From 5fee67c9bade0337b5c2c88a7fa1c1068b477803 Mon Sep 17 00:00:00 2001
From: duerst <duerst@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>
Date: Wed, 3 May 2017 12:18:37 +0000
Subject: [PATCH] move definition of String#unicode_normalize to C to make sure
 it is documented

* lib/unicode_normalize.rb: Remove definition of String#unicode_normalize
  (including documentation)
* string.c: Define String#unicode_normalize in rb_str_unicode_normalize in C,
  (including documentation)
* lib/unicode_normalize/normalize.rb: Remove (re)definition of
  String#unicode_normalize to avoid warnings (when $VERBOSE==true) and
  problems when String is frozen

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@58550 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
---
 lib/unicode_normalize.rb           | 26 ----------------
 lib/unicode_normalize/normalize.rb |  4 ---
 string.c                           | 48 ++++++++++++++++++++++++++++++
 3 files changed, 48 insertions(+), 30 deletions(-)

diff --git a/lib/unicode_normalize.rb b/lib/unicode_normalize.rb
index 0630b8627e..3f359a0ff3 100644
--- a/lib/unicode_normalize.rb
+++ b/lib/unicode_normalize.rb
@@ -8,32 +8,6 @@
 #++
 class String
 
-  # :call-seq:
-  #    str.unicode_normalize(form=:nfc)
-  #
-  # Unicode Normalization---Returns a normalized form of +str+,
-  # using Unicode normalizations NFC, NFD, NFKC, or NFKD.
-  # The normalization form used is determined by +form+, which can
-  # be any of the four values +:nfc+, +:nfd+, +:nfkc+, or +:nfkd+.
-  # The default is +:nfc+.
-  #
-  # If the string is not in a Unicode Encoding, then an Exception is raised.
-  # In this context, 'Unicode Encoding' means any of UTF-8, UTF-16BE/LE,
-  # and UTF-32BE/LE, as well as GB18030, UCS_2BE, and UCS_4BE.
-  # Anything other than UTF-8 is implemented by converting to UTF-8,
-  # which makes it slower than UTF-8.
-  #
-  #   "a\u0300".unicode_normalize        #=> 'à' (same as "\u00E0")
-  #   "a\u0300".unicode_normalize(:nfc)  #=> 'à' (same as "\u00E0")
-  #   "\u00E0".unicode_normalize(:nfd)   #=> 'à' (same as "a\u0300")
-  #   "\xE0".force_encoding('ISO-8859-1').unicode_normalize(:nfd)
-  #                                      #=> Encoding::CompatibilityError raised
-  #
-  def unicode_normalize(form = :nfc)
-    require 'unicode_normalize/normalize.rb'
-    unicode_normalize form   # no recursion, because redefined in unicode_normalize/normalize.rb
-  end
-
   # :call-seq:
   #    str.unicode_normalize!(form=:nfc)
   #
diff --git a/lib/unicode_normalize/normalize.rb b/lib/unicode_normalize/normalize.rb
index 87b84589a5..8bfbbfeea5 100644
--- a/lib/unicode_normalize/normalize.rb
+++ b/lib/unicode_normalize/normalize.rb
@@ -160,10 +160,6 @@ module UnicodeNormalize  # :nodoc:
 end # module
 
 class String  # :nodoc:
-  def unicode_normalize(form = :nfc)
-    UnicodeNormalize.normalize(self, form)
-  end
-
   def unicode_normalize!(form = :nfc)
     replace(UnicodeNormalize.normalize(self, form))
   end
diff --git a/string.c b/string.c
index cfeecd5a26..73d8f0e6fb 100644
--- a/string.c
+++ b/string.c
@@ -9582,6 +9582,48 @@ str_scrub_bang(int argc, VALUE *argv, VALUE str)
     return str;
 }
 
+static VALUE id_normalize;
+static VALUE mUnicodeNormalize;
+static int UnicodeNormalizeRequired = 0;
+
+/*
+ *  call-seq:
+ *    str.unicode_normalize(form=:nfc)
+ *
+ *  Unicode Normalization---Returns a normalized form of +str+,
+ *  using Unicode normalizations NFC, NFD, NFKC, or NFKD.
+ *  The normalization form used is determined by +form+, which can
+ *  be any of the four values +:nfc+, +:nfd+, +:nfkc+, or +:nfkd+.
+ *  The default is +:nfc+.
+ *
+ *  If the string is not in a Unicode Encoding, then an Exception is raised.
+ *  In this context, 'Unicode Encoding' means any of UTF-8, UTF-16BE/LE,
+ *  and UTF-32BE/LE, as well as GB18030, UCS_2BE, and UCS_4BE.
+ *  Anything other than UTF-8 is implemented by converting to UTF-8,
+ *  which makes it slower than UTF-8.
+ *
+ *    "a\u0300".unicode_normalize        #=> 'à' (same as "\u00E0")
+ *    "a\u0300".unicode_normalize(:nfc)  #=> 'à' (same as "\u00E0")
+ *    "\u00E0".unicode_normalize(:nfd)   #=> 'à' (same as "a\u0300")
+ *    "\xE0".force_encoding('ISO-8859-1').unicode_normalize(:nfd)
+ *                                       #=> Encoding::CompatibilityError raised
+ */
+static VALUE
+rb_str_unicode_normalize(int argc, VALUE *argv, VALUE str)
+{
+    if (!UnicodeNormalizeRequired) {
+	rb_require("unicode_normalize/normalize.rb");
+	UnicodeNormalizeRequired = 1;
+    }
+    /* return rb_funcall2(str, id_unicode_normalize, argc, argv); */
+    if (argc==0)
+	return rb_funcall(mUnicodeNormalize, id_normalize, 1, str);
+    else if (argc==1)
+	return rb_funcall(mUnicodeNormalize, id_normalize, 2, str, argv[0]);
+    else
+	rb_raise(rb_eArgError, "too many arguments to unicode_normalize");
+}
+
 /**********************************************************************
  * Document-class: Symbol
  *
@@ -10230,6 +10272,12 @@ Init_String(void)
     rb_define_method(rb_cString, "valid_encoding?", rb_str_valid_encoding_p, 0);
     rb_define_method(rb_cString, "ascii_only?", rb_str_is_ascii_only_p, 0);
 
+    /* define module here so that we don't have to look it up */
+    mUnicodeNormalize          = rb_define_module("UnicodeNormalize"); 
+    id_normalize               = rb_intern("normalize");
+
+    rb_define_method(rb_cString, "unicode_normalize", rb_str_unicode_normalize, -1);
+
     rb_fs = Qnil;
     rb_define_hooked_variable("$;", &rb_fs, 0, rb_fs_setter);
     rb_define_hooked_variable("$-F", &rb_fs, 0, rb_fs_setter);