引用---笔记
iOS代码中包含中文字符的排序搜索比较繁琐,引用大神的样例整理下此笔记
PinYinForObjc.h中的有两个方法,第一是将汉字全部转成拼音、第二是将汉字首字母检索出来,如下:
+ (NSString*)chineseConvertToPinYin:(NSString*)chinese;//转换为拼音
+ (NSString*)chineseConvertToPinYinHead:(NSString *)chinese;//转换为拼音首字母
详细代码:一、(1)#import"ChineseInclude.h"
#import <Foundation/Foundation.h>
@interface ChineseInclude : NSObject
+ (BOOL)isIncludeChineseInString:(NSString*)str;
@end
(2)ChineseInclude.m
#import "ChineseInclude.h"
@implementation ChineseInclude
+ (BOOL)isIncludeChineseInString:(NSString*)str {
for (int i=0; i<str.length; i++) {
unichar ch = [str characterAtIndex:i];
if (0x4e00 < ch && ch < 0x9fff) {
return true;
}
}
return false;
}
@end
二、(1)ChineseToPinyinResource.h
#ifndef _ChineseToPinyinResource_H_
#define _ChineseToPinyinResource_H_
@class NSArray;
@class NSMutableDictionary;
@interface ChineseToPinyinResource : NSObject {
NSString* _directory;
NSDictionary *_unicodeToHanyuPinyinTable;
}
- (id)init;
- (void)initializeResource;
- (NSArray *)getHanyuPinyinStringArrayWithChar:(unichar)ch;
- (BOOL)isValidRecordWithNSString:(NSString *)record;
- (NSString *)getHanyuPinyinRecordFromCharWithChar:(unichar)ch;
+ (ChineseToPinyinResource *)getInstance;
@end
#endif
(2)ChineseToPinyinResource.m
#include "ChineseToPinyinResource.h"
#define LEFT_BRACKET @"("
#define RIGHT_BRACKET @")"
#define COMMA @","
#define kCacheKeyForUnicode2Pinyin @"cache.key.for.unicode.to.pinyin"
static inline NSString* cachePathForKey(NSString* directory, NSString* key) {
return [directory stringByAppendingPathComponent:key];
}
@interface ChineseToPinyinResource ()
- (id<NSCoding>)cachedObjectForKey:(NSString*)key;
-(void)cacheObjec:(id<NSCoding>)obj forKey:(NSString *)key;
@end
@implementation ChineseToPinyinResource
- (id)init {
if (self = [super init]) {
_unicodeToHanyuPinyinTable = nil;
[self initializeResource];
}
return self;
}
- (void)initializeResource {
NSString* cachesDirectory = NSSearchPathForDirectoriesInDomains(NSCachesDirectory, NSUserDomainMask, YES)[0];
NSString* oldCachesDirectory = [[[cachesDirectory stringByAppendingPathComponent:[[NSProcessInfo processInfo] processName]] stringByAppendingPathComponent:@"PinYinCache"] copy];
if([[NSFileManager defaultManager] fileExistsAtPath:oldCachesDirectory]) {
[[NSFileManager defaultManager] removeItemAtPath:oldCachesDirectory error:NULL];
}
_directory = [[[cachesDirectory stringByAppendingPathComponent:[[NSBundle mainBundle] bundleIdentifier]] stringByAppendingPathComponent:@"PinYinCache"] copy];
NSDictionary *dataMap=(NSDictionary *)[self cachedObjectForKey:kCacheKeyForUnicode2Pinyin];
if (dataMap) {
self->_unicodeToHanyuPinyinTable=dataMap;
}else{
NSString *resourceName =[[NSBundle mainBundle] pathForResource:@"unicode_to_hanyu_pinyin" ofType:@"txt"];
NSString *dictionaryText=[NSString stringWithContentsOfFile:resourceName encoding:NSUTF8StringEncoding error:nil];
NSArray *lines = [dictionaryText componentsSeparatedByString:@"\r\n"];
__block NSMutableDictionary *tempMap=[[NSMutableDictionary alloc] init];
@autoreleasepool {
[lines enumerateObjectsUsingBlock:^(id obj, NSUInteger idx, BOOL *stop) {
NSArray *lineComponents=[obj componentsSeparatedByCharactersInSet:[NSCharacterSet whitespaceCharacterSet]];
[tempMap setObject:lineComponents[1] forKey:lineComponents[0]];
}];
}
self->_unicodeToHanyuPinyinTable=tempMap;
[self cacheObjec:self->_unicodeToHanyuPinyinTable forKey:kCacheKeyForUnicode2Pinyin];
}
}
- (id<NSCoding>)cachedObjectForKey:(NSString*)key
{
NSData *data = [NSData dataWithContentsOfFile:cachePathForKey(_directory, key) options:0 error:NULL];
if (data) {
return [NSKeyedUnarchiver unarchiveObjectWithData:data];
}
return nil;
}
-(void)cacheObjec:(id<NSCoding>)obj forKey:(NSString *)key
{
NSData* data= [NSKeyedArchiver archivedDataWithRootObject:obj];
NSString* cachePath = cachePathForKey(_directory, key);
dispatch_async(dispatch_get_main_queue(), ^{
[data writeToFile:cachePath atomically:YES];
});
}
- (NSArray *)getHanyuPinyinStringArrayWithChar:(unichar)ch {
NSString *pinyinRecord = [self getHanyuPinyinRecordFromCharWithChar:ch];
if (nil != pinyinRecord) {
NSRange rangeOfLeftBracket= [pinyinRecord rangeOfString:LEFT_BRACKET];
NSRange rangeOfRightBracket= [pinyinRecord rangeOfString:RIGHT_BRACKET];
NSString *stripedString = [pinyinRecord substringWithRange:NSMakeRange(rangeOfLeftBracket.location+rangeOfLeftBracket.length, rangeOfRightBracket.location-rangeOfLeftBracket.location-rangeOfLeftBracket.length)];
return [stripedString componentsSeparatedByString:COMMA];
}
else return nil;
}
- (BOOL)isValidRecordWithNSString:(NSString *)record {
NSString *noneStr = @"(none0)";
if ((nil != record) && ![record isEqual:noneStr] && [record hasPrefix:LEFT_BRACKET] && [record hasSuffix:RIGHT_BRACKET]) {
return YES;
}
else return NO;
}
- (NSString *)getHanyuPinyinRecordFromCharWithChar:(unichar)ch {
int codePointOfChar = ch;
NSString *codepointHexStr =[[NSString stringWithFormat:@"%x", codePointOfChar] uppercaseString];
NSString *foundRecord =[self->_unicodeToHanyuPinyinTable objectForKey:codepointHexStr];
return [self isValidRecordWithNSString:foundRecord] ? foundRecord : nil;
}
+ (ChineseToPinyinResource *)getInstance {
static ChineseToPinyinResource *sharedInstance=nil;
static dispatch_once_t onceToken;
dispatch_once(&onceToken, ^{
sharedInstance=[[self alloc] init];
});
return sharedInstance;
}
@end
三、HanyuPinyinOutputFormat.h
#ifndef _HanyuPinyinOutputFormat_H_
#define _HanyuPinyinOutputFormat_H_
#import <Foundation/Foundation.h>
typedef enum {
ToneTypeWithToneNumber,
ToneTypeWithoutTone,
ToneTypeWithToneMark
}ToneType;
typedef enum {
CaseTypeUppercase,
CaseTypeLowercase
}CaseType;
typedef enum {
VCharTypeWithUAndColon,
VCharTypeWithV,
VCharTypeWithUUnicode
}VCharType;
@interface HanyuPinyinOutputFormat : NSObject
@property(nonatomic, assign) VCharType vCharType;
@property(nonatomic, assign) CaseType caseType;
@property(nonatomic, assign) ToneType toneType;
- (id)init;
- (void)restoreDefault;
@end
#endif
HanyuPinyinOutputFormat.m
#include "HanyuPinyinOutputFormat.h"
@implementation HanyuPinyinOutputFormat
@synthesize vCharType=_vCharType;
@synthesize caseType=_caseType;
@synthesize toneType=_toneType;
- (id)init {
if (self = [super init]) {
[self restoreDefault];
}
return self;
}
- (void)restoreDefault {
_vCharType = VCharTypeWithUAndColon;
_caseType = CaseTypeLowercase;
_toneType = ToneTypeWithToneNumber;
}
@end
四、NSString+PinYin4Cocoa.h
#import <Foundation/Foundation.h>
@interface NSString (PinYin4Cocoa)
- (NSInteger)indexOfString:(NSString *)s;
- (NSInteger)indexOfString:(NSString *)s fromIndex:(int)index;
- (NSInteger)indexOf:(int)ch;
- (NSInteger)indexOf:(int)ch fromIndex:(int)index;
+ (NSString *)valueOfChar:(unichar)value;
-(NSString *) stringByReplacingRegexPattern:(NSString *)regex withString:(NSString *) replacement;
-(NSString *) stringByReplacingRegexPattern:(NSString *)regex withString:(NSString *) replacement caseInsensitive:(BOOL) ignoreCase;
-(NSString *) stringByReplacingRegexPattern:(NSString *)regex withString:(NSString *) replacement caseInsensitive:(BOOL) ignoreCase treatAsOneLine:(BOOL) assumeMultiLine;
-(NSArray *) stringsByExtractingGroupsUsingRegexPattern:(NSString *)regex;
-(NSArray *) stringsByExtractingGroupsUsingRegexPattern:(NSString *)regex caseInsensitive:(BOOL) ignoreCase treatAsOneLine:(BOOL) assumeMultiLine;
-(BOOL) matchesPatternRegexPattern:(NSString *)regex;
-(BOOL) matchesPatternRegexPattern:(NSString *)regex caseInsensitive:(BOOL) ignoreCase treatAsOneLine:(BOOL) assumeMultiLine;
@end
NSString+PinYin4Cocoa.m
#import "NSString+PinYin4Cocoa.h"
@implementation NSString (PinYin4Cocoa)
- (NSInteger)indexOfString:(NSString *)s {
NSAssert3((s!=nil), @"Error, s is a nil string, %s, %s, %d", __FILE__, __FUNCTION__, __LINE__);
if ([s length] == 0) {
return 0;
}
NSRange range = [self rangeOfString:s];
return range.location == NSNotFound ? -1 : (int) range.location;
}
- (NSInteger)indexOfString:(NSString *)s fromIndex:(int)index {
NSAssert3((s!=nil), @"Error, s is a nil string, %s, %s, %d", __FILE__, __FUNCTION__, __LINE__);
if ([s length] == 0) {
return 0;
}
NSRange searchRange = NSMakeRange((NSUInteger) index,
[self length] - (NSUInteger) index);
NSRange range = [self rangeOfString:s
options:NSLiteralSearch
range:searchRange];
return range.location == NSNotFound ? -1 : (int) range.location;
}
- (NSInteger)indexOf:(int)ch {
return [self indexOf:ch fromIndex:0];
}
- (NSInteger)indexOf:(int)ch fromIndex:(int)index {
unichar c = (unichar) ch;
NSString *s = [NSString stringWithCharacters:&c length:1];
return [self indexOfString:s fromIndex:(int)index];
}
+ (NSString *)valueOfChar:(unichar)value {
return [NSString stringWithFormat:@"%C", value];
}
-(NSString *) stringByReplacingRegexPattern:(NSString *)regex withString:(NSString *) replacement caseInsensitive:(BOOL)ignoreCase {
return [self stringByReplacingRegexPattern:regex withString:replacement caseInsensitive:ignoreCase treatAsOneLine:NO];
}
-(NSString *) stringByReplacingRegexPattern:(NSString *)regex withString:(NSString *) replacement caseInsensitive:(BOOL) ignoreCase treatAsOneLine:(BOOL) assumeMultiLine {
NSUInteger options=0;
if (ignoreCase) {
options = options | NSRegularExpressionCaseInsensitive;
}
if (assumeMultiLine) {
options = options | NSRegularExpressionDotMatchesLineSeparators;
}
NSError *error=nil;
NSRegularExpression *pattern = [NSRegularExpression regularExpressionWithPattern:regex options:options error:&error];
if (error) {
NSLog(@"Error creating Regex: %@",[error description]);
return nil;
}
NSString *retVal= [pattern stringByReplacingMatchesInString:self options:0 range:NSMakeRange(0, [self length]) withTemplate:replacement];
return retVal;
}
-(NSString *) stringByReplacingRegexPattern:(NSString *)regex withString:(NSString *) replacement {
return [self stringByReplacingRegexPattern:regex withString:replacement caseInsensitive:NO treatAsOneLine:NO];
}
-(NSArray *) stringsByExtractingGroupsUsingRegexPattern:(NSString *)regex caseInsensitive:(BOOL) ignoreCase treatAsOneLine:(BOOL) assumeMultiLine {
NSUInteger options=0;
if (ignoreCase) {
options = options | NSRegularExpressionCaseInsensitive;
}
if (assumeMultiLine) {
options = options | NSRegularExpressionDotMatchesLineSeparators;
}
NSError *error=nil;
NSRegularExpression *pattern = [NSRegularExpression regularExpressionWithPattern:regex options:options error:&error];
if (error) {
NSLog(@"Error creating Regex: %@",[error description]);
return nil;
}
__block NSMutableArray *retVal = [NSMutableArray array];
[pattern enumerateMatchesInString:self options:0 range:NSMakeRange(0, [self length]) usingBlock:^(NSTextCheckingResult *result, NSMatchingFlags flags, BOOL *stop) {
//Note, we only want to return the things in parens, so we're skipping index 0 intentionally
for (int i=1; i<[result numberOfRanges]; i++) {
NSString *matchedString=[self substringWithRange:[result rangeAtIndex:i]];
[retVal addObject:matchedString];
}
}];
return retVal;
}
-(NSArray *) stringsByExtractingGroupsUsingRegexPattern:(NSString *)regex {
return [self stringsByExtractingGroupsUsingRegexPattern:regex caseInsensitive:NO treatAsOneLine:NO];
}
-(BOOL) matchesPatternRegexPattern:(NSString *)regex caseInsensitive:(BOOL) ignoreCase treatAsOneLine:(BOOL) assumeMultiLine {
NSUInteger options=0;
if (ignoreCase) {
options = options | NSRegularExpressionCaseInsensitive;
}
if (assumeMultiLine) {
options = options | NSRegularExpressionDotMatchesLineSeparators;
}
NSError *error=nil;
NSRegularExpression *pattern = [NSRegularExpression regularExpressionWithPattern:regex options:options error:&error];
if (error) {
NSLog(@"Error creating Regex: %@",[error description]);
return NO; //Can't possibly match an invalid Regex
}
return ([pattern numberOfMatchesInString:self options:0 range:NSMakeRange(0, [self length])] > 0);
}
-(BOOL) matchesPatternRegexPattern:(NSString *)regex {
return [self matchesPatternRegexPattern:regex caseInsensitive:NO treatAsOneLine:NO];
}
五、PinYin4Objc.h
#import "HanyuPinyinOutputFormat.h"
#import "PinyinHelper.h"
六、PinyinFormatter.h
#ifndef _PinyinFormatter_H_
#define _PinyinFormatter_H_
@class HanyuPinyinOutputFormat;
@interface PinyinFormatter : NSObject {
}
+ (NSString *)formatHanyuPinyinWithNSString:(NSString *)pinyinStr
withHanyuPinyinOutputFormat:(HanyuPinyinOutputFormat *)outputFormat;
+ (NSString *)convertToneNumber2ToneMarkWithNSString:(NSString *)pinyinStr;
- (id)init;
@end
#endif
PinyinFormatter.m
#include "HanyuPinyinOutputFormat.h"
#include "PinyinFormatter.h"
#import "NSString+PinYin4Cocoa.h"
@interface PinyinFormatter ()
+(NSInteger)getNumericValue:(unichar)c;
+(NSInteger)indexOfChar:(int*) table ch:(unichar)c;
@end
@implementation PinyinFormatter
static int numericKeys[] = {
0x0030, 0x0041, 0x0061, 0x00b2, 0x00b9, 0x00bc, 0x0660, 0x06f0,
0x0966, 0x09e6, 0x09f4, 0x09f9, 0x0a66, 0x0ae6, 0x0b66, 0x0be7,
0x0bf1, 0x0bf2, 0x0c66, 0x0ce6, 0x0d66, 0x0e50, 0x0ed0, 0x0f20,
0x1040, 0x1369, 0x1373, 0x1374, 0x1375, 0x1376, 0x1377, 0x1378,
0x1379, 0x137a, 0x137b, 0x137c, 0x16ee, 0x17e0, 0x1810, 0x2070,
0x2074, 0x2080, 0x2153, 0x215f, 0x2160, 0x216c, 0x216d, 0x216e,
0x216f, 0x2170, 0x217c, 0x217d, 0x217e, 0x217f, 0x2180, 0x2181,
0x2182, 0x2460, 0x2474, 0x2488, 0x24ea, 0x2776, 0x2780, 0x278a,
0x3007, 0x3021, 0x3038, 0x3039, 0x303a, 0x3280, 0xff10, 0xff21,
0xff41,
};
static unichar numericValues[] = {
0x0039, 0x0030, 0x005a, 0x0037, 0x007a, 0x0057, 0x00b3, 0x00b0,
0x00b9, 0x00b8, 0x00be, 0x0000, 0x0669, 0x0660, 0x06f9, 0x06f0,
0x096f, 0x0966, 0x09ef, 0x09e6, 0x09f7, 0x09f3, 0x09f9, 0x09e9,
0x0a6f, 0x0a66, 0x0aef, 0x0ae6, 0x0b6f, 0x0b66, 0x0bf0, 0x0be6,
0x0bf1, 0x0b8d, 0x0bf2, 0x080a, 0x0c6f, 0x0c66, 0x0cef, 0x0ce6,
0x0d6f, 0x0d66, 0x0e59, 0x0e50, 0x0ed9, 0x0ed0, 0x0f29, 0x0f20,
0x1049, 0x1040, 0x1372, 0x1368, 0x1373, 0x135f, 0x1374, 0x1356,
0x1375, 0x134d, 0x1376, 0x1344, 0x1377, 0x133b, 0x1378, 0x1332,
0x1379, 0x1329, 0x137a, 0x1320, 0x137b, 0x1317, 0x137c, 0xec6c,
0x16f0, 0x16dd, 0x17e9, 0x17e0, 0x1819, 0x1810, 0x2070, 0x2070,
0x2079, 0x2070, 0x2089, 0x2080, 0x215e, 0x0000, 0x215f, 0x215e,
0x216b, 0x215f, 0x216c, 0x213a, 0x216d, 0x2109, 0x216e, 0x1f7a,
0x216f, 0x1d87, 0x217b, 0x216f, 0x217c, 0x214a, 0x217d, 0x2119,
0x217e, 0x1f8a, 0x217f, 0x1d97, 0x2180, 0x1d98, 0x2181, 0x0df9,
0x2182, 0xfa72, 0x2473, 0x245f, 0x2487, 0x2473, 0x249b, 0x2487,
0x24ea, 0x24ea, 0x277f, 0x2775, 0x2789, 0x277f, 0x2793, 0x2789,
0x3007, 0x3007, 0x3029, 0x3020, 0x3038, 0x302e, 0x3039, 0x3025,
0x303a, 0x301c, 0x3289, 0x327f, 0xff19, 0xff10, 0xff3a, 0xff17,
0xff5a, 0xff37,
};
+ (NSString *)formatHanyuPinyinWithNSString:(NSString *)pinyinStr
withHanyuPinyinOutputFormat:(HanyuPinyinOutputFormat *)outputFormat {
if ((ToneTypeWithToneMark == [outputFormat toneType]) && ((VCharTypeWithV == [outputFormat vCharType]) || (VCharTypeWithUAndColon == [outputFormat vCharType]))) {
@throw [NSException exceptionWithName:@"Throwing a BadHanyuPinyinOutputFormatCombination exception" reason:@"tone marks cannot be added to v or u:." userInfo:nil];
}
if (ToneTypeWithoutTone == [outputFormat toneType]) {
pinyinStr =[pinyinStr stringByReplacingOccurrencesOfString:@"[1-5]" withString:@"" options:NSRegularExpressionSearch range:NSMakeRange(0, pinyinStr.length)];
}
else if (ToneTypeWithToneMark == [outputFormat toneType]) {
pinyinStr =[pinyinStr stringByReplacingOccurrencesOfString:@"u:" withString:@"v"];
pinyinStr = [PinyinFormatter convertToneNumber2ToneMarkWithNSString:pinyinStr];
}
if (VCharTypeWithV == [outputFormat vCharType]) {
pinyinStr =[pinyinStr stringByReplacingOccurrencesOfString:@"u:" withString:@"v"];
}
else if (VCharTypeWithUUnicode == [outputFormat vCharType]) {
pinyinStr =[pinyinStr stringByReplacingOccurrencesOfString:@"u:" withString:@"ü"];
}
if (CaseTypeUppercase == [outputFormat caseType]) {
pinyinStr = [pinyinStr uppercaseString];
}
return pinyinStr;
}
+ (NSString *)convertToneNumber2ToneMarkWithNSString:(NSString *)pinyinStr {
NSString *lowerCasePinyinStr = [pinyinStr lowercaseString];
if ([lowerCasePinyinStr matchesPatternRegexPattern:@"[a-z]*[1-5]?"]) {
unichar defautlCharValue = '$';
int defautlIndexValue = -1;
unichar unmarkedVowel = defautlCharValue;
int indexOfUnmarkedVowel = defautlIndexValue;
unichar charA = 'a';
unichar charE = 'e';
NSString *ouStr = @"ou";
NSString *allUnmarkedVowelStr = @"aeiouv";
NSString *allMarkedVowelStr = @"āáăàaēéĕèeīíĭìiōóŏòoūúŭùuǖǘǚǜü";
if ([lowerCasePinyinStr matchesPatternRegexPattern:@"[a-z]*[1-5]"]) {
int tuneNumber = [PinyinFormatter getNumericValue:[lowerCasePinyinStr characterAtIndex:lowerCasePinyinStr.length -1]];
int indexOfA = [lowerCasePinyinStr indexOf:charA];
int indexOfE = [lowerCasePinyinStr indexOf:charE];
int ouIndex = [lowerCasePinyinStr indexOfString:ouStr];
if (-1 != indexOfA) {
indexOfUnmarkedVowel = indexOfA;
unmarkedVowel = charA;
}
else if (-1 != indexOfE) {
indexOfUnmarkedVowel = indexOfE;
unmarkedVowel = charE;
}
else if (-1 != ouIndex) {
indexOfUnmarkedVowel = ouIndex;
unmarkedVowel = [ouStr characterAtIndex:0];
}
else {
for (int i = [lowerCasePinyinStr length] - 1; i >= 0; i--) {
if ([[NSString valueOfChar:[lowerCasePinyinStr characterAtIndex:i]] matchesPatternRegexPattern:@"[aeiouv]"]) {
indexOfUnmarkedVowel = i;
unmarkedVowel = [lowerCasePinyinStr characterAtIndex:i];
break;
}
}
}
if ((defautlCharValue != unmarkedVowel) && (defautlIndexValue != indexOfUnmarkedVowel)) {
int rowIndex = [allUnmarkedVowelStr indexOf:unmarkedVowel];
int columnIndex = tuneNumber - 1;
int vowelLocation = rowIndex * 5 + columnIndex;
unichar markedVowel = [allMarkedVowelStr characterAtIndex:vowelLocation];
NSMutableString *resultBuffer = [[NSMutableString alloc] init];
[resultBuffer appendString:[[lowerCasePinyinStr substringToIndex:indexOfUnmarkedVowel+1] stringByReplacingOccurrencesOfString:@"v" withString:@"ü"]];
[resultBuffer appendFormat:@"%C",markedVowel];
[resultBuffer appendString:[[lowerCasePinyinStr substringWithRange:NSMakeRange(indexOfUnmarkedVowel + 1, lowerCasePinyinStr.length-indexOfUnmarkedVowel)] stringByReplacingOccurrencesOfString:@"v" withString:@"ü"]];
return [resultBuffer description];
}
else {
return lowerCasePinyinStr;
}
}
else {
return [lowerCasePinyinStr stringByReplacingOccurrencesOfString:@"v" withString:@"ü"];
}
}
else {
return lowerCasePinyinStr;
}
}
+(NSInteger)getNumericValue:(unichar)c
{
if (c < 128) {
// Optimized for ASCII
if (c >= '0' && c <= '9') {
return c - '0';
}
if (c >= 'a' && c <= 'z') {
return c - ('a' - 10);
}
if (c >= 'A' && c <= 'Z') {
return c - ('A' - 10);
}
return -1;
}
NSInteger result = [self indexOfChar:numericKeys ch:c];
if (result >= 0 && c <= numericValues[result * 2]) {
unichar difference = numericValues[result * 2 + 1];
if (difference == 0) {
return -2;
}
// Value is always positive, must be negative value
if (difference > c) {
return c - (short) difference;
}
return c - difference;
}
return -1;
}
+(NSInteger)indexOfChar:(int*) table ch:(unichar)c{
NSInteger len=sizeof(table)/sizeof(table[0]);
for (int i = 0; i < len; i++) {
if (table[i] == (int) c) {
return i;
}
}
return -1;
}
- (id)init {
return [super init];
}
@end
七、PinYinForObjc.h
#import <Foundation/Foundation.h>
#import "HanyuPinyinOutputFormat.h"
#import "PinyinHelper.h"
@interface PinYinForObjc : NSObject
+ (NSString*)chineseConvertToPinYin:(NSString*)chinese;//转换为拼音
+ (NSString*)chineseConvertToPinYinHead:(NSString *)chinese;//转换为拼音首字母
@end
PinYinForObjc.m
#import "PinYinForObjc.h"
@implementation PinYinForObjc
+ (NSString*)chineseConvertToPinYin:(NSString*)chinese {
NSString *sourceText = chinese;
HanyuPinyinOutputFormat *outputFormat = [[HanyuPinyinOutputFormat alloc] init];
[outputFormat setToneType:ToneTypeWithoutTone];
[outputFormat setVCharType:VCharTypeWithV];
[outputFormat setCaseType:CaseTypeLowercase];
NSString *outputPinyin = [PinyinHelper toHanyuPinyinStringWithNSString:sourceText withHanyuPinyinOutputFormat:outputFormat withNSString:@""];
return outputPinyin;
}
+ (NSString*)chineseConvertToPinYinHead:(NSString *)chinese {
HanyuPinyinOutputFormat *outputFormat = [[HanyuPinyinOutputFormat alloc] init];
[outputFormat setToneType:ToneTypeWithoutTone];
[outputFormat setVCharType:VCharTypeWithV];
[outputFormat setCaseType:CaseTypeLowercase];
NSMutableString *outputPinyin = [[NSMutableString alloc] init];
for (int i=0;i <chinese.length;i++) {
NSString *mainPinyinStrOfChar = [PinyinHelper getFirstHanyuPinyinStringWithChar:[chinese characterAtIndex:i] withHanyuPinyinOutputFormat:outputFormat];
if (nil!=mainPinyinStrOfChar) {
[outputPinyin appendString:[mainPinyinStrOfChar substringToIndex:1]];
}
}
// 如果是不是拼音需要判断到底是哪个英文开头的 如果数字特殊服的默认返回#
if (outputPinyin.length==0) {
outputPinyin = (NSMutableString*)[self englishToHeade:chinese];
}
return [[outputPinyin substringToIndex:1] uppercaseString];
}
+ (NSString*)englishToHeade:(NSString*)string
{
NSString *firstStr = [[string substringToIndex:1] uppercaseString];
return [self isKindOfChar:firstStr]?firstStr:@"#";
}
+ (BOOL)isKindOfChar:(NSString*)str
{
NSArray *array = @[@"A",@"B",@"C",@"D",@"E",@"F",@"G",@"H",@"I",@"G",@"K",@"L",@"M",@"N",@"O",@"P",@"Q",@"R",@"S",@"S",@"T",@"U",@"V",@"W",@"X",@"Y",@"Z"];
if ([array containsObject:str]) {
return YES;
}else{
return NO;
}
}
@end
八、PinyinHelper.h
#ifndef _PinyinHelper_H_
#define _PinyinHelper_H_
@class HanyuPinyinOutputFormat;
@interface PinyinHelper : NSObject {
}
+ (NSArray *)toHanyuPinyinStringArrayWithChar:(unichar)ch;
+ (NSArray *)toHanyuPinyinStringArrayWithChar:(unichar)ch
withHanyuPinyinOutputFormat:(HanyuPinyinOutputFormat *)outputFormat;
+ (NSArray *)getFormattedHanyuPinyinStringArrayWithChar:(unichar)ch
withHanyuPinyinOutputFormat:(HanyuPinyinOutputFormat *)outputFormat;
+ (NSArray *)getUnformattedHanyuPinyinStringArrayWithChar:(unichar)ch;
+ (NSArray *)toTongyongPinyinStringArrayWithChar:(unichar)ch;
+ (NSArray *)toWadeGilesPinyinStringArrayWithChar:(unichar)ch;
+ (NSArray *)toMPS2PinyinStringArrayWithChar:(unichar)ch;
+ (NSArray *)toYalePinyinStringArrayWithChar:(unichar)ch;
+ (NSArray *)convertToTargetPinyinStringArrayWithChar:(unichar)ch
withPinyinRomanizationType:(NSString *)targetPinyinSystem;
+ (NSArray *)toGwoyeuRomatzyhStringArrayWithChar:(unichar)ch;
+ (NSArray *)convertToGwoyeuRomatzyhStringArrayWithChar:(unichar)ch;
+ (NSString *)toHanyuPinyinStringWithNSString:(NSString *)str
withHanyuPinyinOutputFormat:(HanyuPinyinOutputFormat *)outputFormat
withNSString:(NSString *)seperater;
+ (NSString *)getFirstHanyuPinyinStringWithChar:(unichar)ch
withHanyuPinyinOutputFormat:(HanyuPinyinOutputFormat *)outputFormat;
- (id)init;
@end
#endif
PinyinHelper.m
#include "ChineseToPinyinResource.h"
#include "HanyuPinyinOutputFormat.h"
#include "PinyinFormatter.h"
#include "PinyinHelper.h"
#define HANYU_PINYIN @"Hanyu"
#define WADEGILES_PINYIN @"Wade"
#define MPS2_PINYIN @"MPSII"
#define YALE_PINYIN @"Yale"
#define TONGYONG_PINYIN @"Tongyong"
#define GWOYEU_ROMATZYH @"Gwoyeu"
@implementation PinyinHelper
+ (NSArray *)toHanyuPinyinStringArrayWithChar:(unichar)ch {
return [PinyinHelper getUnformattedHanyuPinyinStringArrayWithChar:ch];
}
+ (NSArray *)toHanyuPinyinStringArrayWithChar:(unichar)ch
withHanyuPinyinOutputFormat:(HanyuPinyinOutputFormat *)outputFormat {
return [PinyinHelper getFormattedHanyuPinyinStringArrayWithChar:ch withHanyuPinyinOutputFormat:outputFormat];
}
+ (NSArray *)getFormattedHanyuPinyinStringArrayWithChar:(unichar)ch
withHanyuPinyinOutputFormat:(HanyuPinyinOutputFormat *)outputFormat {
NSMutableArray *pinyinStrArray =[NSMutableArray arrayWithArray:[PinyinHelper getUnformattedHanyuPinyinStringArrayWithChar:ch]];
if (nil != pinyinStrArray) {
for (int i = 0; i < (int) [pinyinStrArray count]; i++) {
[pinyinStrArray replaceObjectAtIndex:i withObject:[PinyinFormatter formatHanyuPinyinWithNSString:
[pinyinStrArray objectAtIndex:i]withHanyuPinyinOutputFormat:outputFormat]];
}
return pinyinStrArray;
}
else return nil;
}
+ (NSArray *)getUnformattedHanyuPinyinStringArrayWithChar:(unichar)ch {
return [[ChineseToPinyinResource getInstance] getHanyuPinyinStringArrayWithChar:ch];
}
+ (NSArray *)toTongyongPinyinStringArrayWithChar:(unichar)ch {
return [PinyinHelper convertToTargetPinyinStringArrayWithChar:ch withPinyinRomanizationType: TONGYONG_PINYIN];
}
+ (NSArray *)toWadeGilesPinyinStringArrayWithChar:(unichar)ch {
return [PinyinHelper convertToTargetPinyinStringArrayWithChar:ch withPinyinRomanizationType: WADEGILES_PINYIN];
}
+ (NSArray *)toMPS2PinyinStringArrayWithChar:(unichar)ch {
return [PinyinHelper convertToTargetPinyinStringArrayWithChar:ch withPinyinRomanizationType: MPS2_PINYIN];
}
+ (NSArray *)toYalePinyinStringArrayWithChar:(unichar)ch {
return [PinyinHelper convertToTargetPinyinStringArrayWithChar:ch withPinyinRomanizationType: YALE_PINYIN];
}
+ (NSArray *)convertToTargetPinyinStringArrayWithChar:(unichar)ch
withPinyinRomanizationType:(NSString *)targetPinyinSystem {
NSArray *hanyuPinyinStringArray = [PinyinHelper getUnformattedHanyuPinyinStringArrayWithChar:ch];
if (nil != hanyuPinyinStringArray) {
NSMutableArray *targetPinyinStringArray = [NSMutableArray arrayWithCapacity:hanyuPinyinStringArray.count];
for (int i = 0; i < (int) [hanyuPinyinStringArray count]; i++) {
}
return targetPinyinStringArray;
}
else return nil;
}
+ (NSArray *)toGwoyeuRomatzyhStringArrayWithChar:(unichar)ch {
return [PinyinHelper convertToGwoyeuRomatzyhStringArrayWithChar:ch];
}
+ (NSArray *)convertToGwoyeuRomatzyhStringArrayWithChar:(unichar)ch {
NSArray *hanyuPinyinStringArray = [PinyinHelper getUnformattedHanyuPinyinStringArrayWithChar:ch];
if (nil != hanyuPinyinStringArray) {
NSMutableArray *targetPinyinStringArray =[NSMutableArray arrayWithCapacity:hanyuPinyinStringArray.count];
for (int i = 0; i < (int) [hanyuPinyinStringArray count]; i++) {
}
return targetPinyinStringArray;
}
else return nil;
}
+ (NSString *)toHanyuPinyinStringWithNSString:(NSString *)str
withHanyuPinyinOutputFormat:(HanyuPinyinOutputFormat *)outputFormat
withNSString:(NSString *)seperater {
NSMutableString *resultPinyinStrBuf = [[NSMutableString alloc] init];
for (int i = 0; i < str.length; i++) {
NSString *mainPinyinStrOfChar = [PinyinHelper getFirstHanyuPinyinStringWithChar:[str characterAtIndex:i] withHanyuPinyinOutputFormat:outputFormat];
if (nil != mainPinyinStrOfChar) {
[resultPinyinStrBuf appendString:mainPinyinStrOfChar];
if (i != [str length] - 1) {
[resultPinyinStrBuf appendString:seperater];
}
}
else {
[resultPinyinStrBuf appendFormat:@"%C",[str characterAtIndex:i]];
}
}
return resultPinyinStrBuf;
}
+ (NSString *)getFirstHanyuPinyinStringWithChar:(unichar)ch
withHanyuPinyinOutputFormat:(HanyuPinyinOutputFormat *)outputFormat {
NSArray *pinyinStrArray = [PinyinHelper getFormattedHanyuPinyinStringArrayWithChar:ch withHanyuPinyinOutputFormat:outputFormat];
if ((nil != pinyinStrArray) && ((int) [pinyinStrArray count] > 0)) {
return [pinyinStrArray objectAtIndex:0];
}
else {
return nil;
}
}
- (id)init {
return [super init];
}
@end
九、unicode_to_hanyu_pinyin.txt文件下载-----》
http://pan.baidu.com/s/1mhVQ52g 提取密码5tui