Skip to content

[format] Preserve csv values matching the configured null literal #9492

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
JingsongLi merged 1 commit into from
Sep 2, 2026
+25 −11
Merged

[format] Preserve csv values matching the configured null literal #9492

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion paimon-format/src/main/java/org/apache/paimon/format/csv/CsvFormatWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,8 @@ private String escapeField(String field) {

// Optimized escaping with early exit checks
boolean needsQuoting =
field.indexOf(csvOptions.fieldDelimiter().charAt(0)) >= 0
field.equals(csvOptions.nullLiteral())
|| field.indexOf(csvOptions.fieldDelimiter().charAt(0)) >= 0
|| field.indexOf(csvOptions.lineDelimiter().charAt(0)) >= 0
|| field.indexOf(quote.charAt(0)) >= 0
|| (escapable && field.indexOf(escape.charAt(0)) >= 0);
Expand Down
14 changes: 12 additions & 2 deletions paimon-format/src/main/java/org/apache/paimon/format/csv/CsvParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,7 @@ public class CsvParser {
private final Mode mode;
private final StringBuilder buffer;
private final String[] rowValues;
private final boolean[] rowQuoted;

public CsvParser(RowType dataSchemaRowType, int[] projectMapping, CsvOptions options) {
this.dataSchemaRowType = dataSchemaRowType;
Expand All @@ -70,6 +71,7 @@ public CsvParser(RowType dataSchemaRowType, int[] projectMapping, CsvOptions opt
this.buffer = new StringBuilder(1024);
int columnCount = Arrays.stream(projectMapping).max().orElse(-1) + 1;
this.rowValues = new String[columnCount];
this.rowQuoted = new boolean[columnCount];

this.separatorChar = options.fieldDelimiter().charAt(0);
this.quoteChar = options.quoteCharacter().charAt(0);
Expand All @@ -91,6 +93,7 @@ public CsvParser(RowType dataSchemaRowType, int[] projectMapping, CsvOptions opt
@Nullable
public GenericRow parse(String line) {
Arrays.fill(rowValues, null);
Arrays.fill(rowQuoted, false);
buffer.setLength(0);

// empty line results in all null values
Expand Down Expand Up @@ -136,6 +139,9 @@ public GenericRow parse(String line) {
buffer.append(c);
}
}
if (!inQuotes && buffer.length() == 0) {
rowQuoted[columnIndex] = true;
}
inQuotes = !inQuotes;
}
inField = !inField;
Expand Down Expand Up @@ -166,7 +172,7 @@ public GenericRow parse(String line) {
Exception exception = null;
String parseValue = rowValues[ordinal];
try {
parseResult = parseField(parseValue, type);
parseResult = parseField(parseValue, type, rowQuoted[ordinal]);
} catch (Exception e) {
exception = e;
}
Expand Down Expand Up @@ -203,7 +209,11 @@ private static boolean isAllWhitespace(CharSequence sequence) {

@VisibleForTesting
public Pair<Boolean, Object> parseField(String field, DataType dataType) {
if (field == null || field.equals(nullLiteral)) {
return parseField(field, dataType, false);
}

private Pair<Boolean, Object> parseField(String field, DataType dataType, boolean quoted) {
if (field == null || (!quoted && field.equals(nullLiteral))) {
return Pair.of(true, null);
}

Expand Down
19 changes: 11 additions & 8 deletions paimon-format/src/test/java/org/apache/paimon/format/csv/CsvFileFormatTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -464,17 +464,17 @@ public void testCsvNullLiteralWriteRead() throws IOException {

String[] nullLiterals = {"", "NULL", "null"};

// Create test data with null values
List<InternalRow> testData =
Arrays.asList(
GenericRow.of(1, BinaryString.fromString("Alice"), null),
GenericRow.of(2, null, 100),
GenericRow.of(3, BinaryString.fromString("Charlie"), 300));

for (String nullLiteral : nullLiterals) {
Options options = new Options();
options.set(CsvOptions.NULL_LITERAL, nullLiteral);

List<InternalRow> testData =
Arrays.asList(
GenericRow.of(1, BinaryString.fromString("Alice"), null),
GenericRow.of(2, null, 100),
GenericRow.of(3, BinaryString.fromString("Charlie"), 300),
GenericRow.of(4, BinaryString.fromString(nullLiteral), 400));

List<InternalRow> result =
writeThenRead(
options,
Expand All @@ -484,7 +484,7 @@ public void testCsvNullLiteralWriteRead() throws IOException {
"test_null_literal_" + nullLiteral.hashCode());

// Verify results
assertThat(result).hasSize(3);
assertThat(result).hasSize(4);
assertThat(result.get(0).getInt(0)).isEqualTo(1);
assertThat(result.get(0).getString(1).toString()).isEqualTo("Alice");
assertThat(result.get(0).isNullAt(2)).isTrue();
Expand All @@ -494,6 +494,9 @@ public void testCsvNullLiteralWriteRead() throws IOException {
assertThat(result.get(2).getInt(0)).isEqualTo(3);
assertThat(result.get(2).getString(1).toString()).isEqualTo("Charlie");
assertThat(result.get(2).getInt(2)).isEqualTo(300);
assertThat(result.get(3).getInt(0)).isEqualTo(4);
assertThat(result.get(3).getString(1).toString()).isEqualTo(nullLiteral);
assertThat(result.get(3).getInt(2)).isEqualTo(400);
}
}

Expand Down
Loading