From 4158ef02370b9cfe3a41ceefeca4ad79d4923493 Mon Sep 17 00:00:00 2001
From: iska <iska.gp@gmail.com>
Date: Sat, 11 Apr 2015 22:06:46 +0200
Subject: [PATCH] Use a accumulator-character-token in the tokenizer to reduce
 the initialization overhead

Initializing character tokens, and the NSString objects they use, results in a relatively high overhead. The tokenizer
now accumulated all successive characters in on accumulator token until a non-character token is emitted.

This change reduces the execution time of the performance test on the local machine by 48% (reference to baseline)
---
 HTMLKit/HTMLTokenizer.m                    | 16 ++++++++++------
 HTMLKitTests/HTMLKitTokenizerPerformance.m |  6 +-----
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/HTMLKit/HTMLTokenizer.m b/HTMLKit/HTMLTokenizer.m
index d64cba9..2dc8fd8 100644
--- a/HTMLKit/HTMLTokenizer.m
+++ b/HTMLKit/HTMLTokenizer.m
@@ -33,6 +33,7 @@
 
 	/* Pending Tokens & Attributes*/
 	HTMLTagToken *_currentTagToken;
+	HTMLCharacterToken *_currentCharacterToken;
 	HTMLCommentToken *_currentCommentToken;
 	HTMLDOCTYPEToken *_currentDoctypeToken;
 	NSMutableString	*_currentAttributeName;
@@ -131,6 +132,10 @@
 
 - (void)emitToken:(HTMLToken *)token
 {
+	if (_currentCharacterToken != nil) {
+		[_tokens addObject:_currentCharacterToken];
+		_currentCharacterToken = nil;
+	}
 	[_tokens addObject:token];
 }
 
@@ -174,16 +179,15 @@
 
 - (void)emitCharacterTokenWithString:(NSString *)string
 {
-	if (string == nil) {
+	if (string.length == 0) {
 		return;
 	}
 
-	HTMLToken *previousToken = [_tokens lastObject];
-	if ([previousToken isCharacterToken]) {
-		[(HTMLCharacterToken *)previousToken appendString:string];
-	} else {
-		[self emitToken:[[HTMLCharacterToken alloc] initWithString:string]];
+	if (_currentCharacterToken == nil) {
+		_currentCharacterToken = [HTMLCharacterToken new];
 	}
+
+	[_currentCharacterToken appendString:string];
 }
 
 - (void)emitParseError:(NSString *)format, ... NS_FORMAT_FUNCTION(1, 2)
diff --git a/HTMLKitTests/HTMLKitTokenizerPerformance.m b/HTMLKitTests/HTMLKitTokenizerPerformance.m
index 9aa8cfa..83c3c09 100644
--- a/HTMLKitTests/HTMLKitTokenizerPerformance.m
+++ b/HTMLKitTests/HTMLKitTokenizerPerformance.m
@@ -26,11 +26,7 @@
 
 	[self measureBlock:^{
 		HTMLTokenizer *tokenizer = [[HTMLTokenizer alloc] initWithString:string];
-
-		id token = nil;
-		do {
-			token = [tokenizer nextObject];
-		} while (token != nil);
+		[tokenizer allObjects];
 	}];
 }