MLE-12358: (Technical) Apply fix on MLCP commons-csv to the latest 1.…

…12 release
marklogic · Oct 28, 2024 · b397c16 · b397c16
1 parent 1c52ad3
commit b397c16
Show file tree

Hide file tree

Showing 7 changed files with 35 additions and 28 deletions.
diff --git a/src/main/java/org/apache/commons/csv/CSVFormat.java b/src/main/java/org/apache/commons/csv/CSVFormat.java
@@ -2074,6 +2074,21 @@ public CSVParser parse(final Reader reader) throws IOException {
         return new CSVParser(reader, this);
     }
 
+    /**
+     * Parses the specified content.
+     *
+     * <p>
+     * See also the various static parse methods on {@link CSVParser}.
+     * </p>
+     *
+     * @param reader the input stream
+     * @param characterOffset the character offset
+     * @param recordNumber the record number
+     * @param encoding the encoding
+     * @return a parser over a stream of {@link CSVRecord}s.
+     * @throws IOException If an I/O error occurs
+     * @throws CSVException Thrown on invalid input.
+     */
     public CSVParser parse(final Reader reader, final long characterOffset, final long recordNumber, String encoding) throws IOException {
         return new CSVParser(reader, this, characterOffset, recordNumber, encoding);
     }

diff --git a/src/main/java/org/apache/commons/csv/CSVParser.java b/src/main/java/org/apache/commons/csv/CSVParser.java
@@ -441,7 +441,7 @@ public CSVParser(final Reader reader, final CSVFormat format, final long charact
             this(reader, format, characterOffset, recordNumber, null);
         }
 
-    public CSVParser(final Reader reader, final CSVFormat format, final long characterOffset,final long recordNumber, 
+    public CSVParser(final Reader reader, final CSVFormat format, final long characterOffset, final long recordNumber,
         String encoding) throws IOException {
         Objects.requireNonNull(reader, "reader");
         Objects.requireNonNull(format, "format");

diff --git a/src/main/java/org/apache/commons/csv/CSVRecord.java b/src/main/java/org/apache/commons/csv/CSVRecord.java
@@ -17,8 +17,6 @@
 
 package org.apache.commons.csv;
 
-import static org.apache.commons.csv.Constants.EMPTY_STRING_ARRAY;
-
 import java.io.Serializable;
 import java.util.Arrays;
 import java.util.Iterator;

diff --git a/src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java b/src/main/java/org/apache/commons/csv/ExtendedBufferedReader.java
@@ -57,7 +57,7 @@ final class ExtendedBufferedReader extends UnsynchronizedBufferedReader {
     private long bytesRead;
     /** Encoder used to calculate the bytes of characters */
     CharsetEncoder encoder;
-    
+
     /**
      * A flag to indicate if the read is a peek operation.
      */
@@ -77,7 +77,7 @@ final class ExtendedBufferedReader extends UnsynchronizedBufferedReader {
         }
         isReadPeek = false;
     }
-    
+
     /**
      * Closes the stream.
      *
@@ -141,7 +141,7 @@ public int read() throws IOException {
             lineNumber++;
         }
         if (encoder != null && !isReadPeek) {
-            this.bytesRead += getCharBytes(current); 
+            this.bytesRead += getCharBytes(current);
         }
         lastChar = current;
         position++;
@@ -161,8 +161,8 @@ public int read() throws IOException {
      *     - Consists of UTF-8 some 3-byte chars and 4-byte chars
      */
     private long getCharBytes(int current) throws CharacterCodingException {
-        char cChar = (char)current;
-        char lChar = (char)lastChar;
+        char cChar = (char) current;
+        char lChar = (char) lastChar;
         if (!Character.isSurrogate(cChar)) {
             return encoder.encode(
                 CharBuffer.wrap(new char[] {cChar})).limit();

diff --git a/src/main/java/org/apache/commons/csv/Lexer.java b/src/main/java/org/apache/commons/csv/Lexer.java
@@ -111,7 +111,7 @@ long getCharacterPosition() {
     long getBytesRead() {
         return reader.getBytesRead();
     }
-    
+
     /**
      * Returns the current line number
      *

diff --git a/src/test/java/org/apache/commons/csv/CSVParserTest.java b/src/test/java/org/apache/commons/csv/CSVParserTest.java
@@ -695,21 +695,19 @@ public void testGetHeaderComment_NoComment3() throws IOException {
 
     @Test
     public void testGetRecordThreeBytesRead() throws Exception {
-        String code = "id,date,val5,val4\n"
-                + "11111111111111,'4017-09-01',きちんと節分近くには咲いてる～,v4\n"
-                + "22222222222222,'4017-01-01',おはよう私の友人～,v4\n"
-                + "33333333333333,'4017-01-01',きる自然の力ってすごいな～,v4\n";
-
+        String code = "id,date,val5,val4\n" +
+            "11111111111111,'4017-09-01',きちんと節分近くには咲いてる～,v4\n" +
+            "22222222222222,'4017-01-01',おはよう私の友人～,v4\n" +
+            "33333333333333,'4017-01-01',きる自然の力ってすごいな～,v4\n";
         // final CSVFormat format = CSVFormat.newFormat(',').withQuote('\'');
         final CSVFormat format = CSVFormat.Builder.create()
                                .setDelimiter(',')
                                .setQuote('\'')
                                .build();
         // CSVParser parser = new CSVParser(new StringReader(code), format, 0L, 1L, "UTF-8");
-
         CSVParser parser =  format.parse(new StringReader(code), 0L, 1L, "UTF-8");
 
-        CSVRecord record;
+        CSVRecord record = new CSVRecord(parser, null, null, 1L, 0L, 0L);
         assertEquals(0, parser.getRecordNumber());
         assertNotNull(record = parser.nextRecord());
         assertEquals(1, record.getRecordNumber());
@@ -737,16 +735,16 @@ public void testGetRecordThreeBytesRead() throws Exception {
 
     @Test
     public void testGetRecordFourBytesRead() throws Exception {
-        String code = "id,a,b,c\n"
-            + "1,😊,🤔,😂\n"
-            + "2,😊,🤔,😂\n"
-            + "3,😊,🤔,😂\n";
+        String code = "id,a,b,c\n" +
+            "1,😊,🤔,😂\n" +
+            "2,😊,🤔,😂\n" +
+            "3,😊,🤔,😂\n";
         // final CSVFormat format = CSVFormat.newFormat(',').withQuote('\'');
         final CSVFormat format = CSVFormat.Builder.create()
             .setDelimiter(',')
             .setQuote('\'')
             .build();
-        
+
         // CSVParser parser = new CSVParser(new StringReader(code), format, 0L, 1L, "UTF-8");
         CSVParser parser =  format.parse(new StringReader(code), 0L, 1L, "UTF-8");
 

diff --git a/src/test/java/org/apache/commons/csv/JiraCsv196Test.java b/src/test/java/org/apache/commons/csv/JiraCsv196Test.java
@@ -39,9 +39,7 @@ public void parseThreeBytes() throws IOException {
             // "org/apache/commons/csv/CSV-196/japanese.csv"), format, 0L, 1L, "UTF-8");
         CSVParser parser =  format.parse(getTestInput(
             "org/apache/commons/csv/CSV-196/japanese.csv"), 0L, 1L, "UTF-8");
-
-
-            long[] charByteKey = {0, 89, 242, 395};
+        long[] charByteKey = {0, 89, 242, 395};
         int idx = 0;
         for (CSVRecord record : parser) {
             assertEquals(charByteKey[idx++], record.getCharacterByte());
@@ -57,9 +55,7 @@ public void parseFourBytes() throws IOException {
             .setDelimiter(',')
             .setQuote('\'')
             .build();
-
-        // CSVParser parser = new CSVParser(getTestInput(
-        //     "org/apache/commons/csv/CSV-196/emoji.csv"), format, 0L, 1L, "UTF-8");
+
         CSVParser parser =  format.parse(getTestInput(
                 "org/apache/commons/csv/CSV-196/emoji.csv"), 0L, 1L, "UTF-8");
 
@@ -76,4 +72,4 @@ private Reader getTestInput(String path) {
         return new InputStreamReader(
             ClassLoader.getSystemClassLoader().getResourceAsStream(path));
     }
-}
+}
-Original file line number
+Diff line change
@@ Expand Up / @@ -111,7 +111,7 @@ long getCharacterPosition() { @@
         long getBytesRead() {
             return reader.getBytesRead();
         }
         /**
          * Returns the current line number
          *
@@ Expand Down @@