* include/ruby/oniguruma.h (OnigEncodingTypeST): add precise_ret

  argument for mbc_to_code.
  (ONIGENC_MBC_TO_CODE): provide NULL for precise_ret.
  (ONIGENC_MBC_PRECISE_CODEPOINT): defined.

* include/ruby/encoding.h (rb_enc_mbc_precise_codepoint): defined.

* regenc.h (onigenc_single_byte_mbc_to_code): precise_ret argument
  added.
  (onigenc_mbn_mbc_to_code): ditto.

* regenc.c (onigenc_single_byte_mbc_to_code): precise_ret argument
  added.
  (onigenc_mbn_mbc_to_code): ditto.

* string.c (count_utf8_lead_bytes_with_word): removed.
  (str_utf8_nth): removed.
  (str_utf8_offset): removed.
  (str_strlen): UTF-8 codepoint oriented optimization removed.
  (rb_str_substr): ditto.
  (enc_succ_char): use rb_enc_mbc_precise_codepoint.
  (enc_pred_char): ditto.
  (rb_str_succ): ditto.

* encoding.c (rb_enc_ascget): check length with
  rb_enc_mbc_precise_codepoint.
  (rb_enc_codepoint): use rb_enc_mbc_precise_codepoint.

* regexec.c (string_cmp_ic): add text_end argument.
  (match_at): check end of character after exact string matches.

* enc/utf_8.c (graphme_table): defined for extended graphme cluster
  boundary.
  (grapheme_cmp): defined.
  (get_grapheme_properties): defined.
  (grapheme_boundary_p): defined.
  (MAX_BYTES_LENGTH): defined.
  (comb_char_enc_len): defined.
  (mbc_to_code0): extracted from mbc_to_code.
  (mbc_to_code): use mbc_to_code0.
  (left_adjust_combchar_head): defined.
  (utf_8): use a extended graphme cluster as a unit.

* enc/unicode.c (onigenc_unicode_mbc_case_fold): use
  ONIGENC_MBC_PRECISE_CODEPOINT to extract codepoints.
  (onigenc_unicode_get_case_fold_codes_by_str): ditto.

* enc/euc_jp.c (mbc_to_code): follow mbc_to_code field change.
  use onigenc_mbn_mbc_to_code.

* enc/shift_jis.c (mbc_to_code): ditto.

* enc/emacs_mule.c (mbc_to_code): ditto.

* enc/gbk.c (gbk_mbc_to_code): follow mbc_to_code field and
  onigenc_mbn_mbc_to_code change.

* enc/cp949.c (cp949_mbc_to_code): ditto.

* enc/big5.c (big5_mbc_to_code): ditto.

* enc/euc_tw.c (euctw_mbc_to_code): ditto.

* enc/euc_kr.c (euckr_mbc_to_code): ditto.

* enc/gb18030.c (gb18030_mbc_to_code): ditto.

* enc/utf_32be.c (utf32be_mbc_to_code): follow mbc_to_code field
  change.

* enc/utf_16be.c (utf16be_mbc_to_code): ditto.

* enc/utf_32le.c (utf32le_mbc_to_code): ditto.

* enc/utf_16le.c (utf16le_mbc_to_code): ditto.



git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@19389 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 10 insertions, 10 deletions

diff --git a/enc/unicode.c b/enc/unicode.c
index 2dfcbba3f6..5d2eba79b6 100644
--- a/enc/unicode.c
+++ b/enc/unicode.c
@@ -10966,13 +10966,13 @@ onigenc_unicode_mbc_case_fold(OnigEncoding enc,
 {
   CodePointList3 *to;
   OnigCodePoint code;
-  int i, len, rlen;
+  int i, len, rlen, r;
   const UChar *p = *pp;
 
   if (CaseFoldInited == 0) init_case_fold_table();
 
-  code = ONIGENC_MBC_TO_CODE(enc, p, end);
-  len = enclen(enc, p, end);
+  code = ONIGENC_MBC_PRECISE_CODEPOINT(enc, p, end, &r);
+  len = ONIGENC_MBCLEN_CHARFOUND_LEN(r);
   *pp += len;
 
 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
@@ -11160,7 +11160,7 @@ onigenc_unicode_get_case_fold_codes_by_str(OnigEncoding enc,
     OnigCaseFoldType flag, const OnigUChar* p, const OnigUChar* end,
     OnigCaseFoldCodeItem items[])
 {
-  int n, i, j, k, len;
+  int n, i, j, k, len, r;
   OnigCodePoint code, codes[3];
   CodePointList3 *to, *z3;
   CodePointList2 *z2;
@@ -11169,8 +11169,8 @@ onigenc_unicode_get_case_fold_codes_by_str(OnigEncoding enc,
 
   n = 0;
 
-  code = ONIGENC_MBC_TO_CODE(enc, p, end);
-  len = enclen(enc, p, end);
+  code = ONIGENC_MBC_PRECISE_CODEPOINT(enc, p, end, &r);
+  len = ONIGENC_MBCLEN_CHARFOUND_LEN(r);
 
 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
   if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
@@ -11311,7 +11311,7 @@ onigenc_unicode_get_case_fold_codes_by_str(OnigEncoding enc,
       int clen;
 
       codes[0] = code;
-      code = ONIGENC_MBC_TO_CODE(enc, p, end);
+      code = ONIGENC_MBC_PRECISE_CODEPOINT(enc, p, end, &r);
       if (onig_st_lookup(FoldTable, (st_data_t )code, (void* )&to) != 0
 	  && to->n == 1) {
 	codes[1] = to->code[0];
@@ -11319,7 +11319,7 @@ onigenc_unicode_get_case_fold_codes_by_str(OnigEncoding enc,
       else
 	codes[1] = code;
 
-      clen = enclen(enc, p, end);
+      clen = ONIGENC_MBCLEN_CHARFOUND_LEN(r);
       len += clen;
       if (onig_st_lookup(Unfold2Table, (st_data_t )codes, (void* )&z2) != 0) {
 	for (i = 0; i < z2->n; i++) {
@@ -11332,7 +11332,7 @@ onigenc_unicode_get_case_fold_codes_by_str(OnigEncoding enc,
 
       p += clen;
       if (p < end) {
-	code = ONIGENC_MBC_TO_CODE(enc, p, end);
+        code = ONIGENC_MBC_PRECISE_CODEPOINT(enc, p, end, &r);
 	if (onig_st_lookup(FoldTable, (st_data_t )code, (void* )&to) != 0
 	    && to->n == 1) {
 	  codes[2] = to->code[0];
@@ -11340,7 +11340,7 @@ onigenc_unicode_get_case_fold_codes_by_str(OnigEncoding enc,
 	else
 	  codes[2] = code;
 
-	clen = enclen(enc, p, end);
+        clen = ONIGENC_MBCLEN_CHARFOUND_LEN(r);
 	len += clen;
 	if (onig_st_lookup(Unfold3Table, (st_data_t )codes,
 			   (void* )&z2) != 0) {