URL/Encoding: change query state parsing

See whatwg/encoding#139 for rationale and whatwg/url#386 for the change to the URL Standard. (I found all these resources in part due to @rakuco's work on trying to align Chrome with the earlier iteration of the specification.)
web-platform-tests · May 9, 2018 · 39db988 · 39db988
1 parent 9b96b14
commit 39db988
Show file tree

Hide file tree

Showing 37 changed files with 46 additions and 90 deletions.
diff --git a/encoding/big5-encoder.html b/encoding/big5-encoder.html
@@ -15,17 +15,17 @@
 
  encode("ab", "ab", "very basic")
  // edge cases
- encode("\u9EA6", "&%2340614;", "Highest-pointer BMP character excluded from encoder");
- encode("\uD858\uDE6B", "&%23156267;", "Highest-pointer character excluded from encoder");
+ 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", "&%239731;", "The canonical BMP test character that is not in the index");
- encode("\uD83D\uDCA9", "&%23128169;", "The canonical astral test character that is not in the 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

diff --git a/encoding/gbk-encoder.html b/encoding/gbk-encoder.html
@@ -17,5 +17,5 @@
  encode("\u4E02", "%81@", "character")
  encode("\uE4C6", "%A1@", "PUA")
  encode("\uE4C5", "%FE%FE", "PUA #2")
- encode("\ud83d\udca9", "&%23128169;", "poo")
+ encode("\ud83d\udca9", "%26%23128169%3B", "poo")
 </script>
diff --git a/encoding/iso-2022-jp-encoder.html b/encoding/iso-2022-jp-encoder.html
@@ -15,4 +15,5 @@
  encode("s", "s", "very basic")
  encode("\u00A5\u203Es\\\uFF90\u4F69", "%1B(J\\~s%1B(B\\%1B$B%_PP%1B(B", "basics")
  encode("\x0E\x0F\x1Bx", "%0E%0F%1Bx", "SO/SI ESC")
+ encode("\uFFFD", "%26%2365533%3B", "U+FFFD");
 </script>
diff --git a/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-form-errors-han.html b/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-form-errors-han.html
@@ -170,10 +170,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-form-errors-hangul.html b/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-form-errors-hangul.html
@@ -135,10 +135,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-form-errors-misc.html b/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-form-errors-misc.html
@@ -179,10 +179,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-href-errors-han.html b/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-href-errors-han.html
@@ -21,7 +21,7 @@
         var a = document.createElement("a"); // <a> uses document encoding for URL's query
         a.href = "https://example.com/?" + input;
         result = a.search.substr(1); // remove leading "?"
-        assert_equals(normalizeStr(result), normalizeStr(expected));
+        assert_equals(result, expected);
     }, desc);
 }
 

diff --git a/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-href-errors-hangul.html b/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-href-errors-hangul.html
@@ -21,7 +21,7 @@
         var a = document.createElement("a"); // <a> uses document encoding for URL's query
         a.href = "https://example.com/?" + input;
         result = a.search.substr(1); // remove leading "?"
-        assert_equals(normalizeStr(result), normalizeStr(expected));
+        assert_equals(result, expected);
     }, desc);
 }
 

diff --git a/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-href-errors-misc.html b/encoding/legacy-mb-japanese/euc-jp/eucjp-encode-href-errors-misc.html
@@ -21,7 +21,7 @@
         var a = document.createElement("a"); // <a> uses document encoding for URL's query
         a.href = "https://example.com/?" + input;
         result = a.search.substr(1); // remove leading "?"
-        assert_equals(normalizeStr(result), normalizeStr(expected));
+        assert_equals(result, expected);
     }, desc);
 }
 

diff --git a/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-form-errors-han.html b/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-form-errors-han.html
@@ -170,10 +170,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-form-errors-hangul.html b/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-form-errors-hangul.html
@@ -135,10 +135,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-form-errors-misc.html b/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-form-errors-misc.html
@@ -179,10 +179,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-href-errors-han.html b/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-href-errors-han.html
@@ -21,7 +21,7 @@
         var a = document.createElement("a"); // <a> uses document encoding for URL's query
         a.href = "https://example.com/?" + input;
         result = a.search.substr(1); // remove leading "?"
-        assert_equals(normalizeStr(result), normalizeStr(expected));
+        assert_equals(result, expected);
     }, desc);
 }
 

diff --git a/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-href-errors-hangul.html b/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-href-errors-hangul.html
@@ -21,7 +21,7 @@
         var a = document.createElement("a"); // <a> uses document encoding for URL's query
         a.href = "https://example.com/?" + input;
         result = a.search.substr(1); // remove leading "?"
-        assert_equals(normalizeStr(result), normalizeStr(expected));
+        assert_equals(result, expected);
     }, desc);
 }
 

diff --git a/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-href-errors-misc.html b/encoding/legacy-mb-japanese/iso-2022-jp/iso2022jp-encode-href-errors-misc.html
@@ -21,7 +21,7 @@
         var a = document.createElement("a"); // <a> uses document encoding for URL's query
         a.href = "https://example.com/?" + input;
         result = a.search.substr(1); // remove leading "?"
-        assert_equals(normalizeStr(result), normalizeStr(expected));
+        assert_equals(result, expected);
     }, desc);
 }
 

diff --git a/encoding/legacy-mb-japanese/shift_jis/sjis-encode-form-errors-han.html b/encoding/legacy-mb-japanese/shift_jis/sjis-encode-form-errors-han.html
@@ -165,10 +165,7 @@
     for (var j = 0; j < cplist[i].length; j++) {
       var t = tests[i][j];
       t.step(function() {
-        assert_equals(
-          normalizeStr(results[j]),
-          normalizeStr(cplist[i][j].expected)
-        );
+        assert_equals(results[j], cplist[i][j].expected);
       });
       t.done();
     }

diff --git a/encoding/legacy-mb-japanese/shift_jis/sjis-encode-form-errors-hangul.html b/encoding/legacy-mb-japanese/shift_jis/sjis-encode-form-errors-hangul.html
@@ -135,10 +135,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-japanese/shift_jis/sjis-encode-form-errors-misc.html b/encoding/legacy-mb-japanese/shift_jis/sjis-encode-form-errors-misc.html
@@ -175,10 +175,7 @@
     for (var j = 0; j < cplist[i].length; j++) {
       var t = tests[i][j];
       t.step(function() {
-        assert_equals(
-          normalizeStr(results[j]),
-          normalizeStr(cplist[i][j].expected)
-        );
+        assert_equals(results[j], cplist[i][j].expected);
       });
       t.done();
     }

diff --git a/encoding/legacy-mb-japanese/shift_jis/sjis-encode-href-errors-han.html b/encoding/legacy-mb-japanese/shift_jis/sjis-encode-href-errors-han.html
@@ -21,7 +21,7 @@
 		var a = document.createElement("a"); // <a> uses document encoding for URL's query
 		a.href = "https://example.com/?" + input;
 		result = a.search.substr(1); // remove leading "?"
-		assert_equals(normalizeStr(result), normalizeStr(expected));
+		assert_equals(result, expected);
 	}, desc);
 }
 

diff --git a/encoding/legacy-mb-japanese/shift_jis/sjis-encode-href-errors-hangul.html b/encoding/legacy-mb-japanese/shift_jis/sjis-encode-href-errors-hangul.html
@@ -21,7 +21,7 @@
     var a = document.createElement("a"); // <a> uses document encoding for URL's query
     a.href = "https://example.com/?" + input;
     result = a.search.substr(1); // remove leading "?"
-    assert_equals(normalizeStr(result), normalizeStr(expected));
+    assert_equals(result, expected);
   }, desc);
 }
 

diff --git a/encoding/legacy-mb-japanese/shift_jis/sjis-encode-href-errors-misc.html b/encoding/legacy-mb-japanese/shift_jis/sjis-encode-href-errors-misc.html
@@ -21,7 +21,7 @@
 		var a = document.createElement("a"); // <a> uses document encoding for URL's query
 		a.href = "https://example.com/?" + input;
 		result = a.search.substr(1); // remove leading "?"
-		assert_equals(normalizeStr(result), normalizeStr(expected));
+		assert_equals(result, expected);
 	}, desc);
 }
 

diff --git a/encoding/legacy-mb-korean/euc-kr/euckr-encode-form-errors-han.html b/encoding/legacy-mb-korean/euc-kr/euckr-encode-form-errors-han.html
@@ -166,10 +166,7 @@
     for (var j = 0; j < cplist[i].length; j++) {
       var t = tests[i][j];
       t.step(function() {
-        assert_equals(
-          normalizeStr(results[j]),
-          normalizeStr(cplist[i][j].expected)
-        );
+        assert_equals(results[j], cplist[i][j].expected);
       });
       t.done();
     }

diff --git a/encoding/legacy-mb-korean/euc-kr/euckr-encode-form-errors-misc.html b/encoding/legacy-mb-korean/euc-kr/euckr-encode-form-errors-misc.html
@@ -175,10 +175,7 @@
     for (var j = 0; j < cplist[i].length; j++) {
       var t = tests[i][j];
       t.step(function() {
-        assert_equals(
-          normalizeStr(results[j]),
-          normalizeStr(cplist[i][j].expected)
-        );
+        assert_equals(results[j], cplist[i][j].expected);
       });
       t.done();
     }

diff --git a/encoding/legacy-mb-korean/euc-kr/euckr-encode-href-errors-han.html b/encoding/legacy-mb-korean/euc-kr/euckr-encode-href-errors-han.html
@@ -21,7 +21,7 @@
 		var a = document.createElement("a"); // <a> uses document encoding for URL's query
 		a.href = "https://example.com/?" + input;
 		result = a.search.substr(1); // remove leading "?"
-		assert_equals(normalizeStr(result), normalizeStr(expected));
+		assert_equals(result, expected);
 	}, desc);
 }
 

diff --git a/encoding/legacy-mb-korean/euc-kr/euckr-encode-href-errors-misc.html b/encoding/legacy-mb-korean/euc-kr/euckr-encode-href-errors-misc.html
@@ -21,7 +21,7 @@
 		var a = document.createElement("a"); // <a> uses document encoding for URL's query
 		a.href = "https://example.com/?" + input;
 		result = a.search.substr(1); // remove leading "?"
-		assert_equals(normalizeStr(result), normalizeStr(expected));
+		assert_equals(result, expected);
 	}, desc);
 }
 

diff --git a/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-extBa.html b/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-extBa.html
@@ -136,10 +136,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-extBb.html b/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-extBb.html
@@ -136,10 +136,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-han.html b/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-han.html
@@ -178,10 +178,7 @@
     for (var j = 0; j < cplist[i].length; j++) {
       var t = tests[i][j];
       t.step(function() {
-        assert_equals(
-          normalizeStr(results[j]),
-          normalizeStr(cplist[i][j].expected)
-        );
+        assert_equals(results[j], cplist[i][j].expected);
       });
       t.done();
     }

diff --git a/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-hangul.html b/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-hangul.html
@@ -135,10 +135,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-misc.html b/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-misc.html
@@ -175,10 +175,7 @@
     for (var j = 0; j < cplist[i].length; j++) {
       var t = tests[i][j];
       t.step(function() {
-        assert_equals(
-          normalizeStr(results[j]),
-          normalizeStr(cplist[i][j].expected)
-        );
+        assert_equals(results[j], cplist[i][j].expected);
       });
       t.done();
     }

diff --git a/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-pua.html b/encoding/legacy-mb-tchinese/big5/big5-encode-form-errors-pua.html
@@ -135,10 +135,7 @@
         for (var j = 0; j < cplist[i].length; j++) {
             var t = tests[i][j];
             t.step(function() {
-                assert_equals(
-                    normalizeStr(results[j]),
-                    normalizeStr(cplist[i][j].expected)
-                );
+                assert_equals(results[j], cplist[i][j].expected);
             });
             t.done();
         }

diff --git a/encoding/legacy-mb-tchinese/big5/big5-encode-href-errors-han.html b/encoding/legacy-mb-tchinese/big5/big5-encode-href-errors-han.html
@@ -21,7 +21,7 @@
 		var a = document.createElement("a"); // <a> uses document encoding for URL's query
 		a.href = "https://example.com/?" + input;
 		result = a.search.substr(1); // remove leading "?"
-		assert_equals(normalizeStr(result), normalizeStr(expected));
+		assert_equals(result, expected);
 	}, desc);
 }
 

diff --git a/encoding/legacy-mb-tchinese/big5/big5-encode-href-errors-hangul.html b/encoding/legacy-mb-tchinese/big5/big5-encode-href-errors-hangul.html
@@ -21,7 +21,7 @@
     var a = document.createElement("a"); // <a> uses document encoding for URL's query
     a.href = "https://example.com/?" + input;
     result = a.search.substr(1); // remove leading "?"
-    assert_equals(normalizeStr(result), normalizeStr(expected));
+    assert_equals(result, expected);
   }, desc);
 }
 

diff --git a/encoding/legacy-mb-tchinese/big5/big5-encode-href-errors-misc.html b/encoding/legacy-mb-tchinese/big5/big5-encode-href-errors-misc.html
@@ -21,7 +21,7 @@
 		var a = document.createElement("a"); // <a> uses document encoding for URL's query
 		a.href = "https://example.com/?" + input;
 		result = a.search.substr(1); // remove leading "?"
-		assert_equals(normalizeStr(result), normalizeStr(expected));
+		assert_equals(result, expected);
 	}, desc);
 }
 

diff --git a/html/infrastructure/urls/resolving-urls/query-encoding/resources/resolve-url.js b/html/infrastructure/urls/resolving-urls/query-encoding/resources/resolve-url.js
@@ -14,7 +14,7 @@ onload = function() {
     'utf-16be':'%C3%A5',
     'utf-16le':'%C3%A5',
     'windows-1252':'%E5',
-    'windows-1251':'&%23229;'
+    'windows-1251':'%26%23229%3B'
   };
   var expected_current = expected_obj[encoding];
   var expected_utf8 = expected_obj['utf-8'];

diff --git a/url/README.md b/url/README.md
@@ -1,3 +1,5 @@
+## urltestdata.json
+
 These tests are for browsers, but the data for
 `a-element.html`, `url-constructor.html`, and `a-element-xhtml.xhtml`
 is in `urltestdata.json` and can be re-used by non-browser implementations.
@@ -19,5 +21,10 @@ The keys for each test case are:
     The `origin` key may be missing.
     In that case, the API’s `origin` attribute is not tested.
 
+## URL parser's encoding argument
+
+Tests in `/encoding` and `/html/infrastructure/urls/resolving-urls/query-encoding/` cover the
+encoding argument to the URL parser.
+
 [parsing]: https://url.spec.whatwg.org/#concept-basic-url-parser
 [API]: https://url.spec.whatwg.org/#api