Import and modernize bocoup/test262-regexp-generator

.editorconfig

@@ -7,7 +7,7 @@ end_of_line = lf
 insert_final_newline = true
 trim_trailing_whitespace = true
 
-[{README.md,package.json,*.yml,*.sh,*.js,*.case,*.template}]
+[{README.md,package.json,*.yml,*.sh,*.js,*.mjs,*.case,*.template}]
 indent_style = space
 indent_size = 2
 

.github/workflows/checks.yml

@@ -72,6 +72,11 @@ jobs:
           python -m pip install --upgrade pip
           pip install -r tools/generation/requirements.txt
 
+      - name: Install dependencies for regexp-generator tool
+        run: |
+          cd tools/regexp-generator
+          npm install
+
       - name: Build tests
         run: |
           ./make.py clean >/dev/null

make.py

@@ -8,8 +8,10 @@
 OUT_DIR = os.environ.get('OUT_DIR') or 'test'
 SRC_DIR = os.environ.get('SRC_DIR') or 'src'
 
-def shell(*args):
-    sp = subprocess.Popen(list(args), stdout=subprocess.PIPE, universal_newlines=True)
+
+def shell(*args, **kwargs):
+    sp = subprocess.Popen(list(args), stdout=subprocess.PIPE,
+                          universal_newlines=True, **kwargs)
     cmd_str = ' '.join(args)
 
     print('> ' + cmd_str)
@@ -36,17 +38,27 @@ def wrapped():
         return wrapped
     return other
 
+
 @target()
+def npm_deps():
+    shell('npm', 'install', cwd='./tools/regexp-generator')
+
+
+@target('npm_deps')
 def build():
     shell(sys.executable, 'tools/generation/generator.py',
           'create',
           '--parents',
           '--out', OUT_DIR,
           SRC_DIR)
+    shell('npm', 'run', 'build', cwd='./tools/regexp-generator')
 
-@target()
+
+@target('npm_deps')
 def clean():
     shell(sys.executable, 'tools/generation/generator.py', 'clean', OUT_DIR)
+    shell('npm', 'run', 'clean', cwd='./tools/regexp-generator')
+
 
 if len(sys.argv) == 1:
     targets['build']()

test/built-ins/RegExp/CharacterClassEscapes/character-class-digit-class-escape-flags-u.js

@@ -4,43 +4,51 @@
 /*---
 esid: prod-CharacterClassEscape
 description: >
-    Compare range for digit class escape \d with flags ug
+  Compare range for digit class escape \d with flags ug
 info: |
-    This is a generated test. Please check out
-    https://github.com/bocoup/test262-regexp-generator
-    for any changes.
+  This is a generated test. Please check out
+  https://github.com/tc39/test262/tree/main/tools/regexp-generator/
+  for any changes.
 
-    CharacterClassEscape[U] ::
-        d
-        D
-        s
-        S
-        w
-        W
+  CharacterClassEscape[UnicodeMode] ::
+    d
+    D
+    s
+    S
+    w
+    W
+    [+UnicodeMode] p{ UnicodePropertyValueExpression }
+    [+UnicodeMode] P{ UnicodePropertyValueExpression }
 
-    21.2.2.12 CharacterClassEscape
+  22.2.2.9 Runtime Semantics: CompileToCharSet
 
-    The production CharacterClassEscape :: d evaluates as follows:
-        Return the ten-element set of characters containing the characters 0 through 9 inclusive.
-    The production CharacterClassEscape :: D evaluates as follows:
-        Return the set of all characters not included in the set returned by CharacterClassEscape :: d.
-    The production CharacterClassEscape :: s evaluates as follows:
-        Return the set of characters containing the characters that are on the right-hand side of
-        the WhiteSpace or LineTerminator productions.
-    The production CharacterClassEscape :: S evaluates as follows:
-        Return the set of all characters not included in the set returned by CharacterClassEscape :: s.
-    The production CharacterClassEscape :: w evaluates as follows:
-        Return the set of all characters returned by WordCharacters().
-    The production CharacterClassEscape :: W evaluates as follows:
-        Return the set of all characters not included in the set returned by CharacterClassEscape :: w.
+  CharacterClassEscape :: d
+    1. Return the ten-element CharSet containing the characters 0, 1, 2, 3, 4,
+      5, 6, 7, 8, and 9.
+  CharacterClassEscape :: D
+    1. Let S be the CharSet returned by CharacterClassEscape :: d.
+    2. Return CharacterComplement(rer, S).
+  CharacterClassEscape :: s
+    1. Return the CharSet containing all characters corresponding to a code
+      point on the right-hand side of the WhiteSpace or LineTerminator
+      productions.
+  CharacterClassEscape :: S
+    1. Let S be the CharSet returned by CharacterClassEscape :: s.
+    2. Return CharacterComplement(rer, S).
+  CharacterClassEscape :: w
+    1. Return MaybeSimpleCaseFolding(rer, WordCharacters(rer)).
+  CharacterClassEscape :: W
+    1. Let S be the CharSet returned by CharacterClassEscape :: w.
+    2. Return CharacterComplement(rer, S).
 features: [String.fromCodePoint]
 includes: [regExpUtils.js]
+flags: [generated]
 ---*/
 
 const str = buildString({
     loneCodePoints: [],
     ranges: [
-        [0x0030, 0x0039],
+        [0x000030, 0x000039],
     ],
 });
 
@@ -49,16 +57,16 @@ const re = /\d/ug;
 const errors = [];
 
 if (!re.test(str)) {
-    // Error, let's find out where
-    for (const char of str) {
-        if (!re.test(char)) {
-            errors.push('0x' + char.codePointAt(0).toString(16));
-        }
+  // Error, let's find out where
+  for (const char of str) {
+    if (!re.test(char)) {
+      errors.push('0x' + char.codePointAt(0).toString(16));
     }
+  }
 }
 
 assert.sameValue(
-    errors.length,
-    0,
-    'Expected matching code points, but received: ' + errors.join(',')
+  errors.length,
+  0,
+  'Expected matching code points, but received: ' + errors.join(',')
 );

test/built-ins/RegExp/CharacterClassEscapes/character-class-digit-class-escape-plus-quantifier-flags-u.js

@@ -4,43 +4,51 @@
 /*---
 esid: prod-CharacterClassEscape
 description: >
-    Compare range for digit class escape \d+ with flags ug
+  Compare range for digit class escape \d+ with flags ug
 info: |
-    This is a generated test. Please check out
-    https://github.com/bocoup/test262-regexp-generator
-    for any changes.
+  This is a generated test. Please check out
+  https://github.com/tc39/test262/tree/main/tools/regexp-generator/
+  for any changes.
 
-    CharacterClassEscape[U] ::
-        d
-        D
-        s
-        S
-        w
-        W
+  CharacterClassEscape[UnicodeMode] ::
+    d
+    D
+    s
+    S
+    w
+    W
+    [+UnicodeMode] p{ UnicodePropertyValueExpression }
+    [+UnicodeMode] P{ UnicodePropertyValueExpression }
 
-    21.2.2.12 CharacterClassEscape
+  22.2.2.9 Runtime Semantics: CompileToCharSet
 
-    The production CharacterClassEscape :: d evaluates as follows:
-        Return the ten-element set of characters containing the characters 0 through 9 inclusive.
-    The production CharacterClassEscape :: D evaluates as follows:
-        Return the set of all characters not included in the set returned by CharacterClassEscape :: d.
-    The production CharacterClassEscape :: s evaluates as follows:
-        Return the set of characters containing the characters that are on the right-hand side of
-        the WhiteSpace or LineTerminator productions.
-    The production CharacterClassEscape :: S evaluates as follows:
-        Return the set of all characters not included in the set returned by CharacterClassEscape :: s.
-    The production CharacterClassEscape :: w evaluates as follows:
-        Return the set of all characters returned by WordCharacters().
-    The production CharacterClassEscape :: W evaluates as follows:
-        Return the set of all characters not included in the set returned by CharacterClassEscape :: w.
+  CharacterClassEscape :: d
+    1. Return the ten-element CharSet containing the characters 0, 1, 2, 3, 4,
+      5, 6, 7, 8, and 9.
+  CharacterClassEscape :: D
+    1. Let S be the CharSet returned by CharacterClassEscape :: d.
+    2. Return CharacterComplement(rer, S).
+  CharacterClassEscape :: s
+    1. Return the CharSet containing all characters corresponding to a code
+      point on the right-hand side of the WhiteSpace or LineTerminator
+      productions.
+  CharacterClassEscape :: S
+    1. Let S be the CharSet returned by CharacterClassEscape :: s.
+    2. Return CharacterComplement(rer, S).
+  CharacterClassEscape :: w
+    1. Return MaybeSimpleCaseFolding(rer, WordCharacters(rer)).
+  CharacterClassEscape :: W
+    1. Let S be the CharSet returned by CharacterClassEscape :: w.
+    2. Return CharacterComplement(rer, S).
 features: [String.fromCodePoint]
 includes: [regExpUtils.js]
+flags: [generated]
 ---*/
 
 const str = buildString({
     loneCodePoints: [],
     ranges: [
-        [0x0030, 0x0039],
+        [0x000030, 0x000039],
     ],
 });
 
@@ -49,16 +57,16 @@ const re = /\d+/ug;
 const errors = [];
 
 if (!re.test(str)) {
-    // Error, let's find out where
-    for (const char of str) {
-        if (!re.test(char)) {
-            errors.push('0x' + char.codePointAt(0).toString(16));
-        }
+  // Error, let's find out where
+  for (const char of str) {
+    if (!re.test(char)) {
+      errors.push('0x' + char.codePointAt(0).toString(16));
     }
+  }
 }
 
 assert.sameValue(
-    errors.length,
-    0,
-    'Expected matching code points, but received: ' + errors.join(',')
+  errors.length,
+  0,
+  'Expected matching code points, but received: ' + errors.join(',')
 );

test/built-ins/RegExp/CharacterClassEscapes/character-class-digit-class-escape-plus-quantifier.js

@@ -4,43 +4,51 @@
 /*---
 esid: prod-CharacterClassEscape
 description: >
-    Compare range for digit class escape \d+ with flags g
+  Compare range for digit class escape \d+ with flags g
 info: |
-    This is a generated test. Please check out
-    https://github.com/bocoup/test262-regexp-generator
-    for any changes.
+  This is a generated test. Please check out
+  https://github.com/tc39/test262/tree/main/tools/regexp-generator/
+  for any changes.
 
-    CharacterClassEscape[U] ::
-        d
-        D
-        s
-        S
-        w
-        W
+  CharacterClassEscape[UnicodeMode] ::
+    d
+    D
+    s
+    S
+    w
+    W
+    [+UnicodeMode] p{ UnicodePropertyValueExpression }
+    [+UnicodeMode] P{ UnicodePropertyValueExpression }
 
-    21.2.2.12 CharacterClassEscape
+  22.2.2.9 Runtime Semantics: CompileToCharSet
 
-    The production CharacterClassEscape :: d evaluates as follows:
-        Return the ten-element set of characters containing the characters 0 through 9 inclusive.
-    The production CharacterClassEscape :: D evaluates as follows:
-        Return the set of all characters not included in the set returned by CharacterClassEscape :: d.
-    The production CharacterClassEscape :: s evaluates as follows:
-        Return the set of characters containing the characters that are on the right-hand side of
-        the WhiteSpace or LineTerminator productions.
-    The production CharacterClassEscape :: S evaluates as follows:
-        Return the set of all characters not included in the set returned by CharacterClassEscape :: s.
-    The production CharacterClassEscape :: w evaluates as follows:
-        Return the set of all characters returned by WordCharacters().
-    The production CharacterClassEscape :: W evaluates as follows:
-        Return the set of all characters not included in the set returned by CharacterClassEscape :: w.
+  CharacterClassEscape :: d
+    1. Return the ten-element CharSet containing the characters 0, 1, 2, 3, 4,
+      5, 6, 7, 8, and 9.
+  CharacterClassEscape :: D
+    1. Let S be the CharSet returned by CharacterClassEscape :: d.
+    2. Return CharacterComplement(rer, S).
+  CharacterClassEscape :: s
+    1. Return the CharSet containing all characters corresponding to a code
+      point on the right-hand side of the WhiteSpace or LineTerminator
+      productions.
+  CharacterClassEscape :: S
+    1. Let S be the CharSet returned by CharacterClassEscape :: s.
+    2. Return CharacterComplement(rer, S).
+  CharacterClassEscape :: w
+    1. Return MaybeSimpleCaseFolding(rer, WordCharacters(rer)).
+  CharacterClassEscape :: W
+    1. Let S be the CharSet returned by CharacterClassEscape :: w.
+    2. Return CharacterComplement(rer, S).
 features: [String.fromCodePoint]
 includes: [regExpUtils.js]
+flags: [generated]
 ---*/
 
 const str = buildString({
     loneCodePoints: [],
     ranges: [
-        [0x0030, 0x0039],
+        [0x000030, 0x000039],
     ],
 });
 
@@ -49,16 +57,16 @@ const re = /\d+/g;
 const errors = [];
 
 if (!re.test(str)) {
-    // Error, let's find out where
-    for (const char of str) {
-        if (!re.test(char)) {
-            errors.push('0x' + char.codePointAt(0).toString(16));
-        }
+  // Error, let's find out where
+  for (const char of str) {
+    if (!re.test(char)) {
+      errors.push('0x' + char.codePointAt(0).toString(16));
     }
+  }
 }
 
 assert.sameValue(
-    errors.length,
-    0,
-    'Expected matching code points, but received: ' + errors.join(',')
+  errors.length,
+  0,
+  'Expected matching code points, but received: ' + errors.join(',')
 );