[CSV-219] The behavior of quote char using is not similar as Excel does

garydgregory · garydgregory · commit 8b3de71fd99d · 2017-12-11T11:16:01.000-07:00
when the first string contains CJK char(s).
[CSV-172] Don't quote cells just because they have UTF-8 encoded
characters.
diff --git a/src/changes/changes.xml b/src/changes/changes.xml
@@ -40,6 +40,8 @@
   <body>
     <release version="1.6" date="2017-MM-DD" description="Feature and bug fix release">
       <action issue="CSV-217" type="add" dev="ggregory" due-to="Korolyov Alexei">Add autoFlush option for CsvPrinter. PR #24.</action>
+      <action issue="CSV-219" type="fix" dev="ggregory" due-to="Zhang Hongda">The behavior of quote char using is not similar as Excel does when the first string contains CJK char(s).</action>
+      <action issue="CSV-172" type="fix" dev="ggregory" due-to="Andrew Pennebaker">Don't quote cells just because they have UTF-8 encoded characters.</action>
     </release>
     <release version="1.5" date="2017-09-03" description="Feature and bug fix release">
       <action issue="CSV-203" type="fix" dev="ggregory" due-to="Richard Wheeldon, Kai Paroth">withNullString value is printed without quotes when QuoteMode.ALL is specified; add QuoteMode.ALL_NON_NULL. PR #17.</action>
diff --git a/src/main/java/org/apache/commons/csv/CSVFormat.java b/src/main/java/org/apache/commons/csv/CSVFormat.java
@@ -1186,10 +1186,7 @@ private void printAndQuote(final Object object, final CharSequence value, final
             } else {
                 char c = value.charAt(pos);
 
-                // RFC4180 (https://tools.ietf.org/html/rfc4180) TEXTDATA =  %x20-21 / %x23-2B / %x2D-7E
-                if (newRecord && (c < 0x20 || c > 0x21 && c < 0x23 || c > 0x2B && c < 0x2D || c > 0x7E)) {
-                    quote = true;
-                } else if (c <= COMMENT) {
+                if (c <= COMMENT) {
                     // Some other chars at the start of a value caused the parser to fail, so for now
                     // encapsulate if we start in anything less than '#'. We are being conservative
                     // by including the default comment char too.
diff --git a/src/test/java/org/apache/commons/csv/CSVPrinterTest.java b/src/test/java/org/apache/commons/csv/CSVPrinterTest.java
@@ -1033,11 +1033,20 @@ public void testPrinter1() throws IOException {
     }
 
     @Test
-    public void testRfc4180QuoteSingleChar() throws IOException {
+    public void testDontQuoteEuroFirstChar() throws IOException {
         final StringWriter sw = new StringWriter();
         try (final CSVPrinter printer = new CSVPrinter(sw, CSVFormat.RFC4180)) {
             printer.printRecord(EURO_CH, "Deux");
-            assertEquals("\"" + EURO_CH + "\",Deux" + recordSeparator, sw.toString());
+            assertEquals(EURO_CH + ",Deux" + recordSeparator, sw.toString());
+        }
+    }
+
+    @Test
+    public void testQuoteCommaFirstChar() throws IOException {
+        final StringWriter sw = new StringWriter();
+        try (final CSVPrinter printer = new CSVPrinter(sw, CSVFormat.RFC4180)) {
+            printer.printRecord(",");
+            assertEquals("\",\"" + recordSeparator, sw.toString());
         }
     }
 
