Skip to content

Update CSVParser to further increase csv ingest speed #57

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
kenwenzel merged 2 commits into from
Sep 7, 2026
Merged

Update CSVParser to further increase csv ingest speed #57

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
aa95f27
Replace regex-based CSV double parsing
wmehling Sep 2, 2026
37bfeb1
Parse CSV numbers before booleans
wmehling Sep 2, 2026
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
56 changes: 36 additions & 20 deletions ...kedfactory.core/src/main/java/io/github/linkedfactory/core/kvin/util/CsvFormatParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,6 @@
package io.github.linkedfactory.core.kvin.util;

import com.google.common.math.DoubleMath;
import com.google.common.primitives.Doubles;
import com.google.common.primitives.Ints;
import com.google.common.primitives.Longs;
import com.opencsv.CSVParser;
Expand Down Expand Up @@ -254,26 +253,27 @@ Object parseValue(String valueStr) {
// this is definitely a string
return valueStr.substring(1, valueStr.length() - 1);
}
// handle boolean values
String valueStrLowerCase = valueStr.toLowerCase();
if ("true".equals(valueStrLowerCase)) {
return true;
} else if ("false".equals(valueStrLowerCase)) {
return false;
}
Object value = valueStr;
Double doubleValue = Doubles.tryParse(valueStr);
if (doubleValue == null && valueStr.contains(",")) {
String cleanedValueStr;
if (valueStr.lastIndexOf(',') < valueStr.lastIndexOf('.')) {
// convert numbers like 123,456.78 to 123456.78
cleanedValueStr = valueStr.replace(",", "");
} else {
// convert numbers like 123.456,78 to 123456.78
cleanedValueStr = valueStr.replace(".", "")
.replace(",", ".");
Double doubleValue = tryParseDouble(valueStr);
if (doubleValue == null) {
String valueStrLowerCase = valueStr.toLowerCase();
if ("true".equals(valueStrLowerCase)) {
return true;
} else if ("false".equals(valueStrLowerCase)) {
return false;
}
if (valueStr.contains(",")) {
String cleanedValueStr;
if (valueStr.lastIndexOf(',') < valueStr.lastIndexOf('.')) {
// convert numbers like 123,456.78 to 123456.78
cleanedValueStr = valueStr.replace(",", "");
} else {
// convert numbers like 123.456,78 to 123456.78
cleanedValueStr = valueStr.replace(".", "")
.replace(",", ".");
}
doubleValue = tryParseDouble(cleanedValueStr);
}
doubleValue = Doubles.tryParse(cleanedValueStr);
}
if (doubleValue != null) {
if (DoubleMath.isMathematicalInteger(doubleValue) && !valueStr.contains(".")) {
Expand All @@ -286,6 +286,22 @@ Object parseValue(String valueStr) {
return value;
}

private static Double tryParseDouble(String value) {
if (value.isEmpty() || value.charAt(value.length() - 1) <= ' ') {
return null;
}
char first = value.charAt(0);
if (!((first >= '0' && first <= '9') || first == '+' || first == '-'
|| first == '.' || first == 'N' || first == 'I')) {
return null;
}
try {
return Double.parseDouble(value);
} catch (NumberFormatException ignored) {
return null;
}
}

public CsvFormatParser setContext(URI context) {
this.context = context;
return this;
Expand All @@ -308,4 +324,4 @@ protected static boolean containsWhitespace(String str) {
}
return false;
}
}
}
22 changes: 22 additions & 0 deletions ...actory.core/src/test/java/io/github/linkedfactory/core/kvin/util/CsvFormatParserTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,6 +149,28 @@ public void shouldParseCsvDoubleValues() throws IOException {
assertFalse(tuples.hasNext());
}

@Test
public void shouldParseCommonCsvValueForms() throws IOException {
CsvFormatParser parser = new CsvFormatParser(URIs.createURI("urn:base:"), ',',
new ByteArrayInputStream("time,value\n".getBytes(StandardCharsets.UTF_8)));
Object[][] cases = {
{"42", 42L}, {"+42", 42L}, {"-42", -42L},
{"+.5", 0.5d}, {"1.", 1d}, {"3.14", 3.14d}, {"1e3", 1000L},
{"1f", 1L}, {"0x1.8p1", 3d},
{"1,234.56", 1234.56d}, {"1.234,56", 1234.56d},
{"NaN", Double.NaN}, {"-NaN", Double.NaN},
{"Infinity", Double.POSITIVE_INFINITY}, {"-Infinity", Double.NEGATIVE_INFINITY},
{"true", true}, {"FALSE", false}, {"'quoted'", "quoted"},
{"plain text", "plain text"}, {"NAN", "NAN"}, {"infinity", "infinity"},
{"0x1", "0x1"}, {"1e", "1e"}, {"1_0", "1_0"}, {"1x", "1x"},
{" 1", " 1"}, {"1 ", "1 "}, {"\t1", "\t1"}, {"1\u0000", "1\u0000"}
};
for (Object[] testCase : cases) {
assertEquals("Unexpected value for " + testCase[0], testCase[1],
parser.parseValue((String) testCase[0]));
}
}

@Test
public void shouldPreserveSparseRowsAndTupleFields() throws IOException {
String csv = String.join("\n",
Expand Down