iOS不倒,博客不停
好久沒有更新簡書了,因為新公司,真的很忙!前幾天一直忙emoji,正好陽光明媚就記錄一下
emoji在社交類APP很常用,比如發動態,圈子,還有回復評論,還有會話
在玩弄emoji 我想這位大神更牛逼:http://www.lxweimin.com/p/3bfeb201794a
他介紹了emoji的歷史還有emoji的原理,最后是一份非常漂亮的emoji鍵盤Demo
我這里記錄的是一個我在開發過程比較惡心的東西:
Unicode與utf-8的轉碼;
后臺在處理emoji的態度,直接就是不處理,所以我們需要對emoji包括中文,數字,還有特殊字符進行編碼還有解碼
//編碼
NSString *uniStr = [NSString stringWithUTF8String:[_barrageText.text UTF8String]];
NSData *uniData = [uniStr dataUsingEncoding:NSNonLossyASCIIStringEncoding];
NSString *goodStr = [[NSString alloc] initWithData:uniData encoding:NSUTF8StringEncoding] ;
NSLog(@"---編碼--->[%@]",goodStr);
//解碼
const char *jsonString = [goodStr UTF8String]; // goodStr 服務器返回的 json
NSData *jsonData = [NSData dataWithBytes:jsonString length:strlen(jsonString)];
NSString *goodMsg1 = [[NSString alloc] initWithData:jsonData encoding:NSNonLossyASCIIStringEncoding];
NSLog(@"---解碼--->[%@]",goodMsg1);
2017-05-15 10:16:17.858 DFRomwe[650:153981] ---編碼--->[hello\ud83d\ude18\ud83d\ude18world\u4e16\u754chaha\ud83d\ude17]
2017-05-15 10:16:17.859 DFRomwe[650:153981] ---解碼--->[hello????world世界haha??]
總想著事情就能這么輕松解決!!!
可是,然后,呵呵呵,你不去了解一下東西,還是不行的
果然,后臺不作處理的情況下,如果返回JSON這就不行了,因為會默認帶有轉義字符: *** "\" *** 會導致下面這個情況:
//在這里以??表情為例,??的Unicode編碼為U+1F604,UTF-16編碼為:\ud83d\ude04
NSString * emojiUnicode = @"\U0001F604";
NSLog(@"emojiUnicode:%@",emojiUnicode);
//如果直接輸入\ud83d\ude04會報錯，加了轉義后不會報錯，但是會輸出字符串\ud83d\ude04,而不是??
NSString * emojiUTF16 = @"\\ud83d\\ude04";
NSLog(@"emojiUTF16:%@",emojiUTF16);
//轉換
emojiUTF16 = [NSString stringWithCString:[emojiUTF16 cStringUsingEncoding:NSUTF8StringEncoding] encoding:NSNonLossyASCIIStringEncoding];
NSLog(@"emojiUnicode2:%@",emojiUTF16);
輸出:
emojiUnicode:??
emojiUnicode1:\ud83d\ude04
emojiUnicode2:??
果斷百度另外的方法
//解碼
- (NSString *)decodeEmoji{
NSString *tepStr1 ;
if ([self containsString:@"\\u"]) {
tepStr1 = [self stringByReplacingOccurrencesOfString:@"\\u"withString:@"\U"];
}else{
tepStr1 = [self stringByReplacingOccurrencesOfString:@"\u"withString:@"\U"];
}
NSString *tepStr2 = [tepStr1 stringByReplacingOccurrencesOfString:@"""withString:@"\""];
NSString *tepStr3 = [[@""" stringByAppendingString:tepStr2]stringByAppendingString:@"""];
NSData *tepData = [tepStr3 dataUsingEncoding:NSUTF8StringEncoding];
NSString *axiba = [NSPropertyListSerialization propertyListWithData:tepData options:NSPropertyListMutableContainers format:NULL error:NULL];
return [axiba stringByReplacingOccurrencesOfString:@"\r\n"withString:@"\n"];
}
//編碼
- (NSString *)encodeEmoji{
NSUInteger length = [self length];
NSMutableString *s = [NSMutableString stringWithCapacity:0];
for (int i = 0;i < length; i++){
unichar _char = [self characterAtIndex:i];
//判斷是否為英文和數字
if (_char <= '9' && _char >='0'){
[s appendFormat:@"%@",[self substringWithRange:NSMakeRange(i,1)]];
}else if(_char >='a' && _char <= 'z'){
[s appendFormat:@"%@",[self substringWithRange:NSMakeRange(i,1)]];
}else if(_char >='A' && _char <= 'Z')
{
[s appendFormat:@"%@",[self substringWithRange:NSMakeRange(i,1)]];
}else{
[s appendFormat:@"\\"];
[s appendFormat:@"\\u%x",[self characterAtIndex:i]];
}
}
return s;
}
這是從JSON解碼與編碼,其實原理也很簡單:
- A :就是把多余的轉義斜杠扔掉,
- B :然后Unicode轉utf-8;
- C :然后utf-8轉Unicode;
這里我寫了一個NSString的一個分類:#import "NSString+Emoji.h"
還添加了一些方法:
//判斷是否存在emoji表情:因為emoji表情室友Unicode編碼區間的
+ (BOOL)stringContainsEmoji:(NSString *)string
{
__block BOOL returnValue = NO;
[string enumerateSubstringsInRange:NSMakeRange(0, [string length])
options:NSStringEnumerationByComposedCharacterSequences
usingBlock:^(NSString *substring, NSRange substringRange, NSRange enclosingRange, BOOL *stop) {
const unichar hs = [substring characterAtIndex:0];
if (0xd800 <= hs && hs <= 0xdbff) {
if (substring.length > 1) {
const unichar ls = [substring characterAtIndex:1];
const int uc = ((hs - 0xd800) * 0x400) + (ls - 0xdc00) + 0x10000;
if (0x1d000 <= uc && uc <= 0x1f77f) {
returnValue = YES;
}
}
} else if (substring.length > 1) {
const unichar ls = [substring characterAtIndex:1];
if (ls == 0x20e3) {
returnValue = YES;
}
} else {
if (0x2100 <= hs && hs <= 0x27ff) {
returnValue = YES;
} else if (0x2B05 <= hs && hs <= 0x2b07) {
returnValue = YES;
} else if (0x2934 <= hs && hs <= 0x2935) {
returnValue = YES;
} else if (0x3297 <= hs && hs <= 0x3299) {
returnValue = YES;
} else if (hs == 0xa9 || hs == 0xae || hs == 0x303d || hs == 0x3030 || hs == 0x2b55 || hs == 0x2b1c || hs == 0x2b1b || hs == 0x2b50) {
returnValue = YES;
}
}
}];
return returnValue;
}
//判斷是否存在中文
//因為要保證之前的utf-8的數據也能顯示
- (BOOL)includeChinese
{
for(int i=0; i< [self length];i++)
{
int a =[self characterAtIndex:i];
if( a >0x4e00&& a <0x9fff){
return YES;
}
}
return NO;
}
//判斷是否以中文開頭
- (BOOL)JudgeChineseFirst{
//是否以中文開頭(unicode中文編碼范圍是0x4e00~0x9fa5)
int utfCode = 0;
void *buffer = &utfCode;
NSRange range = NSMakeRange(0, 1);
//判斷是不是中文開頭的,buffer->獲取字符的字節數據 maxLength->buffer的最大長度 usedLength->實際寫入的長度，不需要的話可以傳遞NULL encoding->字符編碼常數，不同編碼方式轉換后的字節長是不一樣的，這里我用了UTF16 Little-Endian，maxLength為2字節，如果使用Unicode，則需要4字節 options->編碼轉換的選項，有兩個值，分別是NSStringEncodingConversionAllowLossy和NSStringEncodingConversionExternalRepresentation range->獲取的字符串中的字符范圍,這里設置的第一個字符 remainingRange->建議獲取的范圍，可以傳遞NULL
BOOL b = [self getBytes:buffer maxLength:2 usedLength:NULL encoding:NSUTF16LittleEndianStringEncoding options:NSStringEncodingConversionExternalRepresentation range:range remainingRange:NULL];
if (b && (utfCode >= 0x4e00 && utfCode <= 0x9fa5))
return YES;
else
return NO;
}
