Fix ECMA 262 regex whitespace tests.

ChALkeR · ChALkeR · commit 1bc0adecde53 · 2020-05-30T10:26:47.000+03:00
Looks like there was a bug at the time of introduction due to #285 Per ECMA 262 specification: https://www.ecma-international.org/ecma-262/10.0/index.html#sec-characterclassescape `\S` refers to `\s`: > # Section 21.2.2.12: > The production `CharacterClassEscape::S` evaluates as follows: > 1. Return the set of all characters not included in the set returned > by `CharacterClassEscape::s`. `\s` refers to `WhiteSpace`: > The production `CharacterClassEscape::s` evaluates as follows: > 1. Return the set of characters containing the characters that are on > the right-hand side of the WhiteSpace or LineTerminator > productions. `WhiteSpace` includes NBSP (**U00A0**): https://www.ecma-international.org/ecma-262/10.0/index.html#prod-WhiteSpace That is the exact opposite of what the current test was checking for. Also, `WhiteSpace` includes any other Unicode "Space_Separator" code points. That's not a new addition, same was true in version 6.0: * https://www.ecma-international.org/ecma-262/6.0/index.html#sec-characterclassescape * https://www.ecma-international.org/ecma-262/6.0/index.html#sec-white-space
diff --git a/tests/draft2019-09/optional/format/ecmascript-regex.json b/tests/draft2019-09/optional/format/ecmascript-regex.json
@@ -173,7 +173,7 @@
         ]
     },
     {
-        "description": "ECMA 262 \\s matches ascii whitespace only",
+        "description": "ECMA 262 \\s matches whitespace",
         "schema": {
             "type": "string",
             "pattern": "^\\s$"
@@ -185,14 +185,59 @@
                 "valid": true
             },
             {
-                "description": "latin-1 non-breaking-space does not match (unlike e.g. Python)",
+                "description": "Character tabulation matches",
+                "data": "\t",
+                "valid": true
+            },
+            {
+                "description": "Line tabulation matches",
+                "data": "\u000b",
+                "valid": true
+            },
+            {
+                "description": "Form feed matches",
+                "data": "\u000c",
+                "valid": true
+            },
+            {
+                "description": "latin-1 non-breaking-space matches",
                 "data": "\u00a0",
+                "valid": true
+            },
+            {
+                "description": "zero-width whitespace matches",
+                "data": "\ufeff",
+                "valid": true
+            },
+            {
+                "description": "line feed matches (line terminator)",
+                "data": "\u000a",
+                "valid": true
+            },
+            {
+                "description": "paragraph separator matches (line terminator)",
+                "data": "\u2029",
+                "valid": true
+            },
+            {
+                "description": "EM SPACE matches (Space_Separator)",
+                "data": "\u2003",
+                "valid": true
+            },
+            {
+                "description": "Non-whitespace control does not match",
+                "data": "\u0001",
+                "valid": false
+            },
+            {
+                "description": "Non-whitespace does not match",
+                "data": "\u2013",
                 "valid": false
             }
         ]
     },
     {
-        "description": "ECMA 262 \\S matches everything but ascii whitespace",
+        "description": "ECMA 262 \\S matches everything but whitespace",
         "schema": {
             "type": "string",
             "pattern": "^\\S$"
@@ -204,8 +249,53 @@
                 "valid": false
             },
             {
-                "description": "latin-1 non-breaking-space matches (unlike e.g. Python)",
+                "description": "Character tabulation does not match",
+                "data": "\t",
+                "valid": false
+            },
+            {
+                "description": "Line tabulation does not match",
+                "data": "\u000b",
+                "valid": false
+            },
+            {
+                "description": "Form feed does not match",
+                "data": "\u000c",
+                "valid": false
+            },
+            {
+                "description": "latin-1 non-breaking-space does not match",
                 "data": "\u00a0",
+                "valid": false
+            },
+            {
+                "description": "zero-width whitespace does not match",
+                "data": "\ufeff",
+                "valid": false
+            },
+            {
+                "description": "line feed does not match (line terminator)",
+                "data": "\u000a",
+                "valid": false
+            },
+            {
+                "description": "paragraph separator does not match (line terminator)",
+                "data": "\u2029",
+                "valid": false
+            },
+            {
+                "description": "EM SPACE does not match (Space_Separator)",
+                "data": "\u2003",
+                "valid": false
+            },
+            {
+                "description": "Non-whitespace control matches",
+                "data": "\u0001",
+                "valid": true
+            },
+            {
+                "description": "Non-whitespace matches",
+                "data": "\u2013",
                 "valid": true
             }
         ]
diff --git a/tests/draft4/optional/ecmascript-regex.json b/tests/draft4/optional/ecmascript-regex.json
@@ -173,7 +173,7 @@
         ]
     },
     {
-        "description": "ECMA 262 \\s matches ascii whitespace only",
+        "description": "ECMA 262 \\s matches whitespace",
         "schema": {
             "type": "string",
             "pattern": "^\\s$"
@@ -185,14 +185,59 @@
                 "valid": true
             },
             {
-                "description": "latin-1 non-breaking-space does not match (unlike e.g. Python)",
+                "description": "Character tabulation matches",
+                "data": "\t",
+                "valid": true
+            },
+            {
+                "description": "Line tabulation matches",
+                "data": "\u000b",
+                "valid": true
+            },
+            {
+                "description": "Form feed matches",
+                "data": "\u000c",
+                "valid": true
+            },
+            {
+                "description": "latin-1 non-breaking-space matches",
                 "data": "\u00a0",
+                "valid": true
+            },
+            {
+                "description": "zero-width whitespace matches",
+                "data": "\ufeff",
+                "valid": true
+            },
+            {
+                "description": "line feed matches (line terminator)",
+                "data": "\u000a",
+                "valid": true
+            },
+            {
+                "description": "paragraph separator matches (line terminator)",
+                "data": "\u2029",
+                "valid": true
+            },
+            {
+                "description": "EM SPACE matches (Space_Separator)",
+                "data": "\u2003",
+                "valid": true
+            },
+            {
+                "description": "Non-whitespace control does not match",
+                "data": "\u0001",
+                "valid": false
+            },
+            {
+                "description": "Non-whitespace does not match",
+                "data": "\u2013",
                 "valid": false
             }
         ]
     },
     {
-        "description": "ECMA 262 \\S matches everything but ascii whitespace",
+        "description": "ECMA 262 \\S matches everything but whitespace",
         "schema": {
             "type": "string",
             "pattern": "^\\S$"
@@ -204,8 +249,53 @@
                 "valid": false
             },
             {
-                "description": "latin-1 non-breaking-space matches (unlike e.g. Python)",
+                "description": "Character tabulation does not match",
+                "data": "\t",
+                "valid": false
+            },
+            {
+                "description": "Line tabulation does not match",
+                "data": "\u000b",
+                "valid": false
+            },
+            {
+                "description": "Form feed does not match",
+                "data": "\u000c",
+                "valid": false
+            },
+            {
+                "description": "latin-1 non-breaking-space does not match",
                 "data": "\u00a0",
+                "valid": false
+            },
+            {
+                "description": "zero-width whitespace does not match",
+                "data": "\ufeff",
+                "valid": false
+            },
+            {
+                "description": "line feed does not match (line terminator)",
+                "data": "\u000a",
+                "valid": false
+            },
+            {
+                "description": "paragraph separator does not match (line terminator)",
+                "data": "\u2029",
+                "valid": false
+            },
+            {
+                "description": "EM SPACE does not match (Space_Separator)",
+                "data": "\u2003",
+                "valid": false
+            },
+            {
+                "description": "Non-whitespace control matches",
+                "data": "\u0001",
+                "valid": true
+            },
+            {
+                "description": "Non-whitespace matches",
+                "data": "\u2013",
                 "valid": true
             }
         ]
diff --git a/tests/draft6/optional/ecmascript-regex.json b/tests/draft6/optional/ecmascript-regex.json
@@ -173,7 +173,7 @@
         ]
     },
     {
-        "description": "ECMA 262 \\s matches ascii whitespace only",
+        "description": "ECMA 262 \\s matches whitespace",
         "schema": {
             "type": "string",
             "pattern": "^\\s$"
@@ -185,14 +185,59 @@
                 "valid": true
             },
             {
-                "description": "latin-1 non-breaking-space does not match (unlike e.g. Python)",
+                "description": "Character tabulation matches",
+                "data": "\t",
+                "valid": true
+            },
+            {
+                "description": "Line tabulation matches",
+                "data": "\u000b",
+                "valid": true
+            },
+            {
+                "description": "Form feed matches",
+                "data": "\u000c",
+                "valid": true
+            },
+            {
+                "description": "latin-1 non-breaking-space matches",
                 "data": "\u00a0",
+                "valid": true
+            },
+            {
+                "description": "zero-width whitespace matches",
+                "data": "\ufeff",
+                "valid": true
+            },
+            {
+                "description": "line feed matches (line terminator)",
+                "data": "\u000a",
+                "valid": true
+            },
+            {
+                "description": "paragraph separator matches (line terminator)",
+                "data": "\u2029",
+                "valid": true
+            },
+            {
+                "description": "EM SPACE matches (Space_Separator)",
+                "data": "\u2003",
+                "valid": true
+            },
+            {
+                "description": "Non-whitespace control does not match",
+                "data": "\u0001",
+                "valid": false
+            },
+            {
+                "description": "Non-whitespace does not match",
+                "data": "\u2013",
                 "valid": false
             }
         ]
     },
     {
-        "description": "ECMA 262 \\S matches everything but ascii whitespace",
+        "description": "ECMA 262 \\S matches everything but whitespace",
         "schema": {
             "type": "string",
             "pattern": "^\\S$"
@@ -204,8 +249,53 @@
                 "valid": false
             },
             {
-                "description": "latin-1 non-breaking-space matches (unlike e.g. Python)",
+                "description": "Character tabulation does not match",
+                "data": "\t",
+                "valid": false
+            },
+            {
+                "description": "Line tabulation does not match",
+                "data": "\u000b",
+                "valid": false
+            },
+            {
+                "description": "Form feed does not match",
+                "data": "\u000c",
+                "valid": false
+            },
+            {
+                "description": "latin-1 non-breaking-space does not match",
                 "data": "\u00a0",
+                "valid": false
+            },
+            {
+                "description": "zero-width whitespace does not match",
+                "data": "\ufeff",
+                "valid": false
+            },
+            {
+                "description": "line feed does not match (line terminator)",
+                "data": "\u000a",
+                "valid": false
+            },
+            {
+                "description": "paragraph separator does not match (line terminator)",
+                "data": "\u2029",
+                "valid": false
+            },
+            {
+                "description": "EM SPACE does not match (Space_Separator)",
+                "data": "\u2003",
+                "valid": false
+            },
+            {
+                "description": "Non-whitespace control matches",
+                "data": "\u0001",
+                "valid": true
+            },
+            {
+                "description": "Non-whitespace matches",
+                "data": "\u2013",
                 "valid": true
             }
         ]
diff --git a/tests/draft7/optional/format/ecmascript-regex.json b/tests/draft7/optional/format/ecmascript-regex.json
