nkf 0.1.3 → 0.3.0

data/ext/nkf/nkf.c

@@ -9,50 +9,44 @@
 
 #define RUBY_NKF_REVISION "$Revision$"
 #define RUBY_NKF_VERSION NKF_VERSION " (" NKF_RELEASE_DATE ")"
-#define NKF_GEM_VERSION "0.1.3"
+#define NKF_GEM_VERSION "0.3.0"
 
 #include "ruby/ruby.h"
 #include "ruby/encoding.h"
 
 /* Replace nkf's getchar/putchar for variable modification */
-/* we never use getc, ungetc */
+/* we never use ungetc */
 
 #undef getc
 #undef ungetc
-#define getc(f)         (input_ctr>=i_len?-1:input[input_ctr++])
-#define ungetc(c,f)     input_ctr--
+#define getc(f)         rb_nkf_getc(nkf_state)
+#define ungetc(c,f)     rb_nkf_ungetc(nkf_state, c)
 
 #define INCSIZE         32
 #undef putchar
 #undef TRUE
 #undef FALSE
-#define putchar(c)      rb_nkf_putchar(c)
+#define putchar(c)      rb_nkf_putchar(nkf_state, c)
 
 /* Input/Output pointers */
 
-static unsigned char *output;
-static unsigned char *input;
-static int input_ctr;
-static int i_len;
-static int output_ctr;
-static int o_len;
-static int incsize;
-
-static VALUE result;
-
-static int
-rb_nkf_putchar(unsigned int c)
-{
-  if (output_ctr >= o_len) {
-    o_len += incsize;
-    rb_str_resize(result, o_len);
-    incsize *= 2;
-    output = (unsigned char *)RSTRING_PTR(result);
-  }
-  output[output_ctr++] = c;
-
-  return c;
-}
+typedef struct {
+    unsigned char *input;
+    int input_ctr;
+    int i_len;
+    unsigned char *output;
+    int output_ctr;
+    int o_len;
+    int incsize;
+    VALUE result;
+} rb_nkf_callback_state_t;
+
+struct nkf_state_t;
+static int rb_nkf_getc(struct nkf_state_t *nkf_state);
+#if 0
+static int rb_nkf_ungetc(struct nkf_state_t *nkf_state, int c);
+#endif
+static int rb_nkf_putchar(struct nkf_state_t *nkf_state, unsigned int c);
 
 /* Include kanji filter main part */
 /* getchar and putchar will be replaced during inclusion */
@@ -62,6 +56,42 @@ rb_nkf_putchar(unsigned int c)
 #include "nkf-utf8/utf8tbl.c"
 #include "nkf-utf8/nkf.c"
 
+static int
+rb_nkf_getc(nkf_state_t *nkf_state)
+{
+    rb_nkf_callback_state_t *callback_state = nkf_state->callback_arg;
+
+    return callback_state->input_ctr >= callback_state->i_len ?
+        -1 : callback_state->input[callback_state->input_ctr++];
+}
+
+#if 0
+static int
+rb_nkf_ungetc(nkf_state_t *nkf_state, int c)
+{
+    rb_nkf_callback_state_t *callback_state = nkf_state->callback_arg;
+
+    callback_state->input_ctr--;
+    return c;
+}
+#endif
+
+static int
+rb_nkf_putchar(nkf_state_t *nkf_state, unsigned int c)
+{
+    rb_nkf_callback_state_t *callback_state = nkf_state->callback_arg;
+
+    if (callback_state->output_ctr >= callback_state->o_len) {
+        callback_state->o_len += callback_state->incsize;
+        rb_str_resize(callback_state->result, callback_state->o_len);
+        callback_state->incsize *= 2;
+        callback_state->output = (unsigned char *)RSTRING_PTR(callback_state->result);
+    }
+    callback_state->output[callback_state->output_ctr++] = c;
+
+    return c;
+}
+
 rb_encoding* rb_nkf_enc_get(const char *name)
 {
     int idx = rb_enc_find_index(name);
@@ -75,7 +105,7 @@ rb_encoding* rb_nkf_enc_get(const char *name)
     return rb_enc_from_index(idx);
 }
 
-int nkf_split_options(const char *arg)
+static int nkf_split_options(nkf_state_t *nkf_state, const char *arg)
 {
     int count = 0;
     unsigned char option[256];
@@ -109,7 +139,7 @@ int nkf_split_options(const char *arg)
             is_double_quoted = TRUE;
         }else if(arg[i] == ' '){
             option[j] = '\0';
-            options(option);
+            options(nkf_state, option);
             j = 0;
         }else{
             option[j++] = arg[i];
@@ -117,7 +147,7 @@ int nkf_split_options(const char *arg)
     }
     if(j){
         option[j] = '\0';
-        options(option);
+        options(nkf_state, option);
     }
     return count;
 }
@@ -136,10 +166,16 @@ int nkf_split_options(const char *arg)
 static VALUE
 rb_nkf_convert(VALUE obj, VALUE opt, VALUE src)
 {
+    nkf_state_t nkf_state_object = {0};
+    nkf_state_t *nkf_state = &nkf_state_object;
+    rb_nkf_callback_state_t callback_state;
     VALUE tmp;
-    reinit();
-    nkf_split_options(StringValueCStr(opt));
-    if (!output_encoding) rb_raise(rb_eArgError, "no output encoding given");
+    nkf_state_init(nkf_state);
+    nkf_split_options(nkf_state, StringValueCStr(opt));
+    if (!output_encoding) {
+        nkf_state_dispose(nkf_state);
+        rb_raise(rb_eArgError, "no output encoding given");
+    }
 
     switch (nkf_enc_to_index(output_encoding)) {
     case UTF_8_BOM:    output_encoding = nkf_enc_from_index(UTF_8); break;
@@ -150,31 +186,33 @@ rb_nkf_convert(VALUE obj, VALUE opt, VALUE src)
     }
     output_bom_f = FALSE;
 
-    incsize = INCSIZE;
+    callback_state.incsize = INCSIZE;
 
-    input_ctr = 0;
-    input = (unsigned char *)StringValuePtr(src);
-    i_len = RSTRING_LENINT(src);
-    tmp = rb_str_new(0, i_len*3 + 10);
+    callback_state.input_ctr = 0;
+    callback_state.input = (unsigned char *)StringValuePtr(src);
+    callback_state.i_len = RSTRING_LENINT(src);
+    tmp = rb_str_new(0, callback_state.i_len*3 + 10);
 
-    output_ctr = 0;
-    output     = (unsigned char *)RSTRING_PTR(tmp);
-    o_len      = RSTRING_LENINT(tmp);
-    *output    = '\0';
+    callback_state.output_ctr = 0;
+    callback_state.output     = (unsigned char *)RSTRING_PTR(tmp);
+    callback_state.o_len      = RSTRING_LENINT(tmp);
+    callback_state.result     = tmp;
+    *callback_state.output    = '\0';
 
     /* use _result_ begin*/
-    result = tmp;
-    kanji_convert(NULL);
-    result = Qnil;
+    nkf_state->callback_arg = &callback_state;
+    kanji_convert(nkf_state, NULL);
+    nkf_state->callback_arg = NULL;
     /* use _result_ end */
 
-    rb_str_set_len(tmp, output_ctr);
+    rb_str_set_len(tmp, callback_state.output_ctr);
 
     if (mimeout_f)
         rb_enc_associate(tmp, rb_usascii_encoding());
     else
         rb_enc_associate(tmp, rb_nkf_enc_get(nkf_enc_name(output_encoding)));
 
+    nkf_state_dispose(nkf_state);
     return tmp;
 }
 
@@ -190,17 +228,23 @@ rb_nkf_convert(VALUE obj, VALUE opt, VALUE src)
 static VALUE
 rb_nkf_guess(VALUE obj, VALUE src)
 {
-    reinit();
+    nkf_state_t nkf_state_object = {0};
+    nkf_state_t *nkf_state = &nkf_state_object;
+    rb_nkf_callback_state_t callback_state = {0};
+    VALUE guessed;
+    nkf_state_init(nkf_state);
 
-    input_ctr = 0;
-    input = (unsigned char *)StringValuePtr(src);
-    i_len = RSTRING_LENINT(src);
+    callback_state.input_ctr = 0;
+    callback_state.input = (unsigned char *)StringValuePtr(src);
+    callback_state.i_len = RSTRING_LENINT(src);
 
     guess_f = TRUE;
-    kanji_convert( NULL );
-    guess_f = FALSE;
+    nkf_state->callback_arg = &callback_state;
+    kanji_convert(nkf_state, NULL);
 
-    return rb_enc_from_encoding(rb_nkf_enc_get(get_guessed_code()));
+    guessed = rb_enc_from_encoding(rb_nkf_enc_get(get_guessed_code(nkf_state)));
+    nkf_state_dispose(nkf_state);
+    return guessed;
 }
 
 
@@ -477,6 +521,10 @@ rb_nkf_guess(VALUE obj, VALUE src)
 void
 Init_nkf(void)
 {
+#ifdef HAVE_RB_EXT_RACTOR_SAFE
+    rb_ext_ractor_safe(true);
+#endif
+
     VALUE mNKF = rb_define_module("NKF");
 
     rb_define_module_function(mNKF, "nkf", rb_nkf_convert, 2);

data/lib/nkf.rb

@@ -0,0 +1,6 @@
+if RUBY_ENGINE == "jruby"
+  require 'nkf.jar'
+  JRuby::Util.load_ext('org.jruby.ext.nkf.NKFLibrary')
+else
+  require 'nkf.so'
+end

data/nkf.gemspec

@@ -11,8 +11,8 @@ end
 Gem::Specification.new do |spec|
   spec.name          = "nkf"
   spec.version       = source_version
-  spec.authors       = ["NARUSE Yui"]
-  spec.email         = ["naruse@airemix.jp"]
+  spec.authors       = ["NARUSE Yui", "Charles Oliver Nutter"]
+  spec.email         = ["naruse@airemix.jp", "headius@headius.com"]
 
   spec.summary       = %q{Ruby extension for Network Kanji Filter}
   spec.description   = %q{Ruby extension for Network Kanji Filter}
@@ -22,14 +22,23 @@ Gem::Specification.new do |spec|
 
   spec.metadata["homepage_uri"] = spec.homepage
   spec.metadata["source_code_uri"] = spec.homepage
+  spec.metadata["changelog_uri"] = spec.homepage + "/releases"
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
   spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
-    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features|bin|.github|test_sig)/}) }
   end
+
+  if Gem::Platform === spec.platform and spec.platform =~ 'java' or RUBY_ENGINE == 'jruby'
+    spec.platform = 'java'
+    spec.licenses      += ["EPL-2.0", "LGPL-2.1"]
+    spec.files += Dir["lib/nkf.jar"]
+  else
+    spec.extensions    = ["ext/nkf/extconf.rb"]
+  end
+
   spec.bindir        = "exe"
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
-  spec.extensions    = ["ext/nkf/extconf.rb"]
 end

data/sig/kconv.rbs

@@ -0,0 +1,166 @@
+# <!-- rdoc-file=lib/kconv.rb -->
+# Kanji Converter for Ruby.
+#
+module Kconv
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # ASCII
+  #
+  ASCII: Encoding
+
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # Auto-Detect
+  #
+  AUTO: nil
+
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # BINARY
+  #
+  BINARY: Encoding
+
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # EUC-JP
+  #
+  EUC: Encoding
+
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # ISO-2022-JP
+  #
+  JIS: Encoding
+
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # NOCONV
+  #
+  NOCONV: nil
+
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # Shift_JIS
+  #
+  SJIS: Encoding
+
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # UNKNOWN
+  #
+  UNKNOWN: nil
+
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # UTF-16
+  #
+  UTF16: Encoding
+
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # UTF-32
+  #
+  UTF32: Encoding
+
+  # <!-- rdoc-file=lib/kconv.rb -->
+  # UTF-8
+  #
+  UTF8: Encoding
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.guess(str)   => encoding
+  # -->
+  # Guess input encoding by NKF.guess
+  #
+  def self.guess: (String str) -> Encoding
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.iseuc(str)   => true or false
+  # -->
+  # Returns whether input encoding is EUC-JP or not.
+  #
+  # **Note** don't expect this return value is MatchData.
+  #
+  def self.iseuc: (String str) -> bool
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.isjis(str)   => true or false
+  # -->
+  # Returns whether input encoding is ISO-2022-JP or not.
+  #
+  def self.isjis: (String str) -> bool
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.issjis(str)   => true or false
+  # -->
+  # Returns whether input encoding is Shift_JIS or not.
+  #
+  def self.issjis: (String str) -> bool
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.isutf8(str)   => true or false
+  # -->
+  # Returns whether input encoding is UTF-8 or not.
+  #
+  def self.isutf8: (String str) -> bool
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.kconv(str, to_enc, from_enc=nil)
+  # -->
+  # Convert `str` to `to_enc`. `to_enc` and `from_enc` are given as constants of
+  # Kconv or Encoding objects.
+  #
+  def self.kconv: (String str, Encoding? out_code, ?Encoding? in_code) -> String
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.toeuc(str)   => string
+  # -->
+  # Convert `str` to EUC-JP
+  #
+  def self.toeuc: (String str) -> String
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.tojis(str)   => string
+  # -->
+  # Convert `str` to ISO-2022-JP
+  #
+  def self.tojis: (String str) -> String
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.tolocale   => string
+  # -->
+  # Convert `self` to locale encoding
+  #
+  def self.tolocale: (String str) -> String
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.tosjis(str)   => string
+  # -->
+  # Convert `str` to Shift_JIS
+  #
+  def self.tosjis: (String str) -> String
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.toutf16(str)   => string
+  # -->
+  # Convert `str` to UTF-16
+  #
+  def self.toutf16: (String str) -> String
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.toutf32(str)   => string
+  # -->
+  # Convert `str` to UTF-32
+  #
+  def self.toutf32: (String str) -> String
+
+  # <!--
+  #   rdoc-file=lib/kconv.rb
+  #   - Kconv.toutf8(str)   => string
+  # -->
+  # Convert `str` to UTF-8
+  #
+  def self.toutf8: (String str) -> String
+end