Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(1057)

Unified Diff: tests/lib/convert/utf82_test.dart

Issue 19187002: Replace old utf8 decoder with new one. (Closed) Base URL: https://dart.googlecode.com/svn/branches/bleeding_edge/dart
Patch Set: Address comments. Created 7 years, 5 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « sdk/lib/convert/utf.dart ('k') | tests/lib/convert/utf83_test.dart » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: tests/lib/convert/utf82_test.dart
diff --git a/tests/lib/convert/utf82_test.dart b/tests/lib/convert/utf82_test.dart
new file mode 100644
index 0000000000000000000000000000000000000000..f972803f21eed0af85d899e55cf5ac3e871723c0
--- /dev/null
+++ b/tests/lib/convert/utf82_test.dart
@@ -0,0 +1,135 @@
+// Copyright (c) 2012, the Dart project authors. Please see the AUTHORS file
+// for details. All rights reserved. Use of this source code is governed by a
+// BSD-style license that can be found in the LICENSE file.
+
+library utf8_test;
+import "package:expect/expect.dart";
+import 'dart:convert';
+import 'dart:codec';
+
+String decode(List<int> bytes) => new Utf8Decoder().convert(bytes);
+String decodeAllowMalformed(List<int> bytes) {
+ return new Utf8Decoder(allowMalformed: true).convert(bytes);
+}
+
+String decode2(List<int> bytes) => UTF8.decode(bytes);
+String decodeAllowMalformed2(List<int> bytes) {
+ return UTF8.decode(bytes, allowMalformed: true);
+}
+
+String decode3(List<int> bytes) => new Utf8Codec().decode(bytes);
+String decodeAllowMalformed3(List<int> bytes) {
+ return new Utf8Codec(allowMalformed: true).decode(bytes);
+}
+
+String decode4(List<int> bytes) => new Utf8Codec().decoder.convert(bytes);
+String decodeAllowMalformed4(List<int> bytes) {
+ return new Utf8Codec(allowMalformed: true).decoder.convert(bytes);
+}
+
+final TESTS = [
+ // Unfinished UTF-8 sequences.
+ [ 0xc3 ],
+ [ 0xE2, 0x82 ],
+ [ 0xF0, 0xA4, 0xAD ],
+ // Overlong encoding of euro-sign.
+ [ 0xF0, 0x82, 0x82, 0xAC ],
+ // Other overlong/unfinished sequences.
+ [ 0xC0 ],
+ [ 0xC1 ],
+ [ 0xF5 ],
+ [ 0xF6 ],
+ [ 0xF7 ],
+ [ 0xF8 ],
+ [ 0xF9 ],
+ [ 0xFA ],
+ [ 0xFB ],
+ [ 0xFC ],
+ [ 0xFD ],
+ [ 0xFE ],
+ [ 0xFF ],
+ [ 0xC0, 0x80 ],
+ [ 0xC1, 0x80 ],
+ // Outside valid range.
+ [ 0xF4, 0xBF, 0xBF, 0xBF ]];
+
+final TESTS2 = [
+ // Test that 0xC0|1, 0x80 does not eat the next character.
+ [[ 0xC0, 0x80, 0x61 ], "Xa" ],
+ [[ 0xC1, 0x80, 0x61 ], "Xa" ],
+ // 0xF5 .. 0xFF never appear in valid UTF-8 sequences.
+ [[ 0xF5, 0x80 ], "XX" ],
+ [[ 0xF6, 0x80 ], "XX" ],
+ [[ 0xF7, 0x80 ], "XX" ],
+ [[ 0xF8, 0x80 ], "XX" ],
+ [[ 0xF9, 0x80 ], "XX" ],
+ [[ 0xFA, 0x80 ], "XX" ],
+ [[ 0xFB, 0x80 ], "XX" ],
+ [[ 0xFC, 0x80 ], "XX" ],
+ [[ 0xFD, 0x80 ], "XX" ],
+ [[ 0xFE, 0x80 ], "XX" ],
+ [[ 0xFF, 0x80 ], "XX" ],
+ [[ 0xF5, 0x80, 0x61 ], "XXa" ],
+ [[ 0xF6, 0x80, 0x61 ], "XXa" ],
+ [[ 0xF7, 0x80, 0x61 ], "XXa" ],
+ [[ 0xF8, 0x80, 0x61 ], "XXa" ],
+ [[ 0xF9, 0x80, 0x61 ], "XXa" ],
+ [[ 0xFA, 0x80, 0x61 ], "XXa" ],
+ [[ 0xFB, 0x80, 0x61 ], "XXa" ],
+ [[ 0xFC, 0x80, 0x61 ], "XXa" ],
+ [[ 0xFD, 0x80, 0x61 ], "XXa" ],
+ [[ 0xFE, 0x80, 0x61 ], "XXa" ],
+ [[ 0xFF, 0x80, 0x61 ], "XXa" ],
+ // Characters outside the valid range.
+ [[ 0xF5, 0x80, 0x80, 0x61 ], "XXXa" ],
+ [[ 0xF6, 0x80, 0x80, 0x61 ], "XXXa" ],
+ [[ 0xF7, 0x80, 0x80, 0x61 ], "XXXa" ],
+ [[ 0xF8, 0x80, 0x80, 0x61 ], "XXXa" ],
+ [[ 0xF9, 0x80, 0x80, 0x61 ], "XXXa" ],
+ [[ 0xFA, 0x80, 0x80, 0x61 ], "XXXa" ],
+ [[ 0xFB, 0x80, 0x80, 0x61 ], "XXXa" ],
+ [[ 0xFC, 0x80, 0x80, 0x61 ], "XXXa" ],
+ [[ 0xFD, 0x80, 0x80, 0x61 ], "XXXa" ],
+ [[ 0xFE, 0x80, 0x80, 0x61 ], "XXXa" ],
+ [[ 0xFF, 0x80, 0x80, 0x61 ], "XXXa" ]];
+
+main() {
+ var allTests = TESTS.expand((test) {
+ // Pairs of test and expected string output when malformed strings are
+ // allowed. Replacement character: U+FFFD
+ return [[ test, "\u{FFFD}" ],
+ [ new List.from([0x61])..addAll(test), "a\u{FFFD}" ],
+ [ new List.from([0x61])..addAll(test)..add(0x61), "a\u{FFFD}a" ],
+ [ new List.from(test)..add(0x61), "\u{FFFD}a" ],
+ [ new List.from(test)..addAll(test), "\u{FFFD}\u{FFFD}" ],
+ [ new List.from(test)..add(0x61)..addAll(test),
+ "\u{FFFD}a\u{FFFD}" ],
+ [ new List.from([0xc3, 0xa5])..addAll(test), "å\u{FFFD}" ],
+ [ new List.from([0xc3, 0xa5])..addAll(test)..addAll([0xc3, 0xa5]),
+ "å\u{FFFD}å" ],
+ [ new List.from(test)..addAll([0xc3, 0xa5]), "\u{FFFD}å" ],
+ [ new List.from(test)..addAll([0xc3, 0xa5])..addAll(test),
+ "\u{FFFD}å\u{FFFD}" ]];
+ });
+
+ var allTests2 = TESTS2.map((test) {
+ // Pairs of test and expected string output when malformed strings are
+ // allowed. Replacement character: U+FFFD
+ String expected = test[1].replaceAll("X", "\u{FFFD}");
+ return [test[0], expected];
+ });
+
+ for (var test in []..addAll(allTests)..addAll(allTests2)) {
+ List<int> bytes = test[0];
+ Expect.throws(() => decode(bytes), (e) => e is FormatException);
+ Expect.throws(() => decode2(bytes), (e) => e is FormatException);
+ Expect.throws(() => decode3(bytes), (e) => e is FormatException);
+ Expect.throws(() => decode4(bytes), (e) => e is FormatException);
+
+ String expected = test[1];
+ Expect.equals(expected, decodeAllowMalformed(bytes));
+ Expect.equals(expected, decodeAllowMalformed2(bytes));
+ Expect.equals(expected, decodeAllowMalformed3(bytes));
+ Expect.equals(expected, decodeAllowMalformed4(bytes));
+ }
+}
« no previous file with comments | « sdk/lib/convert/utf.dart ('k') | tests/lib/convert/utf83_test.dart » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698