[pull] master from ruby:master

.github/workflows/mingw.yml

@@ -76,19 +76,19 @@ jobs:
           # show where
           result=true
           for e in gcc.exe ragel.exe make.exe libcrypto-3-x64.dll libssl-3-x64.dll; do
-            echo ::group::$'\033[93m'$e$'\033[m'
+            echo ::group::$'\e[93m'$e$'\e[m'
             where $e || result=false
             echo ::endgroup::
           done
           # show version
           for e in gcc ragel make "openssl version"; do
             case "$e" in *" "*) ;; *) e="$e --version";; esac
-            echo ::group::$'\033[93m'$e$'\033[m'
+            echo ::group::$'\e[93m'$e$'\e[m'
             $e || result=false
             echo ::endgroup::
           done
           # show packages
-          echo ::group::$'\033[93m'Packages$'\033[m'
+          echo ::group::$'\e[93m'Packages$'\e[m'
           pacman -Qs mingw-w64-ucrt-x86_64-* | sed -n "s,local/mingw-w64-ucrt-x86_64-,,p"
           echo ::endgroup::
           $result

doc/string/grapheme_clusters.rdoc

@@ -1,6 +1,19 @@
 Returns an array of the grapheme clusters in +self+
 (see {Unicode Grapheme Cluster Boundaries}[https://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries]):
 
-  s = "\u0061\u0308-pqr-\u0062\u0308-xyz-\u0063\u0308" # => "ä-pqr-b̈-xyz-c̈"
+  s = "ä-pqr-b̈-xyz-c̈"
+  s.size                   # => 16
+  s.bytesize               # => 19
+  s.grapheme_clusters.size # => 13
   s.grapheme_clusters
   # => ["ä", "-", "p", "q", "r", "-", "b̈", "-", "x", "y", "z", "-", "c̈"]
+
+Details:
+
+  s = "ä"
+  s.grapheme_clusters             # => ["ä"]           # One grapheme cluster.
+  s.bytes                         # => [97, 204, 136]  # Three bytes.
+  s.chars                         # => ["a", "̈"]       # Two characters.
+  s.chars.map {|char| char.ord }  # => [97, 776]       # Their values.
+
+Related: see {Converting to Non-String}[rdoc-ref:String@Converting+to+Non--5CString].

error.c

@@ -1883,7 +1883,7 @@ exc_inspect(VALUE exc)
  *      # String
  *    end
  *
- *  The value returned by this method migth be adjusted when raising (see Kernel#raise),
+ *  The value returned by this method might be adjusted when raising (see Kernel#raise),
  *  or during intermediate handling by #set_backtrace.
  *
  *  See also #backtrace_locations that provide the same value, as structured objects.

gc/default/default.c

@@ -4420,7 +4420,10 @@ rb_gc_impl_mark_and_move(void *objspace_ptr, VALUE *ptr)
         GC_ASSERT(objspace->flags.during_compacting);
         GC_ASSERT(during_gc);
 
-        *ptr = rb_gc_impl_location(objspace, *ptr);
+        VALUE destination = rb_gc_impl_location(objspace, *ptr);
+        if (destination != *ptr) {
+            *ptr = destination;
+        }
     }
     else {
         gc_mark(objspace, *ptr);

internal/symbol.h

@@ -35,6 +35,7 @@ bool rb_obj_is_symbol_table(VALUE obj);
 void rb_sym_global_symbol_table_foreach_weak_reference(int (*callback)(VALUE *key, void *data), void *data);
 void rb_gc_free_dsymbol(VALUE);
 int rb_static_id_valid_p(ID id);
+void rb_free_global_symbol_table(void);
 
 #if __has_builtin(__builtin_constant_p)
 #define rb_sym_intern_ascii_cstr(ptr) \

load.c

@@ -1346,14 +1346,14 @@ rb_resolve_feature_path(VALUE klass, VALUE fname)
 }
 
 static void
-ext_config_push(rb_thread_t *th, struct rb_ext_config *prev)
+ext_config_push(rb_thread_t *th, volatile struct rb_ext_config *prev)
 {
     *prev = th->ext_config;
     th->ext_config = (struct rb_ext_config){0};
 }
 
 static void
-ext_config_pop(rb_thread_t *th, struct rb_ext_config *prev)
+ext_config_pop(rb_thread_t *th, volatile struct rb_ext_config *prev)
 {
     th->ext_config = *prev;
 }
@@ -1407,7 +1407,7 @@ require_internal(rb_execution_context_t *ec, VALUE fname, int exception, bool wa
     VALUE realpaths = get_loaded_features_realpaths(vm_ns);
     VALUE realpath_map = get_loaded_features_realpath_map(vm_ns);
     volatile bool reset_ext_config = false;
-    struct rb_ext_config prev_ext_config;
+    volatile struct rb_ext_config prev_ext_config;
 
     path = rb_str_encode_ospath(fname);
     RUBY_DTRACE_HOOK(REQUIRE_ENTRY, RSTRING_PTR(fname));

prism/config.yml

@@ -322,13 +322,42 @@ warnings:
   - UNUSED_LOCAL_VARIABLE
   - VOID_STATEMENT
 tokens:
+  # The order of the tokens at the beginning is important, because we use them
+  # for a lookup table.
   - name: EOF
     value: 1
     comment: final token in the file
-  - name: MISSING
-    comment: "a token that was expected but not found"
-  - name: NOT_PROVIDED
-    comment: "a token that was not present but it is okay"
+  - name: BRACE_RIGHT
+    comment: "}"
+  - name: COMMA
+    comment: ","
+  - name: EMBEXPR_END
+    comment: "}"
+  - name: KEYWORD_DO
+    comment: "do"
+  - name: KEYWORD_ELSE
+    comment: "else"
+  - name: KEYWORD_ELSIF
+    comment: "elsif"
+  - name: KEYWORD_END
+    comment: "end"
+  - name: KEYWORD_ENSURE
+    comment: "ensure"
+  - name: KEYWORD_IN
+    comment: "in"
+  - name: KEYWORD_RESCUE
+    comment: "rescue"
+  - name: KEYWORD_THEN
+    comment: "then"
+  - name: KEYWORD_WHEN
+    comment: "when"
+  - name: NEWLINE
+    comment: "a newline character outside of other tokens"
+  - name: PARENTHESIS_RIGHT
+    comment: ")"
+  - name: SEMICOLON
+    comment: ";"
+  # Tokens from here on are not used for lookup, and can be in any order.
   - name: AMPERSAND
     comment: "&"
   - name: AMPERSAND_AMPERSAND
@@ -351,8 +380,6 @@ tokens:
     comment: "!~"
   - name: BRACE_LEFT
     comment: "{"
-  - name: BRACE_RIGHT
-    comment: "}"
   - name: BRACKET_LEFT
     comment: "["
   - name: BRACKET_LEFT_ARRAY
@@ -375,8 +402,6 @@ tokens:
     comment: ":"
   - name: COLON_COLON
     comment: "::"
-  - name: COMMA
-    comment: ","
   - name: COMMENT
     comment: "a comment"
   - name: CONSTANT
@@ -395,8 +420,6 @@ tokens:
     comment: "a line inside of embedded documentation"
   - name: EMBEXPR_BEGIN
     comment: "#{"
-  - name: EMBEXPR_END
-    comment: "}"
   - name: EMBVAR
     comment: "#"
   - name: EQUAL
@@ -463,20 +486,10 @@ tokens:
     comment: "def"
   - name: KEYWORD_DEFINED
     comment: "defined?"
-  - name: KEYWORD_DO
-    comment: "do"
   - name: KEYWORD_DO_LOOP
     comment: "do keyword for a predicate in a while, until, or for loop"
-  - name: KEYWORD_ELSE
-    comment: "else"
-  - name: KEYWORD_ELSIF
-    comment: "elsif"
-  - name: KEYWORD_END
-    comment: "end"
   - name: KEYWORD_END_UPCASE
     comment: "END"
-  - name: KEYWORD_ENSURE
-    comment: "ensure"
   - name: KEYWORD_FALSE
     comment: "false"
   - name: KEYWORD_FOR
@@ -485,8 +498,6 @@ tokens:
     comment: "if"
   - name: KEYWORD_IF_MODIFIER
     comment: "if in the modifier form"
-  - name: KEYWORD_IN
-    comment: "in"
   - name: KEYWORD_MODULE
     comment: "module"
   - name: KEYWORD_NEXT
@@ -499,8 +510,6 @@ tokens:
     comment: "or"
   - name: KEYWORD_REDO
     comment: "redo"
-  - name: KEYWORD_RESCUE
-    comment: "rescue"
   - name: KEYWORD_RESCUE_MODIFIER
     comment: "rescue in the modifier form"
   - name: KEYWORD_RETRY
@@ -511,8 +520,6 @@ tokens:
     comment: "self"
   - name: KEYWORD_SUPER
     comment: "super"
-  - name: KEYWORD_THEN
-    comment: "then"
   - name: KEYWORD_TRUE
     comment: "true"
   - name: KEYWORD_UNDEF
@@ -525,8 +532,6 @@ tokens:
     comment: "until"
   - name: KEYWORD_UNTIL_MODIFIER
     comment: "until in the modifier form"
-  - name: KEYWORD_WHEN
-    comment: "when"
   - name: KEYWORD_WHILE
     comment: "while"
   - name: KEYWORD_WHILE_MODIFIER
@@ -563,16 +568,12 @@ tokens:
     comment: "-="
   - name: MINUS_GREATER
     comment: "->"
-  - name: NEWLINE
-    comment: "a newline character outside of other tokens"
   - name: NUMBERED_REFERENCE
     comment: "a numbered reference to a capture group in the previous regular expression match"
   - name: PARENTHESIS_LEFT
     comment: "("
   - name: PARENTHESIS_LEFT_PARENTHESES
     comment: "( for a parentheses node"
-  - name: PARENTHESIS_RIGHT
-    comment: ")"
   - name: PERCENT
     comment: "%"
   - name: PERCENT_EQUAL
@@ -605,8 +606,6 @@ tokens:
     comment: "the beginning of a regular expression"
   - name: REGEXP_END
     comment: "the end of a regular expression"
-  - name: SEMICOLON
-    comment: ";"
   - name: SLASH
     comment: "/"
   - name: SLASH_EQUAL
@@ -651,6 +650,10 @@ tokens:
     comment: "a separator between words in a list"
   - name: __END__
     comment: "marker for the point in the file at which the parser should stop"
+  - name: MISSING
+    comment: "a token that was expected but not found"
+  - name: NOT_PROVIDED
+    comment: "a token that was not present but it is okay"
 flags:
   - name: ArgumentsNodeFlags
     values: