From 1443f89d6942e19516a0fb10d25876021202ec5e Mon Sep 17 00:00:00 2001
From: BurdetteLamar <burdettelamar@yahoo.com>
Date: Sun, 16 Nov 2025 19:46:03 +0000
Subject: [PATCH] [DOC] Tweaks for String#unicode_normalize

---
 doc/string/unicode_normalize.rdoc | 28 ++++++++++++++++++++++++++++
 string.c                          | 28 +---------------------------
 2 files changed, 29 insertions(+), 27 deletions(-)
 create mode 100644 doc/string/unicode_normalize.rdoc

diff --git a/doc/string/unicode_normalize.rdoc b/doc/string/unicode_normalize.rdoc
new file mode 100644
index 00000000000..5f733c0fb84
--- /dev/null
+++ b/doc/string/unicode_normalize.rdoc
@@ -0,0 +1,28 @@
+Returns a copy of +self+ with
+{Unicode normalization}[https://unicode.org/reports/tr15] applied.
+
+Argument +form+ must be one of the following symbols
+(see {Unicode normalization forms}[https://unicode.org/reports/tr15/#Norm_Forms]):
+
+- +:nfc+: Canonical decomposition, followed by canonical composition.
+- +:nfd+: Canonical decomposition.
+- +:nfkc+: Compatibility decomposition, followed by canonical composition.
+- +:nfkd+: Compatibility decomposition.
+
+The encoding of +self+ must be one of:
+
+- <tt>Encoding::UTF_8</tt>.
+- <tt>Encoding::UTF_16BE</tt>.
+- <tt>Encoding::UTF_16LE</tt>.
+- <tt>Encoding::UTF_32BE</tt>.
+- <tt>Encoding::UTF_32LE</tt>.
+- <tt>Encoding::GB18030</tt>.
+- <tt>Encoding::UCS_2BE</tt>.
+- <tt>Encoding::UCS_4BE</tt>.
+
+Examples:
+
+  "a\u0300".unicode_normalize       # => "à"  # Lowercase 'a' with grave accens.
+  "a\u0300".unicode_normalize(:nfd) # => "à"  # Same.
+
+Related: see {Converting to New String}[rdoc-ref:String@Converting+to+New+String].
diff --git a/string.c b/string.c
index f371e185d61..d78d7320be2 100644
--- a/string.c
+++ b/string.c
@@ -11926,34 +11926,8 @@ unicode_normalize_common(int argc, VALUE *argv, VALUE str, ID id)
  *  call-seq:
  *    unicode_normalize(form = :nfc) -> string
  *
- *  Returns a copy of +self+ with
- *  {Unicode normalization}[https://unicode.org/reports/tr15] applied.
+ *  :include: doc/string/unicode_normalize.rdoc
  *
- *  Argument +form+ must be one of the following symbols
- *  (see {Unicode normalization forms}[https://unicode.org/reports/tr15/#Norm_Forms]):
- *
- *  - +:nfc+: Canonical decomposition, followed by canonical composition.
- *  - +:nfd+: Canonical decomposition.
- *  - +:nfkc+: Compatibility decomposition, followed by canonical composition.
- *  - +:nfkd+: Compatibility decomposition.
- *
- *  The encoding of +self+ must be one of:
- *
- *  - Encoding::UTF_8
- *  - Encoding::UTF_16BE
- *  - Encoding::UTF_16LE
- *  - Encoding::UTF_32BE
- *  - Encoding::UTF_32LE
- *  - Encoding::GB18030
- *  - Encoding::UCS_2BE
- *  - Encoding::UCS_4BE
- *
- *  Examples:
- *
- *    "a\u0300".unicode_normalize      # => "a"
- *    "\u00E0".unicode_normalize(:nfd) # => "a "
- *
- *  Related: String#unicode_normalize!, String#unicode_normalized?.
  */
 static VALUE
 rb_str_unicode_normalize(int argc, VALUE *argv, VALUE str)