From: nobu@...
Date: 2017-07-31T11:18:12+00:00
Subject: [ruby-core:82216] [Ruby trunk Bug#13770] Can't create valid	Cyrillic-named class/module

Issue #13770 has been updated by nobu (Nobuyoshi Nakada).


I'm uncertain about the usage of `mbc_case_fold`.

```diff
diff --git i/parse.y w/parse.y
index 02d9412a2c..96f25d893e 100644
--- i/parse.y
+++ w/parse.y
@@ -7790,6 +7790,8 @@ parse_atmark(struct parser_params *parser, const enum lex_state_e last_state)
     return result;
 }
 
+int rb_enc_const_id_char_p(const char *name, const char *end, rb_encoding *enc);
+
 static enum yytokentype
 parse_ident(struct parser_params *parser, int c, int cmd_state)
 {
@@ -7827,7 +7829,9 @@ parse_ident(struct parser_params *parser, int c, int cmd_state)
 		pushback(c);
 	    }
 	}
-	if (result == 0 && ISUPPER(tok()[0])) {
+	if (result == 0 &&
+	    (ISUPPER(tok()[0]) ||
+	     rb_enc_const_id_char_p(tok(), tok()+toklen(), current_enc))) {
 	    result = tCONSTANT;
 	}
 	else {
diff --git i/symbol.c w/symbol.c
index f4516ebbe4..490cae0127 100644
--- i/symbol.c
+++ w/symbol.c
@@ -198,6 +198,28 @@ rb_enc_symname_p(const char *name, rb_encoding *enc)
     return rb_enc_symname2_p(name, strlen(name), enc);
 }
 
+int
+rb_enc_const_id_char_p(const char *name, const char *end, rb_encoding *enc)
+{
+    int c, len;
+
+    if (end <= name) return FALSE;
+    if (ISASCII(*name)) return ISUPPER(*name);
+    c = rb_enc_codepoint_len(name, end, &len, enc);
+    if (c < 0) return FALSE;
+    if (rb_enc_isupper(c, enc)) return TRUE;
+    {
+	OnigUChar fold[ONIGENC_GET_CASE_FOLD_CODES_MAX_NUM];
+	const OnigUChar *beg = (const OnigUChar *)name;
+	int r = enc->mbc_case_fold(ONIGENC_CASE_FOLD,
+				   &beg, (const OnigUChar *)end,
+				   fold, enc);
+	if (r > 0 && (r != len || memcmp(fold, name, r)))
+	    return TRUE;
+    }
+    return FALSE;
+}
+
 #define IDSET_ATTRSET_FOR_SYNTAX ((1U<<ID_LOCAL)|(1U<<ID_CONST))
 #define IDSET_ATTRSET_FOR_INTERN (~(~0U<<(1<<ID_SCOPE_SHIFT)) & ~(1U<<ID_ATTRSET))
 
@@ -278,7 +300,7 @@ rb_enc_symname_type(const char *name, long len, rb_encoding *enc, unsigned int a
 	break;
 
       default:
-	type = ISUPPER(*m) ? ID_CONST : ID_LOCAL;
+	type = rb_enc_const_id_char_p(m, e, enc) ? ID_CONST : ID_LOCAL;
       id:
 	if (m >= e || (*m != '_' && !ISALPHA(*m) && ISASCII(*m))) {
 	    if (len > 1 && *(e-1) == '=') {
```

----------------------------------------
Bug #13770: Can't create valid Cyrillic-named class/module
https://bugs.ruby-lang.org/issues/13770#change-65983

* Author: sb (Sergey Borodanov)
* Status: Open
* Priority: Normal
* Assignee: 
* Target version: 
* ruby -v: 2.4.1p111 (2017-03-22 revision 58053) [x86_64-linux]
* Backport: 2.2: UNKNOWN, 2.3: UNKNOWN, 2.4: UNKNOWN
----------------------------------------
Can't create a valid Cyrillic-named class. If I have a file **������.rb**:

~~~ ruby
# Content of ������.rb:

class ������

  def ����������������������������
    "������������, ������!"
  end

end
~~~

and do in **bash**:

~~~
ruby ������.rb
~~~

I get the error (**SyntaxError**):

~~~
������.rb:1: class/module name must be CONSTANT
~~~

Same error with module creating and same behavior in **irb** (please, see attachment). At the same time Cyrillic-named constants and methods work fine.

It is expected that creating Cyrillic-named class/modules should work without error.

---Files--------------------------------
Screenshot from 2017-07-26 19-08-14.png (64.2 KB)


-- 
https://bugs.ruby-lang.org/

Unsubscribe: <mailto:ruby-core-request@ruby-lang.org?subject=unsubscribe>
<http://lists.ruby-lang.org/cgi-bin/mailman/options/ruby-core>