Changeset 198866 in webkit

Timestamp:

Mar 30, 2016 5:38:20 PM (8 years ago)

Author:

msaboff@apple.com

Message:

[ES6] Quantified unicode regular expressions do not work for counts greater than 1
​https://bugs.webkit.org/show_bug.cgi?id=156044

Reviewed by Mark Lam.

Source/JavaScriptCore:

Fixed incorrect indexing of non-BMP characters in fixed patterns. The old code
was indexing by character units, a single JS character, instead of code points
which is 2 JS characters.

• yarr/YarrInterpreter.cpp:

(JSC::Yarr::Interpreter::matchDisjunction):

LayoutTests:

Added new test cases.

• js/regexp-unicode-expected.txt:
• js/script-tests/regexp-unicode.js:

Location:

trunk

Files:

• LayoutTests/ChangeLog (modified) (1 diff)
• LayoutTests/js/regexp-unicode-expected.txt (modified) (1 diff)
• LayoutTests/js/script-tests/regexp-unicode.js (modified) (1 diff)
• Source/JavaScriptCore/ChangeLog (modified) (1 diff)
• Source/JavaScriptCore/yarr/YarrInterpreter.cpp (modified) (1 diff)

trunk/LayoutTests/ChangeLog

@@ +1 @@
+2016-03-30  Michael Saboff  <msaboff@apple.com>
+
+        [ES6] Quantified unicode regular expressions do not work for counts greater than 1
+        https://bugs.webkit.org/show_bug.cgi?id=156044
+
+        Reviewed by Mark Lam.
+
+        Added new test cases.
+
+        * js/regexp-unicode-expected.txt:
+        * js/script-tests/regexp-unicode.js:
+
 2016-03-30  Myles C. Maxfield  <mmaxfield@apple.com>
 

trunk/LayoutTests/js/regexp-unicode-expected.txt

@@ -58 +58 @@
 PASS re2.test("￿") is false
 PASS re2.test("𒍅") is true
+PASS /𝌆{2}/u.test("𝌆𝌆") is true
+PASS /𝌆{2}/u.test("𝌆𝌆") is true
+PASS "𐐁𐐁𐐀".match(/𐐁{1,3}/u)[0] is "𐐁𐐁"
+PASS "𐐁𐐩".match(/𐐁{1,3}/iu)[0] is "𐐁𐐩"
+PASS "𐐁𐐩𐐪𐐩".match(/𐐁{1,}/iu)[0] is "𐐁𐐩"
 PASS "𐌑𐌑𐌑".match(/𐌑*a|𐌑*./u)[0] is "𐌑𐌑𐌑"
 PASS "a𐌑𐌑".match(/a𐌑*?$/u)[0] is "a𐌑𐌑"

trunk/LayoutTests/js/script-tests/regexp-unicode.js

@@ -93 +93 @@
 // shouldBe('"\uD803\u{10c01}".match(/\uD803\u{10c01}/u)[0].length', '3');
 
+// Check quantified matches
+shouldBeTrue('/\u{1d306}{2}/u.test("\u{1d306}\u{1d306}")');
+shouldBeTrue('/\uD834\uDF06{2}/u.test("\uD834\uDF06\uD834\uDF06")');
+shouldBe('"\u{10401}\u{10401}\u{10400}".match(/\u{10401}{1,3}/u)[0]', '"\u{10401}\u{10401}"');
+shouldBe('"\u{10401}\u{10429}".match(/\u{10401}{1,3}/iu)[0]', '"\u{10401}\u{10429}"');
+shouldBe('"\u{10401}\u{10429}\u{1042a}\u{10429}".match(/\u{10401}{1,}/iu)[0]', '"\u{10401}\u{10429}"');
+
 // Check back tracking on partial matches
 shouldBe('"\u{10311}\u{10311}\u{10311}".match(/\u{10311}*a|\u{10311}*./u)[0]', '"\u{10311}\u{10311}\u{10311}"');

trunk/Source/JavaScriptCore/ChangeLog

@@ +1 @@
+2016-03-30  Michael Saboff  <msaboff@apple.com>
+
+        [ES6] Quantified unicode regular expressions do not work for counts greater than 1
+        https://bugs.webkit.org/show_bug.cgi?id=156044
+
+        Reviewed by Mark Lam.
+
+        Fixed incorrect indexing of non-BMP characters in fixed patterns.  The old code
+        was indexing by character units, a single JS character, instead of code points
+        which is 2 JS characters.
+
+        * yarr/YarrInterpreter.cpp:
+        (JSC::Yarr::Interpreter::matchDisjunction):
+
 2016-03-30  Mark Lam  <mark.lam@apple.com>
 

trunk/Source/JavaScriptCore/yarr/YarrInterpreter.cpp

@@ -1225 +1225 @@
                 if (!U_IS_BMP(currentTerm().atom.patternCharacter)) {
                     for (unsigned matchAmount = 0; matchAmount < currentTerm().atom.quantityCount; ++matchAmount) {
-                        if (!checkSurrogatePair(currentTerm().atom.patternCharacter, currentTerm().inputPosition - matchAmount)) {
+                        if (!checkSurrogatePair(currentTerm().atom.patternCharacter, currentTerm().inputPosition - 2 * matchAmount)) {
                             BACKTRACK();
                         }