Skip to content
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.

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

Add support in Commons CSV for tracking byte positions during parsing #12

Merged
merged 4 commits into from
Nov 19, 2024
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
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
1 change: 0 additions & 1 deletion pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,6 @@
<url>https://commons.apache.org/proper/commons-csv/</url>
<inceptionYear>2005</inceptionYear>
<description>The Apache Commons CSV library provides a simple interface for reading and writing CSV files of various types.</description>
<packaging>jar</packaging>
DarrenJAN marked this conversation as resolved.
Show resolved Hide resolved

<dependencies>
<dependency>
Expand Down
24 changes: 0 additions & 24 deletions src/main/java/org/apache/commons/csv/CSVFormat.java
Original file line number Diff line number Diff line change
Expand Up @@ -2097,30 +2097,6 @@ public CSVParser parse(final Reader reader) throws IOException {
return CSVParser.builder().setReader(reader).setFormat(this).get();
}

/**
* Parses the specified content.
*
* <p>
* This method provides a way to parse CSV data from an input stream, starting at a specified character offset and record number,
* using a specified encoding. It returns a {@link CSVParser} that can be used to iterate over the parsed {@link CSVRecord}s.
* </p>
*
* <p>
* For additional parsing options, see the various static parse methods available on {@link CSVParser}.
* </p>
*
* @param reader the input stream
* @param characterOffset the character offset to start parsing from
* @param recordNumber the initial record number to start counting from
* @param encoding the character encoding of the input stream
* @return a parser over a stream of {@link CSVRecord}s.
* @throws IOException If an I/O error occurs
* @throws CSVException Thrown on invalid input.
*/
public CSVParser parse(final Reader reader, final long characterOffset, final long recordNumber, String encoding) throws IOException {
return new CSVParser(reader, this, characterOffset, recordNumber, encoding);
}

/**
* Prints to the specified output.
*
Expand Down
30 changes: 21 additions & 9 deletions src/main/java/org/apache/commons/csv/CSVParser.java
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 Charset charset;

/**
* 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);
return new CSVParser(getReader(), format != null ? format : CSVFormat.DEFAULT, characterOffset, recordNumber, charset);
}

/**
Expand Down Expand Up @@ -200,6 +201,16 @@ public Builder setRecordNumber(final long recordNumber) {
return asThis();
}

/**
* Sets the character encoding to be used for the reader.
*
* @param charset the character encoding.
* @return this instance.
*/
public Builder setCharset(final Charset charset) {
this.charset = charset;
return asThis();
}
}

final class CSVRecordIterator implements Iterator<CSVRecord> {
Expand Down Expand Up @@ -510,7 +521,7 @@ public CSVParser(final Reader reader, final CSVFormat format, final long charact
this(reader, format, characterOffset, recordNumber, null);
}

/**
/**

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry just noticed an extra indentation problem

* Constructs a new instance using the given {@link CSVFormat}
*
* <p>
Expand All @@ -525,21 +536,22 @@ public CSVParser(final Reader reader, final CSVFormat format, final long charact
* @param characterOffset
* Lexer offset when the parser does not start parsing at the beginning of the source.
* @param recordNumber
* The next record number to assign
* @param encoding
* The encoding to use for the reader
* The next record number to assign.
* @param charset
* The character encoding to be used for the reader.
* @throws IllegalArgumentException
* If the parameters of the format are inconsistent or if either the reader or format is null.
* @throws IOException
* If there is a problem reading the header or skipping the first record
* If there is a problem reading the header or skipping the first record.
* @throws CSVException Thrown on invalid input.
* @since 1.13.0.
*/
public CSVParser(final Reader reader, final CSVFormat format, final long characterOffset, final long recordNumber,
String encoding) throws IOException {
private CSVParser(final Reader reader, final CSVFormat format, final long characterOffset, final long recordNumber, final Charset charset)
throws IOException {
Objects.requireNonNull(reader, "reader");
Objects.requireNonNull(format, "format");
this.format = format.copy();
this.lexer = new Lexer(format, new ExtendedBufferedReader(reader, encoding));
this.lexer = new Lexer(format, new ExtendedBufferedReader(reader, charset));
this.csvRecordIterator = new CSVRecordIterator();
this.headers = createHeaders();
this.characterOffset = characterOffset;
Expand Down
46 changes: 28 additions & 18 deletions src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
Original file line number Diff line number Diff line change
Expand Up @@ -53,12 +53,12 @@ final class ExtendedBufferedReader extends UnsynchronizedBufferedReader {
private long position;
private long positionMark;

/** The number of bytes read so far */
/** The number of bytes read so far. */
private long bytesRead;
private long bytesReadMark;

/** Encoder used to calculate the bytes of characters */
CharsetEncoder encoder;
/** Encoder for calculating the number of bytes for each character read. */
private CharsetEncoder encoder;

/**
* Constructs a new instance using the default buffer size.
Expand All @@ -67,10 +67,10 @@ final class ExtendedBufferedReader extends UnsynchronizedBufferedReader {
super(reader);
}

ExtendedBufferedReader(final Reader reader, String encoding) {
ExtendedBufferedReader(final Reader reader, Charset charset) {
super(reader);
if (encoding != null) {
encoder = Charset.forName(encoding).newEncoder();
if (charset != null) {
encoder = charset.newEncoder();
}
}

Expand Down Expand Up @@ -146,20 +146,30 @@ public int read() throws IOException {
}

/**
* In Java, a char data type are based on the original Unicode
* specification, which defined characters as fixed-width 16-bit entities.
* U+0000 to U+FFFF:
* - BMP, represented using 1 16-bit char
* - Consists of UTF-8 1-byte, 2-byte, some 3-byte chars
* U+10000 to U+10FFFF:
* - Supplementary characters, represented as a pair of characters,
* the first char from the high-surrogates range (\uD800-\uDBFF),
* and the second char from the low-surrogates range (uDC00-\uDFFF).
* - Consists of UTF-8 some 3-byte chars and 4-byte chars
* In Java, the {@code char} data type is based on the original Unicode
* specification, which defined characters as fixed-width 16-bit entities.
* <p>
* The Unicode characters are divided into two main ranges:
* <ul>
* <li><b>U+0000 to U+FFFF (Basic Multilingual Plane, BMP):</b>
* <ul>
* <li>Represented using a single 16-bit {@code char}.</li>
* <li>Includes UTF-8 encodings of 1-byte, 2-byte, and some 3-byte characters.</li>
* </ul>
* </li>
* <li><b>U+10000 to U+10FFFF (Supplementary Characters):</b>
* <ul>
* <li>Represented as a pair of {@code char}s:</li>
* <li>The first {@code char} is from the high-surrogates range (\uD800-\uDBFF).</li>
* <li>The second {@code char} is from the low-surrogates range (\uDC00-\uDFFF).</li>
* <li>Includes UTF-8 encodings of some 3-byte characters and all 4-byte characters.</li>
* </ul>
* </li>
* </ul>
*/
private long getCharBytes(int current) throws CharacterCodingException {
char cChar = (char) current;
char lChar = (char) lastChar;
final char cChar = (char) current;
final char lChar = (char) lastChar;
if (!Character.isSurrogate(cChar)) {
return encoder.encode(
CharBuffer.wrap(new char[] {cChar})).limit();
Expand Down
99 changes: 46 additions & 53 deletions src/test/java/org/apache/commons/csv/CSVParserTest.java
Original file line number Diff line number Diff line change
Expand Up @@ -707,38 +707,34 @@ public void testGetRecordThreeBytesRead() throws Exception {
"11111111111111,'4017-09-01',きちんと節分近くには咲いてる~,v4\n" +
"22222222222222,'4017-01-01',おはよう私の友人~,v4\n" +
"33333333333333,'4017-01-01',きる自然の力ってすごいな~,v4\n";
// String code = "'1',4";
// final CSVFormat format = CSVFormat.newFormat(',').withQuote('\'');
final CSVFormat format = CSVFormat.Builder.create()
.setDelimiter(',')
.setQuote('\'')
.build();
// CSVParser parser = new CSVParser(new StringReader(code), format, 0L, 1L, "UTF-8");
CSVParser parser = format.parse(new StringReader(code), 0L, 1L, "UTF-8");

CSVRecord record = new CSVRecord(parser, null, null, 1L, 0L, 0L);
assertEquals(0, parser.getRecordNumber());
assertNotNull(record = parser.nextRecord());
assertEquals(1, record.getRecordNumber());
assertEquals(code.indexOf('i'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), record.getCharacterPosition());
.setDelimiter(',')
.setQuote('\'')
.get();
try (CSVParser parser = CSVParser.builder().setReader(new StringReader(code)).setFormat(format).setCharset(UTF_8).get() ) {
CSVRecord record = new CSVRecord(parser, null, null, 1L, 0L, 0L);

assertNotNull(record = parser.nextRecord());
assertEquals(2, record.getRecordNumber());
assertEquals(code.indexOf('1'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), record.getCharacterPosition());
assertEquals(0, parser.getRecordNumber());
assertNotNull(record = parser.nextRecord());
assertEquals(1, record.getRecordNumber());
assertEquals(code.indexOf('i'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), record.getCharacterPosition());

assertNotNull(record = parser.nextRecord());
assertEquals(3, record.getRecordNumber());
assertEquals(code.indexOf('2'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), 95);
assertNotNull(record = parser.nextRecord());
assertEquals(2, record.getRecordNumber());
assertEquals(code.indexOf('1'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), record.getCharacterPosition());

assertNotNull(record = parser.nextRecord());
assertEquals(4, record.getRecordNumber());
assertEquals(code.indexOf('3'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), 154);
assertNotNull(record = parser.nextRecord());
assertEquals(3, record.getRecordNumber());
assertEquals(code.indexOf('2'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), 95);

parser.close();
assertNotNull(record = parser.nextRecord());
assertEquals(4, record.getRecordNumber());
assertEquals(code.indexOf('3'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), 154);
};

}

Expand All @@ -748,35 +744,32 @@ public void testGetRecordFourBytesRead() throws Exception {
"1,😊,🤔,😂\n" +
"2,😊,🤔,😂\n" +
"3,😊,🤔,😂\n";
// final CSVFormat format = CSVFormat.newFormat(',').withQuote('\'');
final CSVFormat format = CSVFormat.Builder.create()
.setDelimiter(',')
.setQuote('\'')
.build();

// CSVParser parser = new CSVParser(new StringReader(code), format, 0L, 1L, "UTF-8");
CSVParser parser = format.parse(new StringReader(code), 0L, 1L, "UTF-8");

CSVRecord record;
assertEquals(0, parser.getRecordNumber());
assertNotNull(record = parser.nextRecord());
assertEquals(1, record.getRecordNumber());
assertEquals(code.indexOf('i'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), record.getCharacterPosition());

assertNotNull(record = parser.nextRecord());
assertEquals(2, record.getRecordNumber());
assertEquals(code.indexOf('1'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), record.getCharacterPosition());
assertNotNull(record = parser.nextRecord());
assertEquals(3, record.getRecordNumber());
assertEquals(code.indexOf('2'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), 26);
assertNotNull(record = parser.nextRecord());
assertEquals(4, record.getRecordNumber());
assertEquals(code.indexOf('3'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), 43);
parser.close();
.get();
try (CSVParser parser = CSVParser.builder().setReader(new StringReader(code)).setFormat(format).setCharset(UTF_8).get()) {
CSVRecord record = new CSVRecord(parser, null, null, 1L, 0L, 0L);

assertEquals(0, parser.getRecordNumber());
assertNotNull(record = parser.nextRecord());
assertEquals(1, record.getRecordNumber());
assertEquals(code.indexOf('i'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), record.getCharacterPosition());

assertNotNull(record = parser.nextRecord());
assertEquals(2, record.getRecordNumber());
assertEquals(code.indexOf('1'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), record.getCharacterPosition());
assertNotNull(record = parser.nextRecord());
assertEquals(3, record.getRecordNumber());
assertEquals(code.indexOf('2'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), 26);
assertNotNull(record = parser.nextRecord());
assertEquals(4, record.getRecordNumber());
assertEquals(code.indexOf('3'), record.getCharacterPosition());
assertEquals(record.getCharacterByte(), 43);
}
}

@Test
Expand Down
32 changes: 15 additions & 17 deletions src/test/java/org/apache/commons/csv/JiraCsv196Test.java
Original file line number Diff line number Diff line change
Expand Up @@ -21,24 +21,23 @@
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.Reader;

import java.nio.charset.StandardCharsets;

import org.junit.jupiter.api.Test;


public class JiraCsv196Test {
@Test
public void parseThreeBytes() throws IOException {

// final CSVFormat format = CSVFormat.newFormat(',').withQuote('\'');
final CSVFormat format = CSVFormat.Builder.create()
.setDelimiter(',')
.setQuote('\'')
.build();
// CSVParser parser = new CSVParser(getTestInput(
// "org/apache/commons/csv/CSV-196/japanese.csv"), format, 0L, 1L, "UTF-8");
CSVParser parser = format.parse(getTestInput(
"org/apache/commons/csv/CSV-196/japanese.csv"), 0L, 1L, "UTF-8");
.setDelimiter(',')
.setQuote('\'')
.get();
CSVParser parser = new CSVParser.Builder()
.setFormat(format)
.setReader(getTestInput("org/apache/commons/csv/CSV-196/japanese.csv"))
.setCharset(StandardCharsets.UTF_8)
.get();
long[] charByteKey = {0, 89, 242, 395};
int idx = 0;
for (CSVRecord record : parser) {
Expand All @@ -50,15 +49,15 @@ public void parseThreeBytes() throws IOException {

@Test
public void parseFourBytes() throws IOException {
// final CSVFormat format = CSVFormat.newFormat(',').withQuote('\'');
final CSVFormat format = CSVFormat.Builder.create()
.setDelimiter(',')
.setQuote('\'')
.build();

CSVParser parser = format.parse(getTestInput(
"org/apache/commons/csv/CSV-196/emoji.csv"), 0L, 1L, "UTF-8");

.get();
CSVParser parser = new CSVParser.Builder()
.setFormat(format)
.setReader(getTestInput("org/apache/commons/csv/CSV-196/emoji.csv"))
.setCharset(StandardCharsets.UTF_8)
.get();
long[] charByteKey = {0, 84, 701, 1318, 1935};
int idx = 0;
for (CSVRecord record : parser) {
Expand All @@ -67,7 +66,6 @@ public void parseFourBytes() throws IOException {
parser.close();
}


private Reader getTestInput(String path) {
return new InputStreamReader(
ClassLoader.getSystemClassLoader().getResourceAsStream(path));
Expand Down
Loading