【发布时间】：2011-11-18 09:24:58
【问题描述】：
我需要在一个大的NSString（用于解析源代码）中找到所有关键字，而我目前的实现速度太慢，但我不确定如何改进它。
我正在使用NSRegularExpression，假设它比我能写的任何东西都更优化，但性能比我预期的要慢。有谁知道更快的实现方法吗？
目标字符串将包含 utf-8 字符，但关键字本身将始终是纯字母数字 ascii。我想这可以用来优化一些东西？
@implementation MyClass
// i'm storing the regular expression in a static variable, since it never changes and I need to re-use it often
static NSRegularExpression *keywordsExpression;
+ (void)initialize
{
[super initialize];
NSArray *keywords = [NSArray arrayWithObjects:@"accumsan", @"adipiscing", @"aliquam", @"aliquet", @"amet", @"ante", @"arcu", @"at", @"commodo", @"congue", @"consectetur", @"consequat", @"convallis", @"cras", @"curabitur", @"cursus", @"dapibus", @"diam", @"dolor", @"dui", @"elit", @"enim", @"erat", @"eros", @"est", @"et", @"eu", @"felis", @"fermentum", @"gravida", @"iaculis", @"id", @"imperdiet", @"integer", @"ipsum", @"lacinia", @"lectus", @"leo", nil];
NSString *pattern = [NSString stringWithFormat:@"\\b(%@)\\b", [keywords componentsJoinedByString:@"|"]; // \b(accumsan|adipiscing|aliquam|…)\b
keywordsExpression = [NSRegularExpression regularExpressionWithPattern:pattern] options:NSRegularExpressionCaseInsensitive error:NULL];
}
// this method will be called in quick succession, I need it to be a able to run tens
// of thousands of times per second. The target string is big (50KB or so), but the
// search range is short, rarely more than 30 characters
- (NSRange)findNextKeyword:(NSString *)string inRange:(NSRange)range
{
return [keywordsExpression rangeOfFirstMatchInString:string options:0 range:range];
}
@end
编辑根据@CodeBrickie 的回答，我更新了我的代码以对整个字符串执行一次正则表达式搜索，并将匹配项保存到缓存的@987654324 @，然后每次调用该方法时，它都会在 NSIndexSet 中搜索关键字范围，而不是搜索字符串。结果大约快了一个数量级：
@implementation MyClass
static NSRegularExpression *keywordsExpression;
static NSIndexSet *keywordIndexes = nil;
+ (void)initialize
{
[super initialize];
NSArray *keywords = [NSArray arrayWithObjects:@"accumsan", @"adipiscing", @"aliquam", @"aliquet", @"amet", @"ante", @"arcu", @"at", @"commodo", @"congue", @"consectetur", @"consequat", @"convallis", @"cras", @"curabitur", @"cursus", @"dapibus", @"diam", @"dolor", @"dui", @"elit", @"enim", @"erat", @"eros", @"est", @"et", @"eu", @"felis", @"fermentum", @"gravida", @"iaculis", @"id", @"imperdiet", @"integer", @"ipsum", @"lacinia", @"lectus", @"leo", nil];
NSString *pattern = [NSString stringWithFormat:@"\\b(%@)\\b", [keywords componentsJoinedByString:@"|"]; // \b(accumsan|adipiscing|aliquam|…)\b
keywordsExpression = [NSRegularExpression regularExpressionWithPattern:pattern] options:NSRegularExpressionCaseInsensitive error:NULL];
}
- (void)prepareToFindKeywordsInString:(NSString *)string
{
NSMutableIndexSet *keywordIndexesMutable = [[NSIndexSet indexSet] mutableCopy];
[keywordsExpression enumerateMatchesInString:string options:0 range:NSMakeRange(0, string.length) usingBlock:^(NSTextCheckingResult *match, NSMatchingFlags flags, BOOL *stop){
[keywordIndexesMutable addIndexesInRange:match.range];
}];
keywordIndexes = [keywordIndexesMutable copy];
}
- (NSRange)findNextKeyword:(NSString *)string inRange:(NSRange)range
{
NSUInteger foundKeywordMax = (foundCharacterSetRange.location == NSNotFound) ? string.length : foundCharacterSetRange.location;
NSRange foundKeywordRange = NSMakeRange(NSNotFound, 0);
for (NSUInteger index = startingAt; index < foundKeywordMax; index++) {
if ([keywordIndexes containsIndex:index]) {
if (foundKeywordRange.location == NSNotFound) {
foundKeywordRange.location = index;
foundKeywordRange.length = 1;
} else {
foundKeywordRange.length++;
}
} else {
if (foundKeywordRange.location != NSNotFound) {
break;
}
}
}
return foundKeywordRange;
}
@end
这似乎运作良好，并且性能达到了我想要的范围。不过，我想再等一会儿，看看是否有更多建议，然后再接受。
【问题讨论】：
-
附注 - 您的
findNextKeyword:inRange:方法不应接受指向NSRange的 指针。 -
感谢@JacobRelkin，我刚刚编辑了它。这不是我的实际代码，只是仪器告诉我的部分太慢（我的 CPU 时间的 95%）
标签： objective-c regex string performance cocoa