From 09efb2e578229d19558a2f3ff858a6a6a46f4c2f Mon Sep 17 00:00:00 2001
From: neeldug <5161147+neeldug@users.noreply.github.com>
Date: Thu, 1 Jul 2021 18:58:48 +0100
Subject: [PATCH] feat(boa): adds normalize method (#1369)

* feat(boa): adds normalize method

- adds string.prototype.normalize
- uses `unicode_normalization` crate

Closes #13

* cleanup
---
 Cargo.lock                     |  1 +
 boa/Cargo.toml                 |  1 +
 boa/src/builtins/string/mod.rs | 36 ++++++++++++++++++++++++++++++++++
 3 files changed, 38 insertions(+)

diff --git a/Cargo.lock b/Cargo.lock
index 3449d6427e..2e44dda175 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -24,6 +24,7 @@ dependencies = [
  "ryu-js",
  "serde",
  "serde_json",
+ "unicode-normalization",
 ]
 
 [[package]]
diff --git a/boa/Cargo.toml b/boa/Cargo.toml
index 935b8219ee..82b4c4d04f 100644
--- a/boa/Cargo.toml
+++ b/boa/Cargo.toml
@@ -36,6 +36,7 @@ indexmap = "1.7.0"
 ryu-js = "0.2.1"
 chrono = "0.4.19"
 fast-float = "0.2.0"
+unicode-normalization = "0.1.19"
 
 # Optional Dependencies
 measureme = { version = "9.1.2", optional = true }
diff --git a/boa/src/builtins/string/mod.rs b/boa/src/builtins/string/mod.rs
index b2ee8972e0..851a28cb3c 100644
--- a/boa/src/builtins/string/mod.rs
+++ b/boa/src/builtins/string/mod.rs
@@ -30,6 +30,7 @@ use std::{
     cmp::{max, min},
     string::String as StdString,
 };
+use unicode_normalization::UnicodeNormalization;
 
 pub(crate) fn code_point_at(string: RcString, position: i32) -> Option<(u32, u8, bool)> {
     let size = string.encode_utf16().count() as i32;
@@ -119,6 +120,7 @@ impl BuiltIn for String {
         .method(Self::index_of, "indexOf", 1)
         .method(Self::last_index_of, "lastIndexOf", 1)
         .method(Self::r#match, "match", 1)
+        .method(Self::normalize, "normalize", 1)
         .method(Self::pad_end, "padEnd", 1)
         .method(Self::pad_start, "padStart", 1)
         .method(Self::trim, "trim", 0)
@@ -1329,6 +1331,40 @@ impl String {
         RegExp::match_all(&re, this.to_string(context)?.to_string(), context)
     }
 
+    /// `String.prototype.normalize( [ form ] )`
+    ///
+    /// The normalize() method normalizes a string into a form specified in the Unicode® Standard Annex #15
+    ///
+    /// More information:
+    ///  - [ECMAScript reference][spec]
+    ///  - [MDN documentation][mdn]
+    ///
+    /// [spec]: https://tc39.es/ecma262/#sec-string.prototype.normalize
+    /// [mdn]: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/normalize
+    pub(crate) fn normalize(this: &Value, args: &[Value], context: &mut Context) -> Result<Value> {
+        let this = this.require_object_coercible(context)?;
+        let s = this.to_string(context)?;
+        let form = args.get(0).cloned().unwrap_or_default();
+
+        let f_str;
+
+        let f = if form.is_undefined() {
+            "NFC"
+        } else {
+            f_str = form.to_string(context)?;
+            f_str.as_str()
+        };
+
+        match f {
+            "NFC" => Ok(Value::from(s.nfc().collect::<StdString>())),
+            "NFD" => Ok(Value::from(s.nfd().collect::<StdString>())),
+            "NFKC" => Ok(Value::from(s.nfkc().collect::<StdString>())),
+            "NFKD" => Ok(Value::from(s.nfkd().collect::<StdString>())),
+            _ => context
+                .throw_range_error("The normalization form should be one of NFC, NFD, NFKC, NFKD."),
+        }
+    }
+
     /// `String.prototype.search( regexp )`
     ///
     /// The search() method executes a search for a match between a regular expression and this String object.