diff --git a/src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java b/src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
index 8dcda6517..889b58edc 100644
--- a/src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
+++ b/src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
@@ -37,26 +37,30 @@
/**
* A special buffered reader which supports sophisticated read access.
*
- * In particular the reader supports a look-ahead option, which allows you to see the next char returned by
- * {@link #read()}. This reader also tracks how many characters have been read with {@link #getPosition()}.
+ * In particular the reader supports a look-ahead option, which allows you to see the next char returned by {@link #read()}. This reader also tracks how many
+ * characters have been read with {@link #getPosition()}.
*
*/
final class ExtendedBufferedReader extends UnsynchronizedBufferedReader {
/** The last char returned */
private int lastChar = UNDEFINED;
+
private int lastCharMark = UNDEFINED;
/** The count of EOLs (CR/LF/CRLF) seen so far */
private long lineNumber;
+
private long lineNumberMark;
/** The position, which is the number of characters read so far */
private long position;
+
private long positionMark;
/** The number of bytes read so far. */
private long bytesRead;
+
private long bytesReadMark;
/** Encoder for calculating the number of bytes for each character read. */
@@ -70,12 +74,11 @@ final class ExtendedBufferedReader extends UnsynchronizedBufferedReader {
}
/**
- * Constructs a new instance with the specified reader, character set,
- * and byte tracking option. Initializes an encoder if byte tracking is enabled
- * and a character set is provided.
+ * Constructs a new instance with the specified reader, character set, and byte tracking option. Initializes an encoder if byte tracking is enabled and a
+ * character set is provided.
*
- * @param reader the reader supports a look-ahead option.
- * @param charset the character set for encoding, or {@code null} if not applicable.
+ * @param reader the reader supports a look-ahead option.
+ * @param charset the character set for encoding, or {@code null} if not applicable.
* @param trackBytes {@code true} to enable byte tracking; {@code false} to disable it.
*/
ExtendedBufferedReader(final Reader reader, final Charset charset, final boolean trackBytes) {
@@ -86,8 +89,7 @@ final class ExtendedBufferedReader extends UnsynchronizedBufferedReader {
/**
* Closes the stream.
*
- * @throws IOException
- * If an I/O error occurs
+ * @throws IOException If an I/O error occurs
*/
@Override
public void close() throws IOException {
@@ -105,26 +107,33 @@ long getBytesRead() {
return this.bytesRead;
}
+ private long getEncodedCharLength(final char[] buf, final int offset, final int length) throws CharacterCodingException {
+ int len = 0;
+ for (int i = offset; i < length; i++) {
+ len += getEncodedCharLength(buf[i]);
+ }
+ return len;
+ }
+
/**
- * Gets the byte length of the given character based on the original Unicode
- * specification, which defined characters as fixed-width 16-bit entities.
+ * Gets the byte length of the given character based on the original Unicode specification, which defined characters as fixed-width 16-bit entities.
*
* The Unicode characters are divided into two main ranges:
*
- * - U+0000 to U+FFFF (Basic Multilingual Plane, BMP):
- *
- * - Represented using a single 16-bit {@code char}.
- * - Includes UTF-8 encodings of 1-byte, 2-byte, and some 3-byte characters.
- *
- *
- * - U+10000 to U+10FFFF (Supplementary Characters):
- *
- * - Represented as a pair of {@code char}s:
- * - The first {@code char} is from the high-surrogates range (\uD800-\uDBFF).
- * - The second {@code char} is from the low-surrogates range (\uDC00-\uDFFF).
- * - Includes UTF-8 encodings of some 3-byte characters and all 4-byte characters.
- *
- *
+ * - U+0000 to U+FFFF (Basic Multilingual Plane, BMP):
+ *
+ * - Represented using a single 16-bit {@code char}.
+ * - Includes UTF-8 encodings of 1-byte, 2-byte, and some 3-byte characters.
+ *
+ *
+ * - U+10000 to U+10FFFF (Supplementary Characters):
+ *
+ * - Represented as a pair of {@code char}s:
+ * - The first {@code char} is from the high-surrogates range (\uD800-\uDBFF).
+ * - The second {@code char} is from the low-surrogates range (\uDC00-\uDFFF).
+ * - Includes UTF-8 encodings of some 3-byte characters and all 4-byte characters.
+ *
+ *
*
*
* @param current the current character to process.
@@ -148,10 +157,9 @@ private int getEncodedCharLength(final int current) throws CharacterCodingExcept
}
/**
- * Returns the last character that was read as an integer (0 to 65535). This will be the last character returned by
- * any of the read methods. This will not include a character read using the {@link #peek()} method. If no
- * character has been read then this will return {@link Constants#UNDEFINED}. If the end of the stream was reached
- * on the last read then this will return {@link IOUtils#EOF}.
+ * Returns the last character that was read as an integer (0 to 65535). This will be the last character returned by any of the read methods. This will not
+ * include a character read using the {@link #peek()} method. If no character has been read then this will return {@link Constants#UNDEFINED}. If the end of
+ * the stream was reached on the last read then this will return {@link IOUtils#EOF}.
*
* @return the last character that was read
*/
@@ -193,8 +201,7 @@ public void mark(final int readAheadLimit) throws IOException {
@Override
public int read() throws IOException {
final int current = super.read();
- if (current == CR || current == LF && lastChar != CR ||
- current == EOF && lastChar != CR && lastChar != LF && lastChar != EOF) {
+ if (current == CR || current == LF && lastChar != CR || current == EOF && lastChar != CR && lastChar != LF && lastChar != EOF) {
lineNumber++;
}
if (encoder != null) {
@@ -226,13 +233,15 @@ public int read(final char[] buf, final int offset, final int length) throws IOE
} else if (len == EOF) {
lastChar = EOF;
}
+ if (encoder != null) {
+ this.bytesRead += getEncodedCharLength(buf, offset, len);
+ }
position += len;
return len;
}
/**
- * Gets the next line, dropping the line terminator(s). This method should only be called when processing a
- * comment, otherwise, information can be lost.
+ * Gets the next line, dropping the line terminator(s). This method should only be called when processing a comment, otherwise, information can be lost.
*
* Increments {@link #lineNumber} and updates {@link #position}.
*
@@ -272,5 +281,4 @@ public void reset() throws IOException {
bytesRead = bytesReadMark;
super.reset();
}
-
}
diff --git a/src/test/java/org/apache/commons/csv/CSVParserTest.java b/src/test/java/org/apache/commons/csv/CSVParserTest.java
index d9dd4e545..e18eee026 100644
--- a/src/test/java/org/apache/commons/csv/CSVParserTest.java
+++ b/src/test/java/org/apache/commons/csv/CSVParserTest.java
@@ -648,6 +648,24 @@ void testForEach() throws Exception {
}
}
+ @Test
+ void testGetBytePositionMultiCharacterDelimiter() throws IOException {
+ final String code = "aa[|]bb\ncc[|]dd\n";
+ final CSVFormat format = CSVFormat.DEFAULT.builder().setDelimiter("[|]").get();
+ try (CSVParser parser = CSVParser.builder()
+ .setReader(new StringReader(code))
+ .setFormat(format)
+ .setCharset(StandardCharsets.UTF_8)
+ .setTrackBytes(true)
+ .get()) {
+ final Iterator it = parser.iterator();
+ final CSVRecord first = it.next();
+ final CSVRecord second = it.next();
+ assertEquals(0, first.getBytePosition());
+ assertEquals(8, second.getBytePosition());
+ }
+ }
+
@Test
void testGetHeaderComment_HeaderComment1() throws IOException {
try (CSVParser parser = CSVParser.parse(CSV_INPUT_HEADER_COMMENT, FORMAT_AUTO_HEADER)) {