* string.c: New static function rb_str_ascii_casemap; special-casing

:ascii option in rb_str_upcase_bang and rb_str_downcase_bang.
* regenc.c: Fix a bug (wrong use of unnecessary slack at end of string).
* regenc.h -> include/ruby/oniguruma.h: Move declaration of
  onigenc_ascii_only_case_map so that it is visible in string.c.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55329 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

ChangeLog

@@ -1,3 +1,13 @@
+Wed Jun  8 21:28:36 2016  Martin Duerst  <duerst@it.aoyama.ac.jp>
+
+	* string.c: New static function rb_str_ascii_casemap; special-casing
+	  :ascii option in rb_str_upcase_bang and rb_str_downcase_bang.
+
+	* regenc.c: Fix a bug (wrong use of unnecessary slack at end of string).
+
+	* regenc.h -> include/ruby/oniguruma.h: Move declaration of
+	  onigenc_ascii_only_case_map so that it is visible in string.c.
+
 Wed Jun  8 20:33:44 2016  Naohisa Goto  <ngotogenome@gmail.com>
 
 	* include/ruby/intern.h: Remove excess semicolons in PUREFUNC().

include/ruby/oniguruma.h

@@ -229,6 +229,14 @@ ONIG_EXTERN const OnigEncodingType OnigEncodingASCII;
 
 #define ONIG_ENCODING_UNDEF    ((OnigEncoding )0)
 
+#ifdef ONIG_CASE_MAPPING
+  /* this declaration needs to be here because it is used in string.c */
+  ONIG_EXTERN int    onigenc_ascii_only_case_map P_((OnigCaseFoldType* flagP,
+			  const OnigUChar** pp, const OnigUChar* end,
+			  OnigUChar* to, OnigUChar* to_end,
+			  const struct OnigEncodingTypeST* enc));
+#endif   /* ONIG_CASE_MAPPING */
+
 
 /* work size */
 #define ONIGENC_CODE_TO_MBC_MAXLEN       7

regenc.c

@@ -968,9 +968,7 @@ onigenc_ascii_only_case_map (OnigCaseFoldType* flagP, const OnigUChar** pp, cons
   OnigCaseFoldType flags = *flagP;
   int codepoint_length;
 
-  to_end -= 4; /* longest possible length of a single character */
+  while (*pp<end && to<to_end) {
-
-  while (*pp<end && to<=to_end) {
     codepoint_length = ONIGENC_PRECISE_MBC_ENC_LEN(enc, *pp, end);
     if (codepoint_length < 0)
       return codepoint_length; /* encoding invalid */

regenc.h

@@ -133,7 +133,6 @@ CONSTFUNC(ONIG_EXTERN int onigenc_not_support_get_ctype_code_range P_((OnigCtype
 PUREFUNC(ONIG_EXTERN int onigenc_is_mbc_newline_0x0a P_((const UChar* p, const UChar* end, OnigEncoding enc)));
 
 #ifdef ONIG_CASE_MAPPING
-  ONIG_EXTERN int    onigenc_ascii_only_case_map P_((OnigCaseFoldType* flagP, const OnigUChar** pp, const OnigUChar* end, OnigUChar* to, OnigUChar* to_end, const struct OnigEncodingTypeST* enc));
   ONIG_EXTERN int    onigenc_single_byte_ascii_only_case_map P_((OnigCaseFoldType* flagP, const OnigUChar** pp, const OnigUChar* end, OnigUChar* to, OnigUChar* to_end, const struct OnigEncodingTypeST* enc));
 #endif   /* ONIG_CASE_MAPPING */
 

string.c

@@ -5833,6 +5833,29 @@ rb_str_casemap(VALUE source, OnigCaseFoldType *flags, rb_encoding *enc)
     return target;
 }
 
+static void
+rb_str_ascii_casemap(VALUE source, OnigCaseFoldType *flags, rb_encoding *enc)
+{
+    OnigUChar *source_current, *source_end;
+    int old_length = RSTRING_LEN(source);
+    int length_or_invalid;
+
+    if (old_length == 0) return;
+
+    source_current = (OnigUChar*)RSTRING_PTR(source);
+    source_end = (OnigUChar*)RSTRING_END(source);
+
+    length_or_invalid = onigenc_ascii_only_case_map(flags,
+			       (const OnigUChar**)&source_current, source_end,
+			       source_current, source_end, enc);
+    if (length_or_invalid < 0)
+        rb_raise(rb_eArgError, "input string invalid");
+/*    if (length_or_invalid != old_length)
+printf("problem with rb_str_ascii_casemap; old_length=%d, new_length=%d\n", old_length, length_or_invalid),
+        rb_raise(rb_eArgError, "internal problem with rb_str_ascii_casemap");
+*/
+}
+
 /*
  *  call-seq:
  *     str.upcase!              -> str or nil
@@ -5855,7 +5878,8 @@ rb_str_upcase_bang(int argc, VALUE *argv, VALUE str)
     str_modify_keep_cr(str);
     enc = STR_ENC_GET(str);
     rb_str_check_dummy_enc(enc);
-    if (!(flags&ONIGENC_CASE_FOLD_TURKISH_AZERI) && ENC_CODERANGE(str)==ENC_CODERANGE_7BIT) {
+    if ((flags&ONIGENC_CASE_ASCII_ONLY) && (enc==rb_utf8_encoding() || rb_enc_mbmaxlen(enc)==1)
+	|| (!(flags&ONIGENC_CASE_FOLD_TURKISH_AZERI) && ENC_CODERANGE(str)==ENC_CODERANGE_7BIT)) {
         char *s = RSTRING_PTR(str), *send = RSTRING_END(str);
 
 	while (s < send) {
@@ -5914,14 +5938,14 @@ static VALUE
 rb_str_downcase_bang(int argc, VALUE *argv, VALUE str)
 {
     rb_encoding *enc;
-    int modify = 0;
     OnigCaseFoldType flags = ONIGENC_CASE_DOWNCASE;
 
     flags = check_case_options(argc, argv, flags);
     str_modify_keep_cr(str);
     enc = STR_ENC_GET(str);
     rb_str_check_dummy_enc(enc);
-    if (!(flags&ONIGENC_CASE_FOLD_TURKISH_AZERI) && ENC_CODERANGE(str)==ENC_CODERANGE_7BIT) {
+    if ((flags&ONIGENC_CASE_ASCII_ONLY) && (enc==rb_utf8_encoding() || rb_enc_mbmaxlen(enc)==1)
+	|| (!(flags&ONIGENC_CASE_FOLD_TURKISH_AZERI) && ENC_CODERANGE(str)==ENC_CODERANGE_7BIT)) {
         char *s = RSTRING_PTR(str), *send = RSTRING_END(str);
 
 	while (s < send) {
@@ -5929,17 +5953,17 @@ rb_str_downcase_bang(int argc, VALUE *argv, VALUE str)
 
 	    if (rb_enc_isascii(c, enc) && 'A' <= c && c <= 'Z') {
 		*s = 'a' + (c - 'A');
-		modify = 1;
+		flags |= ONIGENC_CASE_MODIFIED;
 	    }
 	    s++;
 	}
     }
-    else {
+    else if (flags&ONIGENC_CASE_ASCII_ONLY)
+        rb_str_ascii_casemap(str, &flags, enc);
+    else
 	str_shared_replace(str, rb_str_casemap(str, &flags, enc));
-	modify = ONIGENC_CASE_MODIFIED & flags;
-    }
 
-    if (modify) return str;
+    if (ONIGENC_CASE_MODIFIED&flags) return str;
     return Qnil;
 }