idn-ruby 0.1.0

data/Rakefile

@@ -0,0 +1,60 @@
+require 'rubygems'
+require 'rake'
+require 'rake/clean'
+require 'rake/testtask'
+require 'rake/rdoctask'
+require 'rake/extensiontask'
+
+CLEAN << FileList[ 'ext/Makefile', 'ext/*.so', 'ext/*.o' ]
+
+begin
+  require 'jeweler'
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+Jeweler::Tasks.new do |gem|
+  gem.name        = 'idn-ruby'
+  gem.summary     = 'LibIDN Ruby Bindings.'
+  gem.description = %q{
+    Ruby Bindings for the GNU LibIDN library, an implementation of the
+    Stringprep, Punycode and IDNA specifications defined by the IETF
+    Internationalized Domain Names (IDN) working group.
+
+    Included are the most important parts of the Stringprep, Punycode
+    and IDNA APIs like performing Stringprep processings, encoding to
+    and decoding from Punycode strings and converting entire domain names
+    to and from the ACE encoded form.
+  }
+  gem.email       = 'deepfryed@gmail.com'
+  gem.homepage    = 'http://github.com/deepfryed/idn-ruby'
+  gem.authors     = ['Erik Abele', 'Bharanee Rathna']
+  gem.files       = FileList['CHANGES', 'LICENSE', 'NOTICE', 'Rakefile', 'README', 'ext/*.{c,h}']
+  gem.extensions  = FileList[ 'ext/**/extconf.rb' ]
+  gem.test_files  = FileList[ 'test/*.rb' ]
+end
+
+Jeweler::GemcutterTasks.new
+
+Rake::ExtensionTask.new do |ext|
+  ext.name    = 'idn'
+  ext.ext_dir = 'ext'
+  ext.lib_dir = 'ext'
+end
+
+Rake::RDocTask.new do |rdoc|
+  version       = File.exist?('VERSION') ? File.read('VERSION') : ""
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title    = "idn-ruby #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end
+
+Rake::TestTask.new(:test) do |test|
+  test.libs    << 'ext'
+  test.pattern = 'test/*.rb'
+  test.verbose = true
+end
+
+task :test    => [ :compile, :check_dependencies ]
+task :default => :test

data/ext/extconf.rb

@@ -0,0 +1,56 @@
+# Makefile configuration for LibIDN Ruby Bindings.
+#
+# Copyright (c) 2005 Erik Abele. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# Please see the file called LICENSE for further details.
+#
+# You may also obtain a copy of the License at
+#
+# * http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# This software is OSI Certified Open Source Software.
+# OSI Certified is a certification mark of the Open Source Initiative.
+
+require 'mkmf'
+
+@libs = ['idn']
+@headers = ['idna.h', 'punycode.h', 'stringprep.h']
+
+INFO_NOTE = <<EOL
+  Please install the GNU IDN library or alternatively specify at least one
+  of the following options if the library can only be found in a non-standard
+  location:
+    --with-idn-dir=/path/to/non/standard/location
+        or
+    --with-idn-lib=/path/to/non/standard/location/lib
+    --with-idn-include=/path/to/non/standard/location/include
+EOL
+
+dir_config('idn')
+
+@libs.each do |lib|
+  unless have_library(lib)
+    STDERR.puts "ERROR: could not find #{lib} library!\n" +
+                "\n#{INFO_NOTE}\n"
+    exit 1
+  end
+end
+
+@headers.each do |header|
+  unless have_header(header)
+    STDERR.puts "ERROR: could not find #{header} header file!\n" +
+                "\n#{INFO_NOTE}\n"
+    exit 1
+  end
+end
+
+$CFLAGS += ' -Wall' unless $CFLAGS.split.include? '-Wall'
+create_makefile('idn')

data/ext/idn.c

@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2005 Erik Abele. All rights reserved.
+ * Portions Copyright (c) 2005 Yuki Mitsui. All rights reserved.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * Please see the file called LICENSE for further details.
+ *
+ * You may also obtain a copy of the License at
+ *
+ * * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This software is OSI Certified Open Source Software.
+ * OSI Certified is a certification mark of the Open Source Initiative.
+ */
+
+#include <ruby.h>
+#include "idn.h"
+
+/*
+ * Document-class: IDN
+ * The main module of LibIDN Ruby Bindings.
+ *
+ * === Example usage
+ *
+ *   require 'idn'
+ *   include IDN
+ *
+ *   ...
+ */
+
+VALUE mIDN;
+
+/*
+ * Document-class: IDN::IDNError
+ * The superclass for all exceptions raised by the IDN extension.
+ */
+
+VALUE eIDNError;
+
+/*
+ * Module Initialization.
+ */
+
+void Init_idn(void)
+{
+  mIDN = rb_define_module("IDN");
+  eIDNError = rb_define_class_under(mIDN, "IDNError", rb_eStandardError);
+
+  init_idna();
+  init_punycode();
+  init_stringprep();
+}

data/ext/idn.h

@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2005 Erik Abele. All rights reserved.
+ * Portions Copyright (c) 2005 Yuki Mitsui. All rights reserved.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * Please see the file called LICENSE for further details.
+ *
+ * You may also obtain a copy of the License at
+ *
+ * * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This software is OSI Certified Open Source Software.
+ * OSI Certified is a certification mark of the Open Source Initiative.
+ */
+
+#ifndef ___IDN_IDN_H_
+#define ___IDN_IDN_H_
+
+#include <ruby.h>
+#include <ruby/encoding.h>
+
+/*
+ * idn.c
+ */
+extern VALUE mIDN;
+extern VALUE eIDNError;
+
+/*
+ * idna.c
+ */
+extern VALUE mIdna;
+extern VALUE eIdnaError;
+
+void init_idna(void);
+
+/*
+ * punycode.c
+ */
+extern VALUE mPunycode;
+extern VALUE ePunycodeError;
+
+void init_punycode(void);
+
+/*
+ * stringprep.c
+ */
+extern VALUE mStringprep;
+extern VALUE eStringprepError;
+
+void init_stringprep(void);
+
+#endif /* ___IDN_IDN_H_ */

data/ext/idna.c

@@ -0,0 +1,164 @@
+/*
+ * Copyright (c) 2005 Erik Abele. All rights reserved.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * Please see the file called LICENSE for further details.
+ *
+ * You may also obtain a copy of the License at
+ *
+ * * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This software is OSI Certified Open Source Software.
+ * OSI Certified is a certification mark of the Open Source Initiative.
+ */
+
+#include <stdlib.h>
+#include <ruby.h>
+#include <idna.h>
+#include "idn.h"
+
+/*
+ * Document-class: IDN::Idna
+ * The Idna module of LibIDN Ruby Bindings.
+ *
+ * === Example usage
+ *
+ *   require 'idn'
+ *   include IDN
+ *
+ *   puts 'ACE-Prefix: ' + Idna::ACE_PREFIX
+ *
+ *   domain = Idna.toUnicode('xn--rksmrgs-5wao1o.josefsson.org',
+ *     Idna::USE_STD3_ASCII_RULES | Idna::ALLOW_UNASSIGNED)
+ *
+ * === Constants
+ *
+ * <b>ACE_PREFIX</b>
+ * - The ACE prefix: 'xn--'.
+ *
+ * <b>ALLOW_UNASSIGNED</b>
+ * - Used as flag for toASCII/toUnicode.
+ *
+ * <b>USE_STD3_ASCII_RULES</b>
+ * - Used as flag for toASCII/toUnicode.
+ */
+
+VALUE mIdna;
+
+/*
+ * Document-class: IDN::Idna::IdnaError
+ * The base class for all exceptions raised by the IDN::Idna module.
+ */
+
+VALUE eIdnaError;
+
+/*
+ * call-seq:
+ *   IDN::Idna.toASCII(string, flags=nil) => string
+ *
+ * Converts a domain name in UTF-8 format into an ASCII string. The domain
+ * name may contain several labels, separated by dots.
+ *
+ * Raises IDN::Idna::IdnaError on failure.
+ */
+
+static VALUE toASCII(int argc, VALUE argv[], VALUE self)
+{
+  int rc;
+  char *buf;
+  VALUE str, flags, retv;
+
+  rb_scan_args(argc, argv, "11", &str, &flags);
+  str = rb_check_convert_type(str, T_STRING, "String", "to_s");
+
+  if (flags != Qnil) {
+    Check_Type(flags, T_FIXNUM);
+    flags = FIX2INT(flags);
+  } else {
+    flags = 0x0000;
+  }
+
+  rc = idna_to_ascii_8z(RSTRING_PTR(str), &buf, flags);
+
+  if (rc != IDNA_SUCCESS) {
+    xfree(buf);
+    rb_raise(eIdnaError, "%s (%d)", idna_strerror(rc), rc);
+    return Qnil;
+  }
+
+  retv = rb_str_new2(buf);
+  xfree(buf);
+  return retv;
+}
+
+/*
+ * call-seq:
+ *   IDN::Idna.toUnicode(string, flags=nil) => string
+ *
+ * Converts a possibly ACE encoded domain name in UTF-8 format into an
+ * UTF-8 string. The domain name may contain several labels, separated
+ * by dots.
+ *
+ * Raises IDN::Idna::IdnaError on failure.
+ */
+
+static VALUE toUnicode(int argc, VALUE argv[], VALUE self)
+{
+  int rc;
+  char *buf;
+  VALUE str, flags, retv;
+
+  rb_scan_args(argc, argv, "11", &str, &flags);
+  str = rb_check_convert_type(str, T_STRING, "String", "to_s");
+
+  if (flags != Qnil) {
+    Check_Type(flags, T_FIXNUM);
+    flags = FIX2INT(flags);
+  } else {
+    flags = 0x0000;
+  }
+
+  rc = idna_to_unicode_8z8z(RSTRING_PTR(str), &buf, flags);
+
+  if (rc != IDNA_SUCCESS) {
+    xfree(buf);
+    rb_raise(eIdnaError, "%s (%d)", idna_strerror(rc), rc);
+    return Qnil;
+  }
+
+  retv = rb_enc_str_new(buf, strlen(buf), rb_utf8_encoding());
+  xfree(buf);
+  return retv;
+}
+
+/*
+ * Module Initialization.
+ */
+
+void init_idna(void)
+{
+#ifdef mIDN_RDOC_HACK
+  mIDN = rb_define_module("IDN");
+  eIDNError = rb_define_class_under(mIDN, "IDNError", rb_eStandardError);
+#endif
+
+  mIdna = rb_define_module_under(mIDN, "Idna");
+  eIdnaError = rb_define_class_under(mIdna, "IdnaError", eIDNError);
+
+  rb_define_const(mIdna, "ACE_PREFIX",
+                  rb_str_new2(IDNA_ACE_PREFIX));
+  rb_define_const(mIdna, "ALLOW_UNASSIGNED",
+                  INT2FIX(IDNA_ALLOW_UNASSIGNED));
+  rb_define_const(mIdna, "USE_STD3_ASCII_RULES",
+                  INT2FIX(IDNA_USE_STD3_ASCII_RULES));
+
+  rb_define_singleton_method(mIdna, "toASCII", toASCII, -1);
+  rb_define_singleton_method(mIdna, "toUnicode", toUnicode, -1);
+}

data/ext/punycode.c

@@ -0,0 +1,160 @@
+/*
+ * Copyright (c) 2005 Erik Abele. All rights reserved.
+ * Portions Copyright (c) 2005 Yuki Mitsui. All rights reserved.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * Please see the file called LICENSE for further details.
+ *
+ * You may also obtain a copy of the License at
+ *
+ * * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * This software is OSI Certified Open Source Software.
+ * OSI Certified is a certification mark of the Open Source Initiative.
+ */
+
+#include <stdlib.h>
+#include <ruby.h>
+#include <stringprep.h>
+#include <punycode.h>
+#include "idn.h"
+
+/*
+ * Document-class: IDN::Punycode
+ * The Punycode module of LibIDN Ruby Bindings.
+ *
+ * === Example usage
+ *
+ *   require 'idn'
+ *   include IDN
+ *
+ *   str = Punycode.decode('egbpdaj6bu4bxfgehfvwxn')
+ */
+
+VALUE mPunycode;
+
+/*
+ * Document-class: IDN::Punycode::PunycodeError
+ * The base class for all exceptions raised by the IDN::Punycode module.
+ */
+
+VALUE ePunycodeError;
+
+/*
+ * call-seq:
+ *   IDN::Punycode.encode(string) => string
+ *
+ * Converts a string in UTF-8 format to Punycode.
+ *
+ * Raises IDN::Punycode::PunycodeError on failure.
+ */
+
+static VALUE encode(VALUE self, VALUE str)
+{
+  int rc;
+  punycode_uint *ustr;
+  size_t len;
+  size_t buflen = 0x100;
+  char *buf = NULL;
+  VALUE retv;
+
+  str = rb_check_convert_type(str, T_STRING, "String", "to_s");
+  ustr = stringprep_utf8_to_ucs4(RSTRING_PTR(str), RSTRING_LEN(str), &len);
+
+  while (1) {
+    buf = realloc(buf, buflen);
+
+    if (buf == NULL) {
+      xfree(ustr);
+      rb_raise(rb_eNoMemError, "cannot allocate memory (%d bytes)", (uint32_t)buflen);
+      return Qnil;
+    }
+
+    rc = punycode_encode(len, ustr, NULL, &buflen, buf);
+
+    if (rc == PUNYCODE_SUCCESS) {
+      break;
+    } else if (rc == PUNYCODE_BIG_OUTPUT) {
+      buflen += 0x100;
+    } else {
+      xfree(ustr);
+      xfree(buf);
+      rb_raise(ePunycodeError, "%s (%d)", punycode_strerror(rc), rc);
+      return Qnil;
+    }
+  }
+
+  retv = rb_str_new(buf, buflen);
+  xfree(ustr);
+  xfree(buf);
+  return retv;
+}
+
+/*
+ * call-seq:
+ *   IDN::Punycode.decode(string) => string
+ *
+ * Converts Punycode to a string in UTF-8 format.
+ *
+ * Raises IDN::Punycode::PunycodeError on failure.
+ */
+
+static VALUE decode(VALUE self, VALUE str)
+{
+  int rc;
+  punycode_uint *ustr;
+  size_t len;
+  char *buf = NULL;
+  VALUE retv;
+
+  str = rb_check_convert_type(str, T_STRING, "String", "to_s");
+
+  len = RSTRING_LEN(str);
+  ustr = malloc(len * sizeof(punycode_uint));
+
+  if (ustr == NULL) {
+    rb_raise(rb_eNoMemError, "cannot allocate memory (%d bytes)", (uint32_t)len);
+    return Qnil;
+  }
+
+  rc = punycode_decode(RSTRING_LEN(str), RSTRING_PTR(str),
+                       &len, ustr, NULL);
+
+  if (rc != PUNYCODE_SUCCESS) {
+    xfree(ustr);
+    rb_raise(ePunycodeError, "%s (%d)", punycode_strerror(rc), rc);
+    return Qnil;
+  }
+
+  buf = stringprep_ucs4_to_utf8(ustr, len, NULL, &len);
+  retv = rb_enc_str_new(buf, len, rb_utf8_encoding());
+  xfree(ustr);
+  xfree(buf);
+  return retv;
+}
+
+/*
+ * Module Initialization.
+ */
+
+void init_punycode(void)
+{
+#ifdef mIDN_RDOC_HACK
+  mIDN = rb_define_module("IDN");
+  eIDNError = rb_define_class_under(mIDN, "IDNError", rb_eStandardError);
+#endif
+
+  mPunycode = rb_define_module_under(mIDN, "Punycode");
+  ePunycodeError = rb_define_class_under(mPunycode, "PunycodeError",
+                                         eIDNError);
+
+  rb_define_singleton_method(mPunycode, "encode", encode, 1);
+  rb_define_singleton_method(mPunycode, "decode", decode, 1);
+}