[ruby-core:56075] [ruby-trunk - Bug #8653] Unexpected result of String#succ with utf-16 and utf-32 string.

Issue #8653 has been updated by phasis68 (Heesob Park).


I understand String#succ is not easy for UTF-16LE encoded string.

In case of UTF-16 or UTF-32 string, it is possible to convert it to UTF-8 string and get succ value and revert it to the original encoding.

Here is a draft patch for rb_str_succ

diff --git a/string.c b/string.c.new
index f7a12e0..f933052 100644
--- a/string.c
+++ b/string.c.new
@@ -3032,6 +3032,7 @@ enc_succ_alnum_char(char *p, long len, rb_encoding *enc, char *carry)
 VALUE
 rb_str_succ(VALUE orig)
 {
+    int idx;
     rb_encoding *enc;
     VALUE str;
     char *sbeg, *s, *e, *last_alnum = 0;
@@ -3041,12 +3042,26 @@ rb_str_succ(VALUE orig)
     long carry_pos = 0, carry_len = 1;
     enum neighbor_char neighbor = NEIGHBOR_FOUND;
 
-    str = rb_str_new5(orig, RSTRING_PTR(orig), RSTRING_LEN(orig));
-    rb_enc_cr_str_copy_for_substr(str, orig);
+    idx = ENCODING_GET(orig);    
+    switch(idx) {
+        case ENCINDEX_UTF_16BE:
+        case ENCINDEX_UTF_16LE:
+        case ENCINDEX_UTF_32BE:
+        case ENCINDEX_UTF_32LE:
+        case ENCINDEX_UTF_16:
+        case ENCINDEX_UTF_32:
+            str = rb_str_encode(orig, rb_enc_from_encoding(rb_utf8_encoding()), 0, Qnil);
+            break;
+        default:
+            str = rb_str_new5(orig, RSTRING_PTR(orig), RSTRING_LEN(orig));
+            rb_enc_cr_str_copy_for_substr(str, orig);        
+    }
+    
     OBJ_INFECT(str, orig);
     if (RSTRING_LEN(str) == 0) return str;
 
-    enc = STR_ENC_GET(orig);
+        
+    enc = STR_ENC_GET(str);
     sbeg = RSTRING_PTR(str);
     s = e = sbeg + RSTRING_LEN(str);
 
@@ -3066,6 +3081,15 @@ rb_str_succ(VALUE orig)
 	  case NEIGHBOR_NOT_CHAR:
 	    continue;
 	  case NEIGHBOR_FOUND:
+        switch(idx) {
+            case ENCINDEX_UTF_16BE:
+            case ENCINDEX_UTF_16LE:
+            case ENCINDEX_UTF_32BE:
+            case ENCINDEX_UTF_32LE:
+            case ENCINDEX_UTF_16:
+            case ENCINDEX_UTF_32:
+                str = rb_str_encode(str, rb_enc_from_encoding(rb_enc_from_index(idx)), 0, Qnil);    
+        }      
 	    return str;
 	  case NEIGHBOR_WRAPPED:
 	    last_alnum = s;
@@ -3103,6 +3127,17 @@ rb_str_succ(VALUE orig)
     STR_SET_LEN(str, RSTRING_LEN(str) + carry_len);
     RSTRING_PTR(str)[RSTRING_LEN(str)] = '\0';
     rb_enc_str_coderange(str);
+
+    switch(idx) {
+        case ENCINDEX_UTF_16BE:
+        case ENCINDEX_UTF_16LE:
+        case ENCINDEX_UTF_32BE:
+        case ENCINDEX_UTF_32LE:
+        case ENCINDEX_UTF_16:
+        case ENCINDEX_UTF_32:
+            str = rb_str_encode(str, rb_enc_from_encoding(rb_enc_from_index(idx)), 0, Qnil);    
+    }
+    
     return str;
 } 

----------------------------------------
Bug #8653: Unexpected result of String#succ with utf-16 and utf-32 string.
https://bugs.ruby-lang.org/issues/8653#change-40569

Author: phasis68 (Heesob Park)
Status: Open
Priority: Normal
Assignee: 
Category: 
Target version: 
ruby -v: ruby 2.1.0dev (2013-07-17 trunk 42011) [i386-mingw32]
Backport: 1.9.3: UNKNOWN, 2.0.0: UNKNOWN


I found the result of String#succ of UTF-16LE encoded string is incorrect. 

As a result, Range of UTF-16LE encoded string show some unexpected behavior.


C:\work>irb
irb(main):001:0> a = 'A'.encode('UTF-16LE')
=> "A"
irb(main):002:0> b = 'B'.encode('UTF-16LE')
=> "B"
irb(main):003:0> a.succ
=> "\u0141"
irb(main):004:0> r = a..b
=> "A".."B"
irb(main):005:0> r.to_s
=> "A\u2E2EB"
irb(main):006:0> r.count
=> 3
irb(main):007:0> r.to_a
=> ["A", "\u0141", "\u0241"]
irb(main):008:0> r.include?(b)
=> false
irb(main):009:0> a = 'A'.encode('UTF-32LE')
=> "A"
irb(main):010:0> b = 'B'.encode('UTF-32LE')
=> "B"
irb(main):011:0> a.succ
=> "\u{1000041}"
irb(main):012:0> r = a..b
=> "A".."B"
irb(main):013:0> r.to_s
=> "A\u{422E2E}\x00\x00"
irb(main):014:0> r.count
=> 16777217
irb(main):015:0> r.to_a
[FATAL] failed to allocate memory

C:\work>


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