* transcode_data.h (rb_transcoding): new field "stateful".

  (rb_transcoder): preprocessor and postprocessor field removed.
  change arguments of func_ii, func_si, func_io and func_so.
  new field "finish_func".

* tool/transcode-tblgen.rb: make FUNii, FUNsi and FUNio
  generatable.

* transcode.c (transcoder_lib_table): removed.
  (transcoder_table): change structure.
  (transcoder_key): removed because the above structure change.
  (make_transcoder_entry): new function.
  (get_transcoder_entry): ditto.
  (rb_register_transcoder): follow the structure change.
  (declare_transcoder): ditto.
  (transcode_search_path): new function for breadth first search to
  find a list of converters.
  (transcode_search_path_i): new function.
  (transcode_dispatch_cb): ditto.
  (transcode_dispatch): use transcode_search_path.
  (transcode_loop): follow the argument change.
  (str_transcode): preprocessor and postprocessor stuff removed.

* enc/trans/iso2022.erb.c: new file.  ISO-2022-JP conversion
  re-implemented.

* enc/trans/japanese.erb.c: ISO-2022-JP stuff removed.

nute(23:52:53)% head -40 ChangeLog
Thu Aug  7 23:43:11 2008  Tanaka Akira  <akr@fsij.org>

* transcode_data.h (rb_transcoding): new field "stateful".
  (rb_transcoder): preprocessor and postprocessor field removed.
  change arguments of func_ii, func_si, func_io and func_so.
  new field "finish_func".

* tool/transcode-tblgen.rb: make FUNii, FUNsi and FUNio
  generatable.

* transcode.c (transcoder_lib_table): removed.
  (transcoder_table): change structure.
  (transcoder_key): removed because the above structure change.
  (make_transcoder_entry): new function.
  (get_transcoder_entry): ditto.
  (rb_register_transcoder): follow the structure change.
  (declare_transcoder): ditto.
  (transcode_search_path): new function for breadth first search to
  find a list of converters.
  (transcode_search_path_i): new function.
  (transcode_dispatch_cb): ditto.
  (transcode_dispatch): use transcode_search_path.
  (transcode_loop): follow the argument change.
  (str_transcode): preprocessor and postprocessor stuff removed.

* enc/trans/iso2022.erb.c: new file.  ISO-2022-JP conversion
  re-implemented.

* enc/trans/japanese.erb.c: ISO-2022-JP stuff removed.

* enc/trans/utf_16_32.erb.c: follow argument change of FUNso.

[ruby-dev:35798]


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@18419 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 142 insertions, 0 deletions

diff --git a/enc/trans/iso2022.erb.c b/enc/trans/iso2022.erb.c
new file mode 100644
index 0000000000..c3f6be693c
--- /dev/null
+++ b/enc/trans/iso2022.erb.c
@@ -0,0 +1,142 @@
+#include "transcode_data.h"
+
+<%
+  map = {}
+  map["1b2842"] = :func_so       # designate US-ASCII to G0.             "ESC ( B"
+  map["1b284a"] = :func_so       # designate JIS X 0201 latin to G0.     "ESC ( J"
+  map["1b2440"] = :func_so       # designate JIS X 0208 1978 to G0.      "ESC $ @"
+  map["1b2442"] = :func_so       # designate JIS X 0208 1983 to G0.      "ESC $ B"
+  map["{00-0d,10-1a,1c-7f}"] = :func_si
+
+  map_jisx0208_rest = {}
+  map_jisx0208_rest["{21-7e}"] = :func_so
+%>
+
+<%= transcode_generate_node(ActionMap.parse(map), "iso2022jp_to_eucjp", []) %>
+<%= transcode_generate_node(ActionMap.parse(map_jisx0208_rest), "iso2022jp_to_eucjp_jisx0208_rest", []) %>
+
+static VALUE
+fun_si_iso2022jp_to_eucjp(rb_transcoding* t, const unsigned char* s, size_t l)
+{
+    if (t->stateful[0] == 0)
+        return (VALUE)NOMAP;
+    else if (0x21 <= s[0] && s[0] <= 0x7e)
+        return (VALUE)&iso2022jp_to_eucjp_jisx0208_rest;
+    else
+        return (VALUE)INVALID;
+}
+
+static int
+fun_so_iso2022jp_to_eucjp(rb_transcoding* t, const unsigned char* s, size_t l, unsigned char* o)
+{
+    if (s[0] == 0x1b) {
+        if (s[1] == '(') {
+            switch (s[l-1]) {
+              case 'B':
+              case 'J':
+                t->stateful[0] = 0;
+                break;
+            }
+        }
+        else {
+            switch (s[l-1]) {
+              case '@':
+              case 'B':
+                t->stateful[0] = 1;
+                break;
+            }
+        }
+        return 0;
+    }
+    else {
+        o[0] = s[0] | 0x80;
+        o[1] = s[1] | 0x80;
+        return 2;
+    }
+}
+
+static const rb_transcoder
+rb_ISO_2022_JP_to_EUC_JP = {
+    "ISO-2022-JP", "EUC-JP", &iso2022jp_to_eucjp, 3, 0,
+    NULL, fun_si_iso2022jp_to_eucjp, NULL, fun_so_iso2022jp_to_eucjp
+};
+
+<%
+  map_eucjp = {
+    "{0e,0f,1b}" => :undef,
+    "{00-0d,10-1a,1c-7f}" => :func_so,
+    "{a1-fe}{a1-fe}" => :func_so,
+    "8e{a1-fe}" => :undef,
+    "8f{a1-fe}{a1-fe}" => :undef,
+  }
+%>
+
+<%= transcode_generate_node(ActionMap.parse(map_eucjp), "eucjp_to_iso2022jp", []) %>
+
+static int
+fun_so_eucjp_to_iso2022jp(rb_transcoding *t, const unsigned char *s, size_t l, unsigned char *o)
+{
+    unsigned char *output0 = o;
+
+    if (t->stateful[0] == 0) {
+        t->stateful[0] = 1; /* initialized flag */
+        t->stateful[1] = 1; /* ASCII mode */
+    }
+
+    if (l != t->stateful[1]) {
+        if (l == 1) {
+            *o++ = 0x1b;
+            *o++ = '(';
+            *o++ = 'B';
+            t->stateful[1] = 1;
+        }
+        else {
+            *o++ = 0x1b;
+            *o++ = '$';
+            *o++ = 'B';
+            t->stateful[1] = 2;
+        }
+    }
+
+    if (l == 1) {
+        *o++ = s[0] & 0x7f;
+    }
+    else {
+        *o++ = s[0] & 0x7f;
+        *o++ = s[1] & 0x7f;
+    }
+
+    return o - output0;
+}
+
+static int
+finish_eucjp_to_iso2022jp(rb_transcoding *t, unsigned char *o)
+{
+    unsigned char *output0 = o;
+
+    if (t->stateful[0] == 0)
+        return 0;
+
+    if (t->stateful[1] != 1) {
+        *o++ = 0x1b;
+        *o++ = '(';
+        *o++ = 'B';
+        t->stateful[1] = 1;
+    }
+
+    return o - output0;
+}
+
+static const rb_transcoder
+rb_EUC_JP_to_ISO_2022_JP = {
+    "EUC-JP", "ISO-2022-JP", &eucjp_to_iso2022jp, 5, 0,
+    NULL, NULL, NULL, fun_so_eucjp_to_iso2022jp, finish_eucjp_to_iso2022jp
+};
+
+void
+Init_iso2022(void)
+{
+    rb_register_transcoder(&rb_ISO_2022_JP_to_EUC_JP);
+    rb_register_transcoder(&rb_EUC_JP_to_ISO_2022_JP);
+}
+