8028321: Fix for String.split() empty input sequence/JDK-6559590 triggers regression
Summary: to undo the change for 6559590
Reviewed-by: darcy
--- a/jdk/src/share/classes/java/lang/String.java Wed Nov 13 15:48:21 2013 -0500
+++ b/jdk/src/share/classes/java/lang/String.java Wed Nov 13 22:22:28 2013 -0800
@@ -2235,8 +2235,7 @@
* expression or is terminated by the end of the string. The substrings in
* the array are in the order in which they occur in this string. If the
* expression does not match any part of the input then the resulting array
- * has just one element, namely this string. A zero-length input sequence
- * always results zero-length resulting array.
+ * has just one element, namely this string.
*
* <p> When there is a positive-width match at the beginning of this
* string then an empty leading substring is included at the beginning
@@ -2331,8 +2330,6 @@
(ch < Character.MIN_HIGH_SURROGATE ||
ch > Character.MAX_LOW_SURROGATE))
{
- if (value.length == 0)
- return new String[0];
int off = 0;
int next = 0;
boolean limited = limit > 0;
--- a/jdk/src/share/classes/java/util/regex/Pattern.java Wed Nov 13 15:48:21 2013 -0500
+++ b/jdk/src/share/classes/java/util/regex/Pattern.java Wed Nov 13 22:22:28 2013 -0800
@@ -1144,8 +1144,7 @@
* substrings in the array are in the order in which they occur in the
* input. If this pattern does not match any subsequence of the input then
* the resulting array has just one element, namely the input sequence in
- * string form. A zero-length input sequence always results zero-length
- * resulting array.
+ * string form.
*
* <p> When there is a positive-width match at the beginning of the input
* sequence then an empty leading substring is included at the beginning
@@ -1201,8 +1200,6 @@
* around matches of this pattern
*/
public String[] split(CharSequence input, int limit) {
- if (input.length() == 0)
- return new String[0];
int index = 0;
boolean matchLimited = limit > 0;
ArrayList<String> matchList = new ArrayList<>();
@@ -5767,15 +5764,13 @@
* input sequence that is terminated by another subsequence that matches
* this pattern or is terminated by the end of the input sequence. The
* substrings in the stream are in the order in which they occur in the
- * input. Trailing empty strings will be discarded and not encountered in
+ * input. Trailing empty strings will be discarded and not encountered in
* the stream.
*
* <p> If this pattern does not match any subsequence of the input then
* the resulting stream has just one element, namely the input sequence in
* string form.
*
- * <p> A zero-length input sequence always results an empty stream.
- *
* <p> When there is a positive-width match at the beginning of the input
* sequence then an empty leading substring is included at the beginning
* of the stream. A zero-width match at the beginning however never produces
--- a/jdk/test/java/lang/String/Split.java Wed Nov 13 15:48:21 2013 -0500
+++ b/jdk/test/java/lang/String/Split.java Wed Nov 13 22:22:28 2013 -0800
@@ -81,8 +81,10 @@
// split() now returns 0-length for empty source "" see #6559590
source = "";
String[] result = source.split("e", 0);
- if (result.length != 0)
+ if (result.length != 1)
throw new RuntimeException("String.split failure 8");
+ if (!result[0].equals(source))
+ throw new RuntimeException("String.split failure 9");
// check fastpath of String.split()
source = "0123456789abcdefgABCDEFG";
--- a/jdk/test/java/util/regex/RegExTest.java Wed Nov 13 15:48:21 2013 -0500
+++ b/jdk/test/java/util/regex/RegExTest.java Wed Nov 13 22:22:28 2013 -0800
@@ -1781,7 +1781,9 @@
// split() now returns 0-length for empty source "" see #6559590
source = "";
result = source.split("e", 0);
- if (result.length != 0)
+ if (result.length != 1)
+ failCount++;
+ if (!result[0].equals(source))
failCount++;
// Check both split() and splitAsStraem(), especially for zero-lenth
@@ -1817,8 +1819,8 @@
{ "Abc", "Efg", "Hij" },
{ "Abc", "Efg" },
{ "Abc" },
- {},
- {},
+ { "" },
+ { "" },
{ "awgqwefg1fefw", "vssv1vvv1" },
{ "afbfq", "bgwgb", "wngnwggw", "", "hjrnhneerh" },
@@ -1826,7 +1828,7 @@
{ "a\u4ebafg", "fefw\u4eba4\u9f9cvssv\u9f9c", "v\u672c\u672cvv" },
{ "1", "23", "456", "7890" },
{ "1", "23\u9f9c\u672c\u672c", "456", "\u9f9c\u672c7890" },
- {},
+ { "" },
{ "This", "is", "testing", "", "with", "different", "separators" },
{ "b", "", ":and:f" },
{ "b", "", "", "", "", ":and:f" },
@@ -1834,11 +1836,15 @@
};
for (int i = 0; i < input.length; i++) {
pattern = Pattern.compile(input[i][0]);
- if (!Arrays.equals(pattern.split(input[i][1]), expected[i]))
+ if (!Arrays.equals(pattern.split(input[i][1]), expected[i])) {
failCount++;
- if (!Arrays.equals(pattern.splitAsStream(input[i][1]).toArray(),
- expected[i]))
+ }
+ if (input[i][1].length() > 0 && // splitAsStream() return empty resulting
+ // array for zero-length input for now
+ !Arrays.equals(pattern.splitAsStream(input[i][1]).toArray(),
+ expected[i])) {
failCount++;
+ }
}
report("Split");
}