summaryrefslogtreecommitdiffstats
path: root/testing/web-platform/tests/encoding/big5-encoder.html
diff options
context:
space:
mode:
Diffstat (limited to 'testing/web-platform/tests/encoding/big5-encoder.html')
-rw-r--r--testing/web-platform/tests/encoding/big5-encoder.html33
1 files changed, 33 insertions, 0 deletions
diff --git a/testing/web-platform/tests/encoding/big5-encoder.html b/testing/web-platform/tests/encoding/big5-encoder.html
new file mode 100644
index 000000000..7260b6b15
--- /dev/null
+++ b/testing/web-platform/tests/encoding/big5-encoder.html
@@ -0,0 +1,33 @@
+<!doctype html>
+<meta charset=big5> <!-- test breaks if the server overrides this -->
+<script src=/resources/testharness.js></script>
+<script src=/resources/testharnessreport.js></script>
+<div id=log></div>
+<script>
+ function encode(input, output, desc) {
+ test(function() {
+ var a = document.createElement("a"); // <a> uses document encoding for URL's query
+ // Append and prepend X to test for off-by-one errors
+ a.href = "https://example.com/?X" + input + "X";
+ assert_equals(a.search.substr(1), "X" + output + "X"); // remove leading "?"
+ }, "big5 encoder: " + desc);
+ }
+
+ encode("ab", "ab", "very basic")
+ // edge cases
+ encode("\u9EA6", "%26%2340614%3B", "Highest-pointer BMP character excluded from encoder");
+ encode("\uD858\uDE6B", "%26%23156267%3B", "Highest-pointer character excluded from encoder");
+ encode("\u3000", "%A1@", "Lowest-pointer character included in encoder");
+ encode("\u20AC", "%A3%E1", "Euro; the highest-pointer character before a range of 30 unmapped pointers");
+ encode("\u4E00", "%A4@", "The lowest-pointer character after the range of 30 unmapped pointers");
+ encode("\uD85D\uDE07", "%C8%A4", "The highest-pointer character before a range of 41 unmapped pointers");
+ encode("\uFFE2", "%C8%CD", "The lowest-pointer character after the range of 41 unmapped pointers");
+ encode("\u79D4", "%FE%FE", "The last character in the index");
+ // not in index
+ encode("\u2603", "%26%239731%3B", "The canonical BMP test character that is not in the index");
+ encode("\uD83D\uDCA9", "%26%23128169%3B", "The canonical astral test character that is not in the index");
+ // duplicate low bits
+ encode("\uD840\uDFB5", "%FDj", "A Plane 2 character whose low 16 bits match a BMP character that has a lower pointer");
+ // prefer last
+ encode("\u2550", "%F9%F9", "A duplicate-mapped code point that prefers the highest pointer in the encoder");
+</script>