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

Fix Checkstyle: Format for 120 line length. 

git-svn-id: https://svn.apache.org/repos/asf/commons/proper/csv/trunk@1383598 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Gary D. Gregory 2012-09-11 20:12:27 +00:00
parent 8608520aa1
commit 6c1b0fa1c4
8 changed files with 186 additions and 176 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
src/main/java/org/apache/commons/csv/CSVFormat.java
View File

@ -24,7 +24,7 @@ import java.io.StringWriter;
/** /**
* The format specification of a CSV file. * The format specification of a CSV file.
* *
* This class is immutable. * This class is immutable.
*/ */
public class CSVFormat implements Serializable { public class CSVFormat implements Serializable {
@ -95,7 +95,7 @@ public class CSVFormat implements Serializable {
* locale dependent, it might be necessary to customize this format to accomodate to your regional settings. * locale dependent, it might be necessary to customize this format to accomodate to your regional settings.
* <p/> * <p/>
* For example for parsing or generating a CSV file on a French system the following format will be used: * For example for parsing or generating a CSV file on a French system the following format will be used:
* *
* <pre> * <pre>
* CSVFormat fmt = CSVFormat.EXCEL.withDelimiter(';'); * CSVFormat fmt = CSVFormat.EXCEL.withDelimiter(';');
* </pre> * </pre>
@ -120,8 +120,8 @@ public class CSVFormat implements Serializable {
* a tab-delimited format with a LF character as the line separator. Values are not quoted and special characters * a tab-delimited format with a LF character as the line separator. Values are not quoted and special characters
* are escaped with '\'. * are escaped with '\'.
* *
* @see <a * @see <a href="http://dev.mysql.com/doc/refman/5.1/en/load-data.html">
* 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> * http://dev.mysql.com/doc/refman/5.1/en/load-data.html</a>
*/ */
public static final CSVFormat MYSQL = public static final CSVFormat MYSQL =
PRISTINE PRISTINE
@ -132,7 +132,7 @@ public class CSVFormat implements Serializable {
/** /**
* Creates a customized CSV format. * Creates a customized CSV format.
* *
* @param delimiter * @param delimiter
* the char used for value separation * the char used for value separation
* @param encapsulator * @param encapsulator
@ -167,10 +167,10 @@ 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 * @param c
* the character to check * 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) {
@ -209,7 +209,7 @@ 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() {
@ -218,7 +218,7 @@ 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 * @param delimiter
* the delimiter character * 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
@ -236,7 +236,7 @@ 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() {
@ -245,7 +245,7 @@ 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 * @param encapsulator
* the encapsulator character * 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
@ -263,7 +263,7 @@ public class CSVFormat implements Serializable {
/** /**
* 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() {
@ -272,7 +272,7 @@ 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() {
@ -281,9 +281,9 @@ 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 at the start of a line. * Note that the comment introducer character is only recognised at the start of a line.
* *
* @param commentStart * @param commentStart
* the comment start marker * 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
@ -301,9 +301,9 @@ public class CSVFormat implements Serializable {
/** /**
* 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 at the start of a line. * Note that the comment introducer character is only recognised 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() {
@ -312,7 +312,7 @@ 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() {
@ -321,7 +321,7 @@ 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 * @param escape
* the escape character * 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
@ -339,7 +339,7 @@ public class CSVFormat implements Serializable {
/** /**
* 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() {
@ -348,7 +348,7 @@ 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 * @return <tt>true</tt> if spaces around values are ignored, <tt>false</tt> if they are treated as part of the
* value. * value.
*/ */
@ -358,7 +358,7 @@ public class CSVFormat implements Serializable {
/** /**
* Returns a copy of this format with the specified trimming behavior. * Returns a copy of this format with the specified trimming behavior.
* *
* @param surroundingSpacesIgnored * @param surroundingSpacesIgnored
* the trimming behavior, <tt>true</tt> to remove the surrounding spaces, <tt>false</tt> to leave the * the trimming behavior, <tt>true</tt> to remove the surrounding spaces, <tt>false</tt> to leave the
* spaces as is. * spaces as is.
@ -371,7 +371,7 @@ 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 * @return <tt>true</tt> if empty lines between records are ignored, <tt>false</tt> if they are turned into empty
* records. * records.
*/ */
@ -381,7 +381,7 @@ public class CSVFormat implements Serializable {
/** /**
* Returns a copy of this format with the specified empty line skipping behavior. * Returns a copy of this format with the specified empty line skipping behavior.
* *
* @param emptyLinesIgnored * @param emptyLinesIgnored
* the empty line skipping behavior, <tt>true</tt> to ignore the empty lines between the records, * the empty line skipping behavior, <tt>true</tt> to ignore the empty lines between the records,
* <tt>false</tt> to translate empty lines to empty records. * <tt>false</tt> to translate empty lines to empty records.
@ -394,7 +394,7 @@ 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() {
@ -403,10 +403,10 @@ 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 * @param lineSeparator
* the line separator to be used for output. * 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) {
@ -421,20 +421,20 @@ public class CSVFormat implements Serializable {
/** /**
* Returns a copy of this format using the specified header. The header can either be parsed automatically from the * Returns a copy of this format using the specified header. The header can either be parsed automatically from the
* input file with: * input file with:
* *
* <pre> * <pre>
* CSVFormat format = aformat.withHeader(); * CSVFormat format = aformat.withHeader();
* </pre> * </pre>
* *
* or specified manually with: * or specified manually with:
* *
* <pre> * <pre>
* CSVFormat format = aformat.withHeader(&quot;name&quot;, &quot;email&quot;, &quot;phone&quot;); * CSVFormat format = aformat.withHeader(&quot;name&quot;, &quot;email&quot;, &quot;phone&quot;);
* </pre> * </pre>
* *
* @param header * @param header
* the header, <tt>null</tt> if disabled, empty if parsed automatically, user specified otherwise. * the header, <tt>null</tt> if disabled, empty if parsed automatically, user specified otherwise.
* *
* @return A copy of this format using the specified header * @return A copy of this format using the specified header
*/ */
public CSVFormat withHeader(String... header) { public CSVFormat withHeader(String... header) {
@ -444,7 +444,7 @@ public class CSVFormat implements Serializable {
/** /**
* Parses the specified content. * Parses the specified content.
* *
* @param in * @param in
* the input stream * the input stream
*/ */
@ -454,7 +454,7 @@ public class CSVFormat implements Serializable {
/** /**
* Format the specified values. * Format the specified values.
* *
* @param values * @param values
* the values to format * the values to format
*/ */

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

@ -32,7 +32,7 @@ class CSVLexer extends Lexer {
* Returns the next token. * Returns the next token.
* <p/> * <p/>
* A token corresponds to a term, a record change or an end-of-file indicator. * A token corresponds to a term, a record change or an end-of-file indicator.
* *
* @param token * @param token
* an existing Token object to reuse. The caller is responsible to initialize the Token. * an existing Token object to reuse. The caller is responsible to initialize the Token.
* @return the next token found * @return the next token found
@ -128,7 +128,7 @@ class CSVLexer extends Lexer {
* <li>end of stream has been reached (EOF)</li> * <li>end of stream has been reached (EOF)</li>
* <li>an unescaped delimiter has been reached (TOKEN)</li> * <li>an unescaped delimiter has been reached (TOKEN)</li>
* </ul> * </ul>
* *
* @param tkn * @param tkn
* the current token * the current token
* @param c * @param c
@ -179,7 +179,7 @@ class CSVLexer extends Lexer {
* <li>end of line (EORECORD)</li> * <li>end of line (EORECORD)</li>
* </ul> * </ul>
* <li>end of stream has been reached (EOF)</li> </ul> * <li>end of stream has been reached (EOF)</li> </ul>
* *
* @param tkn * @param tkn
* the current token * the current token
* @return a valid token object * @return a valid token object

126
src/main/java/org/apache/commons/csv/CSVParser.java
View File

@ -27,24 +27,29 @@ import java.util.List;
import java.util.Map; import java.util.Map;
import java.util.NoSuchElementException; import java.util.NoSuchElementException;
import static org.apache.commons.csv.Token.Type.*; import static org.apache.commons.csv.Token.Type.*;
/** /**
* Parses CSV files according to the specified configuration. * Parses CSV files according to the specified configuration.
* *
* Because CSV appears in many different dialects, the parser supports many * Because CSV appears in many different dialects, the parser supports many configuration settings by allowing the
* configuration settings by allowing the specification of a {@link CSVFormat}. * specification of a {@link CSVFormat}.
*
* <p>
* Parsing of a csv-string having tabs as separators, '"' as an optional value encapsulator, and comments starting with
* '#':
* </p>
* *
* <p>Parsing of a csv-string having tabs as separators,
* '"' as an optional value encapsulator, and comments starting with '#':</p>
* <pre> * <pre>
* CSVFormat format = new CSVFormat('\t', '"', '#'); * CSVFormat format = new CSVFormat('\t', '&quot;', '#');
* Reader in = new StringReader("a\tb\nc\td"); * Reader in = new StringReader(&quot;a\tb\nc\td&quot;);
* List&lt;CSVRecord> records = new CSVParser(in, format).getRecords(); * List&lt;CSVRecord&gt; records = new CSVParser(in, format).getRecords();
* </pre> * </pre>
* *
* <p>Parsing of a csv-string in Excel CSV format, using a for-each loop:</p> * <p>
* Parsing of a csv-string in Excel CSV format, using a for-each loop:
* </p>
*
* <pre> * <pre>
* Reader in = new StringReader("a;b\nc;d"); * Reader in = new StringReader("a;b\nc;d");
* CSVParser parser = new CSVParser(in, CSVFormat.EXCEL); * CSVParser parser = new CSVParser(in, CSVFormat.EXCEL);
@ -54,11 +59,12 @@ import static org.apache.commons.csv.Token.Type.*;
* </pre> * </pre>
* *
* <p> * <p>
* Internal parser state is completely covered by the format * Internal parser state is completely covered by the format and the reader-state.
* and the reader-state.</p> * </p>
* *
* <p>see <a href="package-summary.html">package documentation</a> * <p>
* for more details</p> * see <a href="package-summary.html">package documentation</a> for more details
* </p>
*/ */
public class CSVParser implements Iterable<CSVRecord> { public class CSVParser implements Iterable<CSVRecord> {
@ -74,8 +80,10 @@ public class CSVParser implements Iterable<CSVRecord> {
/** /**
* CSV parser using the default {@link CSVFormat}. * CSV parser using the default {@link CSVFormat}.
* *
* @param input a Reader containing "csv-formatted" input * @param input
* @throws IllegalArgumentException thrown if the parameters of the format are inconsistent * a Reader containing "csv-formatted" input
* @throws IllegalArgumentException
* thrown if the parameters of the format are inconsistent
*/ */
public CSVParser(Reader input) throws IOException { public CSVParser(Reader input) throws IOException {
this(input, CSVFormat.DEFAULT); this(input, CSVFormat.DEFAULT);
@ -84,9 +92,12 @@ public class CSVParser implements Iterable<CSVRecord> {
/** /**
* Customized CSV parser using the given {@link CSVFormat} * Customized CSV parser using the given {@link CSVFormat}
* *
* @param input a Reader containing "csv-formatted" input * @param input
* @param format the CSVFormat used for CSV parsing * a Reader containing "csv-formatted" input
* @throws IllegalArgumentException thrown if the parameters of the format are inconsistent * @param format
* the CSVFormat used for CSV parsing
* @throws IllegalArgumentException
* thrown if the parameters of the format are inconsistent
*/ */
public CSVParser(Reader input, CSVFormat format) throws IOException { public CSVParser(Reader input, CSVFormat format) throws IOException {
format.validate(); format.validate();
@ -99,23 +110,26 @@ public class CSVParser implements Iterable<CSVRecord> {
/** /**
* Customized CSV parser using the given {@link CSVFormat} * Customized CSV parser using the given {@link CSVFormat}
* *
* @param input a String containing "csv-formatted" input * @param input
* @param format the CSVFormat used for CSV parsing * a String containing "csv-formatted" input
* @throws IllegalArgumentException thrown if the parameters of the format are inconsistent * @param format
* the CSVFormat used for CSV parsing
* @throws IllegalArgumentException
* thrown if the parameters of the format are inconsistent
*/ */
public CSVParser(String input, CSVFormat format) throws IOException{ public CSVParser(String input, CSVFormat format) throws IOException {
this(new StringReader(input), format); this(new StringReader(input), format);
} }
/** /**
* Parses the CSV input according to the given format and returns the content * Parses the CSV input according to the given format and returns the content as an array of {@link CSVRecord}
* as an array of {@link CSVRecord} entries. * entries.
* <p/> * <p/>
* The returned content starts at the current parse-position in the stream. * The returned content starts at the current parse-position in the stream.
* *
* @return list of {@link CSVRecord} entries, may be empty * @return list of {@link CSVRecord} entries, may be empty
* @throws IOException on parse error or input read-failure * @throws IOException
* on parse error or input read-failure
*/ */
public List<CSVRecord> getRecords() throws IOException { public List<CSVRecord> getRecords() throws IOException {
List<CSVRecord> records = new ArrayList<CSVRecord>(); List<CSVRecord> records = new ArrayList<CSVRecord>();
@ -130,7 +144,8 @@ public class CSVParser implements Iterable<CSVRecord> {
* Parses the next record from the current point in the stream. * Parses the next record from the current point in the stream.
* *
* @return the record as an array of values, or <tt>null</tt> if the end of the stream has been reached * @return the record as an array of values, or <tt>null</tt> if the end of the stream has been reached
* @throws IOException on parse error or input read-failure * @throws IOException
* on parse error or input read-failure
*/ */
CSVRecord getRecord() throws IOException { CSVRecord getRecord() throws IOException {
CSVRecord result = new CSVRecord(null, headerMapping, null); CSVRecord result = new CSVRecord(null, headerMapping, null);
@ -140,36 +155,36 @@ public class CSVParser implements Iterable<CSVRecord> {
reusableToken.reset(); reusableToken.reset();
lexer.nextToken(reusableToken); lexer.nextToken(reusableToken);
switch (reusableToken.type) { switch (reusableToken.type) {
case TOKEN: case TOKEN:
record.add(reusableToken.content.toString());
break;
case EORECORD:
record.add(reusableToken.content.toString());
break;
case EOF:
if (reusableToken.isReady) {
record.add(reusableToken.content.toString()); record.add(reusableToken.content.toString());
break; } else {
case EORECORD: result = null;
record.add(reusableToken.content.toString()); }
break; break;
case EOF: case INVALID:
if (reusableToken.isReady) { throw new IOException("(line " + getLineNumber() + ") invalid parse sequence");
record.add(reusableToken.content.toString()); case COMMENT: // Ignored currently
} else { if (sb == null) { // first comment for this record
result = null; sb = new StringBuilder();
} } else {
break; sb.append("\n");
case INVALID: }
throw new IOException("(line " + getLineNumber() + ") invalid parse sequence"); sb.append(reusableToken.content);
case COMMENT: // Ignored currently reusableToken.type = TOKEN; // Read another token
if (sb == null) { // first comment for this record break;
sb = new StringBuilder();
} else {
sb.append("\n");
}
sb.append(reusableToken.content);
reusableToken.type = TOKEN; // Read another token
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 == null ? null : sb.toString()); : sb.toString());
} }
return result; return result;
} }
@ -204,8 +219,8 @@ public class CSVParser implements Iterable<CSVRecord> {
} }
/** /**
* Returns an iterator on the records. IOExceptions occuring * Returns an iterator on the records. IOExceptions occuring during the iteration are wrapped in a
* during the iteration are wrapped in a RuntimeException. * RuntimeException.
*/ */
public Iterator<CSVRecord> iterator() { public Iterator<CSVRecord> iterator() {
return new Iterator<CSVRecord>() { return new Iterator<CSVRecord>() {
@ -251,8 +266,7 @@ public class CSVParser implements Iterable<CSVRecord> {
/** /**
* Returns the current line number in the input stream. * Returns the current line number in the input stream.
* <p/> * <p/>
* ATTENTION: in case your csv has multiline-values the returned * ATTENTION: in case your csv has multiline-values the returned number does not correspond to the record-number
* number does not correspond to the record-number
* *
* @return current line number * @return current line number
*/ */

80
src/main/java/org/apache/commons/csv/CSVPrinter.java
View File

@ -35,12 +35,15 @@ public class CSVPrinter {
/** /**
* Create a printer that will print values to the given stream following the CSVFormat. * Create a printer that will print values to the given stream following the CSVFormat.
* <p/> * <p/>
* Currently, only a pure encapsulation format or a pure escaping format * Currently, only a pure encapsulation format or a pure escaping format is supported. Hybrid formats
* is supported. Hybrid formats (encapsulation and escaping with a different character) are not supported. * (encapsulation and escaping with a different character) are not supported.
* *
* @param out stream to which to print. * @param out
* @param format the CSV format. If null the default format is used ({@link CSVFormat#DEFAULT}) * stream to which to print.
* @throws IllegalArgumentException thrown if the parameters of the format are inconsistent * @param format
* the CSV format. If null the default format is used ({@link CSVFormat#DEFAULT})
* @throws IllegalArgumentException
* thrown if the parameters of the format are inconsistent
*/ */
public CSVPrinter(Appendable out, CSVFormat format) { public CSVPrinter(Appendable out, CSVFormat format) {
this.out = out; this.out = out;
@ -49,7 +52,7 @@ public class CSVPrinter {
} }
// ====================================================== // ======================================================
// printing implementation // printing implementation
// ====================================================== // ======================================================
/** /**
@ -72,11 +75,11 @@ public class CSVPrinter {
} }
/** /**
* Print a single line of comma separated values. * Print a single line of comma separated values. The values will be quoted if needed. Quotes and newLine
* The values will be quoted if needed. Quotes and * characters will be escaped.
* newLine characters will be escaped.
* *
* @param values values to be outputted. * @param values
* values to be outputted.
*/ */
public void println(String... values) throws IOException { public void println(String... values) throws IOException {
for (String value : values) { for (String value : values) {
@ -85,16 +88,15 @@ public class CSVPrinter {
println(); println();
} }
/** /**
* Put a comment on a new line among the comma separated values. Comments * Put a comment on a new line among the comma separated values. Comments will always begin on a new line and
* will always begin on a new line and occupy a least one full line. The * occupy a least one full line. The character specified to start comments and a space will be inserted at the
* character specified to start comments and a space will be inserted at * beginning of each new line in the comment.
* the beginning of each new line in the comment.
* <p/> * <p/>
* If comments are disabled in the current CSV format this method does nothing. * If comments are disabled in the current CSV format this method does nothing.
* *
* @param comment the comment to output * @param comment
* the comment to output
*/ */
public void printComment(String comment) throws IOException { public void printComment(String comment) throws IOException {
if (!format.isCommentingEnabled()) { if (!format.isCommentingEnabled()) {
@ -108,25 +110,24 @@ public class CSVPrinter {
for (int i = 0; i < comment.length(); i++) { for (int i = 0; i < comment.length(); i++) {
char c = comment.charAt(i); char c = comment.charAt(i);
switch (c) { switch (c) {
case '\r': case '\r':
if (i + 1 < comment.length() && comment.charAt(i + 1) == '\n') { if (i + 1 < comment.length() && comment.charAt(i + 1) == '\n') {
i++; i++;
} }
//$FALL-THROUGH$ break intentionally excluded. //$FALL-THROUGH$ break intentionally excluded.
case '\n': case '\n':
println(); println();
out.append(format.getCommentStart()); out.append(format.getCommentStart());
out.append(' '); out.append(' ');
break; break;
default: default:
out.append(c); out.append(c);
break; break;
} }
} }
println(); println();
} }
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);
@ -185,7 +186,7 @@ public class CSVPrinter {
} }
void printAndEncapsulate(CharSequence value, int offset, int len) throws IOException { void printAndEncapsulate(CharSequence value, int offset, int len) throws IOException {
boolean first = newLine; // is this the first value on this line? boolean first = newLine; // is this the first value on this line?
boolean quote = false; boolean quote = false;
int start = offset; int start = offset;
int pos = offset; int pos = offset;
@ -208,16 +209,12 @@ public class CSVPrinter {
char c = value.charAt(pos); char c = value.charAt(pos);
// Hmmm, where did this rule come from? // Hmmm, where did this rule come from?
if (first if (first && (c < '0' || (c > '9' && c < 'A') || (c > 'Z' && c < 'a') || (c > 'z'))) {
&& (c < '0'
|| (c > '9' && c < 'A')
|| (c > 'Z' && c < 'a')
|| (c > 'z'))) {
quote = true; quote = true;
// } else if (c == ' ' || c == '\f' || c == '\t') { // } else if (c == ' ' || c == '\f' || c == '\t') {
} else if (c <= '#') { } else if (c <= '#') {
// Some other chars at the start of a value caused the parser to fail, so for now // Some other chars at the start of a value caused the parser to fail, so for now
// encapsulate if we start in anything less than '#'. We are being conservative // encapsulate if we start in anything less than '#'. We are being conservative
// by including the default comment char too. // by including the default comment char too.
quote = true; quote = true;
} else { } else {
@ -274,10 +271,11 @@ public class CSVPrinter {
} }
/** /**
* Print the string as the next value on the line. The value * Print the string as the next value on the line. The value will be escaped or encapsulated as needed if
* will be escaped or encapsulated as needed if checkForEscape==true * checkForEscape==true
* *
* @param value value to be outputted. * @param value
* value to be outputted.
*/ */
public void print(String value, boolean checkForEscape) throws IOException { public void print(String value, boolean checkForEscape) throws IOException {
if (value == null) { if (value == null) {
@ -295,10 +293,10 @@ public class CSVPrinter {
} }
/** /**
* Print the string as the next value on the line. The value * Print the string as the next value on the line. The value will be escaped or encapsulated as needed.
* will be escaped or encapsulated as needed.
* *
* @param value value to be outputted. * @param value
* value to be outputted.
*/ */
public void print(String value) throws IOException { public void print(String value) throws IOException {
print(value, true); print(value, true);

10
src/main/java/org/apache/commons/csv/CSVRecord.java
View File

@ -49,7 +49,8 @@ public class CSVRecord implements Serializable, Iterable<String> {
/** /**
* Returns a value by index. * Returns a value by index.
* *
* @param i the index of the column retrieved * @param i
* the index of the column retrieved
*/ */
public String get(int i) { public String get(int i) {
return values[i]; return values[i];
@ -58,9 +59,11 @@ public class CSVRecord implements Serializable, Iterable<String> {
/** /**
* Returns a value by name. * Returns a value by name.
* *
* @param name the name of the column to be retrieved * @param name
* the name of the column to be retrieved
* @return the column value, or {@code null} if the column name is not found * @return the column value, or {@code null} if the column name is not found
* @throws IllegalStateException if no header mapping was provided * @throws IllegalStateException
* if no header mapping was provided
*/ */
public String get(String name) { public String get(String name) {
if (mapping == null) { if (mapping == null) {
@ -83,6 +86,7 @@ public class CSVRecord implements Serializable, Iterable<String> {
public String getComment() { public String getComment() {
return comment; return comment;
} }
/** /**
* Returns the number of values in this record. * Returns the number of values in this record.
*/ */

35
src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
View File

@ -22,11 +22,9 @@ import java.io.IOException;
import java.io.Reader; import java.io.Reader;
/** /**
* A special reader decorator which supports more * A special reader decorator which supports more sophisticated access to the underlying reader object.
* sophisticated access to the underlying reader object.
* <p> * <p>
* In particular the reader supports a look-ahead option, * In particular the reader supports a look-ahead option, which allows you to see the next char returned by
* which allows you to see the next char returned by
* {@link #read()}. * {@link #read()}.
*/ */
class ExtendedBufferedReader extends BufferedReader { class ExtendedBufferedReader extends BufferedReader {
@ -65,12 +63,10 @@ class ExtendedBufferedReader extends BufferedReader {
} }
/** /**
* Returns the last character that was read as an integer (0 to 65535). This * Returns the last character that was read as an integer (0 to 65535). This will be the last character returned by
* will be the last character returned by any of the read methods. This will * any of the read methods. This will not include a character read using the {@link #peek()} method. If no
* not include a character read using the {@link #peek()} method. If no * character has been read then this will return {@link #UNDEFINED}. If the end of the stream was reached on the
* character has been read then this will return {@link #UNDEFINED}. If the * last read then this will return {@link #END_OF_STREAM}.
* end of the stream was reached on the last read then this will return
* {@link #END_OF_STREAM}.
* *
* @return the last character that was read * @return the last character that was read
*/ */
@ -91,7 +87,7 @@ class ExtendedBufferedReader extends BufferedReader {
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) {
@ -109,14 +105,12 @@ class ExtendedBufferedReader extends BufferedReader {
} }
/** /**
* Calls {@link BufferedReader#readLine()} which drops the line terminator(s). * Calls {@link BufferedReader#readLine()} which drops the line terminator(s). This method should only be called
* This method should only be called when processing a comment, otherwise * when processing a comment, otherwise information can be lost.
* information can be lost.
* <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.
*/ */
@ -135,12 +129,13 @@ 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
* the next call to {@link #read()} will still return this value. * 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 {
super.mark(1); super.mark(1);

35
src/main/java/org/apache/commons/csv/Lexer.java
View File

@ -64,20 +64,20 @@ abstract class Lexer {
// assume c is the escape char (normally a backslash) // assume c is the escape char (normally a backslash)
int c = in.read(); int c = in.read();
switch (c) { switch (c) {
case 'r': case 'r':
return '\r'; return '\r';
case 'n': case 'n':
return '\n'; return '\n';
case 't': case 't':
return '\t'; return '\t';
case 'b': case 'b':
return '\b'; return '\b';
case 'f': case 'f':
return '\f'; return '\f';
case ExtendedBufferedReader.END_OF_STREAM: case ExtendedBufferedReader.END_OF_STREAM:
throw new IOException("EOF whilst processing escape sequence"); throw new IOException("EOF whilst processing escape sequence");
default: default:
return c; return c;
} }
} }
@ -99,8 +99,7 @@ abstract class Lexer {
} }
/** /**
* Greedy - accepts \n, \r and \r\n * Greedy - accepts \n, \r and \r\n This checker consumes silently the second control-character...
* This checker consumes silently the second control-character...
* *
* @return true if the given character is a line-terminator * @return true if the given character is a line-terminator
*/ */
@ -114,8 +113,7 @@ 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.
@ -123,6 +121,7 @@ abstract class Lexer {
boolean isStartOfLine(int c) { boolean isStartOfLine(int c) {
return c == '\n' || c == '\r' || c == ExtendedBufferedReader.UNDEFINED; return c == '\n' || c == '\r' || c == ExtendedBufferedReader.UNDEFINED;
} }
/** /**
* @return true if the given character indicates end of file * @return true if the given character indicates end of file
*/ */

2
src/main/java/org/apache/commons/csv/Token.java
View File

@ -65,6 +65,6 @@ class Token {
// Provide toString method for IDE debugging // Provide toString method for IDE debugging
@Override @Override
public String toString() { public String toString() {
return type.name()+" ["+content.toString()+"]"; return type.name() + " [" + content.toString() + "]";
} }
} }