Merge pull request #629 from rootvector2/quote-null-starting-record

Quote null value that starts a record in minimal quote mode

Author: garydgregory

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

@@ -2134,6 +2134,15 @@ public boolean isEscapeCharacterSet() {
         return escapeCharacter != null;
     }
 
+    /**
+     * Tests whether the quote policy encapsulates values only when needed, which is also the policy when none is set.
+     *
+     * @return {@code true} if the {@link QuoteMode} is {@link QuoteMode#MINIMAL} or unset.
+     */
+    private boolean isMinimalQuoteMode() {
+        return quoteMode == null || quoteMode == QuoteMode.MINIMAL;
+    }
+
     /**
      * Tests whether a null string has been defined.
      *
@@ -2272,7 +2281,17 @@ private void print(final Object object, final CharSequence value, final Appendab
                 out.append(getDelimiterString());
             }
             if (object == null) {
-                out.append(value);
+                if (len == 0 && newRecord && isQuoteCharacterSet() && isMinimalQuoteMode()) {
+                    // Encapsulate like printWithQuotes does for an empty value that starts a record: an
+                    // unquoted one makes the whole line empty, and a parser with ignoreEmptyLines enabled
+                    // then drops the record. ALL, ALL_NON_NULL, and NON_NUMERIC are excluded because they
+                    // encode null as the bare empty field, distinct from a quoted empty string (CSV-203).
+                    final char quoteChar = quoteCharacter.charValue(); // Explicit unboxing is intentional
+                    out.append(quoteChar);
+                    out.append(quoteChar);
+                } else {
+                    out.append(value);
+                }
             } else if (isQuoteCharacterSet()) {
                 // The original object is needed so can check for Number
                 printWithQuotes(object, value, out, newRecord);

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

@@ -1557,7 +1557,7 @@ void testWithHeaderComments() {
         assertNotEquals(csvFormat, csvFormatTwo); // CSV-244 - should not be equal
 
         assertNotEquals(csvFormatTwo, csvFormat); // CSV-244 - should not be equal
-        assertEquals(",,,,,,,", string);
+        assertEquals("\"\",,,,,,,", string);
 
     }
 

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

@@ -188,6 +188,14 @@ private Connection getH2Connection() throws SQLException, ClassNotFoundException
         return DriverManager.getConnection("jdbc:h2:mem:my_test;", "sa", "");
     }
 
+    private String printNullRecord(final CSVFormat format) throws IOException {
+        final StringWriter sw = new StringWriter();
+        try (CSVPrinter printer = new CSVPrinter(sw, format)) {
+            printer.printRecord((Object) null);
+        }
+        return sw.toString();
+    }
+
     private CSVPrinter printWithHeaderComments(final StringWriter sw, final Date now, final CSVFormat baseFormat) throws IOException {
         // Use withHeaderComments first to test CSV-145
         // @formatter:off
@@ -1721,6 +1729,31 @@ void testPrinter7() throws IOException {
         }
     }
 
+    @Test
+    void testPrintNullValueStartingRecord() throws IOException {
+        final StringWriter sw = new StringWriter();
+        try (CSVPrinter printer = new CSVPrinter(sw, CSVFormat.DEFAULT)) {
+            printer.printRecord("a");
+            printer.printRecord((Object) null);
+            printer.printRecord("b");
+        }
+        final String csv = sw.toString();
+        assertEquals("a" + RECORD_SEPARATOR + "\"\"" + RECORD_SEPARATOR + "b" + RECORD_SEPARATOR, csv);
+        try (CSVParser parser = CSVParser.parse(csv, CSVFormat.DEFAULT)) {
+            final List<CSVRecord> records = parser.getRecords();
+            assertEquals(3, records.size());
+            assertArrayEquals(new String[] { "" }, records.get(1).values());
+        }
+        // An explicit MINIMAL quote mode encapsulates it too.
+        assertEquals("\"\"" + RECORD_SEPARATOR, printNullRecord(CSVFormat.DEFAULT.builder().setQuoteMode(QuoteMode.MINIMAL).get()));
+        // ALL encodes null as the bare empty field, distinct from a quoted empty string (CSV-203).
+        assertEquals(RECORD_SEPARATOR, printNullRecord(CSVFormat.DEFAULT.builder().setQuoteMode(QuoteMode.ALL).get()));
+        // ALL_NON_NULL encodes null as the bare empty field, so it must stay unquoted.
+        assertEquals(RECORD_SEPARATOR, printNullRecord(CSVFormat.DEFAULT.builder().setQuoteMode(QuoteMode.ALL_NON_NULL).get()));
+        // Without a quote character there is nothing to encapsulate with.
+        assertEquals(RECORD_SEPARATOR, printNullRecord(CSVFormat.DEFAULT.builder().setQuote(null).get()));
+    }
+
     @Test
     void testPrintNullValues() throws IOException {
         final StringWriter sw = new StringWriter();
@@ -1854,8 +1887,9 @@ void testPrintRecordsWithObjectArray() throws IOException {
             printer.printRecords(objectArray);
             assertEquals(objectArray.length, printer.getRecordCount());
         }
-        assertEquals(6, charArrayWriter.size());
-        assertEquals("\n\n\n\n\n\n", charArrayWriter.toString());
+        final String expected = "\"\"\n\"\"\n\"\"\n\n\"\"\n\"\"\n";
+        assertEquals(expected.length(), charArrayWriter.size());
+        assertEquals(expected, charArrayWriter.toString());
     }
 
     @Test