ruby-dev

中田さん、こんにちは。

At 04:05 07/12/13, you wrote:
>なかだです。
>
>transcoderを拡張ライブラリに出してみました。ext/とは別にしたほう
>がいいかもしれませんが。

その通りだと思います。これからデータのファイルが増えるので、
メインのところにはちょっと不便ですが、ext にするといちいち
require が必要になると思いますが、これはとても不便だと思います。
require が必要になったら結局 String#encode が定義されているが、
require しないと使えない、という不思議な現象になってしまうでしょう。

データを動機的にロードするのは目指したいですが、require と
切り離して考える必要だと思います。

ファイルの場所を考えると、enc の中、もしくは enc/trans では
いいのではないかと思います。

>include/ruby/transcode.hとext/enc/trans/iso_8859/iso_8859.cは、
>それぞれtranscode_data.hとtranscode_data_iso_8859.cをsvn mv した
>ものです。

細かいところだけいいますと、/iso_8859/ の部分は要らないと思います。
ファイル一つだけのためのディレクトリは余り意味がないと思います。
しかも、iso-8859 見たいに標準にそってファイルをまとめることに
は長期的にはならないと思います。データの効率を考えると文字種
(例えば Latin、Greek、など) にそってまとめた方がいいと思います。

後は、(予定していた) transcode.h と (既に存在する) transcode_data.h
は別物として考えています。transcode.h はルビから使える機能を定義し、
transcode_data.h はデータ形式関係のものを定義し、ルビからは
アクセスしなくていいもの、という考え方です。

以下のところも少しコメントを追加します。色々な変更が
重なってしまってちょっとやりにくいところがあります。

宜しくお願いします。    Martin.

>Index: common.mk
>===================================================================
>--- common.mk  (revision 14198)
>+++ common.mk  (working copy)
>@@ -25,4 +25,6 @@ ENCOBJS       = ascii.$(OBJEXT) \
>               utf8.$(OBJEXT)
> 
>+TRANSCODEOBJS = iso_8859.$(OBJEXT)
>+
> COMMONOBJS    = array.$(OBJEXT) \
>               bignum.$(OBJEXT) \
>@@ -67,5 +69,4 @@ COMMONOBJS    = array.$(OBJEXT) \
>               time.$(OBJEXT) \
>               transcode.$(OBJEXT) \
>-              transcode_data_iso_8859.$(OBJEXT) \
>               util.$(OBJEXT) \
>               variable.$(OBJEXT) \
>@@ -544,7 +545,6 @@ thread.$(OBJEXT): {$(VPATH)}thread.c {$(
>   {$(VPATH)}node.h {$(VPATH)}util.h \
>   {$(VPATH)}signal.h {$(VPATH)}st.h {$(VPATH)}dln.h
>-transcode.$(OBJEXT): {$(VPATH)}transcode.c {$(VPATH)}transcode_data.h 
>{$(VPATH)}ruby.h {$(VPATH)}config.h \
>+transcode.$(OBJEXT): {$(VPATH)}transcode.c {$(VPATH)}transcode.h 
>{$(VPATH)}ruby.h {$(VPATH)}config.h \
>   {$(VPATH)}defines.h {$(VPATH)}intern.h {$(VPATH)}missing.h  
>{$(VPATH)}encoding.h
>-transcode_data_iso_8859.$(OBJEXT): {$(VPATH)}transcode_data_iso_8859.c 
>{$(VPATH)}transcode_data.h
> cont.$(OBJEXT):  {$(VPATH)}cont.c {$(VPATH)}eval_intern.h \
>   {$(VPATH)}ruby.h {$(VPATH)}vm_core.h {$(VPATH)}id.h {$(VPATH)}config.h \
>Index: transcode.c
>===================================================================
>--- transcode.c        (revision 14198)
>+++ transcode.c        (working copy)
>@@ -13,7 +13,7 @@
> #include "ruby/ruby.h"
> #include "ruby/encoding.h"
>-
>-#include "transcode_data.h"
>-
>+#define PType (int)
>+#include "ruby/transcode.h"
>+#include <ctype.h>
> 
> VALUE rb_str_tmp_new(long);
>@@ -24,130 +24,62 @@ VALUE rb_str_shared_replace(VALUE, VALUE
>  */
> 
>-/* extern declarations, should use some include file here */
>-extern const BYTE_LOOKUP from_ISO_8859_1;
>-extern const BYTE_LOOKUP from_ISO_8859_2;
>-extern const BYTE_LOOKUP from_ISO_8859_3;
>-extern const BYTE_LOOKUP from_ISO_8859_4;
>-extern const BYTE_LOOKUP from_ISO_8859_5;
>-extern const BYTE_LOOKUP from_ISO_8859_6;
>-extern const BYTE_LOOKUP from_ISO_8859_7;
>-extern const BYTE_LOOKUP from_ISO_8859_8;
>-extern const BYTE_LOOKUP from_ISO_8859_9;
>-extern const BYTE_LOOKUP from_ISO_8859_10;
>-extern const BYTE_LOOKUP from_ISO_8859_11;
>-extern const BYTE_LOOKUP from_ISO_8859_13;
>-extern const BYTE_LOOKUP from_ISO_8859_14;
>-extern const BYTE_LOOKUP from_ISO_8859_15;
>-
>-extern const BYTE_LOOKUP to_ISO_8859_1;
>-extern const BYTE_LOOKUP to_ISO_8859_2;
>-extern const BYTE_LOOKUP to_ISO_8859_3;
>-extern const BYTE_LOOKUP to_ISO_8859_4;
>-extern const BYTE_LOOKUP to_ISO_8859_5;
>-extern const BYTE_LOOKUP to_ISO_8859_6;
>-extern const BYTE_LOOKUP to_ISO_8859_7;
>-extern const BYTE_LOOKUP to_ISO_8859_8;
>-extern const BYTE_LOOKUP to_ISO_8859_9;
>-extern const BYTE_LOOKUP to_ISO_8859_10;
>-extern const BYTE_LOOKUP to_ISO_8859_11;
>-extern const BYTE_LOOKUP to_ISO_8859_13;
>-extern const BYTE_LOOKUP to_ISO_8859_14;
>-extern const BYTE_LOOKUP to_ISO_8859_15;
>-
>-
>-/* declarations probably need to go into separate header file, e.g. 
>transcode.h */
>-
>-/* static structure, one per supported encoding pair */
>-typedef struct {
>-    const char *from_encoding;
>-    const char *to_encoding;
>-    const BYTE_LOOKUP *conv_tree_start;
>-    int max_output;
>-    int from_utf8;
>-} transcoder;
>-
>-/* todo: dynamic structure, one per conversion (stream) */
>-
>-/* in the future, add some mechanism for dynamically adding stuff here */
>-#define MAX_TRANSCODERS 29  /* todo: fix: this number has to be adjusted 
>by hand */
>-static transcoder transcoder_table[MAX_TRANSCODERS];
>+static st_table *transcoder_table;

ハッシュにするのはありかと思います。


>+#define TRANSCODER_SEP '@'

これは内部だけの決まりだと思いましたが、ファイル名にまで使われているので、
十分検討した方がいいと思います。

> /* not sure why it's not possible to do relocatable initializations */
> /* maybe the code here can be removed (changed to simple initialization) */
> /* if we move this to another file???? */
>-static void
>-register_transcoder(const char *from_e, const char *to_e,
>-    const BYTE_LOOKUP *tree_start, int max_output, int from_utf8)
>-{
>-    static int n = 0;
>-    if (n >= MAX_TRANSCODERS) {
>-        /* we are initializing, is it okay to use rb_raise here? */
>-        rb_raise(rb_eRuntimeError /*change exception*/, "not enough 
>transcoder slots");
>-    }
>-    transcoder_table[n].from_encoding = from_e;
>-    transcoder_table[n].to_encoding = to_e;
>-    transcoder_table[n].conv_tree_start = tree_start;
>-    transcoder_table[n].max_output = max_output;
>-    transcoder_table[n].from_utf8 = from_utf8;
>-
>-    n++;
>-}
>-
>-static void
>-init_transcoder_table(void)
>+void
>+rb_register_transcoder(const char *from_e, const char *to_e,
>+                     rb_transcode_loop_func *func, const void *arg, int max_output)
> {
>-    register_transcoder("ISO-8859-1",  "UTF-8", &from_ISO_8859_1, 2, 0);
>-    register_transcoder("ISO-8859-2",  "UTF-8", &from_ISO_8859_2, 2, 0);
>-    register_transcoder("ISO-8859-3",  "UTF-8", &from_ISO_8859_3, 2, 0);
>-    register_transcoder("ISO-8859-4",  "UTF-8", &from_ISO_8859_4, 2, 0);
>-    register_transcoder("ISO-8859-5",  "UTF-8", &from_ISO_8859_5, 3, 0);
>-    register_transcoder("ISO-8859-6",  "UTF-8", &from_ISO_8859_6, 2, 0);
>-    register_transcoder("ISO-8859-7",  "UTF-8", &from_ISO_8859_7, 3, 0);
>-    register_transcoder("ISO-8859-8",  "UTF-8", &from_ISO_8859_8, 3, 0);
>-    register_transcoder("ISO-8859-9",  "UTF-8", &from_ISO_8859_9, 2, 0);
>-    register_transcoder("ISO-8859-10", "UTF-8", &from_ISO_8859_10, 3, 0);
>-    register_transcoder("ISO-8859-11", "UTF-8", &from_ISO_8859_11, 3, 0);
>-    register_transcoder("ISO-8859-13", "UTF-8", &from_ISO_8859_13, 3, 0);
>-    register_transcoder("ISO-8859-14", "UTF-8", &from_ISO_8859_14, 3, 0);
>-    register_transcoder("ISO-8859-15", "UTF-8", &from_ISO_8859_15, 3, 0);
>-    register_transcoder("UTF-8", "ISO-8859-1",  &to_ISO_8859_1, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-2",  &to_ISO_8859_2, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-3",  &to_ISO_8859_3, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-4",  &to_ISO_8859_4, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-5",  &to_ISO_8859_5, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-6",  &to_ISO_8859_6, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-7",  &to_ISO_8859_7, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-8",  &to_ISO_8859_8, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-9",  &to_ISO_8859_9, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-10", &to_ISO_8859_10, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-11", &to_ISO_8859_11, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-13", &to_ISO_8859_13, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-14", &to_ISO_8859_14, 1, 1);
>-    register_transcoder("UTF-8", "ISO-8859-15", &to_ISO_8859_15, 1, 1);
>-    register_transcoder(NULL, NULL, NULL, 0, 0);
>+    long from_len = strlen(from_e);
>+    long to_len = strlen(to_e);
>+    char *const key = xmalloc(from_len + to_len + 2);
>+    st_data_t val = 0;
>+    rb_transcoder *my_transcoder;
>+
>+    memcpy(key, from_e, from_len);
>+    memcpy(key + from_len + 1, to_e, to_len + 1);
>+    key[from_len] = TRANSCODER_SEP;
>+    if (st_lookup(transcoder_table, (st_data_t)key, &val)) {
>+      xfree(key);
>+      rb_raise(rb_eArgError, "transcoder has been already registered - %s", key);
>+    }
>+    my_transcoder = ALLOC(rb_transcoder);
>+    my_transcoder->transcode_loop = func;
>+    my_transcoder->transcode_arg = (void *)arg;
>+    my_transcoder->max_output = max_output;
>+    st_insert(transcoder_table, (st_data_t)key, (st_data_t)my_transcoder);
> }
> 
>-
>-static transcoder*
>+static rb_transcoder *
> transcode_dispatch(const char* from_encoding, const char* to_encoding)
> {
>-    transcoder *candidate = transcoder_table;
>-    
>-    for (candidate = transcoder_table; candidate->from_encoding; candidate++)
>-        if (0==strcasecmp(from_encoding, candidate->from_encoding)
>-            && 0==strcasecmp(to_encoding, candidate->to_encoding))
>-                break;
>-    /* in the future, add multistep transcoding logic here */
>-    return candidate->from_encoding ? candidate : NULL;
>+    static const char prefix[] = "enc/trans/";
>+    long from_len = strlen(from_encoding);
>+    long to_len = strlen(to_encoding);
>+    char *const path = alloca(from_len + to_len + sizeof(prefix) + 1);
>+    char *const key = path + sizeof(prefix) - 1;
>+    st_data_t val = 0;
>+    char *s;
>+
>+    memcpy(key, from_encoding, from_len);
>+    memcpy(key + from_len + 1, to_encoding, to_len + 1);
>+    key[from_len] = TRANSCODER_SEP;
>+    for (s = key; *s; ++s) {
>+      if (ISUPPER(*s)) *s = tolower(*s);

今まで見たところで、ルビ内の Encoding は全部大文字になっていますので、
なぜでここで小文字にしますか。

後、ここの memcpy などのコードは rb_register_transcoder と
すごく似ています。

>+    }
>+    if (!st_lookup(transcoder_table, (st_data_t)key, &val)) {
>+      memcpy(path, prefix, sizeof(prefix) - 1);
>+      if (!rb_require(path)) return 0;
>+      if (!st_lookup(transcoder_table, (st_data_t)key, &val)) {
>+          return 0;
>+      }
>+    }
>+    return (rb_transcoder *)val;
> }
> 
>-/* dynamic structure, one per conversion (similar to iconv_t) */
>-/* may carry conversion state (e.g. for iso-2022-jp) */
>-typedef struct transcoding {
>-    VALUE ruby_string_dest; /* the String used as the conversion destination,
>-                               or NULL if something else is being converted */
>-    char *(*flush_func)(struct transcoding*, int, int);
>-} transcoding;
>-
> 
> /*
>@@ -157,14 +89,14 @@ static void
> transcode_loop(char **in_pos, char **out_pos,
>              char *in_stop, char *out_stop,
>-             transcoder *my_transcoder,
>-             transcoding *my_transcoding)
>+             const rb_transcoder *my_transcoder,
>+             int from_utf8,

変数を増やさない方がいいと思います。

>+             rb_transcoding *my_transcoding)
> {
>     char *in_p = *in_pos, *out_p = *out_pos;
>-    const BYTE_LOOKUP *conv_tree_start = my_transcoder->conv_tree_start;
>+    const BYTE_LOOKUP *conv_tree_start = my_transcoder->transcode_arg;

変数、メンバーの名前を変える必要がないと思います。

>     const BYTE_LOOKUP *next_table;
>     unsigned int next_offset;
>     VALUE next_info;
>     unsigned char next_byte;
>-    int from_utf8 = my_transcoder->from_utf8;
>     char *out_s = out_stop - my_transcoder->max_output + 1;
>     while (in_p < in_stop) {
>@@ -238,4 +170,24 @@ transcode_loop(char **in_pos, char **out
> }
> 
>+void
>+rb_transcode_loop_from_utf8(char **in_pos, char **out_pos,
>+                          char *in_stop, char *out_stop,
>+                          const rb_transcoder *my_transcoder,
>+                          rb_transcoding *my_transcoding)
>+{
>+    transcode_loop(in_pos, out_pos, in_stop, out_stop,
>+                 my_transcoder, 1, my_transcoding);
>+}
>+
>+void
>+rb_transcode_loop_simple(char **in_pos, char **out_pos,
>+                      char *in_stop, char *out_stop,
>+                      const rb_transcoder *my_transcoder,
>+                      rb_transcoding *my_transcoding)
>+{
>+    transcode_loop(in_pos, out_pos, in_stop, out_stop,
>+                 my_transcoder, 0, my_transcoding);
>+}
>+

関数を増やす必要が現在内と思います。

> /*
>@@ -244,5 +196,5 @@ transcode_loop(char **in_pos, char **out
> 
> static char *
>-str_transcoding_resize(transcoding *my_transcoding, int len, int new_len)
>+str_transcoding_resize(rb_transcoding *my_transcoding, int len, int new_len)
> {
>     VALUE dest_string = my_transcoding->ruby_string_dest;
>@@ -261,6 +213,6 @@ str_transcode(int argc, VALUE *argv, VAL
>     int from_encidx, to_encidx;
>     VALUE from_encval, to_encval;
>-    transcoder *my_transcoder;
>-    transcoding my_transcoding;
>+    rb_transcoder *my_transcoder;
>+    rb_transcoding my_transcoding;
> 
>     if (argc<1 || argc>2) {
>@@ -312,5 +264,6 @@ str_transcode(int argc, VALUE *argv, VAL
> 
>     /* for simple testing: */
>-    transcode_loop(&fromp, &bp, (sp+slen), (bp+blen), my_transcoder, 
>&my_transcoding);
>+    my_transcoder->transcode_loop(&fromp, &bp, (sp+slen), (bp+blen),
>+                                my_transcoder->transcode_arg, &my_transcoding);

やりたいことが分かりますが、あくまでもデータ中心にやった方がいいと思います。

>     if (fromp != sp+slen) {
>       rb_raise(rb_eArgError, "not fully converted, %d bytes left", sp+slen-fromp);
>@@ -375,5 +328,5 @@ void
> Init_transcode(void)
> {
>-    init_transcoder_table();
>+    transcoder_table = st_init_strcasetable();
>     rb_define_method(rb_cString, "encode", rb_str_transcode, -1);
>     rb_define_method(rb_cString, "encode!", rb_str_transcode_bang, -1);
>Index: include/ruby/transcode.h
>===================================================================
>--- include/ruby/transcode.h   (revision 14198)
>+++ include/ruby/transcode.h   (working copy)
>@@ -1,2 +1,5 @@
>+#ifndef RUBY_TRANSCODE_H
>+#define RUBY_TRANSCODE_H
>+
> typedef unsigned char base_element;
> 
>@@ -6,10 +9,15 @@ typedef struct byte_lookup {
> } BYTE_LOOKUP;
> 
>-#ifdef TRANSCODE_DATA
>+/* dynamic structure, one per conversion (similar to iconv_t) */
>+/* may carry conversion state (e.g. for iso-2022-jp) */
>+typedef struct rb_transcoding {
>+    VALUE ruby_string_dest; /* the String used as the conversion destination,
>+                               or NULL if something else is being converted */
>+    char *(*flush_func)(struct rb_transcoding*, int, int);
>+} rb_transcoding;
>+
>+#ifndef PType
> /* data file needs to treat this as a pointer, to remove warnings */
> #define PType (const BYTE_LOOKUP *)
>-#else
>-/* in code, this is treated as just an integer */
>-#define PType (int)
> #endif
> 
>@@ -38,2 +46,23 @@ typedef struct byte_lookup {
> #define THREETRAIL     /* legal but undefined if three more trailing UTF-8 */
> 
>+/* static structure, one per supported encoding pair */
>+typedef struct rb_transcoder rb_transcoder;
>+
>+typedef void rb_transcode_loop_func(char **, char **, char *, char *,
>+                                  const struct rb_transcoder *, rb_transcoding *);
>+
>+struct rb_transcoder {
>+    rb_transcode_loop_func *transcode_loop;
>+    void *transcode_arg;
>+    int max_output;
>+};
>+
>+void rb_transcode_loop_from_utf8(char **, char **, char *, char *,
>+                              const rb_transcoder *, rb_transcoding *);
>+void rb_transcode_loop_simple(char **, char **, char *, char *,
>+                            const rb_transcoder *, rb_transcoding *);
>+
>+void rb_register_transcoder(const char *from_e, const char *to_e,
>+                          rb_transcode_loop_func *func, const void *arg,
>+                          int max_output);
>+#endif
>Index: ext/enc/trans/iso_8859/lib/iso-8859-1@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-1@utf-8.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-1@utf-8.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-1.rb

いちいち一行のファイルを作るのはちょっとやりすぎだと思います。
もうちょっといい方法はないのでしょうか。

このやり方でルビの内部でどの変換があるのか分からないという問題になる
のもよく分かります。これは例えば force_encoding の ([ruby-dev:32563]
など) と関係するだけではなく、utf-8 とか経由の二段階とかで変換するときにも
問題になりそうです。

>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-1.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-1.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-2@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-2@utf-8.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-2@utf-8.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-2.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-2.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-2.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-3@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-3@utf-8.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-3@utf-8.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-3.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-3.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-3.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-4@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-4@utf-8.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-4@utf-8.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-4.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-4.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-4.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-5@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-5@utf-8.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-5@utf-8.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-5.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-5.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-5.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-6@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-6@utf-8.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-6@utf-8.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-6.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-6.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-6.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-7@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-7@utf-8.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-7@utf-8.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-7.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-7.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-7.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-8.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-8.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-8@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-8@utf-8.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-8@utf-8.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-9.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-9.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-9.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-9@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-9@utf-8.rb     (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-9@utf-8.rb     (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-10.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-10.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-10.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-10@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-10@utf-8.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-10@utf-8.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-11.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-11.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-11.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-11@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-11@utf-8.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-11@utf-8.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-12@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-12@utf-8.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-12@utf-8.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-12.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-12.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-12.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-13@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-13@utf-8.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-13@utf-8.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-13.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-13.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-13.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-14.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-14.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-14.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-14@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-14@utf-8.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-14@utf-8.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/utf-8@iso-8859-15.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/utf-8@iso-8859-15.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/utf-8@iso-8859-15.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/lib/iso-8859-15@utf-8.rb
>===================================================================
>--- ext/enc/trans/iso_8859/lib/iso-8859-15@utf-8.rb    (revision 0)
>+++ ext/enc/trans/iso_8859/lib/iso-8859-15@utf-8.rb    (revision 0)
>@@ -0,0 +1 @@
>+require "enc/trans/iso_8859"
>Index: ext/enc/trans/iso_8859/iso_8859.c
>===================================================================
>--- ext/enc/trans/iso_8859/iso_8859.c  (revision 0)
>+++ ext/enc/trans/iso_8859/iso_8859.c  (working copy)
>@@ -1,4 +1,9 @@
>-#define TRANSCODE_DATA
>-#include "transcode_data.h"
>+#include "ruby.h"
>+#include "ruby/transcode.h"
>+
>+typedef struct {
>+    const BYTE_LOOKUP *conv_tree_start;
>+    int max_output;
>+} iso_8859_transcoder;

これは少なくともいまの段階で必要ないかと思います。

> static const unsigned char
>@@ -89,5 +94,5 @@ from_ISO_8859_1_infos[129] = {
>      output2('\xC3','\xBF'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_1 = {
>     from_ISO_8859_1_offsets,
>@@ -182,5 +187,5 @@ to_ISO_8859_1_infos[3] = {
>                  NOMAP, &to_ISO_8859_1_C2, &to_ISO_8859_1_C3,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_1 = {
>     to_ISO_8859_1_offsets,
>@@ -275,5 +280,5 @@ from_ISO_8859_2_infos[129] = {
>      output2('\xCB','\x99'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_2 = {
>     from_ISO_8859_2_offsets,
>@@ -418,5 +423,5 @@ to_ISO_8859_2_infos[6] = {
>      &to_ISO_8859_2_C5, &to_ISO_8859_2_CB,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_2 = {
>     to_ISO_8859_2_offsets,
>@@ -507,5 +512,5 @@ from_ISO_8859_3_infos[122] = {
>      output2('\xC5','\x9D'), output2('\xCB','\x99'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_3 = {
>     from_ISO_8859_3_offsets,
>@@ -649,5 +654,5 @@ to_ISO_8859_3_infos[6] = {
>      &to_ISO_8859_3_C5, &to_ISO_8859_3_CB,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_3 = {
>     to_ISO_8859_3_offsets,
>@@ -742,5 +747,5 @@ from_ISO_8859_4_infos[129] = {
>      output2('\xCB','\x99'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_4 = {
>     from_ISO_8859_4_offsets,
>@@ -886,5 +891,5 @@ to_ISO_8859_4_infos[6] = {
>      &to_ISO_8859_4_C5, &to_ISO_8859_4_CB,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_4 = {
>     to_ISO_8859_4_offsets,
>@@ -979,5 +984,5 @@ from_ISO_8859_5_infos[129] = {
>             output2('\xD1','\x9F'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_5 = {
>     from_ISO_8859_5_offsets,
>@@ -1124,5 +1129,5 @@ to_ISO_8859_5_infos[5] = {
>      &to_ISO_8859_5_E2,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_5 = {
>     to_ISO_8859_5_offsets,
>@@ -1194,5 +1199,5 @@ from_ISO_8859_6_infos[84] = {
>      output2('\xD9','\x91'), output2('\xD9','\x92'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_6 = {
>     from_ISO_8859_6_offsets,
>@@ -1293,5 +1298,5 @@ to_ISO_8859_6_infos[4] = {
>                  NOMAP, &to_ISO_8859_6_C2, &to_ISO_8859_6_D8, &to_ISO_8859_6_D9,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_6 = {
>     to_ISO_8859_6_offsets,
>@@ -1384,5 +1389,5 @@ from_ISO_8859_7_infos[126] = {
>             output2('\xCF','\x8D'),        output2('\xCF','\x8E'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_7 = {
>     from_ISO_8859_7_offsets,
>@@ -1560,5 +1565,5 @@ to_ISO_8859_7_infos[6] = {
>      &to_ISO_8859_7_CF, &to_ISO_8859_7_E2,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_7 = {
>     to_ISO_8859_7_offsets,
>@@ -1635,5 +1640,5 @@ from_ISO_8859_8_infos[93] = {
>      output3('\xE2','\x80','\x8F'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_8 = {
>     from_ISO_8859_8_offsets,
>@@ -1770,5 +1775,5 @@ to_ISO_8859_8_infos[5] = {
>      &to_ISO_8859_8_E2,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_8 = {
>     to_ISO_8859_8_offsets,
>@@ -1863,5 +1868,5 @@ from_ISO_8859_9_infos[129] = {
>      output2('\xC3','\xBF'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_9 = {
>     from_ISO_8859_9_offsets,
>@@ -1990,5 +1995,5 @@ to_ISO_8859_9_infos[5] = {
>      &to_ISO_8859_9_C5,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_9 = {
>     to_ISO_8859_9_offsets,
>@@ -2083,5 +2088,5 @@ from_ISO_8859_10_infos[129] = {
>             output2('\xC4','\xB8'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_10 = {
>     from_ISO_8859_10_offsets,
>@@ -2245,5 +2250,5 @@ to_ISO_8859_10_infos[6] = {
>      &to_ISO_8859_10_C5, &to_ISO_8859_10_E2,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_10 = {
>     to_ISO_8859_10_offsets,
>@@ -2334,5 +2339,5 @@ from_ISO_8859_11_infos[121] = {
>      output3('\xE0','\xB9','\x9B'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_11 = {
>     from_ISO_8859_11_offsets,
>@@ -2459,5 +2464,5 @@ to_ISO_8859_11_infos[3] = {
>                   NOMAP, &to_ISO_8859_11_C2, &to_ISO_8859_11_E0,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_11 = {
>     to_ISO_8859_11_offsets,
>@@ -2552,5 +2557,5 @@ from_ISO_8859_13_infos[129] = {
>      output3('\xE2','\x80','\x99'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_13 = {
>     from_ISO_8859_13_offsets,
>@@ -2712,5 +2717,5 @@ to_ISO_8859_13_infos[6] = {
>      &to_ISO_8859_13_C5, &to_ISO_8859_13_E2,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_13 = {
>     to_ISO_8859_13_offsets,
>@@ -2805,5 +2810,5 @@ from_ISO_8859_14_infos[129] = {
>             output2('\xC3','\xBF'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_14 = {
>     from_ISO_8859_14_offsets,
>@@ -3016,5 +3021,5 @@ to_ISO_8859_14_infos[6] = {
>      &to_ISO_8859_14_C5, &to_ISO_8859_14_E1,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_14 = {
>     to_ISO_8859_14_offsets,
>@@ -3109,5 +3114,5 @@ from_ISO_8859_15_infos[129] = {
>             output2('\xC3','\xBF'),
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> from_ISO_8859_15 = {
>     from_ISO_8859_15_offsets,
>@@ -3253,5 +3258,5 @@ to_ISO_8859_15_infos[5] = {
>      &to_ISO_8859_15_E2,
> };
>-const BYTE_LOOKUP
>+static const BYTE_LOOKUP
> to_ISO_8859_15 = {
>     to_ISO_8859_15_offsets,
>@@ -3259,2 +3264,40 @@ to_ISO_8859_15 = {
> };
> 
>+#define register_transcoder(from_e, to_e, tree_start, max_output, from_utf8) \
>+    rb_register_transcoder(from_e, to_e,                              \
>+                         (from_utf8 ? rb_transcode_loop_from_utf8 :   \
>+                          rb_transcode_loop_simple),                  \
>+                         tree_start, max_output)
>+
>+void
>+Init_iso_8859(void)
>+{
>+    register_transcoder("ISO-8859-1",  "UTF-8", &from_ISO_8859_1, 2, 0);
>+    register_transcoder("ISO-8859-2",  "UTF-8", &from_ISO_8859_2, 2, 0);
>+    register_transcoder("ISO-8859-3",  "UTF-8", &from_ISO_8859_3, 2, 0);
>+    register_transcoder("ISO-8859-4",  "UTF-8", &from_ISO_8859_4, 2, 0);
>+    register_transcoder("ISO-8859-5",  "UTF-8", &from_ISO_8859_5, 3, 0);
>+    register_transcoder("ISO-8859-6",  "UTF-8", &from_ISO_8859_6, 2, 0);
>+    register_transcoder("ISO-8859-7",  "UTF-8", &from_ISO_8859_7, 3, 0);
>+    register_transcoder("ISO-8859-8",  "UTF-8", &from_ISO_8859_8, 3, 0);
>+    register_transcoder("ISO-8859-9",  "UTF-8", &from_ISO_8859_9, 2, 0);
>+    register_transcoder("ISO-8859-10", "UTF-8", &from_ISO_8859_10, 3, 0);
>+    register_transcoder("ISO-8859-11", "UTF-8", &from_ISO_8859_11, 3, 0);
>+    register_transcoder("ISO-8859-13", "UTF-8", &from_ISO_8859_13, 3, 0);
>+    register_transcoder("ISO-8859-14", "UTF-8", &from_ISO_8859_14, 3, 0);
>+    register_transcoder("ISO-8859-15", "UTF-8", &from_ISO_8859_15, 3, 0);
>+    register_transcoder("UTF-8", "ISO-8859-1",  &to_ISO_8859_1, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-2",  &to_ISO_8859_2, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-3",  &to_ISO_8859_3, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-4",  &to_ISO_8859_4, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-5",  &to_ISO_8859_5, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-6",  &to_ISO_8859_6, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-7",  &to_ISO_8859_7, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-8",  &to_ISO_8859_8, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-9",  &to_ISO_8859_9, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-10", &to_ISO_8859_10, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-11", &to_ISO_8859_11, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-13", &to_ISO_8859_13, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-14", &to_ISO_8859_14, 1, 1);
>+    register_transcoder("UTF-8", "ISO-8859-15", &to_ISO_8859_15, 1, 1);
>+}
>Index: ext/enc/trans/iso_8859/extconf.rb
>===================================================================
>--- ext/enc/trans/iso_8859/extconf.rb  (revision 0)
>+++ ext/enc/trans/iso_8859/extconf.rb  (revision 0)
>@@ -0,0 +1 @@
>+create_makefile("enc/trans/iso_8859")
>
>
>-- 
>--- 僕の前にBugはない。
>--- 僕の後ろにBugはできる。
>    中田 伸悦


#-#-#  Martin J. Du"rst, Assoc. Professor, Aoyama Gakuin University
#-#-#  http://www.sw.it.aoyama.ac.jp       mailto:duerst@it.aoyama.ac.jp

Thread

Prev Next

In This Thread

Prev Next

[#32429] eval("\"\xfd".force_encoding("utf-8")) generages garbage in error message. — Tanaka Akira <akr@...>

[#32430] "wrong number of arguments (6 for 2)" by def m(a, b=:b, c, d, e) — Tanaka Akira <akr@...>

[#32432] eval("a"): illegal multibyte char — Tanaka Akira <akr@...>

[#32434] signature of exit() on C++ — "KISHIMOTO, Makoto" <ksmakoto@...4u.or.jp>

[#32447] ruby 1.9 trunk NKF and KCONV Encoding:ASCII-8BIT — WATANABE Tetsuya <Tetsuya.WATANABE@...>

[#32448] SEGV on "abcd\xf0".force_encoding("utf-8").reverse — Tanaka Akira <akr@...>

[#32451] -e:1:in `conv': no implicit conversion from nil to integer (TypeError) — Tanaka Akira <akr@...>

[#32452] `split': negative string size (or size too big) (ArgumentError) — Tanaka Akira <akr@...>

[#32459] Enumerator raises `dead fiber called' — "Yusuke ENDOH" <mame@...>

[#32462] SEGV by test/ruby/test_fiber.rb — Tanaka Akira <akr@...>

[#32468] Iconv.list patch for NetBSD/Citrus — "NARUSE, Yui" <naruse@...>

[#32473] about to_path and to_open — "Yusuke ENDOH" <mame@...>

[#32475] ext/tk/sample/tkextlib/vu/canvSticker2.rb — Tanaka Akira <akr@...>

[#32485] self-calling method dumps core — Tadashi Saito <shiba@...2.accsnet.ne.jp>

[#32493] Regexp#names, MatchData#names, MatchData#regexp — Tanaka Akira <akr@...>

[#32498] Re: [ruby-cvs:21399] Ruby:r14162 (trunk): * parse.y (expr): redefinable not (!) operator. — SASADA Koichi <ko1@...>

[#32502] :!@.inspect — Kazuhiro NISHIYAMA <zn@...>

[#32509] ruby-core:13961での問題(Error while bulding Ruby 1.9 from snapshot 2007/12/09) — KIMURA Koichi <kimura.koichi@...>

[#32512] Re: [ruby-cvs:21409] Ruby:r14172 (trunk): * transcode.c: new file to provide encoding conversion features. — Nobuyoshi Nakada <nobu@...>

[#32514] typo in lib/uri/common.rb — Ueda Satoshi <s-ueda@...>

[#32518] bug in Array#slice! — Satoshi Nakagawa <snakagawa@...>

[#32531] eigenmethod definition for BasicObjects dumps core — Tadashi Saito <shiba@...2.accsnet.ne.jp>

[#32536] timezone 関数が cygwin で見つかりません — Martin Duerst <duerst@...>

[#32550] Binary String — Hidetoshi NAGAI <nagai@...>

[#32556] default completion for irb1.9 — Tadashi Saito <shiba@...2.accsnet.ne.jp>

[#32563] transcoder loading — Nobuyoshi Nakada <nobu@...>

[#32565] Re: [ruby-cvs:21436] Ruby:r14199 (trunk): * io.c (rb_io_check_readable): set default external encoding to — Tanaka Akira <akr@...>

[#32566] hang with write — Tanaka Akira <akr@...>

[#32567] [nil, [...]] — Tanaka Akira <akr@...>

[#32569] Re: [ruby-cvs:21441] Ruby:r14204 (trunk): * io.c (rb_io_getc): use default external encoding if fptr->enc is — Tanaka Akira <akr@...>

[#32581] expandarray may mark dirty VALUE beyond stack — "Yusuke ENDOH" <mame@...>

[#32585] SEGV by IO.pipe — Tanaka Akira <akr@...>

[#32588] /(?<foo>...)/ =~ str assigns foo — Tanaka Akira <akr@...>

[#32590] Circular dependency on AIX — "Yutaka Kanemoto" <kinpoco@...>

[#32604] stack overflow by GC in a thread — Tanaka Akira <akr@...>

[#32606] encoding loading — Nobuyoshi Nakada <nobu@...>

[#32608] $! == 8 — Tanaka Akira <akr@...>

[#32609] Re: [ruby-cvs:21475] Ruby:r14238 (trunk): * configure.in (enc/Makefile): add external encoding objects list. — Yukihiro Matsumoto <matz@...>

[#32610] 1.9.1 issues left (as of 12/15) — Yukihiro Matsumoto <matz@...>

[#32622] binding of caller — Nobuyoshi Nakada <nobu@...>

[#32624] rss and base64 — Tanaka Akira <akr@...>

[#32625] Re: [ruby-cvs:21528] Ruby:r14292 (trunk): more tests. — Yukihiro Matsumoto <matz@...>

[#32628] Bignum#to_s doesn't check base — "Yusuke ENDOH" <mame@...>

[#32629] faster Bignum#* — "Yusuke ENDOH" <mame@...>

[#32631] Cygwin 上で Ruby最新版 をインストールする場合 — "Koji Tominaga" <crimsonshower@...>

[#32636] Re: [ruby-cvs:21552] Ruby:r14315 (trunk): * ext/nkf/nkf.c (NKF::_ENCODING): removed. — Tanaka Akira <akr@...>

[#32640] inspect closed dir. — Tanaka Akira <akr@...>

[#32641] interrupt in * — Tanaka Akira <akr@...>

[#32644] unparenthesized method call with block — "Yusuke ENDOH" <mame@...>

[#32645] unparenthesized method call with block — "Yusuke ENDOH" <mame@...>

[#32662] encode! は変換しないときに <nil> になってしまう。 — Martin Duerst <duerst@...>

[#32665] Net::POP3#enable_sslの仕様変更 — Shugo Maeda <shugo@...>

[#32668] syntax errors on ext/tk/sample — "U.Nakamura" <usa@...>

[#32675] /(?<break>a)/ =~ "a" 等によるローカル変数 — "Keita Yamaguchi" <keita.yamaguchi@...>

[#32677] nil.freeze in date.rb — Shugo Maeda <shugo@...>

[#32680] fail to compile version.c in trunk — Masaki Suketa <masaki.suketa@...>

[#32685] test/webrick/test_server.rb hang — Tanaka Akira <akr@...>

[#32686] enum_inject の説明文 — "Keita Yamaguchi" <keita.yamaguchi@...>

[#32687] Re: [ruby-cvs:21753] Ruby:r14516 (trunk): * lib/time.rb (Time.httpdate): use Time.utc for — Tadayoshi Funaba <tadf@...>

[#32691] Why only inject() accepts :symbols as if it's a Proc in Enumerable? — Tadashi Saito <shiba@...2.accsnet.ne.jp>

[#32693] String#== is not transitive — Tanaka Akira <akr@...>

[#32695] ISO-2022-JP output for transcode — "NARUSE, Yui" <naruse@...>

[#32699] cygwin 上で r14576 現在の test の失敗 — Martin Duerst <duerst@...>

[#32706] Fwd: RDoc: [FATAL] failed to allocate memory — Martin Duerst <duerst@...>

[#32708] Enumerable can't take multiple parameters — GOTOU Yuuzou <gotoyuzo@...>

[#32709] Re: [ruby-cvs:21826] Ruby:r14589 (trunk): Mon Dec 24 17:20:34 2007 NAKAMURA, Hiroshi <nahi@ruby-lang.org> — Tadayoshi Funaba <tadf@...>

[#32710] \e — "U.Nakamura" <usa@...>

[#32713] pre-release note for the christmas release. — Yukihiro Matsumoto <matz@...>

[#32715] issues left as of 12/25 2:00am JST — Yukihiro Matsumoto <matz@...>

[#32718] next dumps core when poped is 0 — "Yusuke ENDOH" <mame@...>

[#32725] more ANSI'ize — Tadashi Saito <shiba@...2.accsnet.ne.jp>

[#32726] Can't build on MacOSX 10.4(Tiger) (was Re: Re: 1.9.1 issues left (as of 12/15)) — "MOROHASHI Kyosuke" <moronatural@...>

[#32740] distinguish "w" and "w:euc-jp" — Tanaka Akira <akr@...>

[#32746] appendline Invalid read of size 1 — Tanaka Akira <akr@...>

[#32747] test-all on Debian/GNU etch — SASADA Koichi <ko1@...>

[#32748] resut of make test on cygwin — SASADA Koichi <ko1@...>

[#32756] make rdoc cause segv on OpenBSD — SASADA Koichi <ko1@...>

[#32763] Re: [ruby-cvs:21913] Ruby:r14676 (trunk): * trunk/common.mk, goruby.c, golf_prelude.rb: for golfers. — Yukihiro Matsumoto <matz@...>

[#32765] test/ruby/test_transcode.rb の問題 — Martin Duerst <duerst@...>

[#32767] result of test-all on FreeBSD 6.2 — SASADA Koichi <ko1@...>

[#32631] Cygwin 上で Ruby最新版をインストールする場合 — "Koji Tominaga" <crimsonshower@...>