*/ */
public boolean isEmptyLinesIgnored() { public boolean isEmptyLinesIgnored() {
@ -373,7 +373,7 @@ public class CSVFormat implements Serializable {
/** /**
* Returns the line separator delimiting output records. * Returns the line separator delimiting output records.
* *
* @return the line separator * @return the line separator
*/ */
public String getLineSeparator() { public String getLineSeparator() {
@ -382,9 +382,9 @@ public class CSVFormat implements Serializable {
/** /**
* Returns a copy of this format using the specified output line separator. * Returns a copy of this format using the specified output line separator.
* *
* @param lineSeparator the line separator to be used for output. * @param lineSeparator the line separator to be used for output.
* *
* @return A copy of this format using the specified output line separator * @return A copy of this format using the specified output line separator
*/ */
public CSVFormat withLineSeparator(String lineSeparator) { public CSVFormat withLineSeparator(String lineSeparator) {
@ -415,7 +415,7 @@ public class CSVFormat implements Serializable {
/** /**
* Parses the specified content. * Parses the specified content.
* *
* @param in the input stream * @param in the input stream
*/ */
public Iterable<CSVRecord> parse(Reader in) throws IOException { public Iterable<CSVRecord> parse(Reader in) throws IOException {
@ -424,7 +424,7 @@ public class CSVFormat implements Serializable {
/** /**
* Format the specified values. * Format the specified values.
* *
* @param values the values to format * @param values the values to format
*/ */
public String format(String... values) { public String format(String... values) {
@ -435,7 +435,7 @@ public class CSVFormat implements Serializable {
} catch (IOException e) { } catch (IOException e) {
// should not happen // should not happen
throw new IllegalStateException(e); throw new IllegalStateException(e);
} }
} }
@Override @Override
@ -448,19 +448,19 @@ public class CSVFormat implements Serializable {
} }
if (isEncapsulating()) { if (isEncapsulating()) {
sb.append(' '); sb.append(' ');
sb.append("Encapsulator=<").append(encapsulator).append('>'); sb.append("Encapsulator=<").append(encapsulator).append('>');
} }
if (isCommentingEnabled()) { if (isCommentingEnabled()) {
sb.append(' '); sb.append(' ');
sb.append("CommentStart=<").append(commentStart).append('>'); sb.append("CommentStart=<").append(commentStart).append('>');
} }
if (isEmptyLinesIgnored()) { if (isEmptyLinesIgnored()) {
sb.append(" EmptyLines:ignored"); sb.append(" EmptyLines:ignored");
} }
if (isSurroundingSpacesIgnored()) { if (isSurroundingSpacesIgnored()) {
sb.append(" SurroundingSpaces:ignored"); sb.append(" SurroundingSpaces:ignored");
} }
return sb.toString(); return sb.toString();
} }
} }

8
src/main/java/org/apache/commons/csv/CSVLexer.java
View File

@ -27,7 +27,7 @@ class CSVLexer extends Lexer {
public CSVLexer(CSVFormat format, ExtendedBufferedReader in) { public CSVLexer(CSVFormat format, ExtendedBufferedReader in) {
super(format, in); super(format, in);
} }
/** /**
* Returns the next token. * Returns the next token.
* <p/> * <p/>
@ -92,7 +92,7 @@ class CSVLexer extends Lexer {
eol = isEndOfLine(c); eol = isEndOfLine(c);
} }
} }
// ok, start of token reached: encapsulated, or token // ok, start of token reached: encapsulated, or token
if (isDelimiter(c)) { if (isDelimiter(c)) {
// empty token return TOKEN("") // empty token return TOKEN("")
@ -183,7 +183,7 @@ class CSVLexer extends Lexer {
* *
* @param tkn the current token * @param tkn the current token
* @return a valid token object * @return a valid token object
* @throws IOException on invalid state: * @throws IOException on invalid state:
* EOF before closing encapsulator or invalid character before delimiter or EOL * EOF before closing encapsulator or invalid character before delimiter or EOL
*/ */
private Token encapsulatedTokenLexer(Token tkn) throws IOException { private Token encapsulatedTokenLexer(Token tkn) throws IOException {
@ -192,7 +192,7 @@ class CSVLexer extends Lexer {
int c; int c;
while (true) { while (true) {
c = in.read(); c = in.read();
if (isEscape(c)) { if (isEscape(c)) {
tkn.content.append((char) readEscape()); tkn.content.append((char) readEscape());
} else if (isEncapsulator(c)) { } else if (isEncapsulator(c)) {

18
src/main/java/org/apache/commons/csv/CSVParser.java
View File

@ -66,7 +66,7 @@ public class CSVParser implements Iterable<CSVRecord> {
private final Map<String, Integer> headerMapping; private final Map<String, Integer> headerMapping;
// the following objects are shared to reduce garbage // the following objects are shared to reduce garbage
/** A record buffer for getRecord(). Grows as necessary and is reused. */ /** A record buffer for getRecord(). Grows as necessary and is reused. */
private final List<String> record = new ArrayList<String>(); private final List<String> record = new ArrayList<String>();
private final Token reusableToken = new Token(); private final Token reusableToken = new Token();
@ -90,9 +90,9 @@ public class CSVParser implements Iterable<CSVRecord> {
*/ */
public CSVParser(Reader input, CSVFormat format) throws IOException { public CSVParser(Reader input, CSVFormat format) throws IOException {
format.validate(); format.validate();
this.lexer = new CSVLexer(format, new ExtendedBufferedReader(input)); this.lexer = new CSVLexer(format, new ExtendedBufferedReader(input));
this.headerMapping = initializeHeader(format); this.headerMapping = initializeHeader(format);
} }
@ -166,9 +166,9 @@ public class CSVParser implements Iterable<CSVRecord> {
break; break;
} }
} while (reusableToken.type == TOKEN); } while (reusableToken.type == TOKEN);
if (!record.isEmpty()) { if (!record.isEmpty()) {
result = new CSVRecord(record.toArray(new String[record.size()]), headerMapping, result = new CSVRecord(record.toArray(new String[record.size()]), headerMapping,
sb == null ? null : sb.toString()); sb == null ? null : sb.toString());
} }
return result; return result;
@ -210,12 +210,12 @@ public class CSVParser implements Iterable<CSVRecord> {
public Iterator<CSVRecord> iterator() { public Iterator<CSVRecord> iterator() {
return new Iterator<CSVRecord>() { return new Iterator<CSVRecord>() {
private CSVRecord current; private CSVRecord current;
public boolean hasNext() { public boolean hasNext() {
if (current == null) { if (current == null) {
current = getNextRecord(); current = getNextRecord();
} }
return current != null; return current != null;
} }
@ -230,10 +230,10 @@ public class CSVParser implements Iterable<CSVRecord> {
throw new NoSuchElementException("No more CSV records available"); throw new NoSuchElementException("No more CSV records available");
} }
} }
return next; return next;
} }
private CSVRecord getNextRecord() { private CSVRecord getNextRecord() {
try { try {
return getRecord(); return getRecord();

6
src/main/java/org/apache/commons/csv/CSVPrinter.java
View File

@ -62,7 +62,7 @@ public class CSVPrinter {
/** /**
* Flush the underlying stream. * Flush the underlying stream.
* *
* @throws IOException * @throws IOException
*/ */
public void flush() throws IOException { public void flush() throws IOException {
@ -127,7 +127,7 @@ public class CSVPrinter {
} }
private void print(CharSequence value, int offset, int len) throws IOException { private void print(CharSequence value, int offset, int len) throws IOException {
if (format.isEncapsulating()) { if (format.isEncapsulating()) {
printAndEncapsulate(value, offset, len); printAndEncapsulate(value, offset, len);
} else if (format.isEscaping()) { } else if (format.isEscaping()) {
@ -284,7 +284,7 @@ public class CSVPrinter {
// null values are considered empty // null values are considered empty
value = ""; value = "";
} }
if (!checkForEscape) { if (!checkForEscape) {
// write directly from string // write directly from string
printSep(); printSep();

4
src/main/java/org/apache/commons/csv/CSVRecord.java
View File

@ -26,11 +26,11 @@ import java.util.Map;
* A CSV record * A CSV record
*/ */
public class CSVRecord implements Serializable, Iterable<String> { public class CSVRecord implements Serializable, Iterable<String> {
private static final long serialVersionUID = 1L; private static final long serialVersionUID = 1L;
private static final String[] EMPTY_STRING_ARRAY = new String[0]; private static final String[] EMPTY_STRING_ARRAY = new String[0];
/** The values of the record */ /** The values of the record */
private final String[] values; private final String[] values;

20
src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
View File

@ -71,7 +71,7 @@ class ExtendedBufferedReader extends BufferedReader {
* character has been read then this will return {@link #UNDEFINED}. If the * character has been read then this will return {@link #UNDEFINED}. If the
* end of the stream was reached on the last read then this will return * end of the stream was reached on the last read then this will return
* {@link #END_OF_STREAM}. * {@link #END_OF_STREAM}.
* *
* @return the last character that was read * @return the last character that was read
*/ */
int readAgain() { int readAgain() {
@ -83,16 +83,16 @@ class ExtendedBufferedReader extends BufferedReader {
if (length == 0) { if (length == 0) {
return 0; return 0;
} }
int len = super.read(buf, offset, length); int len = super.read(buf, offset, length);
if (len > 0) { if (len > 0) {
for (int i = offset; i < offset + len; i++) { for (int i = offset; i < offset + len; i++) {
char ch = buf[i]; char ch = buf[i];
if (ch == LF) { if (ch == LF) {
if (CR != (i > 0 ? buf[i-1]: lastChar)) { if (CR != (i > 0 ? buf[i-1]: lastChar)) {
lineCounter++; lineCounter++;
} }
} else if (ch == CR) { } else if (ch == CR) {
lineCounter++; lineCounter++;
@ -104,7 +104,7 @@ class ExtendedBufferedReader extends BufferedReader {
} else if (len == -1) { } else if (len == -1) {
lastChar = END_OF_STREAM; lastChar = END_OF_STREAM;
} }
return len; return len;
} }
@ -115,9 +115,9 @@ class ExtendedBufferedReader extends BufferedReader {
* <p> * <p>
* Increments {@link #lineCounter} * Increments {@link #lineCounter}
* <p> * <p>
* Sets {@link #lastChar} to {@link #END_OF_STREAM} at EOF, * Sets {@link #lastChar} to {@link #END_OF_STREAM} at EOF,
* otherwise to LF * otherwise to LF
* *
* @return the line that was read, or null if reached EOF. * @return the line that was read, or null if reached EOF.
*/ */
@Override @Override
@ -137,9 +137,9 @@ class ExtendedBufferedReader extends BufferedReader {
/** /**
* Returns the next character in the current reader without consuming it. So * Returns the next character in the current reader without consuming it. So
* the next call to {@link #read()} will still return this value. * the next call to {@link #read()} will still return this value.
* *
* @return the next character * @return the next character
* *
* @throws IOException if there is an error in reading * @throws IOException if there is an error in reading
*/ */
int lookAhead() throws IOException { int lookAhead() throws IOException {

12
src/main/java/org/apache/commons/csv/Lexer.java
View File

@ -27,17 +27,17 @@ abstract class Lexer {
private final boolean isEncapsulating; private final boolean isEncapsulating;
private final boolean isEscaping; private final boolean isEscaping;
private final boolean isCommentEnabled; private final boolean isCommentEnabled;
private final char delimiter; private final char delimiter;
private final char escape; private final char escape;
private final char encapsulator; private final char encapsulator;
private final char commmentStart; private final char commmentStart;
final boolean surroundingSpacesIgnored; final boolean surroundingSpacesIgnored;
final boolean emptyLinesIgnored; final boolean emptyLinesIgnored;
final CSVFormat format; final CSVFormat format;
/** The input stream */ /** The input stream */
final ExtendedBufferedReader in; final ExtendedBufferedReader in;
@ -116,7 +116,7 @@ abstract class Lexer {
/** /**
* Checks if the current character represents the start of a line: * Checks if the current character represents the start of a line:
* a CR, LF or is at the start of the file. * a CR, LF or is at the start of the file.
* *
* @param c * @param c
* @return true if the character is at the start of a line. * @return true if the character is at the start of a line.
*/ */
@ -131,7 +131,7 @@ abstract class Lexer {
} }
abstract Token nextToken(Token reusableToken) throws IOException; abstract Token nextToken(Token reusableToken) throws IOException;
boolean isDelimiter(int c) { boolean isDelimiter(int c) {
return c == delimiter; return c == delimiter;
} }

16
src/main/java/org/apache/commons/csv/Token.java
View File

@ -28,30 +28,30 @@ class Token {
/** length of the initial token (content-)buffer */ /** length of the initial token (content-)buffer */
private static final int INITIAL_TOKEN_LENGTH = 50; private static final int INITIAL_TOKEN_LENGTH = 50;
enum Type { enum Type {
/** Token has no valid content, i.e. is in its initialized state. */ /** Token has no valid content, i.e. is in its initialized state. */
INVALID, INVALID,
/** Token with content, at beginning or in the middle of a line. */ /** Token with content, at beginning or in the middle of a line. */
TOKEN, TOKEN,
/** Token (which can have content) when end of file is reached. */ /** Token (which can have content) when end of file is reached. */
EOF, EOF,
/** Token with content when end of a line is reached. */ /** Token with content when end of a line is reached. */
EORECORD, EORECORD,
/** Token is a comment line */ /** Token is a comment line */
COMMENT COMMENT
} }
/** Token type */ /** Token type */
Token.Type type = INVALID; Token.Type type = INVALID;
/** The content buffer. */ /** The content buffer. */
StringBuilder content = new StringBuilder(INITIAL_TOKEN_LENGTH); StringBuilder content = new StringBuilder(INITIAL_TOKEN_LENGTH);
/** Token ready flag: indicates a valid token with content (ready for the parser). */ /** Token ready flag: indicates a valid token with content (ready for the parser). */
boolean isReady; boolean isReady;

28
src/main/java/org/apache/commons/csv/package-info.java
View File

@ -17,11 +17,11 @@
/** /**
* Apache Commons CSV Format Support. * Apache Commons CSV Format Support.
* *
* <p>CSV (or its dialects) are widely used as interfaces to legacy systems or * <p>CSV (or its dialects) are widely used as interfaces to legacy systems or
* manual data-imports. Basically CSV stands for "Comma Separated Values" but * manual data-imports. Basically CSV stands for "Comma Separated Values" but
* this simple abbreviation leads to more confusion than definitions.</p> * this simple abbreviation leads to more confusion than definitions.</p>
* *
* <p>Common to all file dialects is its basic structure: The CSV data-format * <p>Common to all file dialects is its basic structure: The CSV data-format
* is record oriented, whereas each record starts on a new textual line. A * is record oriented, whereas each record starts on a new textual line. A
* record is build of a list of values. Keep in mind that not all records * record is build of a list of values. Keep in mind that not all records
@ -30,41 +30,41 @@
* csv := records* * csv := records*
* record := values* * record := values*
* </pre> * </pre>
* *
* <p>The following list contains the csv aspects the Commons CSV parser supports:</p> * <p>The following list contains the csv aspects the Commons CSV parser supports:</p>
* <dl> * <dl>
* <dt>Separators (for lines)</dt> * <dt>Separators (for lines)</dt>
* <dd>The record separators are hardcoded and cannot be changed. The must be '\r', '\n' or '\r\n'.</dd> * <dd>The record separators are hardcoded and cannot be changed. The must be '\r', '\n' or '\r\n'.</dd>
* *
* <dt>Delimiter (for values)</dt> * <dt>Delimiter (for values)</dt>
* <dd>The delimiter for values is freely configurable (default ',').</dd> * <dd>The delimiter for values is freely configurable (default ',').</dd>
* *
* <dt>Comments</dt> * <dt>Comments</dt>
* <dd>Some CSV-dialects support a simple comment syntax. A comment is a record * <dd>Some CSV-dialects support a simple comment syntax. A comment is a record
* which must start with a designated character (the commentStarter). A record * which must start with a designated character (the commentStarter). A record
* of this kind is treated as comment and gets removed from the input (default none)</dd> * of this kind is treated as comment and gets removed from the input (default none)</dd>
* *
* <dt>Encapsulator</dt> * <dt>Encapsulator</dt>
* <dd>Two encapsulator characters (default '"') are used to enclose -&gt; complex values.</dd> * <dd>Two encapsulator characters (default '"') are used to enclose -&gt; complex values.</dd>
* *
* <dt>Simple values</dt> * <dt>Simple values</dt>
* <dd>A simple value consist of all characters (except the delimiter) until * <dd>A simple value consist of all characters (except the delimiter) until
* (but not including) the next delimiter or a record-terminator. Optionally * (but not including) the next delimiter or a record-terminator. Optionally
* all surrounding whitespaces of a simple value can be ignored (default: true).</dd> * all surrounding whitespaces of a simple value can be ignored (default: true).</dd>
* *
* <dt>Complex values</dt> * <dt>Complex values</dt>
* <dd>Complex values are encapsulated within a pair of the defined encapsulator characters. * <dd>Complex values are encapsulated within a pair of the defined encapsulator characters.
* The encapsulator itself must be escaped or doubled when used inside complex values. * The encapsulator itself must be escaped or doubled when used inside complex values.
* Complex values preserve all kind of formatting (including newlines -&gt; multiline-values)</dd> * Complex values preserve all kind of formatting (including newlines -&gt; multiline-values)</dd>
* *
* <dt>Empty line skipping</dt> * <dt>Empty line skipping</dt>
* <dd>Optionally empty lines in CSV files can be skipped. * <dd>Optionally empty lines in CSV files can be skipped.
* Otherwise, empty lines will return a record with a single empty value.</dd> * Otherwise, empty lines will return a record with a single empty value.</dd>
* </dl> * </dl>
* *
* <p>In addition to individually defined dialects, two predefined dialects (strict-csv, and excel-csv) * <p>In addition to individually defined dialects, two predefined dialects (strict-csv, and excel-csv)
* can be set directly.</p> <!-- TODO fix --> * can be set directly.</p> <!-- TODO fix -->
* *
* <p>Example usage:</p> * <p>Example usage:</p>
* <blockquote><pre> * <blockquote><pre>
* Reader in = new StringReader("a,b,c"); * Reader in = new StringReader("a,b,c");

12
src/test/java/org/apache/commons/csv/CSVFileParserTest.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -45,7 +45,7 @@ import org.junit.runners.Parameterized.Parameters;
public class CSVFileParserTest { public class CSVFileParserTest {
private static final File BASE = new File("src/test/resources/CSVFileParser"); private static final File BASE = new File("src/test/resources/CSVFileParser");
private final BufferedReader testData; private final BufferedReader testData;
private final String testName; private final String testName;
@ -67,7 +67,7 @@ public class CSVFileParserTest {
public static Collection<Object[]> generateData() public static Collection<Object[]> generateData()
{ {
List<Object[]> list = new ArrayList<Object[]>(); List<Object[]> list = new ArrayList<Object[]>();
final FilenameFilter filenameFilter = new FilenameFilter() { final FilenameFilter filenameFilter = new FilenameFilter() {
public boolean accept(File dir, String name) { public boolean accept(File dir, String name) {
return name.startsWith("test") && name.endsWith(".txt"); return name.startsWith("test") && name.endsWith(".txt");
@ -79,7 +79,7 @@ public class CSVFileParserTest {
} }
return list; return list;
} }
@Test @Test
public void testCSVFile() throws Exception { public void testCSVFile() throws Exception {
String line = readTestData(); String line = readTestData();
@ -107,7 +107,7 @@ public class CSVFileParserTest {
} }
line = readTestData(); // get string version of format line = readTestData(); // get string version of format
assertEquals(testName+" Expected format ", line, fmt.toString()); assertEquals(testName+" Expected format ", line, fmt.toString());
// Now parse the file and compare against the expected results // Now parse the file and compare against the expected results
for(CSVRecord rec : fmt.parse(csvFile)) { for(CSVRecord rec : fmt.parse(csvFile)) {
String parsed = rec.toString(); String parsed = rec.toString();

50
src/test/java/org/apache/commons/csv/CSVFormatTest.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -31,7 +31,7 @@ public class CSVFormatTest {
@Test @Test
public void testImmutalibity() { public void testImmutalibity() {
CSVFormat format = new CSVFormat('!', '!', '!', '!', true, true, CSVFormat.CRLF, null); CSVFormat format = new CSVFormat('!', '!', '!', '!', true, true, CSVFormat.CRLF, null);
format.withDelimiter('?'); format.withDelimiter('?');
format.withEncapsulator('?'); format.withEncapsulator('?');
format.withCommentStart('?'); format.withCommentStart('?');
@ -39,13 +39,13 @@ public class CSVFormatTest {
format.withEscape('?'); format.withEscape('?');
format.withSurroundingSpacesIgnored(false); format.withSurroundingSpacesIgnored(false);
format.withEmptyLinesIgnored(false); format.withEmptyLinesIgnored(false);
assertEquals('!', format.getDelimiter()); assertEquals('!', format.getDelimiter());
assertEquals('!', format.getEncapsulator()); assertEquals('!', format.getEncapsulator());
assertEquals('!', format.getCommentStart()); assertEquals('!', format.getCommentStart());
assertEquals('!', format.getEscape()); assertEquals('!', format.getEscape());
assertEquals(CSVFormat.CRLF, format.getLineSeparator()); assertEquals(CSVFormat.CRLF, format.getLineSeparator());
assertTrue(format.isSurroundingSpacesIgnored()); assertTrue(format.isSurroundingSpacesIgnored());
assertTrue(format.isEmptyLinesIgnored()); assertTrue(format.isEmptyLinesIgnored());
} }
@ -53,13 +53,13 @@ public class CSVFormatTest {
@Test @Test
public void testMutators() { public void testMutators() {
CSVFormat format = new CSVFormat('!', '!', '!', '!', true, true, CSVFormat.CRLF, null); CSVFormat format = new CSVFormat('!', '!', '!', '!', true, true, CSVFormat.CRLF, null);
assertEquals('?', format.withDelimiter('?').getDelimiter()); assertEquals('?', format.withDelimiter('?').getDelimiter());
assertEquals('?', format.withEncapsulator('?').getEncapsulator()); assertEquals('?', format.withEncapsulator('?').getEncapsulator());
assertEquals('?', format.withCommentStart('?').getCommentStart()); assertEquals('?', format.withCommentStart('?').getCommentStart());
assertEquals("?", format.withLineSeparator("?").getLineSeparator()); assertEquals("?", format.withLineSeparator("?").getLineSeparator());
assertEquals('?', format.withEscape('?').getEscape()); assertEquals('?', format.withEscape('?').getEscape());
assertFalse(format.withSurroundingSpacesIgnored(false).isSurroundingSpacesIgnored()); assertFalse(format.withSurroundingSpacesIgnored(false).isSurroundingSpacesIgnored());
assertFalse(format.withEmptyLinesIgnored(false).isEmptyLinesIgnored()); assertFalse(format.withEmptyLinesIgnored(false).isEmptyLinesIgnored());
} }
@ -67,77 +67,77 @@ public class CSVFormatTest {
@Test @Test
public void testFormat() { public void testFormat() {
CSVFormat format = CSVFormat.DEFAULT; CSVFormat format = CSVFormat.DEFAULT;
assertEquals("", format.format()); assertEquals("", format.format());
assertEquals("a,b,c", format.format("a", "b", "c")); assertEquals("a,b,c", format.format("a", "b", "c"));
assertEquals("\"x,y\",z", format.format("x,y", "z")); assertEquals("\"x,y\",z", format.format("x,y", "z"));
} }
@Test @Test
public void testValidation() { public void testValidation() {
CSVFormat format = CSVFormat.DEFAULT; CSVFormat format = CSVFormat.DEFAULT;
try { try {
format.withDelimiter('\n'); format.withDelimiter('\n');
fail(); fail();
} catch (IllegalArgumentException e) { } catch (IllegalArgumentException e) {
// expected // expected
} }
try { try {
format.withEscape('\r'); format.withEscape('\r');
fail(); fail();
} catch (IllegalArgumentException e) { } catch (IllegalArgumentException e) {
// expected // expected
} }
try { try {
format.withEncapsulator('\n'); format.withEncapsulator('\n');
fail(); fail();
} catch (IllegalArgumentException e) { } catch (IllegalArgumentException e) {
// expected // expected
} }
try { try {
format.withCommentStart('\r'); format.withCommentStart('\r');
fail(); fail();
} catch (IllegalArgumentException e) { } catch (IllegalArgumentException e) {
// expected // expected
} }
try { try {
format.withDelimiter('!').withEscape('!').validate(); format.withDelimiter('!').withEscape('!').validate();
fail(); fail();
} catch (IllegalArgumentException e) { } catch (IllegalArgumentException e) {
// expected // expected
} }
try { try {
format.withDelimiter('!').withCommentStart('!').validate(); format.withDelimiter('!').withCommentStart('!').validate();
fail(); fail();
} catch (IllegalArgumentException e) { } catch (IllegalArgumentException e) {
// expected // expected
} }
try { try {
format.withEncapsulator('!').withCommentStart('!').validate(); format.withEncapsulator('!').withCommentStart('!').validate();
fail(); fail();
} catch (IllegalArgumentException e) { } catch (IllegalArgumentException e) {
// expected // expected
} }
format.withEncapsulator(CSVFormat.DISABLED).withCommentStart(CSVFormat.DISABLED).validate(); format.withEncapsulator(CSVFormat.DISABLED).withCommentStart(CSVFormat.DISABLED).validate();
try { try {
format.withEscape('!').withCommentStart('!').validate(); format.withEscape('!').withCommentStart('!').validate();
fail(); fail();
} catch (IllegalArgumentException e) { } catch (IllegalArgumentException e) {
// expected // expected
} }
format.withEscape(CSVFormat.DISABLED).withCommentStart(CSVFormat.DISABLED).validate(); format.withEscape(CSVFormat.DISABLED).withCommentStart(CSVFormat.DISABLED).validate();
try { try {
format.withEncapsulator('!').withDelimiter('!').validate(); format.withEncapsulator('!').withDelimiter('!').validate();
fail(); fail();
@ -150,15 +150,15 @@ public class CSVFormatTest {
@Test @Test
public void testSerialization() throws Exception { public void testSerialization() throws Exception {
ByteArrayOutputStream out = new ByteArrayOutputStream(); ByteArrayOutputStream out = new ByteArrayOutputStream();
ObjectOutputStream oos = new ObjectOutputStream(out); ObjectOutputStream oos = new ObjectOutputStream(out);
oos.writeObject(CSVFormat.DEFAULT); oos.writeObject(CSVFormat.DEFAULT);
oos.flush(); oos.flush();
oos.close(); oos.close();
ObjectInputStream in = new ObjectInputStream(new ByteArrayInputStream(out.toByteArray())); ObjectInputStream in = new ObjectInputStream(new ByteArrayInputStream(out.toByteArray()));
CSVFormat format = (CSVFormat) in.readObject(); CSVFormat format = (CSVFormat) in.readObject();
assertNotNull(format); assertNotNull(format);
assertEquals("delimiter", CSVFormat.DEFAULT.getDelimiter(), format.getDelimiter()); assertEquals("delimiter", CSVFormat.DEFAULT.getDelimiter(), format.getDelimiter());
assertEquals("encapsulator", CSVFormat.DEFAULT.getEncapsulator(), format.getEncapsulator()); assertEquals("encapsulator", CSVFormat.DEFAULT.getEncapsulator(), format.getEncapsulator());
@ -168,4 +168,4 @@ public class CSVFormatTest {
assertEquals("trim", CSVFormat.DEFAULT.isSurroundingSpacesIgnored(), format.isSurroundingSpacesIgnored()); assertEquals("trim", CSVFormat.DEFAULT.isSurroundingSpacesIgnored(), format.isSurroundingSpacesIgnored());
assertEquals("empty lines", CSVFormat.DEFAULT.isEmptyLinesIgnored(), format.isEmptyLinesIgnored()); assertEquals("empty lines", CSVFormat.DEFAULT.isEmptyLinesIgnored(), format.isEmptyLinesIgnored());
} }
} }

12
src/test/java/org/apache/commons/csv/CSVLexer1.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -24,12 +24,12 @@ import static org.apache.commons.csv.Token.Type.*;
class CSVLexer1 extends Lexer { class CSVLexer1 extends Lexer {
private final StringBuilder wsBuf = new StringBuilder(); private final StringBuilder wsBuf = new StringBuilder();
// ctor needs to be public so can be called dynamically by PerformanceTest class // ctor needs to be public so can be called dynamically by PerformanceTest class
public CSVLexer1(CSVFormat format, ExtendedBufferedReader in) { public CSVLexer1(CSVFormat format, ExtendedBufferedReader in) {
super(format, in); super(format, in);
} }
/** /**
* Returns the next token. * Returns the next token.
* <p/> * <p/>
@ -89,7 +89,7 @@ class CSVLexer1 extends Lexer {
eol = isEndOfLine(c); eol = isEndOfLine(c);
} }
} }
// ok, start of token reached: comment, encapsulated, or token // ok, start of token reached: comment, encapsulated, or token
if (c == format.getCommentStart()) { if (c == format.getCommentStart()) {
// ignore everything till end of line and continue (incr linecount) // ignore everything till end of line and continue (incr linecount)
@ -194,7 +194,7 @@ class CSVLexer1 extends Lexer {
// assert c == delimiter; // assert c == delimiter;
while (true) { while (true) {
c = in.read(); c = in.read();
if (c == format.getEscape()) { if (c == format.getEscape()) {
tkn.content.append((char) readEscape()); tkn.content.append((char) readEscape());
} else if (c == format.getEncapsulator()) { } else if (c == format.getEncapsulator()) {

10
src/test/java/org/apache/commons/csv/CSVLexer1306663.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -27,7 +27,7 @@ class CSVLexer1306663 extends Lexer {
public CSVLexer1306663(CSVFormat format, ExtendedBufferedReader in) { public CSVLexer1306663(CSVFormat format, ExtendedBufferedReader in) {
super(format, in); super(format, in);
} }
/** /**
* Returns the next token. * Returns the next token.
* <p/> * <p/>
@ -92,7 +92,7 @@ class CSVLexer1306663 extends Lexer {
eol = isEndOfLine(c); eol = isEndOfLine(c);
} }
} }
// ok, start of token reached: encapsulated, or token // ok, start of token reached: encapsulated, or token
if (isDelimiter(c)) { if (isDelimiter(c)) {
// empty token return TOKEN("") // empty token return TOKEN("")
@ -184,7 +184,7 @@ class CSVLexer1306663 extends Lexer {
int c; int c;
while (true) { while (true) {
c = in.read(); c = in.read();
if (isEscape(c)) { if (isEscape(c)) {
tkn.content.append((char) readEscape()); tkn.content.append((char) readEscape());
} else if (isEncapsulator(c)) { } else if (isEncapsulator(c)) {

10
src/test/java/org/apache/commons/csv/CSVLexer1306667.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -27,7 +27,7 @@ class CSVLexer1306667 extends Lexer {
public CSVLexer1306667(CSVFormat format, ExtendedBufferedReader in) { public CSVLexer1306667(CSVFormat format, ExtendedBufferedReader in) {
super(format, in); super(format, in);
} }
/** /**
* Returns the next token. * Returns the next token.
* <p/> * <p/>
@ -92,7 +92,7 @@ class CSVLexer1306667 extends Lexer {
eol = isEndOfLine(c); eol = isEndOfLine(c);
} }
} }
// ok, start of token reached: encapsulated, or token // ok, start of token reached: encapsulated, or token
if (isDelimiter(c)) { if (isDelimiter(c)) {
// empty token return TOKEN("") // empty token return TOKEN("")
@ -184,7 +184,7 @@ class CSVLexer1306667 extends Lexer {
int c; int c;
while (true) { while (true) {
c = in.read(); c = in.read();
if (isEscape(c)) { if (isEscape(c)) {
tkn.content.append((char) readEscape()); tkn.content.append((char) readEscape());
} else if (isEncapsulator(c)) { } else if (isEncapsulator(c)) {

16
src/test/java/org/apache/commons/csv/CSVLexer3.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -25,18 +25,18 @@ import static org.apache.commons.csv.Token.Type.*;
* Experimental Lexer using enums to keep track of state and character type. * Experimental Lexer using enums to keep track of state and character type.
* Unfortunately it is twice as slow. * Unfortunately it is twice as slow.
* For reference purpose only. * For reference purpose only.
* *
*/ */
class CSVLexer3 extends Lexer { class CSVLexer3 extends Lexer {
private final char escape; private final char escape;
// ctor needs to be public so can be called dynamically by PerformanceTest class // ctor needs to be public so can be called dynamically by PerformanceTest class
public CSVLexer3(CSVFormat format, ExtendedBufferedReader in) { public CSVLexer3(CSVFormat format, ExtendedBufferedReader in) {
super(format, in); super(format, in);
this.escape = format.getEscape(); this.escape = format.getEscape();
} }
/** /**
* Classify the character types * Classify the character types
*/ */
@ -130,7 +130,7 @@ class CSVLexer3 extends Lexer {
case WHITESPACE: case WHITESPACE:
if (!surroundingSpacesIgnored){ if (!surroundingSpacesIgnored){
tkn.content.append((char) intch); tkn.content.append((char) intch);
state = State.PLAIN; state = State.PLAIN;
} }
break; break;
} }
@ -165,7 +165,7 @@ class CSVLexer3 extends Lexer {
break; break;
case EOFCHAR: case EOFCHAR:
throw new IOException("(line " + getLineNumber() + ") unexpected EOF in quoted string"); throw new IOException("(line " + getLineNumber() + ") unexpected EOF in quoted string");
default: default:
tkn.content.append((char) intch); tkn.content.append((char) intch);
break; break;
} }
@ -209,7 +209,7 @@ class CSVLexer3 extends Lexer {
break; break;
case COMMENT_START: // TODO should comment be escaped? case COMMENT_START: // TODO should comment be escaped?
case ENCAP: // TODO is this correct? case ENCAP: // TODO is this correct?
case OTHER: // TODO may need to escape further case OTHER: // TODO may need to escape further
case WHITESPACE: case WHITESPACE:
tkn.content.append(escape); tkn.content.append(escape);
tkn.content.append((char) intch); tkn.content.append((char) intch);

16
src/test/java/org/apache/commons/csv/CSVLexerTest.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -26,7 +26,7 @@ import static org.apache.commons.csv.Token.Type.*;
import static org.junit.Assert.*; import static org.junit.Assert.*;
public class CSVLexerTest { public class CSVLexerTest {
private Lexer getLexer(String input, CSVFormat format) { private Lexer getLexer(String input, CSVFormat format) {
return new CSVLexer(format, new ExtendedBufferedReader(new StringReader(input))); return new CSVLexer(format, new ExtendedBufferedReader(new StringReader(input)));
} }
@ -35,7 +35,7 @@ public class CSVLexerTest {
assertEquals("Token type", expectedType, token.type); assertEquals("Token type", expectedType, token.type);
assertEquals("Token content", expectedContent, token.content.toString()); assertEquals("Token content", expectedContent, token.content.toString());
} }
// Single line (without comment) // Single line (without comment)
@Test @Test
public void testNextToken1() throws IOException { public void testNextToken1() throws IOException {
@ -56,7 +56,7 @@ public class CSVLexerTest {
// multiline including comments (and empty lines) // multiline including comments (and empty lines)
@Test @Test
public void testNextToken2() throws IOException { public void testNextToken2() throws IOException {
final String code = final String code =
"1,2,3,\n"+ // 1 "1,2,3,\n"+ // 1
"\n"+ "\n"+
"\n"+ "\n"+
@ -74,7 +74,7 @@ public class CSVLexerTest {
"# Final comment\n"; // 7 "# Final comment\n"; // 7
CSVFormat format = CSVFormat.DEFAULT.withCommentStart('#'); CSVFormat format = CSVFormat.DEFAULT.withCommentStart('#');
assertTrue("Should ignore empty lines", format.isEmptyLinesIgnored()); assertTrue("Should ignore empty lines", format.isEmptyLinesIgnored());
Lexer parser = getLexer(code, format); Lexer parser = getLexer(code, format);
@ -100,7 +100,7 @@ public class CSVLexerTest {
// multiline including comments (and empty lines) // multiline including comments (and empty lines)
@Test @Test
public void testNextToken2EmptyLines() throws IOException { public void testNextToken2EmptyLines() throws IOException {
final String code = final String code =
"1,2,3,\n"+ // 1 "1,2,3,\n"+ // 1
"\n"+ // 1b "\n"+ // 1b
"\n"+ // 1c "\n"+ // 1c
@ -117,7 +117,7 @@ public class CSVLexerTest {
"# Final comment\n"; // 7 "# Final comment\n"; // 7
CSVFormat format = CSVFormat.DEFAULT.withCommentStart('#').withEmptyLinesIgnored(false); CSVFormat format = CSVFormat.DEFAULT.withCommentStart('#').withEmptyLinesIgnored(false);
assertFalse("Should not ignore empty lines", format.isEmptyLinesIgnored()); assertFalse("Should not ignore empty lines", format.isEmptyLinesIgnored());
Lexer parser = getLexer(code, format); Lexer parser = getLexer(code, format);

38
src/test/java/org/apache/commons/csv/CSVParserTest.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -60,7 +60,7 @@ public class CSVParserTest {
for (String[] re : RESULT) { for (String[] re : RESULT) {
assertArrayEquals(re, parser.getRecord().values()); assertArrayEquals(re, parser.getRecord().values());
} }
assertNull(parser.getRecord()); assertNull(parser.getRecord());
} }
@ -132,7 +132,7 @@ public class CSVParserTest {
{""}, // Excel format does not ignore empty lines {""}, // Excel format does not ignore empty lines
{"world", ""} {"world", ""}
}; };
for (String code : codes) { for (String code : codes) {
CSVParser parser = new CSVParser(code, CSVFormat.EXCEL); CSVParser parser = new CSVParser(code, CSVFormat.EXCEL);
List<CSVRecord> records = parser.getRecords(); List<CSVRecord> records = parser.getRecords();
@ -369,7 +369,7 @@ public class CSVParserTest {
format = CSVFormat.DEFAULT.withCommentStart('#'); format = CSVFormat.DEFAULT.withCommentStart('#');
parser = new CSVParser(code, format); parser = new CSVParser(code, format);
records = parser.getRecords(); records = parser.getRecords();
Utils.compare("Failed to parse with comments", res_comments, records); Utils.compare("Failed to parse with comments", res_comments, records);
} }
@ -410,13 +410,13 @@ public class CSVParserTest {
@Test @Test
public void testForEach() throws Exception { public void testForEach() throws Exception {
List<CSVRecord> records = new ArrayList<CSVRecord>(); List<CSVRecord> records = new ArrayList<CSVRecord>();
Reader in = new StringReader("a,b,c\n1,2,3\nx,y,z"); Reader in = new StringReader("a,b,c\n1,2,3\nx,y,z");
for (CSVRecord record : CSVFormat.DEFAULT.parse(in)) { for (CSVRecord record : CSVFormat.DEFAULT.parse(in)) {
records.add(record); records.add(record);
} }
assertEquals(3, records.size()); assertEquals(3, records.size());
assertArrayEquals(new String[]{"a", "b", "c"}, records.get(0).values()); assertArrayEquals(new String[]{"a", "b", "c"}, records.get(0).values());
assertArrayEquals(new String[]{"1", "2", "3"}, records.get(1).values()); assertArrayEquals(new String[]{"1", "2", "3"}, records.get(1).values());
@ -426,9 +426,9 @@ public class CSVParserTest {
@Test @Test
public void testIterator() throws Exception { public void testIterator() throws Exception {
Reader in = new StringReader("a,b,c\n1,2,3\nx,y,z"); Reader in = new StringReader("a,b,c\n1,2,3\nx,y,z");
Iterator<CSVRecord> iterator = CSVFormat.DEFAULT.parse(in).iterator(); Iterator<CSVRecord> iterator = CSVFormat.DEFAULT.parse(in).iterator();
assertTrue(iterator.hasNext()); assertTrue(iterator.hasNext());
try { try {
iterator.remove(); iterator.remove();
@ -442,7 +442,7 @@ public class CSVParserTest {
assertTrue(iterator.hasNext()); assertTrue(iterator.hasNext());
assertArrayEquals(new String[]{"x", "y", "z"}, iterator.next().values()); assertArrayEquals(new String[]{"x", "y", "z"}, iterator.next().values());
assertFalse(iterator.hasNext()); assertFalse(iterator.hasNext());
try { try {
iterator.next(); iterator.next();
fail("NoSuchElementException expected"); fail("NoSuchElementException expected");
@ -450,13 +450,13 @@ public class CSVParserTest {
// expected // expected
} }
} }
@Test @Test
public void testHeader() throws Exception { public void testHeader() throws Exception {
Reader in = new StringReader("a,b,c\n1,2,3\nx,y,z"); Reader in = new StringReader("a,b,c\n1,2,3\nx,y,z");
Iterator<CSVRecord> records = CSVFormat.DEFAULT.withHeader().parse(in).iterator(); Iterator<CSVRecord> records = CSVFormat.DEFAULT.withHeader().parse(in).iterator();
for (int i = 0; i < 2; i++) { for (int i = 0; i < 2; i++) {
assertTrue(records.hasNext()); assertTrue(records.hasNext());
CSVRecord record = records.next(); CSVRecord record = records.next();
@ -464,7 +464,7 @@ public class CSVParserTest {
assertEquals(record.get(1), record.get("b")); assertEquals(record.get(1), record.get("b"));
assertEquals(record.get(2), record.get("c")); assertEquals(record.get(2), record.get("c"));
} }
assertFalse(records.hasNext()); assertFalse(records.hasNext());
} }
@ -473,7 +473,7 @@ public class CSVParserTest {
Reader in = new StringReader("# comment\na,b,c\n1,2,3\nx,y,z"); Reader in = new StringReader("# comment\na,b,c\n1,2,3\nx,y,z");
Iterator<CSVRecord> records = CSVFormat.DEFAULT.withCommentStart('#').withHeader().parse(in).iterator(); Iterator<CSVRecord> records = CSVFormat.DEFAULT.withCommentStart('#').withHeader().parse(in).iterator();
for (int i = 0; i < 2; i++) { for (int i = 0; i < 2; i++) {
assertTrue(records.hasNext()); assertTrue(records.hasNext());
CSVRecord record = records.next(); CSVRecord record = records.next();
@ -481,7 +481,7 @@ public class CSVParserTest {
assertEquals(record.get(1), record.get("b")); assertEquals(record.get(1), record.get("b"));
assertEquals(record.get(2), record.get("c")); assertEquals(record.get(2), record.get("c"));
} }
assertFalse(records.hasNext()); assertFalse(records.hasNext());
} }
@ -505,7 +505,7 @@ public class CSVParserTest {
@Test @Test
public void testGetLineNumberWithLF() throws Exception { public void testGetLineNumberWithLF() throws Exception {
CSVParser parser = new CSVParser("a\nb\nc", CSVFormat.DEFAULT.withLineSeparator("\n")); CSVParser parser = new CSVParser("a\nb\nc", CSVFormat.DEFAULT.withLineSeparator("\n"));
assertEquals(0, parser.getLineNumber()); assertEquals(0, parser.getLineNumber());
assertNotNull(parser.getRecord()); assertNotNull(parser.getRecord());
assertEquals(1, parser.getLineNumber()); assertEquals(1, parser.getLineNumber());
@ -519,7 +519,7 @@ public class CSVParserTest {
@Test @Test
public void testGetLineNumberWithCRLF() throws Exception { public void testGetLineNumberWithCRLF() throws Exception {
CSVParser parser = new CSVParser("a\r\nb\r\nc", CSVFormat.DEFAULT.withLineSeparator(CSVFormat.CRLF)); CSVParser parser = new CSVParser("a\r\nb\r\nc", CSVFormat.DEFAULT.withLineSeparator(CSVFormat.CRLF));
assertEquals(0, parser.getLineNumber()); assertEquals(0, parser.getLineNumber());
assertNotNull(parser.getRecord()); assertNotNull(parser.getRecord());
assertEquals(1, parser.getLineNumber()); assertEquals(1, parser.getLineNumber());
@ -533,7 +533,7 @@ public class CSVParserTest {
@Test @Test
public void testGetLineNumberWithCR() throws Exception { public void testGetLineNumberWithCR() throws Exception {
CSVParser parser = new CSVParser("a\rb\rc", CSVFormat.DEFAULT.withLineSeparator("\r")); CSVParser parser = new CSVParser("a\rb\rc", CSVFormat.DEFAULT.withLineSeparator("\r"));
assertEquals(0, parser.getLineNumber()); assertEquals(0, parser.getLineNumber());
assertNotNull(parser.getRecord()); assertNotNull(parser.getRecord());
assertEquals(1, parser.getLineNumber()); assertEquals(1, parser.getLineNumber());

14
src/test/java/org/apache/commons/csv/CSVPrinterTest.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -115,7 +115,7 @@ public class CSVPrinterTest {
StringWriter sw = new StringWriter(); StringWriter sw = new StringWriter();
CSVPrinter printer = new CSVPrinter(sw, CSVFormat.DEFAULT); CSVPrinter printer = new CSVPrinter(sw, CSVFormat.DEFAULT);
printer.printComment("This is a comment"); printer.printComment("This is a comment");
assertEquals("", sw.toString()); assertEquals("", sw.toString());
} }
@ -124,7 +124,7 @@ public class CSVPrinterTest {
StringWriter sw = new StringWriter(); StringWriter sw = new StringWriter();
CSVPrinter printer = new CSVPrinter(sw, CSVFormat.DEFAULT.withCommentStart('#')); CSVPrinter printer = new CSVPrinter(sw, CSVFormat.DEFAULT.withCommentStart('#'));
printer.printComment("This is a comment"); printer.printComment("This is a comment");
assertEquals("# This is a comment" + lineSeparator, sw.toString()); assertEquals("# This is a comment" + lineSeparator, sw.toString());
} }
@ -133,7 +133,7 @@ public class CSVPrinterTest {
StringWriter sw = new StringWriter(); StringWriter sw = new StringWriter();
CSVPrinter printer = new CSVPrinter(sw, CSVFormat.DEFAULT.withCommentStart('#')); CSVPrinter printer = new CSVPrinter(sw, CSVFormat.DEFAULT.withCommentStart('#'));
printer.printComment("This is a comment\non multiple lines"); printer.printComment("This is a comment\non multiple lines");
assertEquals("# This is a comment" + lineSeparator + "# on multiple lines" + lineSeparator, sw.toString()); assertEquals("# This is a comment" + lineSeparator + "# on multiple lines" + lineSeparator, sw.toString());
} }
@ -153,7 +153,7 @@ public class CSVPrinterTest {
public void doOneRandom(CSVFormat format) throws Exception { public void doOneRandom(CSVFormat format) throws Exception {
Random r = new Random(); Random r = new Random();
int nLines = r.nextInt(4) + 1; int nLines = r.nextInt(4) + 1;
int nCol = r.nextInt(3) + 1; int nCol = r.nextInt(3) + 1;
// nLines=1;nCol=2; // nLines=1;nCol=2;
@ -199,7 +199,7 @@ public class CSVPrinterTest {
public String randStr() { public String randStr() {
Random r = new Random(); Random r = new Random();
int sz = r.nextInt(20); int sz = r.nextInt(20);
// sz = r.nextInt(3); // sz = r.nextInt(3);
char[] buf = new char[sz]; char[] buf = new char[sz];

10
src/test/java/org/apache/commons/csv/ExtendedBufferedReaderTest.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -90,7 +90,7 @@ public class ExtendedBufferedReaderTest {
public void testReadLookahead2() throws Exception { public void testReadLookahead2() throws Exception {
char[] ref = new char[5]; char[] ref = new char[5];
char[] res = new char[5]; char[] res = new char[5];
ExtendedBufferedReader br = getBufferedReader("abcdefg"); ExtendedBufferedReader br = getBufferedReader("abcdefg");
ref[0] = 'a'; ref[0] = 'a';
ref[1] = 'b'; ref[1] = 'b';
@ -151,7 +151,7 @@ public class ExtendedBufferedReaderTest {
/* /*
* Test to illustrate https://issues.apache.org/jira/browse/CSV-75 * Test to illustrate https://issues.apache.org/jira/browse/CSV-75
* *
*/ */
@Test @Test
public void testReadChar() throws Exception { public void testReadChar() throws Exception {
@ -160,7 +160,7 @@ public class ExtendedBufferedReaderTest {
// EOL eol EOL EOL eol eol EOL+CR EOL // EOL eol EOL EOL eol eol EOL+CR EOL
final int EOLeolct=9; final int EOLeolct=9;
ExtendedBufferedReader br; ExtendedBufferedReader br;
br = getBufferedReader(test); br = getBufferedReader(test);
assertEquals(0, br.getLineNumber()); assertEquals(0, br.getLineNumber());
while(br.readLine()!=null) {} while(br.readLine()!=null) {}

10
src/test/java/org/apache/commons/csv/Utils.java
View File

@ -13,7 +13,7 @@
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and * See the License for the specific language governing permissions and
* limitations under the License. * limitations under the License.
* *
*/ */
package org.apache.commons.csv; package org.apache.commons.csv;
@ -29,10 +29,10 @@ public class Utils {
private Utils() { private Utils() {
} }
/** /**
* Checks if the two 2d arrays have identical contents. * Checks if the two 2d arrays have identical contents.
* *
* @param message the message to be displayed * @param message the message to be displayed
* @param expected the 2d array of expected results * @param expected the 2d array of expected results
* @param actual the 2d array of actual results * @param actual the 2d array of actual results
@ -43,10 +43,10 @@ public class Utils {
Assert.assertArrayEquals(message+" (entry "+i+")",expected[i], actual[i]); Assert.assertArrayEquals(message+" (entry "+i+")",expected[i], actual[i]);
} }
} }
/** /**
* Checks if the 2d array has the same contents as the list of records. * Checks if the 2d array has the same contents as the list of records.
* *
* @param message the message to be displayed * @param message the message to be displayed
* @param expected the 2d array of expected results * @param expected the 2d array of expected results
* @param actual the List of {@link CSVRecord} entries, each containing an array of values * @param actual the List of {@link CSVRecord} entries, each containing an array of values

6
src/test/java/org/apache/commons/csv/perf/PerformanceTest.java
View File

@ -5,9 +5,9 @@
* The ASF licenses this file to You under the Apache License, Version 2.0 * The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with * (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at * the License. You may obtain a copy of the License at
* *
* http://www.apache.org/licenses/LICENSE-2.0 * http://www.apache.org/licenses/LICENSE-2.0
* *
* Unless required by applicable law or agreed to in writing, software * Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, * distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@ -28,7 +28,7 @@ import org.junit.Test;
/** /**
* Tests performance. * Tests performance.
* *
* Only enable for your own development. * Only enable for your own development.
*/ */
public class PerformanceTest { public class PerformanceTest {