[CSV-304] Accessors for header/trailer comments
Add accessors for header comments (before the header row) and trailer comments (after the last record) Also add javadoc and tests
This commit is contained in:
parent
c51b595e34
commit
31a546adab
|
@ -352,6 +352,9 @@ public final class CSVParser implements Iterable<CSVRecord>, Closeable {
|
||||||
|
|
||||||
return new CSVParser(new InputStreamReader(url.openStream(), charset), format);
|
return new CSVParser(new InputStreamReader(url.openStream(), charset), format);
|
||||||
}
|
}
|
||||||
|
private String headerComment;
|
||||||
|
|
||||||
|
private String trailerComment;
|
||||||
|
|
||||||
private final CSVFormat format;
|
private final CSVFormat format;
|
||||||
|
|
||||||
|
@ -480,10 +483,12 @@ public final class CSVParser implements Iterable<CSVRecord>, Closeable {
|
||||||
final CSVRecord nextRecord = this.nextRecord();
|
final CSVRecord nextRecord = this.nextRecord();
|
||||||
if (nextRecord != null) {
|
if (nextRecord != null) {
|
||||||
headerRecord = nextRecord.values();
|
headerRecord = nextRecord.values();
|
||||||
|
headerComment = nextRecord.getComment();
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
if (this.format.getSkipHeaderRecord()) {
|
if (this.format.getSkipHeaderRecord()) {
|
||||||
this.nextRecord();
|
final CSVRecord csvRecord = this.nextRecord();
|
||||||
|
headerComment = csvRecord.getComment();
|
||||||
}
|
}
|
||||||
headerRecord = formatHeader;
|
headerRecord = formatHeader;
|
||||||
}
|
}
|
||||||
|
@ -596,7 +601,49 @@ public final class CSVParser implements Iterable<CSVRecord>, Closeable {
|
||||||
public List<String> getHeaderNames() {
|
public List<String> getHeaderNames() {
|
||||||
return Collections.unmodifiableList(headers.headerNames);
|
return Collections.unmodifiableList(headers.headerNames);
|
||||||
}
|
}
|
||||||
|
/**
|
||||||
|
* Checks whether this parser has a header comment, false otherwise.
|
||||||
|
* The header comment appears before the header record.
|
||||||
|
* Note that if the parser's format has been given an explicit header
|
||||||
|
* (with {@link CSVFormat.Builder#setHeader(String... )} or another overload)
|
||||||
|
* and the header record is not being skipped
|
||||||
|
* ({@link CSVFormat.Builder#setSkipHeaderRecord} is false) then any initial comments
|
||||||
|
* will be associated with the first record, not the header.
|
||||||
|
*
|
||||||
|
* @return true if this parser has seen a header comment, false otherwise
|
||||||
|
*/
|
||||||
|
public boolean hasHeaderComment() {
|
||||||
|
return headerComment != null;
|
||||||
|
}
|
||||||
|
/**
|
||||||
|
* Returns the header comment for this parser, if any.
|
||||||
|
* The header comment appears before the header record.
|
||||||
|
*
|
||||||
|
* @return the header comment for this stream, or null if no comment is available.
|
||||||
|
*/
|
||||||
|
public String getHeaderComment() {
|
||||||
|
return headerComment;
|
||||||
|
}
|
||||||
|
/**
|
||||||
|
* Checks whether this parser has seen a trailer comment, false otherwise.
|
||||||
|
* Trailer comments are located between the last record and EOF.
|
||||||
|
* The trailer comments will only be available after the parser has
|
||||||
|
* finished processing this stream.
|
||||||
|
*
|
||||||
|
* @return true if this parser has seen a trailer comment, false otherwise
|
||||||
|
*/
|
||||||
|
public boolean hasTrailerComment() {
|
||||||
|
return trailerComment != null;
|
||||||
|
}
|
||||||
|
/**
|
||||||
|
* Returns the trailer comment for this record, if any.
|
||||||
|
* Trailer comments are located between the last record and EOF
|
||||||
|
*
|
||||||
|
* @return the trailer comment for this stream, or null if no comment is available.
|
||||||
|
*/
|
||||||
|
public String getTrailerComment() {
|
||||||
|
return trailerComment;
|
||||||
|
}
|
||||||
/**
|
/**
|
||||||
* Returns the current record number in the input stream.
|
* Returns the current record number in the input stream.
|
||||||
*
|
*
|
||||||
|
@ -713,6 +760,10 @@ public final class CSVParser implements Iterable<CSVRecord>, Closeable {
|
||||||
case EOF:
|
case EOF:
|
||||||
if (this.reusableToken.isReady) {
|
if (this.reusableToken.isReady) {
|
||||||
this.addRecordValue(true);
|
this.addRecordValue(true);
|
||||||
|
} else {
|
||||||
|
if (sb != null) {
|
||||||
|
trailerComment = sb.toString();
|
||||||
|
}
|
||||||
}
|
}
|
||||||
break;
|
break;
|
||||||
case INVALID:
|
case INVALID:
|
||||||
|
|
|
@ -1375,4 +1375,128 @@ public class CSVParserTest {
|
||||||
|
|
||||||
parser.close();
|
parser.close();
|
||||||
}
|
}
|
||||||
|
@Test
|
||||||
|
public void getHeaderComment() throws IOException {
|
||||||
|
// File with no header comments
|
||||||
|
String text_1 = "A,B"+CRLF+"1,2"+CRLF;
|
||||||
|
// File with a single line header comment
|
||||||
|
String text_2 = "# comment"+CRLF+"A,B"+CRLF+"1,2"+CRLF;
|
||||||
|
// File with a multi-line header comment
|
||||||
|
String text_3 = "# multi-line" + CRLF + "# comment"+CRLF+"A,B"+CRLF+"1,2"+CRLF;
|
||||||
|
// Format with auto-detected header
|
||||||
|
CSVFormat format_a = CSVFormat.Builder.create(CSVFormat.DEFAULT).setCommentMarker('#').setHeader().build();
|
||||||
|
// Format with explicit header
|
||||||
|
CSVFormat format_b = CSVFormat.Builder.create(CSVFormat.DEFAULT)
|
||||||
|
.setSkipHeaderRecord(true)
|
||||||
|
.setCommentMarker('#')
|
||||||
|
.setHeader("A","B")
|
||||||
|
.build();
|
||||||
|
// Format with explicit header that does not skip the header line
|
||||||
|
CSVFormat format_c = CSVFormat.Builder.create(CSVFormat.DEFAULT)
|
||||||
|
.setCommentMarker('#')
|
||||||
|
.setHeader("A","B")
|
||||||
|
.build();
|
||||||
|
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_1, format_a)) {
|
||||||
|
parser.getRecords();
|
||||||
|
// Expect no header comment
|
||||||
|
assertFalse(parser.hasHeaderComment());
|
||||||
|
assertNull(parser.getHeaderComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_2, format_a)) {
|
||||||
|
parser.getRecords();
|
||||||
|
// Expect a header comment
|
||||||
|
assertTrue(parser.hasHeaderComment());
|
||||||
|
assertEquals("comment", parser.getHeaderComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_3, format_a)) {
|
||||||
|
parser.getRecords();
|
||||||
|
// Expect a header comment
|
||||||
|
assertTrue(parser.hasHeaderComment());
|
||||||
|
assertEquals("multi-line"+LF+"comment", parser.getHeaderComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_1, format_b)) {
|
||||||
|
parser.getRecords();
|
||||||
|
// Expect no header comment
|
||||||
|
assertFalse(parser.hasHeaderComment());
|
||||||
|
assertNull(parser.getHeaderComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_2, format_b)) {
|
||||||
|
parser.getRecords();
|
||||||
|
// Expect a header comment
|
||||||
|
assertTrue(parser.hasHeaderComment());
|
||||||
|
assertEquals("comment", parser.getHeaderComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_1, format_c)) {
|
||||||
|
parser.getRecords();
|
||||||
|
// Expect no header comment
|
||||||
|
assertFalse(parser.hasHeaderComment());
|
||||||
|
assertNull(parser.getHeaderComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_2, format_c)) {
|
||||||
|
parser.getRecords();
|
||||||
|
// Expect no header comment - the text "comment" is attached to the first record
|
||||||
|
assertFalse(parser.hasHeaderComment());
|
||||||
|
assertNull(parser.getHeaderComment());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
@Test
|
||||||
|
public void getTrailerComment() throws IOException {
|
||||||
|
// File with a header comment
|
||||||
|
String text_1 = "# header comment"+CRLF+"A,B"+CRLF+"1,2"+CRLF;
|
||||||
|
// File with a single line header and trailer comment
|
||||||
|
String text_2 = "# header comment"+CRLF+"A,B"+CRLF+"1,2"+CRLF + "# comment";
|
||||||
|
// File with a multi-line header and trailer comment
|
||||||
|
String text_3 = "# multi-line" + CRLF + "# header comment"+CRLF+"A,B"+CRLF+"1,2"+CRLF+"# multi-line"+CRLF+"# comment";
|
||||||
|
// Format with auto-detected header
|
||||||
|
CSVFormat format_a = CSVFormat.Builder.create(CSVFormat.DEFAULT).setCommentMarker('#').setHeader().build();
|
||||||
|
// Format with explicit header
|
||||||
|
CSVFormat format_b = CSVFormat.Builder.create(CSVFormat.DEFAULT)
|
||||||
|
.setSkipHeaderRecord(true)
|
||||||
|
.setCommentMarker('#')
|
||||||
|
.setHeader("A","B")
|
||||||
|
.build();
|
||||||
|
// Format with explicit header that does not skip the header line
|
||||||
|
CSVFormat format_c = CSVFormat.Builder.create(CSVFormat.DEFAULT)
|
||||||
|
.setCommentMarker('#')
|
||||||
|
.setHeader("A","B")
|
||||||
|
.build();
|
||||||
|
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_1, format_a)) {
|
||||||
|
parser.getRecords();
|
||||||
|
assertFalse(parser.hasTrailerComment());
|
||||||
|
assertNull(parser.getTrailerComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_2, format_a)) {
|
||||||
|
parser.getRecords();
|
||||||
|
assertTrue(parser.hasTrailerComment());
|
||||||
|
assertEquals("comment", parser.getTrailerComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_3, format_a)) {
|
||||||
|
parser.getRecords();
|
||||||
|
assertTrue(parser.hasTrailerComment());
|
||||||
|
assertEquals("multi-line"+LF+"comment", parser.getTrailerComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_1, format_b)) {
|
||||||
|
parser.getRecords();
|
||||||
|
assertFalse(parser.hasTrailerComment());
|
||||||
|
assertNull(parser.getTrailerComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_2, format_b)) {
|
||||||
|
parser.getRecords();
|
||||||
|
assertTrue(parser.hasTrailerComment());
|
||||||
|
assertEquals("comment", parser.getTrailerComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_1, format_c)) {
|
||||||
|
parser.getRecords();
|
||||||
|
assertFalse(parser.hasTrailerComment());
|
||||||
|
assertNull(parser.getTrailerComment());
|
||||||
|
}
|
||||||
|
try (CSVParser parser = CSVParser.parse(text_2, format_c)) {
|
||||||
|
parser.getRecords();
|
||||||
|
assertTrue(parser.hasTrailerComment());
|
||||||
|
assertEquals("comment", parser.getTrailerComment());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in New Issue