IOS 实现TXT文本自动识别编码的方法

from :http://kyoworkios.blog.51cto.com/878347/1344013

TXT识别编码是个复杂的问题。幸好有c/c++的一个库能识别。

库的叫uchardet，可以自己去github下载。但是没有具体的使用手册什么的。小研究了下 。

把uchardet文件夹下的.h和.cpp和.tab文件全部copy到自己的应用里面。然后在要自动识别编码的地方

#include "uchardet.h"

如下代码实现。

//

// EBOOKReadViewController.m

// EBOOk

//

// Created by 赵锋 on 13-12-18.

// Copyright (c) 2013年赵锋. All rights reserved.

//

#import "EBOOKReadViewController.h"

#include "uchardet.h"

#define NUMBER_OF_SAMPLES (2048)

@interfaceEBOOKReadViewController ()

{

constchar *encode;

}

@end

@implementation EBOOKReadViewController

- (id)initWithNibName:(NSString *)nibNameOrNil bundle:(NSBundle *)nibBundleOrNil

{

self = [superinitWithNibName:nibNameOrNil bundle:nibBundleOrNil];

if (self) {

// Custom initialization

}

returnself;

}

- (void)viewDidLoad

{

[superviewDidLoad];

NSString *path=[[NSBundlemainBundle] pathForResource:@"五界至尊" ofType:@"txt"];

int result=[selfhaveTextBianMa:[path UTF8String]];

CFStringEncoding cfEncode = 0;

if (result==0) {

NSString *encodeStr=[[NSStringalloc] initWithCString:encodeencoding:NSUTF8StringEncoding];

if ([encodeStr isEqualToString:@"gb18030"]) {

cfEncode= kCFStringEncodingGB_18030_2000;

}elseif([encodeStr isEqualToString:@"Big5"]){

cfEncode= kCFStringEncodingBig5;

}elseif([encodeStr isEqualToString:@"UTF-8"]){

cfEncode= kCFStringEncodingUTF8;

}elseif([encodeStr isEqualToString:@"Shift_JIS"]){

cfEncode= kCFStringEncodingShiftJIS;

}elseif([encodeStr isEqualToString:@"windows-1252"]){

cfEncode= kCFStringEncodingWindowsLatin1;

}elseif([encodeStr isEqualToString:@"x-euc-tw"]){

cfEncode= kCFStringEncodingEUC_TW;

}elseif([encodeStr isEqualToString:@"EUC-KR"]){

cfEncode= kCFStringEncodingEUC_KR;

}elseif([encodeStr isEqualToString:@"EUC-JP"]){

cfEncode= kCFStringEncodingEUC_JP;

}

}

NSError *err;

NSString *str=[NSStringstringWithContentsOfFile:pathencoding:CFStringConvertEncodingToNSStringEncoding(cfEncode) error:&err];

NSString *st=[str substringToIndex:1000];

self.txtView.text=st;

}

-(int)haveTextBianMa:(constchar*)strTxtPath{

FILE* file;

char buf[NUMBER_OF_SAMPLES];

size_t len;

uchardet_t ud;

/* 打开被检测文本文件，并读取一定数量的样本字符 */

file = fopen(strTxtPath, "rt");

if (file==NULL) {

printf("文件打开失败！\n");

return1;

}

len = fread(buf, sizeof(char), NUMBER_OF_SAMPLES, file);

fclose(file);

ud = uchardet_new();

if(uchardet_handle_data(ud, buf, len) != 0)

{

printf("分析编码失败！\n");

return -1;

}

uchardet_data_end(ud);

printf("文本的编码方式是%s。\n", uchardet_get_charset(ud));

encode=uchardet_get_charset(ud);

uchardet_delete(ud);

return0;

}

- (void)didReceiveMemoryWarning

{

[superdidReceiveMemoryWarning];

// Dispose of any resources that can be recreated.

}

@end