From 9bde99040e8be75d44541c3362a7e65c63814400 Mon Sep 17 00:00:00 2001 From: gbidsilva Date: Wed, 30 Aug 2023 17:04:54 +0530 Subject: [PATCH 01/16] removing duplicated exception class name from error message --- .../org/apache/commons/csv/CSVParser.java | 2 +- .../org/apache/commons/csv/CSVBenchmark.java | 454 +++++++++--------- .../java/org/apache/commons/csv/CSVTest.java | 79 +++ 3 files changed, 307 insertions(+), 228 deletions(-) create mode 100644 src/test/java/org/apache/commons/csv/CSVTest.java diff --git a/src/main/java/org/apache/commons/csv/CSVParser.java b/src/main/java/org/apache/commons/csv/CSVParser.java index 96e77a77..7d292c6a 100644 --- a/src/main/java/org/apache/commons/csv/CSVParser.java +++ b/src/main/java/org/apache/commons/csv/CSVParser.java @@ -147,7 +147,7 @@ public final class CSVParser implements Iterable, Closeable { try { return CSVParser.this.nextRecord(); } catch (final IOException e) { - throw new UncheckedIOException(e.getClass().getSimpleName() + " reading next record: " + e.toString(), e); + throw new UncheckedIOException("Error in reading next record: " + e.toString(), e); } } diff --git a/src/test/java/org/apache/commons/csv/CSVBenchmark.java b/src/test/java/org/apache/commons/csv/CSVBenchmark.java index 64d3f498..232142ef 100644 --- a/src/test/java/org/apache/commons/csv/CSVBenchmark.java +++ b/src/test/java/org/apache/commons/csv/CSVBenchmark.java @@ -1,227 +1,227 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.commons.csv; - -import java.io.BufferedReader; -import java.io.IOException; -import java.io.InputStream; -import java.io.Reader; -import java.io.StringReader; -import java.nio.charset.StandardCharsets; -import java.util.Iterator; -import java.util.Scanner; -import java.util.concurrent.TimeUnit; -import java.util.zip.GZIPInputStream; - -import com.generationjava.io.CsvReader; -import com.opencsv.CSVParserBuilder; -import com.opencsv.CSVReaderBuilder; - -import org.apache.commons.io.IOUtils; -import org.apache.commons.lang3.StringUtils; -import org.openjdk.jmh.annotations.Benchmark; -import org.openjdk.jmh.annotations.BenchmarkMode; -import org.openjdk.jmh.annotations.Fork; -import org.openjdk.jmh.annotations.Measurement; -import org.openjdk.jmh.annotations.Mode; -import org.openjdk.jmh.annotations.OutputTimeUnit; -import org.openjdk.jmh.annotations.Scope; -import org.openjdk.jmh.annotations.Setup; -import org.openjdk.jmh.annotations.State; -import org.openjdk.jmh.annotations.Threads; -import org.openjdk.jmh.annotations.Warmup; -import org.openjdk.jmh.infra.Blackhole; -import org.supercsv.io.CsvListReader; -import org.supercsv.prefs.CsvPreference; - -@BenchmarkMode(Mode.AverageTime) -@Fork(value = 1, jvmArgs = {"-server", "-Xms1024M", "-Xmx1024M"}) -@Threads(1) -@Warmup(iterations = 5) -@Measurement(iterations = 20) -@OutputTimeUnit(TimeUnit.MILLISECONDS) -@State(Scope.Benchmark) -public class CSVBenchmark { - - private String data; - - /** - * Load the data in memory before running the benchmarks, this takes out IO from the results. - */ - @Setup - public void init() throws IOException { - InputStream in = this.getClass().getClassLoader().getResourceAsStream( - "org/apache/commons/csv/perf/worldcitiespop.txt.gz"); - try (final InputStream gzin = new GZIPInputStream(in, 8192)) { - this.data = IOUtils.toString(gzin, StandardCharsets.ISO_8859_1); - } - } - - private Reader getReader() { - return new StringReader(data); - } - - @Benchmark - public int read(final Blackhole bh) throws Exception { - int count = 0; - - try (BufferedReader reader = new BufferedReader(getReader())) { - while (reader.readLine() != null) { - count++; - } - } - - bh.consume(count); - return count; - } - - @Benchmark - public int scan(final Blackhole bh) throws Exception { - int count = 0; - - try (Scanner scanner = new Scanner(getReader())) { - while (scanner.hasNextLine()) { - scanner.nextLine(); - count++; - } - } - - bh.consume(count); - return count; - } - - @Benchmark - public int split(final Blackhole bh) throws Exception { - int count = 0; - - try (BufferedReader reader = new BufferedReader(getReader())) { - String line; - while ((line = reader.readLine()) != null) { - final String[] values = StringUtils.split(line, ','); - count += values.length; - } - } - - bh.consume(count); - return count; - } - - @Benchmark - public int parseCommonsCSV(final Blackhole bh) throws Exception { - int count = 0; - - try (final Reader in = getReader()) { - final CSVFormat format = CSVFormat.Builder.create().setSkipHeaderRecord(true).build(); - Iterator iter = format.parse(in).iterator(); - while (iter.hasNext()) { - count++; - iter.next(); - } - } - - bh.consume(count); - return count; - } - - @Benchmark - public int parseGenJavaCSV(final Blackhole bh) throws Exception { - int count = 0; - - try (final Reader in = getReader()) { - final CsvReader reader = new CsvReader(in); - reader.setFieldDelimiter(','); - while (reader.readLine() != null) { - count++; - } - } - - bh.consume(count); - return count; - } - - @Benchmark - public int parseJavaCSV(final Blackhole bh) throws Exception { - int count = 0; - - try (final Reader in = getReader()) { - final com.csvreader.CsvReader reader = new com.csvreader.CsvReader(in, ','); - reader.setRecordDelimiter('\n'); - while (reader.readRecord()) { - count++; - } - } - - bh.consume(count); - return count; - } - - @Benchmark - public int parseOpenCSV(final Blackhole bh) throws Exception { - int count = 0; - - final com.opencsv.CSVParser parser = new CSVParserBuilder() - .withSeparator(',').withIgnoreQuotations(true).build(); - - try (final Reader in = getReader()) { - final com.opencsv.CSVReader reader = new CSVReaderBuilder(in).withSkipLines(1).withCSVParser(parser).build(); - while (reader.readNext() != null) { - count++; - } - } - - bh.consume(count); - return count; - } - - @Benchmark - public int parseSkifeCSV(final Blackhole bh) throws Exception { - final org.skife.csv.CSVReader reader = new org.skife.csv.SimpleReader(); - reader.setSeperator(','); - final CountingReaderCallback callback = new CountingReaderCallback(); - - try (final Reader in = getReader()) { - reader.parse(in, callback); - } - - bh.consume(callback); - return callback.count; - } - - private static class CountingReaderCallback implements org.skife.csv.ReaderCallback { - public int count; - - @Override - public void onRow(final String[] fields) { - count++; - } - } - - @Benchmark - public int parseSuperCSV(final Blackhole bh) throws Exception { - int count = 0; - - try (final CsvListReader reader = new CsvListReader(getReader(), CsvPreference.STANDARD_PREFERENCE)) { - while (reader.read() != null) { - count++; - } - } - - bh.consume(count); - return count; - } -} +///* +// * Licensed to the Apache Software Foundation (ASF) under one or more +// * contributor license agreements. See the NOTICE file distributed with +// * this work for additional information regarding copyright ownership. +// * The ASF licenses this file to You under the Apache License, Version 2.0 +// * (the "License"); you may not use this file except in compliance with +// * the License. You may obtain a copy of the License at +// * +// * http://www.apache.org/licenses/LICENSE-2.0 +// * +// * Unless required by applicable law or agreed to in writing, software +// * distributed under the License is distributed on an "AS IS" BASIS, +// * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// * See the License for the specific language governing permissions and +// * limitations under the License. +// */ +// +//package org.apache.commons.csv; +// +//import java.io.BufferedReader; +//import java.io.IOException; +//import java.io.InputStream; +//import java.io.Reader; +//import java.io.StringReader; +//import java.nio.charset.StandardCharsets; +//import java.util.Iterator; +//import java.util.Scanner; +//import java.util.concurrent.TimeUnit; +//import java.util.zip.GZIPInputStream; +// +//import com.generationjava.io.CsvReader; +//import com.opencsv.CSVParserBuilder; +//import com.opencsv.CSVReaderBuilder; +// +//import org.apache.commons.io.IOUtils; +//import org.apache.commons.lang3.StringUtils; +//import org.openjdk.jmh.annotations.Benchmark; +//import org.openjdk.jmh.annotations.BenchmarkMode; +//import org.openjdk.jmh.annotations.Fork; +//import org.openjdk.jmh.annotations.Measurement; +//import org.openjdk.jmh.annotations.Mode; +//import org.openjdk.jmh.annotations.OutputTimeUnit; +//import org.openjdk.jmh.annotations.Scope; +//import org.openjdk.jmh.annotations.Setup; +//import org.openjdk.jmh.annotations.State; +//import org.openjdk.jmh.annotations.Threads; +//import org.openjdk.jmh.annotations.Warmup; +//import org.openjdk.jmh.infra.Blackhole; +//import org.supercsv.io.CsvListReader; +//import org.supercsv.prefs.CsvPreference; +// +//@BenchmarkMode(Mode.AverageTime) +//@Fork(value = 1, jvmArgs = {"-server", "-Xms1024M", "-Xmx1024M"}) +//@Threads(1) +//@Warmup(iterations = 5) +//@Measurement(iterations = 20) +//@OutputTimeUnit(TimeUnit.MILLISECONDS) +//@State(Scope.Benchmark) +//public class CSVBenchmark { +// +// private String data; +// +// /** +// * Load the data in memory before running the benchmarks, this takes out IO from the results. +// */ +// @Setup +// public void init() throws IOException { +// InputStream in = this.getClass().getClassLoader().getResourceAsStream( +// "org/apache/commons/csv/perf/worldcitiespop.txt.gz"); +// try (final InputStream gzin = new GZIPInputStream(in, 8192)) { +// this.data = IOUtils.toString(gzin, StandardCharsets.ISO_8859_1); +// } +// } +// +// private Reader getReader() { +// return new StringReader(data); +// } +// +// @Benchmark +// public int read(final Blackhole bh) throws Exception { +// int count = 0; +// +// try (BufferedReader reader = new BufferedReader(getReader())) { +// while (reader.readLine() != null) { +// count++; +// } +// } +// +// bh.consume(count); +// return count; +// } +// +// @Benchmark +// public int scan(final Blackhole bh) throws Exception { +// int count = 0; +// +// try (Scanner scanner = new Scanner(getReader())) { +// while (scanner.hasNextLine()) { +// scanner.nextLine(); +// count++; +// } +// } +// +// bh.consume(count); +// return count; +// } +// +// @Benchmark +// public int split(final Blackhole bh) throws Exception { +// int count = 0; +// +// try (BufferedReader reader = new BufferedReader(getReader())) { +// String line; +// while ((line = reader.readLine()) != null) { +// final String[] values = StringUtils.split(line, ','); +// count += values.length; +// } +// } +// +// bh.consume(count); +// return count; +// } +// +// @Benchmark +// public int parseCommonsCSV(final Blackhole bh) throws Exception { +// int count = 0; +// +// try (final Reader in = getReader()) { +// final CSVFormat format = CSVFormat.Builder.create().setSkipHeaderRecord(true).build(); +// Iterator iter = format.parse(in).iterator(); +// while (iter.hasNext()) { +// count++; +// iter.next(); +// } +// } +// +// bh.consume(count); +// return count; +// } +// +// @Benchmark +// public int parseGenJavaCSV(final Blackhole bh) throws Exception { +// int count = 0; +// +// try (final Reader in = getReader()) { +// final CsvReader reader = new CsvReader(in); +// reader.setFieldDelimiter(','); +// while (reader.readLine() != null) { +// count++; +// } +// } +// +// bh.consume(count); +// return count; +// } +// +// @Benchmark +// public int parseJavaCSV(final Blackhole bh) throws Exception { +// int count = 0; +// +// try (final Reader in = getReader()) { +// final com.csvreader.CsvReader reader = new com.csvreader.CsvReader(in, ','); +// reader.setRecordDelimiter('\n'); +// while (reader.readRecord()) { +// count++; +// } +// } +// +// bh.consume(count); +// return count; +// } +// +// @Benchmark +// public int parseOpenCSV(final Blackhole bh) throws Exception { +// int count = 0; +// +// final com.opencsv.CSVParser parser = new CSVParserBuilder() +// .withSeparator(',').withIgnoreQuotations(true).build(); +// +// try (final Reader in = getReader()) { +// final com.opencsv.CSVReader reader = new CSVReaderBuilder(in).withSkipLines(1).withCSVParser(parser).build(); +// while (reader.readNext() != null) { +// count++; +// } +// } +// +// bh.consume(count); +// return count; +// } +// +// @Benchmark +// public int parseSkifeCSV(final Blackhole bh) throws Exception { +// final org.skife.csv.CSVReader reader = new org.skife.csv.SimpleReader(); +// reader.setSeperator(','); +// final CountingReaderCallback callback = new CountingReaderCallback(); +// +// try (final Reader in = getReader()) { +// reader.parse(in, callback); +// } +// +// bh.consume(callback); +// return callback.count; +// } +// +// private static class CountingReaderCallback implements org.skife.csv.ReaderCallback { +// public int count; +// +// @Override +// public void onRow(final String[] fields) { +// count++; +// } +// } +// +// @Benchmark +// public int parseSuperCSV(final Blackhole bh) throws Exception { +// int count = 0; +// +// try (final CsvListReader reader = new CsvListReader(getReader(), CsvPreference.STANDARD_PREFERENCE)) { +// while (reader.read() != null) { +// count++; +// } +// } +// +// bh.consume(count); +// return count; +// } +//} diff --git a/src/test/java/org/apache/commons/csv/CSVTest.java b/src/test/java/org/apache/commons/csv/CSVTest.java new file mode 100644 index 00000000..5e01c3c1 --- /dev/null +++ b/src/test/java/org/apache/commons/csv/CSVTest.java @@ -0,0 +1,79 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + + +package org.apache.commons.csv; + +import org.junit.jupiter.api.Test; + +import java.io.FileReader; +import java.io.Reader; +import java.io.StringReader; + +public class CSVTest { + + // @Test + public void readCSVFileSimpleOne() { + // happy path one + try { + // change your csv file path properly + Reader in = new FileReader("D:\\code\\apache\\csv\\samples\\basicCsvSample-1\\src\\main\\resources\\longCsvFile.csv"); + + CSVFormat csvFormat = CSVFormat.DEFAULT.builder() + .setHeader() + .setSkipHeaderRecord(true) + .build(); + + Iterable records = csvFormat.parse(in); // return a CSVParser - which is an Iterable + + for (CSVRecord record : records) { + String firstName = record.get("firstname"); + String lastName = record.get("lastname"); + String age = record.get("age"); + String email = record.get("email"); + System.out.println("FirstName: " + firstName + ", LastName: "+ lastName +", Age: " + age + ", Email: " + email); + } + } catch (Exception e) { + System.out.println("An error occurred"); + e.printStackTrace(); + } + } + + @Test + public void testFaultyCSVshouldThrowErrorWithDetailedMessage(){ + + String csvContent = "col1,col2,col3,col4,col5,col6,col7,col8,col9,col10\n" + + "rec1,rec2,rec3,rec4,rec5,rec6,rec7,rec8,\"\"rec9\"\",rec10"; + + try { + StringReader stringReader = new StringReader(csvContent); + CSVFormat csvFormat = CSVFormat.DEFAULT.builder() + .setHeader() + .setSkipHeaderRecord(true) + .build(); + + Iterable records = csvFormat.parse(stringReader); + + for (CSVRecord record : records) { + System.out.println(record.get(0) + " " + record.get(1) + " " + record.get(2) + " " + record.get(3) + " " + record.get(4) + " " + record.get(5) + " " + record.get(6) + " " + record.get(7) + " " + record.get(8) + " " + record.get(9)); + } + } catch (Exception e) { + System.out.println("An error occurred"); + e.printStackTrace(); + } + } +} From eaba3415351e279611730e258e69011ad9c989fc Mon Sep 17 00:00:00 2001 From: gbidsilva Date: Wed, 30 Aug 2023 17:08:12 +0530 Subject: [PATCH 02/16] removing unwanted files --- .../org/apache/commons/csv/CSVBenchmark.java | 454 +++++++++--------- .../java/org/apache/commons/csv/CSVTest.java | 79 --- 2 files changed, 227 insertions(+), 306 deletions(-) delete mode 100644 src/test/java/org/apache/commons/csv/CSVTest.java diff --git a/src/test/java/org/apache/commons/csv/CSVBenchmark.java b/src/test/java/org/apache/commons/csv/CSVBenchmark.java index 232142ef..64d3f498 100644 --- a/src/test/java/org/apache/commons/csv/CSVBenchmark.java +++ b/src/test/java/org/apache/commons/csv/CSVBenchmark.java @@ -1,227 +1,227 @@ -///* -// * Licensed to the Apache Software Foundation (ASF) under one or more -// * contributor license agreements. See the NOTICE file distributed with -// * this work for additional information regarding copyright ownership. -// * The ASF licenses this file to You under the Apache License, Version 2.0 -// * (the "License"); you may not use this file except in compliance with -// * the License. You may obtain a copy of the License at -// * -// * http://www.apache.org/licenses/LICENSE-2.0 -// * -// * Unless required by applicable law or agreed to in writing, software -// * distributed under the License is distributed on an "AS IS" BASIS, -// * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -// * See the License for the specific language governing permissions and -// * limitations under the License. -// */ -// -//package org.apache.commons.csv; -// -//import java.io.BufferedReader; -//import java.io.IOException; -//import java.io.InputStream; -//import java.io.Reader; -//import java.io.StringReader; -//import java.nio.charset.StandardCharsets; -//import java.util.Iterator; -//import java.util.Scanner; -//import java.util.concurrent.TimeUnit; -//import java.util.zip.GZIPInputStream; -// -//import com.generationjava.io.CsvReader; -//import com.opencsv.CSVParserBuilder; -//import com.opencsv.CSVReaderBuilder; -// -//import org.apache.commons.io.IOUtils; -//import org.apache.commons.lang3.StringUtils; -//import org.openjdk.jmh.annotations.Benchmark; -//import org.openjdk.jmh.annotations.BenchmarkMode; -//import org.openjdk.jmh.annotations.Fork; -//import org.openjdk.jmh.annotations.Measurement; -//import org.openjdk.jmh.annotations.Mode; -//import org.openjdk.jmh.annotations.OutputTimeUnit; -//import org.openjdk.jmh.annotations.Scope; -//import org.openjdk.jmh.annotations.Setup; -//import org.openjdk.jmh.annotations.State; -//import org.openjdk.jmh.annotations.Threads; -//import org.openjdk.jmh.annotations.Warmup; -//import org.openjdk.jmh.infra.Blackhole; -//import org.supercsv.io.CsvListReader; -//import org.supercsv.prefs.CsvPreference; -// -//@BenchmarkMode(Mode.AverageTime) -//@Fork(value = 1, jvmArgs = {"-server", "-Xms1024M", "-Xmx1024M"}) -//@Threads(1) -//@Warmup(iterations = 5) -//@Measurement(iterations = 20) -//@OutputTimeUnit(TimeUnit.MILLISECONDS) -//@State(Scope.Benchmark) -//public class CSVBenchmark { -// -// private String data; -// -// /** -// * Load the data in memory before running the benchmarks, this takes out IO from the results. -// */ -// @Setup -// public void init() throws IOException { -// InputStream in = this.getClass().getClassLoader().getResourceAsStream( -// "org/apache/commons/csv/perf/worldcitiespop.txt.gz"); -// try (final InputStream gzin = new GZIPInputStream(in, 8192)) { -// this.data = IOUtils.toString(gzin, StandardCharsets.ISO_8859_1); -// } -// } -// -// private Reader getReader() { -// return new StringReader(data); -// } -// -// @Benchmark -// public int read(final Blackhole bh) throws Exception { -// int count = 0; -// -// try (BufferedReader reader = new BufferedReader(getReader())) { -// while (reader.readLine() != null) { -// count++; -// } -// } -// -// bh.consume(count); -// return count; -// } -// -// @Benchmark -// public int scan(final Blackhole bh) throws Exception { -// int count = 0; -// -// try (Scanner scanner = new Scanner(getReader())) { -// while (scanner.hasNextLine()) { -// scanner.nextLine(); -// count++; -// } -// } -// -// bh.consume(count); -// return count; -// } -// -// @Benchmark -// public int split(final Blackhole bh) throws Exception { -// int count = 0; -// -// try (BufferedReader reader = new BufferedReader(getReader())) { -// String line; -// while ((line = reader.readLine()) != null) { -// final String[] values = StringUtils.split(line, ','); -// count += values.length; -// } -// } -// -// bh.consume(count); -// return count; -// } -// -// @Benchmark -// public int parseCommonsCSV(final Blackhole bh) throws Exception { -// int count = 0; -// -// try (final Reader in = getReader()) { -// final CSVFormat format = CSVFormat.Builder.create().setSkipHeaderRecord(true).build(); -// Iterator iter = format.parse(in).iterator(); -// while (iter.hasNext()) { -// count++; -// iter.next(); -// } -// } -// -// bh.consume(count); -// return count; -// } -// -// @Benchmark -// public int parseGenJavaCSV(final Blackhole bh) throws Exception { -// int count = 0; -// -// try (final Reader in = getReader()) { -// final CsvReader reader = new CsvReader(in); -// reader.setFieldDelimiter(','); -// while (reader.readLine() != null) { -// count++; -// } -// } -// -// bh.consume(count); -// return count; -// } -// -// @Benchmark -// public int parseJavaCSV(final Blackhole bh) throws Exception { -// int count = 0; -// -// try (final Reader in = getReader()) { -// final com.csvreader.CsvReader reader = new com.csvreader.CsvReader(in, ','); -// reader.setRecordDelimiter('\n'); -// while (reader.readRecord()) { -// count++; -// } -// } -// -// bh.consume(count); -// return count; -// } -// -// @Benchmark -// public int parseOpenCSV(final Blackhole bh) throws Exception { -// int count = 0; -// -// final com.opencsv.CSVParser parser = new CSVParserBuilder() -// .withSeparator(',').withIgnoreQuotations(true).build(); -// -// try (final Reader in = getReader()) { -// final com.opencsv.CSVReader reader = new CSVReaderBuilder(in).withSkipLines(1).withCSVParser(parser).build(); -// while (reader.readNext() != null) { -// count++; -// } -// } -// -// bh.consume(count); -// return count; -// } -// -// @Benchmark -// public int parseSkifeCSV(final Blackhole bh) throws Exception { -// final org.skife.csv.CSVReader reader = new org.skife.csv.SimpleReader(); -// reader.setSeperator(','); -// final CountingReaderCallback callback = new CountingReaderCallback(); -// -// try (final Reader in = getReader()) { -// reader.parse(in, callback); -// } -// -// bh.consume(callback); -// return callback.count; -// } -// -// private static class CountingReaderCallback implements org.skife.csv.ReaderCallback { -// public int count; -// -// @Override -// public void onRow(final String[] fields) { -// count++; -// } -// } -// -// @Benchmark -// public int parseSuperCSV(final Blackhole bh) throws Exception { -// int count = 0; -// -// try (final CsvListReader reader = new CsvListReader(getReader(), CsvPreference.STANDARD_PREFERENCE)) { -// while (reader.read() != null) { -// count++; -// } -// } -// -// bh.consume(count); -// return count; -// } -//} +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.commons.csv; + +import java.io.BufferedReader; +import java.io.IOException; +import java.io.InputStream; +import java.io.Reader; +import java.io.StringReader; +import java.nio.charset.StandardCharsets; +import java.util.Iterator; +import java.util.Scanner; +import java.util.concurrent.TimeUnit; +import java.util.zip.GZIPInputStream; + +import com.generationjava.io.CsvReader; +import com.opencsv.CSVParserBuilder; +import com.opencsv.CSVReaderBuilder; + +import org.apache.commons.io.IOUtils; +import org.apache.commons.lang3.StringUtils; +import org.openjdk.jmh.annotations.Benchmark; +import org.openjdk.jmh.annotations.BenchmarkMode; +import org.openjdk.jmh.annotations.Fork; +import org.openjdk.jmh.annotations.Measurement; +import org.openjdk.jmh.annotations.Mode; +import org.openjdk.jmh.annotations.OutputTimeUnit; +import org.openjdk.jmh.annotations.Scope; +import org.openjdk.jmh.annotations.Setup; +import org.openjdk.jmh.annotations.State; +import org.openjdk.jmh.annotations.Threads; +import org.openjdk.jmh.annotations.Warmup; +import org.openjdk.jmh.infra.Blackhole; +import org.supercsv.io.CsvListReader; +import org.supercsv.prefs.CsvPreference; + +@BenchmarkMode(Mode.AverageTime) +@Fork(value = 1, jvmArgs = {"-server", "-Xms1024M", "-Xmx1024M"}) +@Threads(1) +@Warmup(iterations = 5) +@Measurement(iterations = 20) +@OutputTimeUnit(TimeUnit.MILLISECONDS) +@State(Scope.Benchmark) +public class CSVBenchmark { + + private String data; + + /** + * Load the data in memory before running the benchmarks, this takes out IO from the results. + */ + @Setup + public void init() throws IOException { + InputStream in = this.getClass().getClassLoader().getResourceAsStream( + "org/apache/commons/csv/perf/worldcitiespop.txt.gz"); + try (final InputStream gzin = new GZIPInputStream(in, 8192)) { + this.data = IOUtils.toString(gzin, StandardCharsets.ISO_8859_1); + } + } + + private Reader getReader() { + return new StringReader(data); + } + + @Benchmark + public int read(final Blackhole bh) throws Exception { + int count = 0; + + try (BufferedReader reader = new BufferedReader(getReader())) { + while (reader.readLine() != null) { + count++; + } + } + + bh.consume(count); + return count; + } + + @Benchmark + public int scan(final Blackhole bh) throws Exception { + int count = 0; + + try (Scanner scanner = new Scanner(getReader())) { + while (scanner.hasNextLine()) { + scanner.nextLine(); + count++; + } + } + + bh.consume(count); + return count; + } + + @Benchmark + public int split(final Blackhole bh) throws Exception { + int count = 0; + + try (BufferedReader reader = new BufferedReader(getReader())) { + String line; + while ((line = reader.readLine()) != null) { + final String[] values = StringUtils.split(line, ','); + count += values.length; + } + } + + bh.consume(count); + return count; + } + + @Benchmark + public int parseCommonsCSV(final Blackhole bh) throws Exception { + int count = 0; + + try (final Reader in = getReader()) { + final CSVFormat format = CSVFormat.Builder.create().setSkipHeaderRecord(true).build(); + Iterator iter = format.parse(in).iterator(); + while (iter.hasNext()) { + count++; + iter.next(); + } + } + + bh.consume(count); + return count; + } + + @Benchmark + public int parseGenJavaCSV(final Blackhole bh) throws Exception { + int count = 0; + + try (final Reader in = getReader()) { + final CsvReader reader = new CsvReader(in); + reader.setFieldDelimiter(','); + while (reader.readLine() != null) { + count++; + } + } + + bh.consume(count); + return count; + } + + @Benchmark + public int parseJavaCSV(final Blackhole bh) throws Exception { + int count = 0; + + try (final Reader in = getReader()) { + final com.csvreader.CsvReader reader = new com.csvreader.CsvReader(in, ','); + reader.setRecordDelimiter('\n'); + while (reader.readRecord()) { + count++; + } + } + + bh.consume(count); + return count; + } + + @Benchmark + public int parseOpenCSV(final Blackhole bh) throws Exception { + int count = 0; + + final com.opencsv.CSVParser parser = new CSVParserBuilder() + .withSeparator(',').withIgnoreQuotations(true).build(); + + try (final Reader in = getReader()) { + final com.opencsv.CSVReader reader = new CSVReaderBuilder(in).withSkipLines(1).withCSVParser(parser).build(); + while (reader.readNext() != null) { + count++; + } + } + + bh.consume(count); + return count; + } + + @Benchmark + public int parseSkifeCSV(final Blackhole bh) throws Exception { + final org.skife.csv.CSVReader reader = new org.skife.csv.SimpleReader(); + reader.setSeperator(','); + final CountingReaderCallback callback = new CountingReaderCallback(); + + try (final Reader in = getReader()) { + reader.parse(in, callback); + } + + bh.consume(callback); + return callback.count; + } + + private static class CountingReaderCallback implements org.skife.csv.ReaderCallback { + public int count; + + @Override + public void onRow(final String[] fields) { + count++; + } + } + + @Benchmark + public int parseSuperCSV(final Blackhole bh) throws Exception { + int count = 0; + + try (final CsvListReader reader = new CsvListReader(getReader(), CsvPreference.STANDARD_PREFERENCE)) { + while (reader.read() != null) { + count++; + } + } + + bh.consume(count); + return count; + } +} diff --git a/src/test/java/org/apache/commons/csv/CSVTest.java b/src/test/java/org/apache/commons/csv/CSVTest.java deleted file mode 100644 index 5e01c3c1..00000000 --- a/src/test/java/org/apache/commons/csv/CSVTest.java +++ /dev/null @@ -1,79 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - - -package org.apache.commons.csv; - -import org.junit.jupiter.api.Test; - -import java.io.FileReader; -import java.io.Reader; -import java.io.StringReader; - -public class CSVTest { - - // @Test - public void readCSVFileSimpleOne() { - // happy path one - try { - // change your csv file path properly - Reader in = new FileReader("D:\\code\\apache\\csv\\samples\\basicCsvSample-1\\src\\main\\resources\\longCsvFile.csv"); - - CSVFormat csvFormat = CSVFormat.DEFAULT.builder() - .setHeader() - .setSkipHeaderRecord(true) - .build(); - - Iterable records = csvFormat.parse(in); // return a CSVParser - which is an Iterable - - for (CSVRecord record : records) { - String firstName = record.get("firstname"); - String lastName = record.get("lastname"); - String age = record.get("age"); - String email = record.get("email"); - System.out.println("FirstName: " + firstName + ", LastName: "+ lastName +", Age: " + age + ", Email: " + email); - } - } catch (Exception e) { - System.out.println("An error occurred"); - e.printStackTrace(); - } - } - - @Test - public void testFaultyCSVshouldThrowErrorWithDetailedMessage(){ - - String csvContent = "col1,col2,col3,col4,col5,col6,col7,col8,col9,col10\n" + - "rec1,rec2,rec3,rec4,rec5,rec6,rec7,rec8,\"\"rec9\"\",rec10"; - - try { - StringReader stringReader = new StringReader(csvContent); - CSVFormat csvFormat = CSVFormat.DEFAULT.builder() - .setHeader() - .setSkipHeaderRecord(true) - .build(); - - Iterable records = csvFormat.parse(stringReader); - - for (CSVRecord record : records) { - System.out.println(record.get(0) + " " + record.get(1) + " " + record.get(2) + " " + record.get(3) + " " + record.get(4) + " " + record.get(5) + " " + record.get(6) + " " + record.get(7) + " " + record.get(8) + " " + record.get(9)); - } - } catch (Exception e) { - System.out.println("An error occurred"); - e.printStackTrace(); - } - } -} From dbc418b9e79369d4a4b440340322b45192d10aed Mon Sep 17 00:00:00 2001 From: Gary Gregory Date: Wed, 30 Aug 2023 08:36:48 -0400 Subject: [PATCH 03/16] Update CSVParser.java --- src/main/java/org/apache/commons/csv/CSVParser.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/main/java/org/apache/commons/csv/CSVParser.java b/src/main/java/org/apache/commons/csv/CSVParser.java index 7d292c6a..8679367c 100644 --- a/src/main/java/org/apache/commons/csv/CSVParser.java +++ b/src/main/java/org/apache/commons/csv/CSVParser.java @@ -147,7 +147,7 @@ public final class CSVParser implements Iterable, Closeable { try { return CSVParser.this.nextRecord(); } catch (final IOException e) { - throw new UncheckedIOException("Error in reading next record: " + e.toString(), e); + throw new UncheckedIOException("Exception reading next record: " + e.toString(), e); } } From 1492c7465fb911b11afbc4a0da9de2d27764e72b Mon Sep 17 00:00:00 2001 From: Gary Gregory Date: Wed, 30 Aug 2023 08:42:23 -0400 Subject: [PATCH 04/16] Update exception message in CSVRecord#getNextRecord() #348 --- src/changes/changes.xml | 1 + 1 file changed, 1 insertion(+) diff --git a/src/changes/changes.xml b/src/changes/changes.xml index 1a5552d4..b65bce7c 100644 --- a/src/changes/changes.xml +++ b/src/changes/changes.xml @@ -53,6 +53,7 @@ Bump commons-parent from 57 to 60. Bump h2 from 2.1.214 to 2.2.220 #333. Bump commons-lang3 from 3.12.0 to 3.13.0. + Update exception message in CSVRecord#getNextRecord() #348. From 00738efb0df1b6ac3118e606a199bd0ec0d0089f Mon Sep 17 00:00:00 2001 From: Gary Gregory Date: Wed, 30 Aug 2023 08:44:39 -0400 Subject: [PATCH 05/16] Javadoc --- .../org/apache/commons/csv/CSVParser.java | 24 +++++++++---------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/src/main/java/org/apache/commons/csv/CSVParser.java b/src/main/java/org/apache/commons/csv/CSVParser.java index 8679367c..4ce3774b 100644 --- a/src/main/java/org/apache/commons/csv/CSVParser.java +++ b/src/main/java/org/apache/commons/csv/CSVParser.java @@ -53,7 +53,7 @@ import java.util.stream.StreamSupport; * Because CSV appears in many different dialects, the parser supports many formats by allowing the * specification of a {@link CSVFormat}. * - * The parser works record wise. It is not possible to go back, once a record has been parsed from the input stream. + * The parser works record-wise. It is not possible to go back, once a record has been parsed from the input stream. * *

Creating instances

*

@@ -105,13 +105,13 @@ import java.util.stream.StreamSupport; * * *

- * If the predefined formats don't match the format at hands, custom formats can be defined. More information about - * customising CSVFormats is available in {@link CSVFormat CSVFormat Javadoc}. + * If the predefined formats don't match the format at hand, custom formats can be defined. More information about + * customizing CSVFormats is available in {@link CSVFormat CSVFormat Javadoc}. *

* *

Parsing into memory

*

- * If parsing record wise is not desired, the contents of the input can be read completely into memory. + * If parsing record-wise is not desired, the contents of the input can be read completely into memory. *

* * 
@@ -126,14 +126,14 @@ import java.util.stream.StreamSupport;
  *
  * 
    
  *     
  1. Parsing into memory starts at the current position of the parser. If you have already parsed records from
- *     the input, those records will not end up in the in memory representation of your CSV data.
    2. 
- *     
  2. Parsing into memory may consume a lot of system resources depending on the input. For example if you're
+ *     the input, those records will not end up in the in-memory representation of your CSV data.
    3. 
+ *     
  3. Parsing into memory may consume a lot of system resources depending on the input. For example, if you're
  *     parsing a 150MB file of CSV data the contents will be read completely into memory.
    4. 
  * 

  *
  * 
Notes

  * 

- * Internal parser state is completely covered by the format and the reader-state.
+ * The internal parser state is completely covered by the format and the reader state.
  * 

  *
  * @see package documentation for more details
@@ -304,8 +304,6 @@ public final class CSVParser implements Iterable, Closeable {
         return new CSVParser(reader, format);
     }
 
-    // the following objects are shared to reduce garbage
-
     /**
      * Creates a parser for the given {@link String}.
      *
@@ -421,7 +419,7 @@ public final class CSVParser implements Iterable, Closeable {
      * @param recordNumber
      *            The next record number to assign
      * @throws IllegalArgumentException
-     *             If the parameters of the format are inconsistent or if either reader or format are null.
+     *             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
      * @since 1.1
@@ -662,11 +660,11 @@ public final class CSVParser implements Iterable, Closeable {
     }
 
     /**
-     * Handle whether input is parsed as null
+     * Handles whether the input is parsed as null
      *
      * @param input
      *           the cell data to further processed
-     * @return null if input is parsed as null, or input itself if input isn't parsed as null
+     * @return null if input is parsed as null, or input itself if the input isn't parsed as null
      */
     private String handleNull(final String input) {
         final boolean isQuoted = this.reusableToken.isQuoted;
@@ -733,7 +731,7 @@ public final class CSVParser implements Iterable, Closeable {
      * Returns the record iterator.
      *
      * 

-     * An {@link IOException} caught during the iteration are re-thrown as an
+     * An {@link IOException} caught during the iteration is re-thrown as an
      * {@link IllegalStateException}.
      * 

      * 


From 83760258af3279f7efd9deca788c9b3625cc5d1b Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 08:54:59 -0400
Subject: [PATCH 06/16] Javadoc

---
 .../org/apache/commons/csv/CSVFormat.java     | 60 +++++++++----------
 1 file changed, 30 insertions(+), 30 deletions(-)

diff --git a/src/main/java/org/apache/commons/csv/CSVFormat.java b/src/main/java/org/apache/commons/csv/CSVFormat.java
index b3ac7ace..77d557ba 100644
--- a/src/main/java/org/apache/commons/csv/CSVFormat.java
+++ b/src/main/java/org/apache/commons/csv/CSVFormat.java
@@ -477,7 +477,7 @@ public final class CSVFormat implements Serializable {
          * The header is also used by the {@link CSVPrinter}.
          * 

          *
-         * @param headerEnum the enum defining the header, {@code null} if disabled, empty if parsed automatically, user specified otherwise.
+         * @param headerEnum the enum defining the header, {@code null} if disabled, empty if parsed automatically, user-specified otherwise.
          * @return This instance.
          */
         public Builder setHeader(final Class> headerEnum) {
@@ -491,7 +491,7 @@ public final class CSVFormat implements Serializable {
         }
 
         /**
-         * Sets the header from the result set metadata. The header can either be parsed automatically from the input file with:
+         * Sets the header from the result set metadata. The header can be parsed automatically from the input file with:
          *
          * 
          * builder.setHeader();
@@ -506,7 +506,7 @@ public final class CSVFormat implements Serializable {
          * The header is also used by the {@link CSVPrinter}.
          * 

          *
-         * @param resultSet the resultSet for the header, {@code null} if disabled, empty if parsed automatically, user specified otherwise.
+         * @param resultSet the resultSet for the header, {@code null} if disabled, empty if parsed automatically, user-specified otherwise.
          * @return This instance.
          * @throws SQLException SQLException if a database access error occurs or this method is called on a closed result set.
          */
@@ -515,7 +515,7 @@ public final class CSVFormat implements Serializable {
         }
 
         /**
-         * Sets the header from the result set metadata. The header can either be parsed automatically from the input file with:
+         * Sets the header from the result set metadata. The header can be parsed automatically from the input file with:
          *
          * 
          * builder.setHeader();
@@ -530,7 +530,7 @@ public final class CSVFormat implements Serializable {
          * The header is also used by the {@link CSVPrinter}.
          * 

          *
-         * @param resultSetMetaData the metaData for the header, {@code null} if disabled, empty if parsed automatically, user specified otherwise.
+         * @param resultSetMetaData the metaData for the header, {@code null} if disabled, empty if parsed automatically, user-specified otherwise.
          * @return This instance.
          * @throws SQLException SQLException if a database access error occurs or this method is called on a closed result set.
          */
@@ -547,7 +547,7 @@ public final class CSVFormat implements Serializable {
         }
 
         /**
-         * Sets the header to the given values. The header can either be parsed automatically from the input file with:
+         * Sets the header to the given values. The header can be parsed automatically from the input file with:
          *
          * 
          * builder.setHeader();
@@ -562,7 +562,7 @@ public final class CSVFormat implements Serializable {
          * The header is also used by the {@link CSVPrinter}.
          * 

          *
-         * @param header the header, {@code null} if disabled, empty if parsed automatically, user specified otherwise.
+         * @param header the header, {@code null} if disabled, empty if parsed automatically, user-specified otherwise.
          * @return This instance.
          */
         public Builder setHeader(final String... header) {
@@ -909,8 +909,8 @@ public final class CSVFormat implements Serializable {
             false, false, false, DuplicateHeaderMode.ALLOW_ALL);
 
     /**
-     * Excel file format (using a comma as the value delimiter). Note that the actual value delimiter used by Excel is locale dependent, it might be necessary
-     * to customize this format to accommodate to your regional settings.
+     * Excel file format (using a comma as the value delimiter). Note that the actual value delimiter used by Excel is locale-dependent, it might be necessary
+     * to customize this format to accommodate your regional settings.
      *
      * 

      * For example for parsing or generating a CSV file on a French system the following format will be used:
@@ -949,7 +949,7 @@ public final class CSVFormat implements Serializable {
      * Default Informix CSV UNLOAD format used by the {@code UNLOAD TO file_name} operation.
      *
      * 

-     * This is a comma-delimited format with a LF character as the line separator. Values are not quoted and special characters are escaped with {@code '\'}.
+     * This is a comma-delimited format with an LF character as the line separator. Values are not quoted and special characters are escaped with {@code '\'}.
      * The default NULL string is {@code "\\N"}.
      * 

      *
@@ -981,7 +981,7 @@ public final class CSVFormat implements Serializable {
      * Default Informix CSV UNLOAD format used by the {@code UNLOAD TO file_name} operation (escaping is disabled.)
      *
      * 

-     * This is a comma-delimited format with a LF character as the line separator. Values are not quoted and special characters are escaped with {@code '\'}.
+     * This is a comma-delimited format with an LF character as the line separator. Values are not quoted and special characters are escaped with {@code '\'}.
      * The default NULL string is {@code "\\N"}.
      * 

      *
@@ -1084,7 +1084,7 @@ public final class CSVFormat implements Serializable {
      * Default MySQL format used by the {@code SELECT INTO OUTFILE} and {@code LOAD DATA INFILE} operations.
      *
      * 

-     * This is a tab-delimited format with a LF character as the line separator. Values are not quoted and special
+     * This is a tab-delimited format with an LF character as the line separator. Values are not quoted and special
      * characters are escaped with {@code '\'}. The default NULL string is {@code "\\N"}.
      * 

      *
@@ -1121,7 +1121,7 @@ public final class CSVFormat implements Serializable {
      * Default Oracle format used by the SQL*Loader utility.
      *
      * 

-     * This is a comma-delimited format with the system line separator character as the record separator.Values are
+     * This is a comma-delimited format with the system line separator character as the record separator. Values are
      * double quoted when needed and special characters are escaped with {@code '"'}. The default NULL string is
      * {@code ""}. Values are trimmed.
      * 

@@ -1161,7 +1161,7 @@ public final class CSVFormat implements Serializable {
      * Default PostgreSQL CSV format used by the {@code COPY} operation.
      *
      * 

-     * This is a comma-delimited format with a LF character as the line separator. Values are double quoted and special
+     * This is a comma-delimited format with an LF character as the line separator. Values are double quoted and special
      * characters are not escaped. The default NULL string is {@code ""}.
      * 

      *
@@ -1199,7 +1199,7 @@ public final class CSVFormat implements Serializable {
      * Default PostgreSQL text format used by the {@code COPY} operation.
      *
      * 

-     * This is a tab-delimited format with a LF character as the line separator. Values are not quoted and special
+     * This is a tab-delimited format with an LF character as the line separator. Values are not quoted and special
      * characters are escaped with {@code '\\'}. The default NULL string is {@code "\\N"}.
      * 

      *
@@ -1890,7 +1890,7 @@ public final class CSVFormat implements Serializable {
     }
 
     /**
-     * Tests whether escape are being processed.
+     * Tests whether escapes are being processed.
      *
      * @return {@code true} if escapes are processed
      */
@@ -1899,7 +1899,7 @@ public final class CSVFormat implements Serializable {
     }
 
     /**
-     * Tests whether a nullString has been defined.
+     * Tests whether a null string has been defined.
      *
      * @return {@code true} if a nullString is defined
      */
@@ -2009,7 +2009,7 @@ public final class CSVFormat implements Serializable {
         if (object == null) {
             out.append(value);
         } else if (isQuoteCharacterSet()) {
-            // the original object is needed so can check for Number
+            // The original object is needed so can check for Number
             printWithQuotes(object, value, out, newRecord);
         } else if (isEscapeCharacterSet()) {
             printWithEscapes(value, out);
@@ -2086,7 +2086,7 @@ public final class CSVFormat implements Serializable {
     }
 
     /**
-     * Prints the given {@code values} to {@code out} as a single record of delimiter separated values followed by the record separator.
+     * Prints the given {@code values} to {@code out} as a single record of delimiter-separated values followed by the record separator.
      *
      * 

      * The values will be quoted if needed. Quotes and new-line characters will be escaped. This method adds the record separator to the output after printing
@@ -2241,7 +2241,7 @@ public final class CSVFormat implements Serializable {
             return;
         case MINIMAL:
             if (len <= 0) {
-                // always quote an empty token that is the first
+                // Always quote an empty token that is the first
                 // on the line, as it may be the only thing on the
                 // line. If it were not quoted in that case,
                 // an empty line has no tokens.
@@ -2279,7 +2279,7 @@ public final class CSVFormat implements Serializable {
             }
 
             if (!quote) {
-                // no encapsulation needed - write out the original value
+                // No encapsulation needed - write out the original value
                 out.append(charSeq, start, len);
                 return;
             }
@@ -2289,12 +2289,12 @@ public final class CSVFormat implements Serializable {
         }
 
         if (!quote) {
-            // no encapsulation needed - write out the original value
+            // No encapsulation needed - write out the original value
             out.append(charSeq, start, len);
             return;
         }
 
-        // we hit something that needed encapsulation
+        // We hit something that needed encapsulation
         out.append(quoteChar);
 
         // Pick up where we left off: pos should be positioned on the first character that caused
@@ -2310,13 +2310,13 @@ public final class CSVFormat implements Serializable {
             pos++;
         }
 
-        // write the last segment
+        // Write the last segment
         out.append(charSeq, start, pos);
         out.append(quoteChar);
     }
 
     /**
-     * Always use quotes unless QuoteMode is NONE, so we not have to look ahead.
+     * Always use quotes unless QuoteMode is NONE, so we do not have to look ahead.
      *
      * @param reader What to print
      * @param appendable Where to print it
@@ -2417,7 +2417,7 @@ public final class CSVFormat implements Serializable {
     /**
      * Verifies the validity and consistency of the attributes, and throws an {@link IllegalArgumentException} if necessary.
      * 

-     * Because an instance can be used for both writing an parsing, not all conditions can be tested here. For example allowMissingColumnNames is only used for
+     * Because an instance can be used for both writing and parsing, not all conditions can be tested here. For example, allowMissingColumnNames is only used for
      * parsing, so it cannot be used here.
      * 

      *
@@ -2570,7 +2570,7 @@ public final class CSVFormat implements Serializable {
      * Builds a new {@code CSVFormat} with the delimiter of the format set to the specified character.
      *
      * @param delimiter the delimiter character
-     * @return A new CSVFormat that is equal to this with the specified character as delimiter
+     * @return A new CSVFormat that is equal to this with the specified character as a delimiter
      * @throws IllegalArgumentException thrown if the specified character is a line break
      * @deprecated Use {@link Builder#setDelimiter(char)}
      */
@@ -2679,7 +2679,7 @@ public final class CSVFormat implements Serializable {
      * The header is also used by the {@link CSVPrinter}.
      * 

      *
-     * @param resultSet the resultSet for the header, {@code null} if disabled, empty if parsed automatically, user specified otherwise.
+     * @param resultSet the resultSet for the header, {@code null} if disabled, empty if parsed automatically, user-specified otherwise.
      * @return A new CSVFormat that is equal to this but with the specified header
      * @throws SQLException SQLException if a database access error occurs or this method is called on a closed result set.
      * @since 1.1
@@ -2735,7 +2735,7 @@ public final class CSVFormat implements Serializable {
      * The header is also used by the {@link CSVPrinter}.
      * 

      *
-     * @param header the header, {@code null} if disabled, empty if parsed automatically, user specified otherwise.
+     * @param header the header, {@code null} if disabled, empty if parsed automatically, user-specified otherwise.
      * @return A new CSVFormat that is equal to this but with the specified header
      * @see Builder#setSkipHeaderRecord(boolean)
      * @deprecated Use {@link Builder#setHeader(String...)}
@@ -2793,7 +2793,7 @@ public final class CSVFormat implements Serializable {
     /**
      * Builds a new {@code CSVFormat} with the header ignore case behavior set to {@code true}.
      *
-     * @return A new CSVFormat that will ignore case header name.
+     * @return A new CSVFormat that will ignore the new case header name behavior.
      * @see Builder#setIgnoreHeaderCase(boolean)
      * @since 1.3
      * @deprecated Use {@link Builder#setIgnoreHeaderCase(boolean) Builder#setIgnoreHeaderCase(true)}

From 2ce1fbb0c82a4c4bd62e6078d7766b770ac8e286 Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 08:57:11 -0400
Subject: [PATCH 07/16] Javadoc

---
 .../org/apache/commons/csv/CSVPrinter.java    | 20 +++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/src/main/java/org/apache/commons/csv/CSVPrinter.java b/src/main/java/org/apache/commons/csv/CSVPrinter.java
index dba6de9e..421de13e 100644
--- a/src/main/java/org/apache/commons/csv/CSVPrinter.java
+++ b/src/main/java/org/apache/commons/csv/CSVPrinter.java
@@ -171,7 +171,7 @@ public final class CSVPrinter implements Flushable, Closeable {
     }
 
     /**
-     * Prints a comment on a new line among the delimiter separated values.
+     * Prints a comment on a new line among the delimiter-separated values.
      *
      * 

      * Comments will always begin on a new line and occupy at least one full line. The character specified to start
@@ -184,7 +184,7 @@ public final class CSVPrinter implements Flushable, Closeable {
      *
      * 
This method detects line breaks inside the comment string and inserts {@link CSVFormat#getRecordSeparator()}
      * to start a new line of the comment. Note that this might produce unexpected results for formats that do not use
-     * line breaks as record separator.

+     * line breaks as record separators.

      *
      * @param comment
      *            the comment to output
@@ -224,7 +224,7 @@ public final class CSVPrinter implements Flushable, Closeable {
     /**
      * Prints headers for a result set based on its metadata.
      *
-     * @param resultSet The result set to query for metadata.
+     * @param resultSet The ResultSet to query for metadata.
      * @throws IOException If an I/O error occurs.
      * @throws SQLException If a database access error occurs or this method is called on a closed result set.
      * @since 1.9.0
@@ -245,7 +245,7 @@ public final class CSVPrinter implements Flushable, Closeable {
     }
 
     /**
-     * Prints the given values as a single record of delimiter separated values followed by the record separator.
+     * Prints the given values as a single record of delimiter-separated values followed by the record separator.
      *
      * 

      * The values will be quoted if needed. Quotes and newLine characters will be escaped. This method adds the record
@@ -265,7 +265,7 @@ public final class CSVPrinter implements Flushable, Closeable {
     }
 
     /**
-     * Prints the given values as a single record of delimiter separated values followed by the record separator.
+     * Prints the given values as a single record of delimiter-separated values followed by the record separator.
      *
      * 

      * The values will be quoted if needed. Quotes and newLine characters will be escaped. This method adds the record
@@ -282,7 +282,7 @@ public final class CSVPrinter implements Flushable, Closeable {
     }
 
     /**
-     * Prints the given values as a single record of delimiter separated values followed by the record separator.
+     * Prints the given values as a single record of delimiter-separated values followed by the record separator.
      *
      * 

      * The values will be quoted if needed. Quotes and newLine characters will be escaped. This method adds the record
@@ -366,7 +366,7 @@ public final class CSVPrinter implements Flushable, Closeable {
      *
      * 

      * If the given array only contains simple objects, this method will print a single record like
-     * {@link #printRecord(Object...)}. If the given collections contains nested collections/arrays those nested
+     * {@link #printRecord(Object...)}. If the given collections contain nested collections or arrays, those nested
      * elements will each be printed as records using {@link #printRecord(Object...)}.
      * 

      *
@@ -408,11 +408,11 @@ public final class CSVPrinter implements Flushable, Closeable {
      * Prints all the objects in the given JDBC result set.
      *
      * @param resultSet
-     *            result set the values to print.
+     *             The values to print.
      * @throws IOException
-     *             If an I/O error occurs
+     *             If an I/O error occurs.
      * @throws SQLException
-     *             if a database access error occurs
+     *             Thrown when a database access error occurs.
      */
     public void printRecords(final ResultSet resultSet) throws SQLException, IOException {
         final int columnCount = resultSet.getMetaData().getColumnCount();

From d103cba8b5d8e996698997c70072eaf65591e718 Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 08:59:04 -0400
Subject: [PATCH 08/16] Javadoc

---
 .../org/apache/commons/csv/CSVRecord.java     | 26 +++++++++----------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/src/main/java/org/apache/commons/csv/CSVRecord.java b/src/main/java/org/apache/commons/csv/CSVRecord.java
index 71d5f953..189cc07e 100644
--- a/src/main/java/org/apache/commons/csv/CSVRecord.java
+++ b/src/main/java/org/apache/commons/csv/CSVRecord.java
@@ -32,10 +32,10 @@ import java.util.stream.Stream;
  * 

  * Note: Support for {@link Serializable} is scheduled to be removed in version 2.0.
  * In version 1.8 the mapping between the column header and the column index was
- * removed from the serialised state. The class maintains serialization compatibility
+ * removed from the serialized state. The class maintains serialization compatibility
  * with versions pre-1.8 for the record values; these must be accessed by index
- * following deserialization. There will be loss of any functionally linked to the header
- * mapping when transferring serialised forms pre-1.8 to 1.8 and vice versa.
+ * following deserialization. There will be a loss of any functionally linked to the header
+ * mapping when transferring serialized forms pre-1.8 to 1.8 and vice versa.
  * 

  */
 public final class CSVRecord implements Serializable, Iterable {
@@ -143,8 +143,8 @@ public final class CSVRecord implements Serializable, Iterable {
     /**
      * Returns the comment for this record, if any.
      * Note that comments are attached to the following record.
-     * If there is no following record (i.e. the comment is at EOF)
-     * the comment will be ignored.
+     * If there is no following record (i.e. the comment is at EOF),
+     * then the comment will be ignored.
      *
      * @return the comment for this record, or null if no comment for this record is available.
      */
@@ -189,8 +189,8 @@ public final class CSVRecord implements Serializable, Iterable {
     /**
      * Checks whether this record has a comment, false otherwise.
      * Note that comments are attached to the following record.
-     * If there is no following record (i.e. the comment is at EOF)
-     * the comment will be ignored.
+     * If there is no following record (i.e. the comment is at EOF),
+     * then the comment will be ignored.
      *
      * @return true if this record has a comment, false otherwise
      * @since 1.3
@@ -227,22 +227,22 @@ public final class CSVRecord implements Serializable, Iterable {
     }
 
     /**
-     * Checks whether a column with given index has a value.
+     * Checks whether a column with a given index has a value.
      *
      * @param index
      *         a column index (0-based)
-     * @return whether a column with given index has a value
+     * @return whether a column with a given index has a value
      */
     public boolean isSet(final int index) {
         return 0 <= index && index < values.length;
     }
 
     /**
-     * Checks whether a given columns is mapped and has a value.
+     * Checks whether a given column is mapped and has a value.
      *
      * @param name
      *            the name of the column to be retrieved.
-     * @return whether a given columns is mapped and has a value
+     * @return whether a given column is mapped and has a value
      */
     public boolean isSet(final String name) {
         return isMapped(name) && getHeaderMapRaw().get(name).intValue() < values.length;
@@ -311,8 +311,8 @@ public final class CSVRecord implements Serializable, Iterable {
     }
 
     /**
-     * Copies this record into a new Map of header name to record value. If multiple instances of a header name exists,
-     * only the last occurrence is mapped.
+     * Copies this record into a new Map of header name to record value. If multiple instances of a header name exist,
+     * then only the last occurrence is mapped.
      *
      * 

      * Editing the map does not update this instance.

From 346e217559379872d0b439c221f851e06d8d8ce7 Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 09:00:53 -0400
Subject: [PATCH 09/16] Javadoc

---
 .../org/apache/commons/csv/ExtendedBufferedReader.java | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java b/src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
index 89e63e3a..429b07cb 100644
--- a/src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
+++ b/src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
@@ -41,13 +41,13 @@ final class ExtendedBufferedReader extends BufferedReader {
     /** The count of EOLs (CR/LF/CRLF) seen so far */
     private long eolCounter;
 
-    /** The position, which is number of characters read so far */
+    /** The position, which is the number of characters read so far */
     private long position;
 
     private boolean closed;
 
     /**
-     * Created extended buffered reader using default buffer-size
+     * Constructs a new instance using the default buffer size.
      */
     ExtendedBufferedReader(final Reader reader) {
         super(reader);
@@ -107,7 +107,7 @@ final class ExtendedBufferedReader extends BufferedReader {
 
     /**
      * Returns the next character in the current reader without consuming it. So the next call to {@link #read()} will
-     * still return this value. Does not affect line number or last character.
+     * still return this value. Does not affect the line number or the last character.
      *
      * @return the next character
      *
@@ -125,7 +125,7 @@ final class ExtendedBufferedReader extends BufferedReader {
     /**
      * Populates the buffer with the next {@code buf.length} characters in the
      * current reader without consuming them. The next call to {@link #read()} will
-     * still return the next value. This doesn't affect line number or last
+     * still return the next value. This doesn't affect the line number or the last
      * character.
      *
      * @param buf the buffer to fill for the look ahead.
@@ -199,7 +199,7 @@ final class ExtendedBufferedReader extends BufferedReader {
 
     /**
      * Gets the next line, dropping the line terminator(s). This method should only be called when processing a
-     * comment, otherwise information can be lost.
+     * comment, otherwise, information can be lost.
      * 

      * Increments {@link #eolCounter} and updates {@link #position}.
      * 


From aa7fd80838fd43c0800b2d1d14b4a20fd5fa1f8f Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 09:02:22 -0400
Subject: [PATCH 10/16] Javadoc

---
 src/main/java/org/apache/commons/csv/CSVFormat.java | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/main/java/org/apache/commons/csv/CSVFormat.java b/src/main/java/org/apache/commons/csv/CSVFormat.java
index 77d557ba..2f7e6b9f 100644
--- a/src/main/java/org/apache/commons/csv/CSVFormat.java
+++ b/src/main/java/org/apache/commons/csv/CSVFormat.java
@@ -2417,8 +2417,8 @@ public final class CSVFormat implements Serializable {
     /**
      * Verifies the validity and consistency of the attributes, and throws an {@link IllegalArgumentException} if necessary.
      * 

-     * Because an instance can be used for both writing and parsing, not all conditions can be tested here. For example, allowMissingColumnNames is only used for
-     * parsing, so it cannot be used here.
+     * Because an instance can be used for both writing and parsing, not all conditions can be tested here. For example, allowMissingColumnNames is only used
+     * for parsing, so it cannot be used here.
      * 

      *
      * @throws IllegalArgumentException Throw when any attribute is invalid or inconsistent with other attributes.

From ecb056fd77ee7424bcc9dadc76070c1843d8be53 Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 09:07:23 -0400
Subject: [PATCH 11/16] Javadoc

---
 .../java/org/apache/commons/csv/Lexer.java    | 43 ++++++++++---------
 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/src/main/java/org/apache/commons/csv/Lexer.java b/src/main/java/org/apache/commons/csv/Lexer.java
index 06b2c9c2..ea29ff68 100644
--- a/src/main/java/org/apache/commons/csv/Lexer.java
+++ b/src/main/java/org/apache/commons/csv/Lexer.java
@@ -42,7 +42,7 @@ final class Lexer implements Closeable {
     private static final String LF_STRING = Character.toString(LF);
 
     /**
-     * Constant char to use for disabling comments, escapes and encapsulation. The value -2 is used because it
+     * Constant char to use for disabling comments, escapes, and encapsulation. The value -2 is used because it
      * won't be confused with an EOF signal (-1), and because the Unicode value {@code FFFE} would be encoded as two
      * chars (using surrogates) and thus there should never be a collision with a real text char.
      */
@@ -146,9 +146,9 @@ final class Lexer implements Closeable {
     }
 
     /**
-     * Tests if the given character indicates end of file.
+     * Tests if the given character indicates the end of the file.
      *
-     * @return true if the given character indicates end of file.
+     * @return true if the given character indicates the end of the file.
      */
     boolean isEndOfFile(final int ch) {
         return ch == END_OF_STREAM;
@@ -168,7 +168,7 @@ final class Lexer implements Closeable {
      *
      * For example, for delimiter "[|]" and escape '!', return true if the next characters constitute "![!|!]".
      *
-     * @return true if the next characters constitute a escape delimiter.
+     * @return true if the next characters constitute an escape delimiter.
      * @throws IOException If an I/O error occurs.
      */
     boolean isEscapeDelimiter() throws IOException {
@@ -194,7 +194,7 @@ final class Lexer implements Closeable {
     }
 
     /**
-     * Tests if the current character represents the start of a line: a CR, LF or is at the start of the file.
+     * Tests if the current character represents the start of a line: a CR, LF, or is at the start of the file.
      *
      * @param ch the character to check
      * @return true if the character is at the start of a line.
@@ -214,13 +214,13 @@ final class Lexer implements Closeable {
      * 

      *
      * @param token
-     *            an existing Token object to reuse. The caller is responsible to initialize the Token.
+     *            an existing Token object to reuse. The caller is responsible for initializing the Token.
      * @return the next token found.
      * @throws IOException on stream access error.
      */
     Token nextToken(final Token token) throws IOException {
 
-        // get the last read char (required for empty line detection)
+        // Get the last read char (required for empty line detection)
         int lastChar = reader.getLastChar();
 
         // read the next char and set eol
@@ -234,11 +234,11 @@ final class Lexer implements Closeable {
         // empty line detection: eol AND (last char was EOL or beginning)
         if (ignoreEmptyLines) {
             while (eol && isStartOfLine(lastChar)) {
-                // go on char ahead ...
+                // Go on char ahead ...
                 lastChar = c;
                 c = reader.read();
                 eol = readEndOfLine(c);
-                // reached end of file without any content (empty line at the end)
+                // reached the end of the file without any content (empty line at the end)
                 if (isEndOfFile(c)) {
                     token.type = EOF;
                     // don't set token.isReady here because no content
@@ -247,7 +247,7 @@ final class Lexer implements Closeable {
             }
         }
 
-        // did we reach eof during the last iteration already ? EOF
+        // Did we reach EOF during the last iteration already? EOF
         if (isEndOfFile(lastChar) || !isLastTokenDelimiter && isEndOfFile(c)) {
             token.type = EOF;
             // don't set token.isReady here because no content
@@ -267,7 +267,7 @@ final class Lexer implements Closeable {
             return token;
         }
 
-        // important: make sure a new char gets consumed in each iteration
+        // Important: make sure a new char gets consumed in each iteration
         while (token.type == INVALID) {
             // ignore whitespaces at beginning of a token
             if (ignoreSurroundingSpaces) {
@@ -305,12 +305,12 @@ final class Lexer implements Closeable {
     /**
      * Parses an encapsulated token.
      * 

-     * Encapsulated tokens are surrounded by the given encapsulating-string. The encapsulator itself might be included
+     * Encapsulated tokens are surrounded by the given encapsulating string. The encapsulator itself might be included
      * in the token using a doubling syntax (as "", '') or using escaping (as in \", \'). Whitespaces before and after
-     * an encapsulated token are ignored. The token is finished when one of the following conditions become true:
+     * an encapsulated token is ignored. The token is finished when one of the following conditions becomes true:
      * 

      * 
    
-     * 
  • an unescaped encapsulator has been reached, and is followed by optional whitespace then:
    • 
+     * 
  • An unescaped encapsulator has been reached and is followed by optional whitespace then:
    • 
      * 
      
      * 
    • delimiter (TOKEN)
      • 
      * 
    • end of line (EORECORD)
      • 
@@ -321,11 +321,12 @@ final class Lexer implements Closeable {
      *            the current token
      * @return a valid token object
      * @throws IOException
-     *             on invalid state: EOF before closing encapsulator or invalid character before delimiter or EOL
+     *             Thrown when in an invalid state: EOF before closing encapsulator or invalid character before 
+     *             delimiter or EOL.
      */
     private Token parseEncapsulatedToken(final Token token) throws IOException {
         token.isQuoted = true;
-        // save current line number in case needed for IOE
+        // Save current line number in case needed for IOE
         final long startLineNumber = getCurrentLineNumber();
         int c;
         while (true) {
@@ -385,13 +386,13 @@ final class Lexer implements Closeable {
     /**
      * Parses a simple token.
      * 
      
-     * Simple token are tokens which are not surrounded by encapsulators. A simple token might contain escaped
-     * delimiters (as \, or \;). The token is finished when one of the following conditions become true:
+     * Simple tokens are tokens that are not surrounded by encapsulators. A simple token might contain escaped
+     * delimiters (as \, or \;). The token is finished when one of the following conditions becomes true:
      * 
      
      * 
        
-     * 
      • end of line has been reached (EORECORD)
        • 
-     * 
      • end of stream has been reached (EOF)
        • 
-     * 
      • an unescaped delimiter has been reached (TOKEN)
        • 
+     * 
      • The end of line has been reached (EORECORD)
        • 
+     * 
      • The end of stream has been reached (EOF)
        • 
+     * 
      • An unescaped delimiter has been reached (TOKEN)
        • 
      * 
      
      *
      * @param token

From b55e022d0ed39d9d55912281febca50e285bda64 Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 09:07:57 -0400
Subject: [PATCH 12/16] Javadoc

---
 src/main/java/org/apache/commons/csv/QuoteMode.java | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/main/java/org/apache/commons/csv/QuoteMode.java b/src/main/java/org/apache/commons/csv/QuoteMode.java
index a9b33a10..f2fb1f94 100644
--- a/src/main/java/org/apache/commons/csv/QuoteMode.java
+++ b/src/main/java/org/apache/commons/csv/QuoteMode.java
@@ -32,7 +32,7 @@ public enum QuoteMode {
     ALL_NON_NULL,
 
     /**
-     * Quotes fields which contain special characters such as a the field delimiter, quote character or any of the
+     * Quotes fields that contain special characters such as a field delimiter, quote character, or any of the
      * characters in the line separator string.
      */
     MINIMAL,

From 4e0b0fb8a501cccad9531249bcc8b0aafce7bb3a Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 09:08:38 -0400
Subject: [PATCH 13/16] Javadoc

---
 src/main/java/org/apache/commons/csv/Token.java | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/src/main/java/org/apache/commons/csv/Token.java b/src/main/java/org/apache/commons/csv/Token.java
index 2dedc58a..a33b220e 100644
--- a/src/main/java/org/apache/commons/csv/Token.java
+++ b/src/main/java/org/apache/commons/csv/Token.java
@@ -21,8 +21,9 @@ import static org.apache.commons.csv.Token.Type.INVALID;
 
 /**
  * Internal token representation.
- * 
      
- * It is used as contract between the lexer and the parser.
+ * 
      
+ * It is used as a contract between the lexer and the parser.
+ * 
      
  */
 final class Token {
 
@@ -30,7 +31,7 @@ final class Token {
         /** Token has no valid content, i.e. is in its initialized state. */
         INVALID,
 
-        /** Token with content, at beginning or in the middle of a line. */
+        /** Token with content, at the beginning or in the middle of a line. */
         TOKEN,
 
         /** Token (which can have content) when the end of file is reached. */

From 386e6e7cc1e5ff2a05a4d46b763cdae22460c39c Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 09:09:27 -0400
Subject: [PATCH 14/16] Javadoc

---
 .../org/apache/commons/csv/package-info.java     | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/src/main/java/org/apache/commons/csv/package-info.java b/src/main/java/org/apache/commons/csv/package-info.java
index 29e7fef6..023096f6 100644
--- a/src/main/java/org/apache/commons/csv/package-info.java
+++ b/src/main/java/org/apache/commons/csv/package-info.java
@@ -18,14 +18,14 @@
 /**
  * Apache Commons CSV Format Support.
  *
- * 
      CSV are widely used as interfaces to legacy systems or manual data-imports.
+ * 
      CSV are widely used as interfaces to legacy systems or manual data imports.
  *    CSV stands for "Comma Separated Values" (or sometimes "Character Separated
  *    Values"). The CSV data format is defined in
  *    RFC 4180
  *    but many dialects exist.
      
  *
  * 
      Common to all file dialects is its basic structure: The CSV data-format
- *    is record oriented, whereas each record starts on a new textual line. A
+ *    is record-oriented, whereas each record starts on a new textual line. A
  *    record is build of a list of values. Keep in mind that not all records
  *    must have an equal number of values:
      
  * 
      @@ -36,28 +36,28 @@
  * 
      The following list contains the CSV aspects the Commons CSV parser supports:
      
  * 
      
  *   
      Separators (for lines)
      
- *   
      The record separators are hardcoded and cannot be changed. The must be '\r', '\n' or '\r\n'.
      
+ *   
      The record separators are hardcoded and cannot be changed. The must be '\r', '\n', or '\r\n'.
      
  *
  *   
      Delimiter (for values)
      
  *   
      The delimiter for values is freely configurable (default ',').
      
  *
  *   
      Comments
      
- *   
      Some CSV-dialects support a simple comment syntax. A comment is a record
+ *   
      Some CSV dialects support a simple comment syntax. A comment is a record
  *       which must start with a designated character (the commentStarter). A record
- *       of this kind is treated as comment and gets removed from the input (default none)
      
+ *       of this kind is treated as a comment and gets removed from the input (default none)
  *
  *   
      Encapsulator
      
  *  
      Two encapsulator characters (default '"') are used to enclose -> complex values.
      
  *
  *   
      Simple values
      
- *   
      A simple value consist of all characters (except the delimiter) until
- *       (but not including) the next delimiter or a record-terminator. Optionally
+ *   
      A simple value consists of all characters (except the delimiter) until
+ *       (but not including) the next delimiter or a record terminator. Optionally
  *       all surrounding whitespaces of a simple value can be ignored (default: true).
      
  *
  *   
      Complex values
      
  *   
      Complex values are encapsulated within a pair of the defined encapsulator characters.
  *       The encapsulator itself must be escaped or doubled when used inside complex values.
- *       Complex values preserve all kind of formatting (including newlines -> multiline-values)
      
+ *       Complex values preserve all kinds of formatting (including newlines -> multiline-values)
  *
  *  
      Empty line skipping
      
  *   
      Optionally empty lines in CSV files can be skipped.

From e613a3cc1b4029d253d34220eec40d73908e6075 Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 09:12:10 -0400
Subject: [PATCH 15/16] Javadoc

---
 src/main/java/org/apache/commons/csv/Lexer.java | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/main/java/org/apache/commons/csv/Lexer.java b/src/main/java/org/apache/commons/csv/Lexer.java
index ea29ff68..01716720 100644
--- a/src/main/java/org/apache/commons/csv/Lexer.java
+++ b/src/main/java/org/apache/commons/csv/Lexer.java
@@ -321,7 +321,7 @@ final class Lexer implements Closeable {
      *            the current token
      * @return a valid token object
      * @throws IOException
-     *             Thrown when in an invalid state: EOF before closing encapsulator or invalid character before 
+     *             Thrown when in an invalid state: EOF before closing encapsulator or invalid character before
      *             delimiter or EOL.
      */
     private Token parseEncapsulatedToken(final Token token) throws IOException {

From 710459843cbe3cf4f1ca3aaac5a6eb22d049e643 Mon Sep 17 00:00:00 2001
From: Gary Gregory 
Date: Wed, 30 Aug 2023 09:16:49 -0400
Subject: [PATCH 16/16] Bump commons-parent from 60 to 61

---
 pom.xml                 | 2 +-
 src/changes/changes.xml | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/pom.xml b/pom.xml
index f57853c3..b59fd6bf 100644
--- a/pom.xml
+++ b/pom.xml
@@ -20,7 +20,7 @@
   
     org.apache.commons
     commons-parent
-    60
+    61
   
   commons-csv
   1.10.1-SNAPSHOT
diff --git a/src/changes/changes.xml b/src/changes/changes.xml
index b65bce7c..de874fed 100644
--- a/src/changes/changes.xml
+++ b/src/changes/changes.xml
@@ -50,7 +50,7 @@
       [StepSecurity] CI: Harden GitHub Actions #329, #330.
       
       Bump commons-io:commons-io: from 2.11.0 to 2.13.0.
-      Bump commons-parent from 57 to 60.
+      Bump commons-parent from 57 to 61.
       Bump h2 from 2.1.214 to 2.2.220 #333.
       Bump commons-lang3 from 3.12.0 to 3.13.0.
       Update exception message in CSVRecord#getNextRecord() #348.