From 7a7ec178b9fdbe8641278608cb6fb16fe9913a2e Mon Sep 17 00:00:00 2001
From: bluss <bluss@users.noreply.github.com>
Date: Tue, 4 Oct 2016 14:40:33 +0200
Subject: [PATCH] Fix ArrayString to implement .push(char) faster

Previously we used formatting, which is a virtual call and quite the
detour. Now copy the utf-8 encoding code from Rust (thank you Alex
Crichton) and use that.
---
 src/array_string.rs | 21 ++++++++++++++++--
 src/char_ext.rs     | 52 +++++++++++++++++++++++++++++++++++++++++++++
 src/lib.rs          |  1 +
 tests/tests.rs      | 15 +++++++++++++
 4 files changed, 87 insertions(+), 2 deletions(-)
 create mode 100644 src/char_ext.rs

diff --git a/src/array_string.rs b/src/array_string.rs
index ee1b0aa..d5bd904 100644
--- a/src/array_string.rs
+++ b/src/array_string.rs
@@ -10,6 +10,7 @@ use std::slice;
 use array::Array;
 use array::Index;
 use CapacityError;
+use char_ext::encode_utf8;
 
 /// A string with a fixed capacity.
 ///
@@ -108,8 +109,16 @@ impl<A: Array<Item=u8>> ArrayString<A> {
     /// assert_eq!(overflow.unwrap_err().element(), 'c');
     /// ```
     pub fn push(&mut self, c: char) -> Result<(), CapacityError<char>> {
-        use std::fmt::Write;
-        self.write_char(c).map_err(|_| CapacityError::new(c))
+        let len = self.len();
+        unsafe {
+            match encode_utf8(c, &mut self.raw_mut_bytes()[len..]) {
+                Ok(n) => {
+                    self.set_len(len + n);
+                    Ok(())
+                }
+                Err(_) => Err(CapacityError::new(c)),
+            }
+        }
     }
 
     /// Adds the given string slice to the end of the string.
@@ -169,6 +178,11 @@ impl<A: Array<Item=u8>> ArrayString<A> {
     pub fn as_str(&self) -> &str {
         self
     }
+
+    /// Return a mutable slice of the whole string's buffer
+    unsafe fn raw_mut_bytes(&mut self) -> &mut [u8] {
+        slice::from_raw_parts_mut(self.xs.as_mut_ptr(), self.capacity())
+    }
 }
 
 impl<A: Array<Item=u8>> Deref for ArrayString<A> {
@@ -237,6 +251,9 @@ impl<A: Array<Item=u8>> fmt::Display for ArrayString<A> {
 
 /// `Write` appends written data to the end of the string.
 impl<A: Array<Item=u8>> fmt::Write for ArrayString<A> {
+    fn write_char(&mut self, c: char) -> fmt::Result {
+        self.push(c).map_err(|_| fmt::Error)
+    }
     fn write_str(&mut self, s: &str) -> fmt::Result {
         self.push_str(s).map_err(|_| fmt::Error)
     }
diff --git a/src/char_ext.rs b/src/char_ext.rs
new file mode 100644
index 0000000..74d816f
--- /dev/null
+++ b/src/char_ext.rs
@@ -0,0 +1,52 @@
+// Copyright 2012-2016 The Rust Project Developers. See the COPYRIGHT
+// file at the top-level directory of this distribution and at
+// http://rust-lang.org/COPYRIGHT.
+//
+// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+//
+// Original authors: alexchrichton
+
+
+// UTF-8 ranges and tags for encoding characters
+const TAG_CONT: u8    = 0b1000_0000;
+const TAG_TWO_B: u8   = 0b1100_0000;
+const TAG_THREE_B: u8 = 0b1110_0000;
+const TAG_FOUR_B: u8  = 0b1111_0000;
+const MAX_ONE_B: u32   =     0x80;
+const MAX_TWO_B: u32   =    0x800;
+const MAX_THREE_B: u32 =  0x10000;
+
+/// Placeholder
+pub struct EncodeError;
+
+/// Encode a char into buf
+#[inline]
+pub fn encode_utf8(ch: char, buf: &mut [u8]) -> Result<usize, EncodeError>
+{
+    let code = ch as u32;
+    if code < MAX_ONE_B && buf.len() >= 1 {
+        buf[0] = code as u8;
+        return Ok(1);
+    } else if code < MAX_TWO_B && buf.len() >= 2 {
+        buf[0] = (code >> 6 & 0x1F) as u8 | TAG_TWO_B;
+        buf[1] = (code & 0x3F) as u8 | TAG_CONT;
+        return Ok(2);
+    } else if code < MAX_THREE_B && buf.len() >= 3 {
+        buf[0] = (code >> 12 & 0x0F) as u8 | TAG_THREE_B;
+        buf[1] = (code >>  6 & 0x3F) as u8 | TAG_CONT;
+        buf[2] = (code & 0x3F) as u8 | TAG_CONT;
+        return Ok(3);
+    } else if buf.len() >= 4 {
+        buf[0] = (code >> 18 & 0x07) as u8 | TAG_FOUR_B;
+        buf[1] = (code >> 12 & 0x3F) as u8 | TAG_CONT;
+        buf[2] = (code >>  6 & 0x3F) as u8 | TAG_CONT;
+        buf[3] = (code & 0x3F) as u8 | TAG_CONT;
+        return Ok(4);
+    };
+    Err(EncodeError)
+}
+
diff --git a/src/lib.rs b/src/lib.rs
index 390c691..d06798b 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -55,6 +55,7 @@ use nodrop::NoDrop;
 
 mod array;
 mod array_string;
+mod char_ext;
 
 pub use array::Array;
 pub use odds::IndexRange as RangeArgument;
diff --git a/tests/tests.rs b/tests/tests.rs
index 3dc204c..42ecc99 100644
--- a/tests/tests.rs
+++ b/tests/tests.rs
@@ -356,6 +356,21 @@ fn test_string_clone() {
     assert_eq!(&t, &s);
 }
 
+#[test]
+fn test_string_push() {
+    let text = "abcαβγ";
+    let mut s = ArrayString::<[_; 8]>::new();
+    for c in text.chars() {
+        if let Err(_) = s.push(c) {
+            break;
+        }
+    }
+    assert_eq!("abcαβ", &s[..]);
+    s.push('x').ok();
+    assert_eq!("abcαβx", &s[..]);
+    assert!(s.push('x').is_err());
+}
+
 
 #[test]
 fn test_insert_at_length() {