kotovalexarian-likes-github/ruby--ruby
1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
Code Releases Activity

* transcode.c (get_replacement_character): don't return ASCII

Browse source 
incompatible replacements.
  (make_replacement): don't convert the result of
  get_replacement_character.



git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@19277 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
akr 2008-09-09 16:18:29 +00:00
parent 817a623d13
commit 3cc7c9d0dd
2 changed files with 16 additions and 44 deletions
Download patch file Download diff file Expand all files Collapse all files

7
ChangeLog
View file

@ -1,3 +1,10 @@
Wed Sep 10 01:16:07 2008 Tanaka Akira <akr@fsij.org>
* transcode.c (get_replacement_character): don't return ASCII
incompatible replacements.
(make_replacement): don't convert the result of
get_replacement_character.
Wed Sep 10 01:05:00 2008 Tanaka Akira <akr@fsij.org> Wed Sep 10 01:05:00 2008 Tanaka Akira <akr@fsij.org>
* enc/trans/newline.trans (rb_universal_newline): swap src_encoding * enc/trans/newline.trans (rb_universal_newline): swap src_encoding

53
transcode.c
View file

@ -372,44 +372,16 @@ load_transcoder_entry(transcoder_entry_t *entry)
} }
static const char* static const char*
get_replacement_character(rb_encoding *enc, size_t *len_ret, const char **repl_enc_ptr) get_replacement_character(const char *encname, size_t *len_ret, const char **repl_encname_ptr)
{ {
static rb_encoding *utf16be_encoding, *utf16le_encoding; if (encoding_equal(encname, "UTF-8")) {
static rb_encoding *utf32be_encoding, *utf32le_encoding;
if (!utf16be_encoding) {
utf16be_encoding = rb_enc_find("UTF-16BE");
utf16le_encoding = rb_enc_find("UTF-16LE");
utf32be_encoding = rb_enc_find("UTF-32BE");
utf32le_encoding = rb_enc_find("UTF-32LE");
}
if (rb_utf8_encoding() == enc) {
*len_ret = 3; *len_ret = 3;
*repl_enc_ptr = "UTF-8"; *repl_encname_ptr = "UTF-8";
return "\xEF\xBF\xBD"; return "\xEF\xBF\xBD";
} }
else if (utf16be_encoding == enc) {
*len_ret = 2;
*repl_enc_ptr = "UTF-16BE";
return "\xFF\xFD";
}
else if (utf16le_encoding == enc) {
*len_ret = 2;
*repl_enc_ptr = "UTF-16LE";
return "\xFD\xFF";
}
else if (utf32be_encoding == enc) {
*len_ret = 4;
*repl_enc_ptr = "UTF-32BE";
return "\x00\x00\xFF\xFD";
}
else if (utf32le_encoding == enc) {
*len_ret = 4;
*repl_enc_ptr = "UTF-32LE";
return "\xFD\xFF\x00\x00";
}
else { else {
*len_ret = 1; *len_ret = 1;
*repl_enc_ptr = "US-ASCII"; *repl_encname_ptr = "US-ASCII";
return "?"; return "?";
} }
} }
@ -2034,16 +2006,17 @@ make_replacement(rb_econv_t *ec)
const char *repl_enc; const char *repl_enc;
const char *ins_enc; const char *ins_enc;
size_t len; size_t len;
int allocated = 0;
if (ec->replacement_str) if (ec->replacement_str)
return 0; return 0;
ins_enc = rb_econv_encoding_to_insert_output(ec);
tc = ec->last_tc; tc = ec->last_tc;
if (tc) { if (*ins_enc) {
tr = tc->transcoder; tr = tc->transcoder;
enc = rb_enc_find(tr->dst_encoding); enc = rb_enc_find(tr->dst_encoding);
replacement = (const unsigned char *)get_replacement_character(enc, &len, &repl_enc); replacement = (const unsigned char *)get_replacement_character(ins_enc, &len, &repl_enc);
} }
else { else {
replacement = (unsigned char *)"?"; replacement = (unsigned char *)"?";
@ -2051,18 +2024,10 @@ make_replacement(rb_econv_t *ec)
repl_enc = ""; repl_enc = "";
} }
ins_enc = rb_econv_encoding_to_insert_output(ec);
if (*repl_enc && !encoding_equal(repl_enc, ins_enc)) {
replacement = allocate_converted_string(repl_enc, ins_enc, replacement, len, NULL, 0, &len);
if (!replacement)
return -1;
allocated = 1;
repl_enc = ins_enc;
}
ec->replacement_str = replacement; ec->replacement_str = replacement;
ec->replacement_len = len; ec->replacement_len = len;
ec->replacement_enc = repl_enc; ec->replacement_enc = repl_enc;
ec->replacement_allocated = allocated; ec->replacement_allocated = 0;
return 0; return 0;
} }