Merge branch 'master' of https://gitbox.apache.org/repos/asf/commons-csv

.github/workflows/codeql-analysis.yml

@@ -57,7 +57,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@4dd16135b69a43b6c8efb853346f8437d92d3c93    # 3.26.6
+      uses: github/codeql-action/init@294a9d92911152fe08befb9ec03e240add280cb3    # 3.26.8
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -68,7 +68,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@4dd16135b69a43b6c8efb853346f8437d92d3c93    # 3.26.6
+      uses: github/codeql-action/autobuild@294a9d92911152fe08befb9ec03e240add280cb3    # 3.26.8
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -82,4 +82,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@4dd16135b69a43b6c8efb853346f8437d92d3c93    # 3.26.6
+      uses: github/codeql-action/analyze@294a9d92911152fe08befb9ec03e240add280cb3    # 3.26.8

.github/workflows/dependency-review.yml

@@ -0,0 +1,31 @@
+# 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.
+
+name: 'Dependency Review'
+on: [pull_request]
+
+permissions:
+  contents: read
+
+jobs:
+  dependency-review:
+    runs-on: ubuntu-latest
+    steps:
+      - name: 'Checkout Repository'
+        uses: actions/checkout@v4
+      - name: 'Dependency Review'
+        uses: actions/dependency-review-action@v4

.github/workflows/scorecards-analysis.yml

@@ -64,6 +64,6 @@ jobs:
           retention-days: 5
 
       - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@4dd16135b69a43b6c8efb853346f8437d92d3c93    # 3.26.6
+        uses: github/codeql-action/upload-sarif@294a9d92911152fe08befb9ec03e240add280cb3    # 3.26.8
         with:
           sarif_file: results.sarif

pom.xml

@@ -206,6 +206,7 @@
             <configLocation>${checkstyle.config.file}</configLocation>
             <enableRulesSummary>false</enableRulesSummary>
             <suppressionsLocation>${checkstyle.suppress.file}</suppressionsLocation>
+            <includeTestSourceDirectory>true</includeTestSourceDirectory>
           </configuration>
         </plugin>
         <plugin>

src/main/java/org/apache/commons/csv/CSVParser.java

@@ -72,7 +72,7 @@
  * For those who like fluent APIs, parsers can be created using {@link CSVFormat#parse(java.io.Reader)} as a shortcut:
  * </p>
  * <pre>
- * for(CSVRecord record : CSVFormat.EXCEL.parse(in)) {
+ * for (CSVRecord record : CSVFormat.EXCEL.parse(in)) {
  *     ...
  * }
  * </pre>

src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java

@@ -56,22 +56,6 @@ final class ExtendedBufferedReader extends UnsynchronizedBufferedReader {
         super(reader);
     }
 
-    @Override
-    public void mark(final int readAheadLimit) throws IOException {
-        lineNumberMark = lineNumber;
-        lastCharMark = lastChar;
-        positionMark = position;
-        super.mark(readAheadLimit);
-    }
-
-    @Override
-    public void reset() throws IOException {
-        lineNumber = lineNumberMark;
-        lastChar = lastCharMark;
-        position = positionMark;
-        super.reset();
-    }
-
     /**
      * Closes the stream.
      *
@@ -85,6 +69,18 @@ public void close() throws IOException {
         super.close();
     }
 
+    /**
+     * Returns the last character that was read as an integer (0 to 65535). This will be the last character returned by
+     * any of the read methods. This will not include a character read using the {@link #peek()} method. If no
+     * character has been read then this will return {@link Constants#UNDEFINED}. If the end of the stream was reached
+     * on the last read then this will return {@link IOUtils#EOF}.
+     *
+     * @return the last character that was read
+     */
+    int getLastChar() {
+        return lastChar;
+    }
+
     /**
      * Returns the current line number
      *
@@ -98,18 +94,6 @@ long getLineNumber() {
         return lineNumber + 1; // Allow for counter being incremented only at EOL
     }
 
-    /**
-     * Returns the last character that was read as an integer (0 to 65535). This will be the last character returned by
-     * any of the read methods. This will not include a character read using the {@link #peek()} method. If no
-     * character has been read then this will return {@link Constants#UNDEFINED}. If the end of the stream was reached
-     * on the last read then this will return {@link IOUtils#EOF}.
-     *
-     * @return the last character that was read
-     */
-    int getLastChar() {
-        return lastChar;
-    }
-
     /**
      * Gets the character position in the reader.
      *
@@ -119,6 +103,14 @@ long getPosition() {
         return this.position;
     }
 
+    @Override
+    public void mark(final int readAheadLimit) throws IOException {
+        lineNumberMark = lineNumber;
+        lastCharMark = lastChar;
+        positionMark = position;
+        super.mark(readAheadLimit);
+    }
+
     @Override
     public int read() throws IOException {
         final int current = super.read();
@@ -190,4 +182,12 @@ public String readLine() throws IOException {
         return buffer.toString();
     }
 
+    @Override
+    public void reset() throws IOException {
+        lineNumber = lineNumberMark;
+        lastChar = lastCharMark;
+        position = positionMark;
+        super.reset();
+    }
+
 }

src/main/java/org/apache/commons/csv/Lexer.java

@@ -63,6 +63,26 @@ final class Lexer implements Closeable {
         this.escapeDelimiterBuf = new char[2 * delimiter.length - 1];
     }
 
+    /**
+     * Appends the next escaped character to the token's content.
+     *
+     * @param token the current token
+     * @throws IOException  on stream access error
+     * @throws CSVException Thrown on invalid input.
+     */
+    private void appendNextEscapedCharacterToToken(final Token token) throws IOException {
+        if (isEscapeDelimiter()) {
+            token.content.append(delimiter);
+        } else {
+            final int unescaped = readEscape();
+            if (unescaped == EOF) { // unexpected char after escape
+                token.content.append((char) escape).append((char) reader.getLastChar());
+            } else {
+                token.content.append((char) unescaped);
+            }
+        }
+    }
+
     /**
      * Closes resources.
      *
@@ -190,10 +210,6 @@ boolean isStartOfLine(final int ch) {
         return ch == Constants.LF || ch == Constants.CR || ch == Constants.UNDEFINED;
     }
 
-    private int nullToDisabled(final Character c) {
-        return c == null ? Constants.UNDEFINED : c.charValue(); // Explicit unboxing
-    }
-
     /**
      * Returns the next token.
      * <p>
@@ -279,6 +295,10 @@ Token nextToken(final Token token) throws IOException {
         return token;
     }
 
+    private int nullToDisabled(final Character c) {
+        return c == null ? Constants.UNDEFINED : c.charValue(); // Explicit unboxing
+    }
+
     /**
      * Parses an encapsulated token.
      * <p>
@@ -408,26 +428,6 @@ private Token parseSimpleToken(final Token token, int ch) throws IOException {
         return token;
     }
 
-    /**
-     * Appends the next escaped character to the token's content.
-     *
-     * @param token the current token
-     * @throws IOException  on stream access error
-     * @throws CSVException Thrown on invalid input.
-     */
-    private void appendNextEscapedCharacterToToken(final Token token) throws IOException {
-        if (isEscapeDelimiter()) {
-            token.content.append(delimiter);
-        } else {
-            final int unescaped = readEscape();
-            if (unescaped == EOF) { // unexpected char after escape
-                token.content.append((char) escape).append((char) reader.getLastChar());
-            } else {
-                token.content.append((char) unescaped);
-            }
-        }
-    }
-
     /**
      * Greedily accepts \n, \r and \r\n This checker consumes silently the second control-character...
      *

src/test/java/org/apache/commons/csv/CSVBenchmark.java

@@ -28,10 +28,6 @@
 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;
@@ -49,6 +45,10 @@
 import org.supercsv.io.CsvListReader;
 import org.supercsv.prefs.CsvPreference;
 
+import com.generationjava.io.CsvReader;
+import com.opencsv.CSVParserBuilder;
+import com.opencsv.CSVReaderBuilder;
+
 @BenchmarkMode(Mode.AverageTime)
 @Fork(value = 1, jvmArgs = {"-server", "-Xms1024M", "-Xmx1024M"})
 @Threads(1)

src/test/java/org/apache/commons/csv/CSVDuplicateHeaderTest.java

@@ -307,25 +307,24 @@ public void testCSVParser(final DuplicateHeaderMode duplicateHeaderMode,
                               final boolean allowMissingColumnNames,
                               final boolean ignoreHeaderCase,
                               final String[] headers,
-                              final boolean valid) throws IOException {
-        final CSVFormat format =
-            CSVFormat.DEFAULT.builder()
-                             .setDuplicateHeaderMode(duplicateHeaderMode)
-                             .setAllowMissingColumnNames(allowMissingColumnNames)
-                             .setIgnoreHeaderCase(ignoreHeaderCase)
-                             .setNullString("NULL")
-                             .setHeader()
-                             .build();
+            final boolean valid) throws IOException {
+        // @formatter:off
+        final CSVFormat format = CSVFormat.DEFAULT.builder()
+                .setDuplicateHeaderMode(duplicateHeaderMode)
+                .setAllowMissingColumnNames(allowMissingColumnNames)
+                .setIgnoreHeaderCase(ignoreHeaderCase)
+                .setNullString("NULL")
+                .setHeader()
+                .build();
+        // @formatter:on
         final String input = Arrays.stream(headers)
                 .map(s -> s == null ? format.getNullString() : s)
                 .collect(Collectors.joining(format.getDelimiterString()));
+        // @formatter:off
         if (valid) {
-            try(CSVParser parser = CSVParser.parse(input, format)) {
+            try (CSVParser parser = CSVParser.parse(input, format)) {
                 // Parser ignores null headers
-                final List<String> expected =
-                    Arrays.stream(headers)
-                          .filter(s -> s != null)
-                          .collect(Collectors.toList());
+                final List<String> expected = Arrays.stream(headers).filter(s -> s != null).collect(Collectors.toList());
                 Assertions.assertEquals(expected, parser.getHeaderNames(), "HeaderNames");
             }
         } else {

src/test/java/org/apache/commons/csv/CSVFormatTest.java

@@ -715,11 +715,21 @@ public void testFormatThrowsNullPointerException() {
 
     @Test
     public void testFormatToString() {
-        final CSVFormat format = CSVFormat.RFC4180.withEscape('?').withDelimiter(',').withQuoteMode(QuoteMode.MINIMAL).withRecordSeparator(CRLF).withQuote('"')
-                .withNullString("").withIgnoreHeaderCase(true).withHeaderComments("This is HeaderComments").withHeader("col1", "col2", "col3");
+        // @formatter:off
+        final CSVFormat format = CSVFormat.RFC4180
+                .withEscape('?')
+                .withDelimiter(',')
+                .withQuoteMode(QuoteMode.MINIMAL)
+                .withRecordSeparator(CRLF)
+                .withQuote('"')
+                .withNullString("")
+                .withIgnoreHeaderCase(true)
+                .withHeaderComments("This is HeaderComments")
+                .withHeader("col1", "col2", "col3");
+        // @formatter:on
         assertEquals(
-                "Delimiter=<,> Escape=<?> QuoteChar=<\"> QuoteMode=<MINIMAL> NullString=<> RecordSeparator=<" + CRLF
-                        + "> IgnoreHeaderCase:ignored SkipHeaderRecord:false HeaderComments:[This is HeaderComments] Header:[col1, col2, col3]",
+                "Delimiter=<,> Escape=<?> QuoteChar=<\"> QuoteMode=<MINIMAL> NullString=<> RecordSeparator=<" + CRLF +
+                        "> IgnoreHeaderCase:ignored SkipHeaderRecord:false HeaderComments:[This is HeaderComments] Header:[col1, col2, col3]",
                 format.toString());
     }
 
@@ -960,12 +970,14 @@ public void testQuoteCharSameAsDelimiterThrowsException_Deprecated() {
 
     @Test
     public void testQuoteModeNoneShouldReturnMeaningfulExceptionMessage() {
-        final Exception exception = assertThrows(IllegalArgumentException.class, () -> {
+        final Exception exception = assertThrows(IllegalArgumentException.class, () ->
+        // @formatter:off
             CSVFormat.DEFAULT.builder()
                     .setHeader("Col1", "Col2", "Col3", "Col4")
                     .setQuoteMode(QuoteMode.NONE)
-                    .build();
-        });
+                    .build()
+        // @formatter:on
+        );
         final String actualMessage = exception.getMessage();
         final String expectedMessage = "Quote mode set to NONE but no escape character is set";
         assertEquals(expectedMessage, actualMessage);