Skip to content

Adding a boolean to drive byte tracking opt-in behavior #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
DarrenJAN merged 2 commits into from
Dec 3, 2024
Merged

Adding a boolean to drive byte tracking opt-in behavior #14

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
edb48ed
Adding a boolean to drive byte tracking opt-in behavior
DarrenJAN Dec 3, 2024
df8899d
Adding a boolean to drive byte tracking opt-in behavior
DarrenJAN Dec 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 11 additions & 4 deletions src/main/java/org/apache/commons/csv/CSVParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -153,6 +153,7 @@ public static class Builder extends AbstractStreamBuilder<CSVParser, Builder> {
private CSVFormat format;
private long characterOffset;
private long recordNumber = 1;
private boolean enableByteTracking = false;

/**
* Constructs a new instance.
Expand All @@ -164,7 +165,7 @@ protected Builder() {
@SuppressWarnings("resource")
@Override
public CSVParser get() throws IOException {
return new CSVParser(getReader(), format != null ? format : CSVFormat.DEFAULT, characterOffset, recordNumber, getCharset());
return new CSVParser(getReader(), format != null ? format : CSVFormat.DEFAULT, characterOffset, recordNumber, getCharset(), enableByteTracking);
}

/**
Expand Down Expand Up @@ -200,6 +201,11 @@ public Builder setRecordNumber(final long recordNumber) {
return asThis();
}

public Builder setEnableByteTracking(final boolean enableByteTracking) {
this.enableByteTracking = enableByteTracking;
return asThis();
}

}

final class CSVRecordIterator implements Iterator<CSVRecord> {
Expand Down Expand Up @@ -507,7 +513,7 @@ public CSVParser(final Reader reader, final CSVFormat format) throws IOException
@SuppressWarnings("resource")
public CSVParser(final Reader reader, final CSVFormat format, final long characterOffset, final long recordNumber)
throws IOException {
this(reader, format, characterOffset, recordNumber, null);
this(reader, format, characterOffset, recordNumber, null, false);
}

/**
Expand Down Expand Up @@ -535,12 +541,13 @@ public CSVParser(final Reader reader, final CSVFormat format, final long charact
* @throws CSVException Thrown on invalid input.
* @since 1.13.0.
*/
private CSVParser(final Reader reader, final CSVFormat format, final long characterOffset, final long recordNumber, final Charset charset)
private CSVParser(final Reader reader, final CSVFormat format, final long characterOffset, final long recordNumber,
final Charset charset, final boolean enableByteTracking)
throws IOException {
Objects.requireNonNull(reader, "reader");
Objects.requireNonNull(format, "format");
this.format = format.copy();
this.lexer = new Lexer(format, new ExtendedBufferedReader(reader, charset));
this.lexer = new Lexer(format, new ExtendedBufferedReader(reader, charset, enableByteTracking));
this.csvRecordIterator = new CSVRecordIterator();
this.headers = createHeaders();
this.characterOffset = characterOffset;
Expand Down
4 changes: 2 additions & 2 deletions src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,9 +67,9 @@ final class ExtendedBufferedReader extends UnsynchronizedBufferedReader {
super(reader);
}

ExtendedBufferedReader(final Reader reader, Charset charset) {
ExtendedBufferedReader(final Reader reader, Charset charset, boolean enableByteTracking) {
super(reader);
if (charset != null) {
if (charset != null && enableByteTracking) {
encoder = charset.newEncoder();
}
}
Expand Down
4 changes: 2 additions & 2 deletions src/test/java/org/apache/commons/csv/CSVParserTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -711,7 +711,7 @@ public void testGetRecordThreeBytesRead() throws Exception {
.setDelimiter(',')
.setQuote('\'')
.get();
try (CSVParser parser = CSVParser.builder().setReader(new StringReader(code)).setFormat(format).setCharset(UTF_8).get() ) {
try (CSVParser parser = CSVParser.builder().setReader(new StringReader(code)).setFormat(format).setCharset(UTF_8).setEnableByteTracking(true).get() ) {
CSVRecord record = new CSVRecord(parser, null, null, 1L, 0L, 0L);

assertEquals(0, parser.getRecordNumber());
Expand Down Expand Up @@ -748,7 +748,7 @@ public void testGetRecordFourBytesRead() throws Exception {
.setDelimiter(',')
.setQuote('\'')
.get();
try (CSVParser parser = CSVParser.builder().setReader(new StringReader(code)).setFormat(format).setCharset(UTF_8).get()) {
try (CSVParser parser = CSVParser.builder().setReader(new StringReader(code)).setFormat(format).setCharset(UTF_8).setEnableByteTracking(true).get()) {
CSVRecord record = new CSVRecord(parser, null, null, 1L, 0L, 0L);

assertEquals(0, parser.getRecordNumber());
Expand Down
2 changes: 2 additions & 0 deletions src/test/java/org/apache/commons/csv/JiraCsv196Test.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@ public void parseThreeBytes() throws IOException {
.setFormat(format)
.setReader(getTestInput("org/apache/commons/csv/CSV-196/japanese.csv"))
.setCharset(StandardCharsets.UTF_8)
.setEnableByteTracking(true)
.get();
long[] charByteKey = {0, 89, 242, 395};
int idx = 0;
Expand All @@ -57,6 +58,7 @@ public void parseFourBytes() throws IOException {
.setFormat(format)
.setReader(getTestInput("org/apache/commons/csv/CSV-196/emoji.csv"))
.setCharset(StandardCharsets.UTF_8)
.setEnableByteTracking(true)
.get();
long[] charByteKey = {0, 84, 701, 1318, 1935};
int idx = 0;
Expand Down