[ a84668e ] before bug fix 6

Author: dodoyoon

checkstyle.xml

@@ -36,7 +36,7 @@ limitations under the License.
   <!-- Checks for Tab characters -->
   <!-- See http://checkstyle.sourceforge.net/config_whitespace.html#FileTabCharacter -->
   <module name="FileTabCharacter">
-    <property name="fileExtensions" value="java" />
+    <property name="fileExtensions" value="java,xml" />
   </module>
 
   <!-- Checks for white space at the end of the line -->

pom.xml

@@ -127,11 +127,11 @@ CSV files of various types.
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
     <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
     <commons.encoding>UTF-8</commons.encoding>
-    <!-- 
+    <!--
         Use 2.9.1 instead of 2.10; 2.10 seems to scan the 'target' dir
-        and wants license headers in .properties to be the header for Java files. 
+        and wants license headers in .properties to be the header for Java files.
     -->
-    <checkstyle.version>2.9.1</checkstyle.version>
+    <checkstyle.version>2.12</checkstyle.version>
     <checkstyle.header.file>${basedir}/LICENSE-header.txt</checkstyle.header.file>
   </properties>
 
@@ -194,15 +194,15 @@ CSV files of various types.
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-pmd-plugin</artifactId>
-        <version>3.0.1</version>
+        <version>3.1</version>
         <configuration>
           <targetJdk>${maven.compiler.target}</targetJdk>
         </configuration>
       </plugin>
       <plugin>
         <groupId>org.codehaus.mojo</groupId>
         <artifactId>findbugs-maven-plugin</artifactId>
-        <version>2.5.2</version>
+        <version>2.5.3</version>
       </plugin>
       <plugin>
         <groupId>org.codehaus.mojo</groupId>

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

@@ -29,6 +29,7 @@
 import java.net.URL;
 import java.nio.charset.Charset;
 import java.util.ArrayList;
+import java.util.Collection;
 import java.util.Iterator;
 import java.util.LinkedHashMap;
 import java.util.List;
@@ -54,7 +55,7 @@
  * </p>
  * <p>
  * Alternatively parsers can also be created by passing a {@link Reader} directly to the sole constructor.
- * 
+ *
  * For those who like fluent APIs, parsers can be created using {@link CSVFormat#parse(java.io.Reader)} as a shortcut:
  * </p>
  * <pre>
@@ -197,8 +198,7 @@ public static CSVParser parse(final URL url, final Charset charset, final CSVFor
         Assertions.notNull(charset, "charset");
         Assertions.notNull(format, "format");
 
-        return new CSVParser(new InputStreamReader(url.openStream(),
-                             charset == null ? Charset.forName("UTF-8") : charset), format);
+        return new CSVParser(new InputStreamReader(url.openStream(), charset), format);
     }
 
     // the following objects are shared to reduce garbage
@@ -310,7 +310,22 @@ public long getRecordNumber() {
      *             on parse error or input read-failure
      */
     public List<CSVRecord> getRecords() throws IOException {
-        final List<CSVRecord> records = new ArrayList<CSVRecord>();
+        return getRecords(new ArrayList<CSVRecord>());
+    }
+
+    /**
+     * Parses the CSV input according to the given format and adds the content to the collection of {@link CSVRecord
+     * CSVRecords}.
+     * <p/>
+     * The returned content starts at the current parse-position in the stream.
+     * 
+     * @param records
+     *            The collection to add to.
+     * @return a collection of {@link CSVRecord CSVRecords}, may be empty
+     * @throws IOException
+     *             on parse error or input read-failure
+     */
+    public <T extends Collection<CSVRecord>> T getRecords(T records) throws IOException {
         CSVRecord rec;
         while ((rec = this.nextRecord()) != null) {
             records.add(rec);
@@ -320,7 +335,7 @@ public List<CSVRecord> getRecords() throws IOException {
 
     /**
      * Initializes the name to index mapping if the format defines a header.
-     * 
+     *
      * @return null if the format has no header.
      */
     private Map<String, Integer> initializeHeader() throws IOException {
@@ -450,6 +465,8 @@ CSVRecord nextRecord() throws IOException {
                 sb.append(this.reusableToken.content);
                 this.reusableToken.type = TOKEN; // Read another token
                 break;
+            default:
+                throw new IllegalStateException("Unexpected Token type: " + this.reusableToken.type);
             }
         } while (this.reusableToken.type == TOKEN);
 

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

@@ -240,6 +240,8 @@ private void printAndQuote(final Object object, final CharSequence value,
                 return;
             }
             break;
+        default:
+            throw new IllegalStateException("Unexpected Quote value: " + quotePolicy);
         }
 
         if (!quote) {
@@ -420,9 +422,9 @@ public void printRecords(final ResultSet resultSet) throws SQLException, IOExcep
     }
 
     /**
-     * Gets the target Appendable. 
-     * 
-     * @return the target Appendable. 
+     * Gets the target Appendable.
+     *
+     * @return the target Appendable.
      */
     public Appendable getOut() {
         return this.out;

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

@@ -172,7 +172,7 @@ public Iterator<String> iterator() {
 
     /**
      * Puts all values of this record into the given Map.
-     * 
+     *
      * @param map The Map to populate.
      * @return the given map.
      */
@@ -194,7 +194,7 @@ public int size() {
 
     /**
      * Converts the values to a List.
-     * 
+     *
      * TODO: Maybe make this public?
      * @return a new List
      */
@@ -204,7 +204,7 @@ private List<String> toList() {
 
     /**
      * Copies this record into a new Map. The new map is not connect
-     * 
+     *
      * @return A new Map. The map is empty if the record has no headers.
      */
     public Map<String, String> toMap() {

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

@@ -39,6 +39,13 @@ final class Constants {
     static final char LF = '\n';
     static final char SP = ' ';
     static final char TAB = '\t';
+
+    /** ASCII record separator */
+    static final char RS = 30;
+
+    /** ASCII unit separator */
+    static final char US = 31;
+
     static final String EMPTY = "";
 
     /** The end of stream symbol */

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

@@ -55,11 +55,11 @@ final class Lexer {
     private final boolean ignoreEmptyLines;
 
     /** The input stream */
-    private final ExtendedBufferedReader in;
+    private final ExtendedBufferedReader reader;
 
     /** INTERNAL API. but ctor needs to be called dynamically by PerformanceTest class */
-    Lexer(final CSVFormat format, final ExtendedBufferedReader in) {
-        this.in = in;
+    Lexer(final CSVFormat format, final ExtendedBufferedReader reader) {
+        this.reader = reader;
         this.delimiter = format.getDelimiter();
         this.escape = mapNullToDisabled(format.getEscape());
         this.quoteChar = mapNullToDisabled(format.getQuoteChar());
@@ -82,10 +82,10 @@ final class Lexer {
     Token nextToken(final Token token) throws IOException {
 
         // get the last read char (required for empty line detection)
-        int lastChar = in.getLastChar();
+        int lastChar = reader.getLastChar();
 
         // read the next char and set eol
-        int c = in.read();
+        int c = reader.read();
         /*
          * Note: The following call will swallow LF if c == CR. But we don't need to know if the last char was CR or LF
          * - they are equivalent here.
@@ -97,7 +97,7 @@ Token nextToken(final Token token) throws IOException {
             while (eol && isStartOfLine(lastChar)) {
                 // go on char ahead ...
                 lastChar = c;
-                c = in.read();
+                c = reader.read();
                 eol = readEndOfLine(c);
                 // reached end of file without any content (empty line at the end)
                 if (isEndOfFile(c)) {
@@ -116,7 +116,7 @@ Token nextToken(final Token token) throws IOException {
         }
 
         if (isStartOfLine(lastChar) && isCommentStart(c)) {
-            final String line = in.readLine();
+            final String line = reader.readLine();
             if (line == null) {
                 token.type = EOF;
                 // don't set token.isReady here because no content
@@ -133,7 +133,7 @@ Token nextToken(final Token token) throws IOException {
             // ignore whitespaces at beginning of a token
             if (ignoreSurroundingSpaces) {
                 while (isWhitespace(c) && !eol) {
-                    c = in.read();
+                    c = reader.read();
                     eol = readEndOfLine(c);
                 }
             }
@@ -198,14 +198,14 @@ private Token parseSimpleToken(final Token token, int ch) throws IOException {
             } else if (isEscape(ch)) {
                 final int unescaped = readEscape();
                 if (unescaped == Constants.END_OF_STREAM) { // unexpected char after escape
-                    token.content.append((char) ch).append((char) in.getLastChar());
+                    token.content.append((char) ch).append((char) reader.getLastChar());
                 } else {
                     token.content.append((char) unescaped);
                 }
-                ch = in.read(); // continue
+                ch = reader.read(); // continue
             } else {
                 token.content.append((char) ch);
-                ch = in.read(); // continue
+                ch = reader.read(); // continue
             }
         }
 
@@ -241,24 +241,24 @@ private Token parseEncapsulatedToken(final Token token) throws IOException {
         final long startLineNumber = getCurrentLineNumber();
         int c;
         while (true) {
-            c = in.read();
+            c = reader.read();
 
             if (isEscape(c)) {
                 final int unescaped = readEscape();
                 if (unescaped == Constants.END_OF_STREAM) { // unexpected char after escape
-                    token.content.append((char) c).append((char) in.getLastChar());
+                    token.content.append((char) c).append((char) reader.getLastChar());
                 } else {
                     token.content.append((char) unescaped);
                 }
             } else if (isQuoteChar(c)) {
-                if (isQuoteChar(in.lookAhead())) {
+                if (isQuoteChar(reader.lookAhead())) {
                     // double or escaped encapsulator -> add single encapsulator to token
-                    c = in.read();
+                    c = reader.read();
                     token.content.append((char) c);
                 } else {
                     // token finish mark (encapsulator) reached: ignore whitespace till delimiter
                     while (true) {
-                        c = in.read();
+                        c = reader.read();
                         if (isDelimiter(c)) {
                             token.type = TOKEN;
                             return token;
@@ -297,7 +297,7 @@ private char mapNullToDisabled(final Character c) {
      * @return the current line number
      */
     long getCurrentLineNumber() {
-        return in.getCurrentLineNumber();
+        return reader.getCurrentLineNumber();
     }
 
     // TODO escape handling needs more work
@@ -314,7 +314,7 @@ long getCurrentLineNumber() {
      */
     int readEscape() throws IOException {
         // the escape char has just been read (normally a backslash)
-        final int ch = in.read();
+        final int ch = reader.read();
         switch (ch) {
         case 'r':
             return CR;
@@ -361,15 +361,15 @@ void trimTrailingSpaces(final StringBuilder buffer) {
      */
     boolean readEndOfLine(int ch) throws IOException {
         // check if we have \r\n...
-        if (ch == CR && in.lookAhead() == LF) {
+        if (ch == CR && reader.lookAhead() == LF) {
             // note: does not change ch outside of this method!
-            ch = in.read();
+            ch = reader.read();
         }
         return ch == LF || ch == CR;
     }
 
     boolean isClosed() {
-        return in.isClosed();
+        return reader.isClosed();
     }
 
     /**
@@ -426,6 +426,6 @@ private boolean isMetaChar(final int ch) {
      *             If an I/O error occurs
      */
     void close() throws IOException {
-        in.close();
+        reader.close();
     }
 }

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

@@ -124,6 +124,7 @@ public void testCSVFile() throws Exception {
             final int count = record.size();
             assertEquals(testName, readTestData(), count+":"+parsed);
         }
+        parser.close();
     }
 
     @Test
@@ -167,5 +168,6 @@ public void testCSVUrl() throws Exception {
             final int count = record.size();
             assertEquals(testName, readTestData(), count + ":" + parsed);
         }
+        parser.close();
     }
 }

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

@@ -55,7 +55,7 @@ private static CSVFormat copy(final CSVFormat format) {
     public void testDelimiterSameAsCommentStartThrowsException() {
         CSVFormat.DEFAULT.withDelimiter('!').withCommentStart('!').validate();
     }
-    
+
     @Test(expected = IllegalStateException.class)
     public void testDelimiterSameAsEscapeThrowsException() {
         CSVFormat.DEFAULT.withDelimiter('!').withEscape('!').validate();