Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "6e2d0224d9e03f6bf236cd1e1cad7b79812e91ea"
Commit 0f9dc829 authored by liucong's avatar liucong
Browse files

重新格式化Cppd代码格式

parent 824cfb81
Hide whitespace changes
Inline Side-by-side
Showing with 2235 additions and 1957 deletions
Src/GPT2.cpp
View file @ 0f9dc829
......@@ -12,90 +12,82 @@
namespace migraphxSamples
{
GPT2::GPT2()
{
}
GPT2::~GPT2()
{
GPT2::GPT2() {}
}
GPT2::~GPT2() {}
ErrorCode GPT2::Initialize()
{
// 获取模型文件
std::string modelPath="../Resource/GPT2_shici.onnx";
std::string modelPath = "../Resource/GPT2_shici.onnx";
// 设置最大输入shape
migraphx::onnx_options onnx_options;
onnx_options.map_input_dims["input"] = {1,1000};
onnx_options.map_input_dims["input"] = {1, 1000};
// 加载模型
if(!Exists(modelPath))
{
LOG_ERROR(stdout,"%s not exist!\n",modelPath.c_str());
LOG_ERROR(stdout, "%s not exist!\n", modelPath.c_str());
return MODEL_NOT_EXIST;
}
net = migraphx::parse_onnx(modelPath, onnx_options);
LOG_INFO(stdout,"succeed to load model: %s\n",GetFileName(modelPath).c_str());
net = migraphx::parse_onnx(modelPath, onnx_options);
LOG_INFO(stdout, "succeed to load model: %s\n", GetFileName(modelPath).c_str());
// 获取模型输入/输出节点信息
std::unordered_map<std::string, migraphx::shape> inputs = net.get_inputs();
std::unordered_map<std::string, migraphx::shape> inputs = net.get_inputs();
std::unordered_map<std::string, migraphx::shape> outputs = net.get_outputs();
inputName=inputs.begin()->first;
inputShape=inputs.begin()->second;
inputName = inputs.begin()->first;
inputShape = inputs.begin()->second;
// 设置模型为GPU模式
migraphx::target gpuTarget = migraphx::gpu::target{};
// 编译模型
migraphx::compile_options options;
options.device_id = 0; // 设置GPU设备，默认为0号设备
options.offload_copy = true; // 设置offload_copy
net.compile(gpuTarget,options);
LOG_INFO(stdout,"succeed to compile model: %s\n",GetFileName(modelPath).c_str());
options.device_id = 0; // 设置GPU设备，默认为0号设备
options.offload_copy = true; // 设置offload_copy
net.compile(gpuTarget, options);
LOG_INFO(stdout, "succeed to compile model: %s\n", GetFileName(modelPath).c_str());
return SUCCESS;
}
static bool CompareM(Predictions a, Predictions b)
{
return a.predictionvalue > b.predictionvalue;
}
static bool CompareM(Predictions a, Predictions b) { return a.predictionvalue > b.predictionvalue; }
long unsigned int GPT2::Inference(const std::vector<long unsigned int> &input_id)
long unsigned int GPT2::Inference(const std::vector<long unsigned int>& input_id)
{
long unsigned int input[1][input_id.size()];
for (int j=0;j<input_id.size();++j)
for(int j = 0; j < input_id.size(); ++j)
{
input[0][j] = input_id[j];
}
// 设置输入shape
std::vector<std::vector<std::size_t>> inputShapes;
inputShapes.push_back({1,input_id.size()});
inputShapes.push_back({1, input_id.size()});
// 创建输入数据
std::unordered_map<std::string, migraphx::argument> inputData;
inputData[inputName]=migraphx::argument{migraphx::shape(inputShape.type(),inputShapes[0]),(long unsigned int*)input};
inputData[inputName] = migraphx::argument{migraphx::shape(inputShape.type(), inputShapes[0]),
(long unsigned int*)input};
// 推理
std::vector<migraphx::argument> results = net.eval(inputData);
// 获取输出节点的属性
migraphx::argument result = results[0];
migraphx::shape outputShape = result.get_shape(); // 输出节点的shape
int numberOfOutput=outputShape.elements(); // 输出节点元素的个数
float *data = (float *)result.data(); // 输出节点数据指针
migraphx::argument result = results[0];
migraphx::shape outputShape = result.get_shape(); // 输出节点的shape
int numberOfOutput = outputShape.elements(); // 输出节点元素的个数
float* data = (float*)result.data(); // 输出节点数据指针
// 保存推理结果
long unsigned int n = 0;
std::vector<Predictions> resultsOfPredictions(22557);
for(int i=(input_id.size()-1)*22557; i<input_id.size()*22557; ++i)
for(int i = (input_id.size() - 1) * 22557; i < input_id.size() * 22557; ++i)
{
resultsOfPredictions[n].index = n;
resultsOfPredictions[n].index = n;
resultsOfPredictions[n].predictionvalue = data[i];
++n;
}
......@@ -110,8 +102,8 @@ long unsigned int GPT2::Inference(const std::vector<long unsigned int> &input_id
}
ErrorCode GPT2::Preprocessing(cuBERT::FullTokenizer tokenizer,
char *question,
std::vector<long unsigned int> &input_id)
char* question,
std::vector<long unsigned int>& input_id)
{
// 分词操作
int max_seq_length = 1000;
......@@ -121,7 +113,7 @@ ErrorCode GPT2::Preprocessing(cuBERT::FullTokenizer tokenizer,
// 保存编码信息
input_id.push_back(tokenizer.convert_token_to_id("[CLS]"));
for (int i=0;i<tokens_question.size();++i)
for(int i = 0; i < tokens_question.size(); ++i)
{
input_id.push_back(tokenizer.convert_token_to_id(tokens_question[i]));
}
......@@ -129,4 +121,4 @@ ErrorCode GPT2::Preprocessing(cuBERT::FullTokenizer tokenizer,
return SUCCESS;
}
}
\ No newline at end of file
} // namespace migraphxSamples
\ No newline at end of file
Src/GPT2.h
View file @ 0f9dc829
......@@ -8,42 +8,42 @@
namespace migraphxSamples
{
typedef enum _ErrorCode
{
SUCCESS=0,
MODEL_NOT_EXIST,
CONFIG_FILE_NOT_EXIST,
FAIL_TO_LOAD_MODEL,
FAIL_TO_OPEN_CONFIG_FILE,
}ErrorCode;
typedef struct _Predictions
{
long unsigned int index;
float predictionvalue;
}Predictions;
typedef enum _ErrorCode
{
SUCCESS = 0,
MODEL_NOT_EXIST,
CONFIG_FILE_NOT_EXIST,
FAIL_TO_LOAD_MODEL,
FAIL_TO_OPEN_CONFIG_FILE,
} ErrorCode;
typedef struct _Predictions
{
long unsigned int index;
float predictionvalue;
} Predictions;
class GPT2
{
public:
public:
GPT2();
~GPT2();
ErrorCode Initialize();
ErrorCode Preprocessing(cuBERT::FullTokenizer tokenizer,
char *question,
std::vector<long unsigned int> &input_id);
char* question,
std::vector<long unsigned int>& input_id);
long unsigned int Inference(const std::vector<long unsigned int> &input_id);
long unsigned int Inference(const std::vector<long unsigned int>& input_id);
private:
private:
migraphx::program net;
std::string inputName;
migraphx::shape inputShape;
};
}
} // namespace migraphxSamples
#endif
\ No newline at end of file
Src/Utility/Filesystem.cpp
View file @ 0f9dc829
......@@ -14,9 +14,9 @@
// 路径分隔符(Linux:‘/’,Windows:’\\’)
#ifdef _WIN32
#define PATH_SEPARATOR '\\'
#define PATH_SEPARATOR '\\'
#else
#define PATH_SEPARATOR '/'
#define PATH_SEPARATOR '/'
#endif
using namespace std;
......@@ -28,666 +28,672 @@ static std::vector<std::string> SplitString(std::string str, std::string separat
{
std::string::size_type pos;
std::vector<std::string> result;
str+=separator;//扩展字符串以方便操作
int size=str.size();
str += separator; // 扩展字符串以方便操作
int size = str.size();
for(int i=0; i<size; i++)
for(int i = 0; i < size; i++)
{
pos=str.find(separator,i);
if(pos<size)
pos = str.find(separator, i);
if(pos < size)
{
std::string s=str.substr(i,pos-i);
std::string s = str.substr(i, pos - i);
result.push_back(s);
i=pos+separator.size()-1;
i = pos + separator.size() - 1;
}
}
return result;
}
#if defined _WIN32 || defined WINCE
const char dir_separators[] = "/\\";
const char dir_separators[] = "/\\";
struct dirent
{
const char* d_name;
};
struct dirent
{
const char* d_name;
};
struct DIR
{
struct DIR
{
#ifdef WINRT
WIN32_FIND_DATAW data;
WIN32_FIND_DATAW data;
#else
WIN32_FIND_DATAA data;
WIN32_FIND_DATAA data;
#endif
HANDLE handle;
dirent ent;
HANDLE handle;
dirent ent;
#ifdef WINRT
DIR() { }
~DIR()
{
if (ent.d_name)
delete[] ent.d_name;
}
DIR() {}
~DIR()
{
if(ent.d_name)
delete[] ent.d_name;
}
#endif
};
};
DIR* opendir(const char* path)
{
DIR* dir = new DIR;
dir->ent.d_name = 0;
DIR* opendir(const char* path)
{
DIR* dir = new DIR;
dir->ent.d_name = 0;
#ifdef WINRT
string full_path = string(path) + "\\*";
wchar_t wfull_path[MAX_PATH];
size_t copied = mbstowcs(wfull_path, full_path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
dir->handle = ::FindFirstFileExW(wfull_path, FindExInfoStandard,
&dir->data, FindExSearchNameMatch, NULL, 0);
string full_path = string(path) + "\\*";
wchar_t wfull_path[MAX_PATH];
size_t copied = mbstowcs(wfull_path, full_path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
dir->handle = ::FindFirstFileExW(
wfull_path, FindExInfoStandard, &dir->data, FindExSearchNameMatch, NULL, 0);
#else
dir->handle = ::FindFirstFileExA((string(path) + "\\*").c_str(),
FindExInfoStandard, &dir->data, FindExSearchNameMatch, NULL, 0);
dir->handle = ::FindFirstFileExA((string(path) + "\\*").c_str(),
FindExInfoStandard,
&dir->data,
FindExSearchNameMatch,
NULL,
0);
#endif
if (dir->handle == INVALID_HANDLE_VALUE)
{
/*closedir will do all cleanup*/
delete dir;
return 0;
}
return dir;
}
dirent* readdir(DIR* dir)
{
if(dir->handle == INVALID_HANDLE_VALUE)
{
/*closedir will do all cleanup*/
delete dir;
return 0;
}
return dir;
}
dirent* readdir(DIR* dir)
{
#ifdef WINRT
if (dir->ent.d_name != 0)
{
if (::FindNextFileW(dir->handle, &dir->data) != TRUE)
return 0;
}
size_t asize = wcstombs(NULL, dir->data.cFileName, 0);
CV_Assert((asize != 0) && (asize != (size_t)-1));
char* aname = new char[asize + 1];
aname[asize] = 0;
wcstombs(aname, dir->data.cFileName, asize);
dir->ent.d_name = aname;
if(dir->ent.d_name != 0)
{
if(::FindNextFileW(dir->handle, &dir->data) != TRUE)
return 0;
}
size_t asize = wcstombs(NULL, dir->data.cFileName, 0);
CV_Assert((asize != 0) && (asize != (size_t)-1));
char* aname = new char[asize + 1];
aname[asize] = 0;
wcstombs(aname, dir->data.cFileName, asize);
dir->ent.d_name = aname;
#else
if (dir->ent.d_name != 0)
{
if (::FindNextFileA(dir->handle, &dir->data) != TRUE)
return 0;
}
dir->ent.d_name = dir->data.cFileName;
if(dir->ent.d_name != 0)
{
if(::FindNextFileA(dir->handle, &dir->data) != TRUE)
return 0;
}
dir->ent.d_name = dir->data.cFileName;
#endif
return &dir->ent;
}
void closedir(DIR* dir)
{
::FindClose(dir->handle);
delete dir;
}
return &dir->ent;
}
void closedir(DIR* dir)
{
::FindClose(dir->handle);
delete dir;
}
#else
# include <dirent.h>
# include <sys/stat.h>
const char dir_separators[] = "/";
#include <dirent.h>
#include <sys/stat.h>
const char dir_separators[] = "/";
#endif
static bool isDir(const string &path, DIR* dir)
{
static bool isDir(const string& path, DIR* dir)
{
#if defined _WIN32 || defined WINCE
DWORD attributes;
BOOL status = TRUE;
if (dir)
attributes = dir->data.dwFileAttributes;
else
{
WIN32_FILE_ATTRIBUTE_DATA all_attrs;
DWORD attributes;
BOOL status = TRUE;
if(dir)
attributes = dir->data.dwFileAttributes;
else
{
WIN32_FILE_ATTRIBUTE_DATA all_attrs;
#ifdef WINRT
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
status = ::GetFileAttributesExW(wpath, GetFileExInfoStandard, &all_attrs);
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
status = ::GetFileAttributesExW(wpath, GetFileExInfoStandard, &all_attrs);
#else
status = ::GetFileAttributesExA(path.c_str(), GetFileExInfoStandard, &all_attrs);
status = ::GetFileAttributesExA(path.c_str(), GetFileExInfoStandard, &all_attrs);
#endif
attributes = all_attrs.dwFileAttributes;
}
attributes = all_attrs.dwFileAttributes;
}
return status && ((attributes & FILE_ATTRIBUTE_DIRECTORY) != 0);
return status && ((attributes & FILE_ATTRIBUTE_DIRECTORY) != 0);
#else
(void)dir;
struct stat stat_buf;
if (0 != stat(path.c_str(), &stat_buf))
return false;
int is_dir = S_ISDIR(stat_buf.st_mode);
return is_dir != 0;
(void)dir;
struct stat stat_buf;
if(0 != stat(path.c_str(), &stat_buf))
return false;
int is_dir = S_ISDIR(stat_buf.st_mode);
return is_dir != 0;
#endif
}
}
bool IsDirectory(const string &path)
{
return isDir(path, NULL);
}
bool IsDirectory(const string& path) { return isDir(path, NULL); }
bool Exists(const string& path)
{
bool Exists(const string& path)
{
#if defined _WIN32 || defined WINCE
BOOL status = TRUE;
{
WIN32_FILE_ATTRIBUTE_DATA all_attrs;
BOOL status = TRUE;
{
WIN32_FILE_ATTRIBUTE_DATA all_attrs;
#ifdef WINRT
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
status = ::GetFileAttributesExW(wpath, GetFileExInfoStandard, &all_attrs);
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
status = ::GetFileAttributesExW(wpath, GetFileExInfoStandard, &all_attrs);
#else
status = ::GetFileAttributesExA(path.c_str(), GetFileExInfoStandard, &all_attrs);
status = ::GetFileAttributesExA(path.c_str(), GetFileExInfoStandard, &all_attrs);
#endif
}
}
return !!status;
return !!status;
#else
struct stat stat_buf;
return (0 == stat(path.c_str(), &stat_buf));
struct stat stat_buf;
return (0 == stat(path.c_str(), &stat_buf));
#endif
}
bool IsPathSeparator(char c)
{
return c == '/' || c == '\\';
}
string JoinPath(const string& base, const string& path)
{
if (base.empty())
return path;
if (path.empty())
return base;
bool baseSep = IsPathSeparator(base[base.size() - 1]);
bool pathSep = IsPathSeparator(path[0]);
string result;
if (baseSep && pathSep)
{
result = base + path.substr(1);
}
else if (!baseSep && !pathSep)
{
result = base + PATH_SEPARATOR + path;
}
else
{
result = base + path;
}
return result;
}
static bool wildcmp(const char *string, const char *wild)
{
const char *cp = 0, *mp = 0;
while ((*string) && (*wild != '*'))
{
if ((*wild != *string) && (*wild != '?'))
{
return false;
}
wild++;
string++;
}
while (*string)
{
if (*wild == '*')
{
if (!*++wild)
{
return true;
}
mp = wild;
cp = string + 1;
}
else if ((*wild == *string) || (*wild == '?'))
{
wild++;
string++;
}
else
{
wild = mp;
string = cp++;
}
}
while (*wild == '*')
{
wild++;
}
return *wild == 0;
}
static void glob_rec(const string &directory, const string& wildchart, std::vector<string>& result,
bool recursive, bool includeDirectories, const string& pathPrefix)
{
DIR *dir;
if ((dir = opendir(directory.c_str())) != 0)
{
/* find all the files and directories within directory */
try
{
struct dirent *ent;
while ((ent = readdir(dir)) != 0)
{
const char* name = ent->d_name;
if ((name[0] == 0) || (name[0] == '.' && name[1] == 0) || (name[0] == '.' && name[1] == '.' && name[2] == 0))
continue;
string path = JoinPath(directory, name);
string entry = JoinPath(pathPrefix, name);
if (isDir(path, dir))
{
if (recursive)
glob_rec(path, wildchart, result, recursive, includeDirectories, entry);
if (!includeDirectories)
continue;
}
if (wildchart.empty() || wildcmp(name, wildchart.c_str()))
result.push_back(entry);
}
}
catch (...)
{
closedir(dir);
throw;
}
closedir(dir);
}
else
{
printf("could not open directory: %s", directory.c_str());
}
}
void GetFileNameList(const string &directory, const string &pattern, std::vector<string>& result, bool recursive, bool addPath)
{
// split pattern
vector<string> patterns=SplitString(pattern,",");
result.clear();
for(int i=0;i<patterns.size();++i)
}
bool IsPathSeparator(char c) { return c == '/' || c == '\\'; }
string JoinPath(const string& base, const string& path)
{
if(base.empty())
return path;
if(path.empty())
return base;
bool baseSep = IsPathSeparator(base[base.size() - 1]);
bool pathSep = IsPathSeparator(path[0]);
string result;
if(baseSep && pathSep)
{
result = base + path.substr(1);
}
else if(!baseSep && !pathSep)
{
result = base + PATH_SEPARATOR + path;
}
else
{
result = base + path;
}
return result;
}
static bool wildcmp(const char* string, const char* wild)
{
const char *cp = 0, *mp = 0;
while((*string) && (*wild != '*'))
{
if((*wild != *string) && (*wild != '?'))
{
string eachPattern=patterns[i];
std::vector<string> eachResult;
glob_rec(directory, eachPattern, eachResult, recursive, true, directory);
for(int j=0;j<eachResult.size();++j)
return false;
}
wild++;
string++;
}
while(*string)
{
if(*wild == '*')
{
if(!*++wild)
{
if (IsDirectory(eachResult[j]))
continue;
if(addPath)
return true;
}
mp = wild;
cp = string + 1;
}
else if((*wild == *string) || (*wild == '?'))
{
wild++;
string++;
}
else
{
wild = mp;
string = cp++;
}
}
while(*wild == '*')
{
wild++;
}
return *wild == 0;
}
static void glob_rec(const string& directory,
const string& wildchart,
std::vector<string>& result,
bool recursive,
bool includeDirectories,
const string& pathPrefix)
{
DIR* dir;
if((dir = opendir(directory.c_str())) != 0)
{
/* find all the files and directories within directory */
try
{
struct dirent* ent;
while((ent = readdir(dir)) != 0)
{
const char* name = ent->d_name;
if((name[0] == 0) || (name[0] == '.' && name[1] == 0) ||
(name[0] == '.' && name[1] == '.' && name[2] == 0))
continue;
string path = JoinPath(directory, name);
string entry = JoinPath(pathPrefix, name);
if(isDir(path, dir))
{
if(recursive)
glob_rec(path, wildchart, result, recursive, includeDirectories, entry);
if(!includeDirectories)
continue;
}
if(wildchart.empty() || wildcmp(name, wildchart.c_str()))
result.push_back(entry);
}
}
catch(...)
{
closedir(dir);
throw;
}
closedir(dir);
}
else
{
printf("could not open directory: %s", directory.c_str());
}
}
void GetFileNameList(const string& directory,
const string& pattern,
std::vector<string>& result,
bool recursive,
bool addPath)
{
// split pattern
vector<string> patterns = SplitString(pattern, ",");
result.clear();
for(int i = 0; i < patterns.size(); ++i)
{
string eachPattern = patterns[i];
std::vector<string> eachResult;
glob_rec(directory, eachPattern, eachResult, recursive, true, directory);
for(int j = 0; j < eachResult.size(); ++j)
{
if(IsDirectory(eachResult[j]))
continue;
if(addPath)
{
result.push_back(eachResult[j]);
}
else
{
result.push_back(GetFileName(eachResult[j]));
}
}
}
std::sort(result.begin(), result.end());
}
void GetFileNameList2(const string& directory,
const string& pattern,
std::vector<string>& result,
bool recursive,
bool addPath)
{
// split pattern
vector<string> patterns = SplitString(pattern, ",");
result.clear();
for(int i = 0; i < patterns.size(); ++i)
{
string eachPattern = patterns[i];
std::vector<string> eachResult;
glob_rec(directory, eachPattern, eachResult, recursive, true, directory);
for(int j = 0; j < eachResult.size(); ++j)
{
string filePath = eachResult[j];
if(IsDirectory(filePath))
{
filePath = filePath + "/";
for(int k = 0; k < filePath.size(); ++k)
{
result.push_back(eachResult[j]);
if(IsPathSeparator(filePath[k]))
{
filePath[k] = '/';
}
}
else
}
if(addPath)
{
result.push_back(filePath);
}
else
{
if(!IsDirectory(filePath))
{
result.push_back(GetFileName(eachResult[j]));
result.push_back(GetFileName(filePath));
}
}
}
std::sort(result.begin(), result.end());
}
void GetFileNameList2(const string &directory, const string &pattern, std::vector<string>& result, bool recursive, bool addPath)
{
// split pattern
vector<string> patterns = SplitString(pattern, ",");
result.clear();
for (int i = 0; i<patterns.size(); ++i)
{
string eachPattern = patterns[i];
std::vector<string> eachResult;
glob_rec(directory, eachPattern, eachResult, recursive, true, directory);
for (int j = 0; j<eachResult.size(); ++j)
{
string filePath = eachResult[j];
if (IsDirectory(filePath))
{
filePath = filePath + "/";
for (int k = 0; k < filePath.size(); ++k)
{
if (IsPathSeparator(filePath[k]))
{
filePath[k] = '/';
}
}
}
if (addPath)
{
result.push_back(filePath);
}
else
{
if (!IsDirectory(filePath))
{
result.push_back(GetFileName(filePath));
}
}
}
}
std::sort(result.begin(), result.end());
}
void RemoveAll(const string& path)
{
if (!Exists(path))
return;
if (IsDirectory(path))
{
std::vector<string> entries;
GetFileNameList2(path, string(), entries, false, true);
for (size_t i = 0; i < entries.size(); i++)
{
const string& e = entries[i];
RemoveAll(e);
}
}
std::sort(result.begin(), result.end());
}
void RemoveAll(const string& path)
{
if(!Exists(path))
return;
if(IsDirectory(path))
{
std::vector<string> entries;
GetFileNameList2(path, string(), entries, false, true);
for(size_t i = 0; i < entries.size(); i++)
{
const string& e = entries[i];
RemoveAll(e);
}
#ifdef _MSC_VER
bool result = _rmdir(path.c_str()) == 0;
bool result = _rmdir(path.c_str()) == 0;
#else
bool result = rmdir(path.c_str()) == 0;
bool result = rmdir(path.c_str()) == 0;
#endif
if (!result)
{
printf("can't remove directory: %s\n", path.c_str());
}
}
else
{
if(!result)
{
printf("can't remove directory: %s\n", path.c_str());
}
}
else
{
#ifdef _MSC_VER
bool result = _unlink(path.c_str()) == 0;
bool result = _unlink(path.c_str()) == 0;
#else
bool result = unlink(path.c_str()) == 0;
bool result = unlink(path.c_str()) == 0;
#endif
if (!result)
{
printf("can't remove file: %s\n", path.c_str());
}
}
}
void Remove(const string &directory, const string &extension)
{
DIR *dir;
static int numberOfFiles = 0;
if ((dir = opendir(directory.c_str())) != 0)
{
/* find all the files and directories within directory */
try
{
struct dirent *ent;
while ((ent = readdir(dir)) != 0)
{
const char* name = ent->d_name;
if ((name[0] == 0) || (name[0] == '.' && name[1] == 0) || (name[0] == '.' && name[1] == '.' && name[2] == 0))
continue;
string path = JoinPath(directory, name);
if (isDir(path, dir))
{
Remove(path, extension);
}
// �ж���չ��
if (extension.empty() || wildcmp(name, extension.c_str()))
{
RemoveAll(path);
++numberOfFiles;
printf("%s deleted! number of deleted files:%d\n", path.c_str(), numberOfFiles);
}
}
}
catch (...)
{
closedir(dir);
throw;
}
closedir(dir);
}
else
{
printf("could not open directory: %s", directory.c_str());
}
// ����RemoveAllɾ��Ŀ¼
RemoveAll(directory);
}
string GetFileName(const string &path)
{
string fileName;
int indexOfPathSeparator = -1;
for (int i = path.size() - 1; i >= 0; --i)
{
if (IsPathSeparator(path[i]))
{
fileName = path.substr(i + 1, path.size() - i - 1);
indexOfPathSeparator = i;
break;
}
}
if (indexOfPathSeparator == -1)
if(!result)
{
fileName = path;
printf("can't remove file: %s\n", path.c_str());
}
}
}
void Remove(const string& directory, const string& extension)
{
return fileName;
}
string GetFileName_NoExtension(const string &path)
DIR* dir;
static int numberOfFiles = 0;
if((dir = opendir(directory.c_str())) != 0)
{
string fileName=GetFileName(path);
string fileName_NoExtension;
for(int i=fileName.size()-1;i>0;--i)
/* find all the files and directories within directory */
try
{
if(fileName[i]=='.')
struct dirent* ent;
while((ent = readdir(dir)) != 0)
{
fileName_NoExtension=fileName.substr(0,i);
break;
}
}
const char* name = ent->d_name;
if((name[0] == 0) || (name[0] == '.' && name[1] == 0) ||
(name[0] == '.' && name[1] == '.' && name[2] == 0))
continue;
return fileName_NoExtension;
}
string GetExtension(const string &path)
{
string fileName;
for (int i = path.size() - 1; i >= 0; --i)
{
if (path[i]=='.')
{
fileName = path.substr(i, path.size() - i);
break;
}
}
return fileName;
}
string GetParentPath(const string &path)
{
string fileName;
for (int i = path.size() - 1; i >= 0; --i)
{
if (IsPathSeparator(path[i]))
{
fileName = path.substr(0, i+1);
break;
}
}
return fileName;
}
static bool CreateDirectory(const string &path)
{
#if defined WIN32 || defined _WIN32 || defined WINCE
#ifdef WINRT
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
int result = CreateDirectoryA(wpath, NULL) ? 0 : -1;
#else
int result = _mkdir(path.c_str());
#endif
#elif defined __linux__ || defined __APPLE__
int result = mkdir(path.c_str(), 0777);
#else
int result = -1;
#endif
if (result == -1)
{
return IsDirectory(path);
string path = JoinPath(directory, name);
if(isDir(path, dir))
{
Remove(path, extension);
}
// �ж���չ��
if(extension.empty() || wildcmp(name, extension.c_str()))
{
RemoveAll(path);
++numberOfFiles;
printf("%s deleted! number of deleted files:%d\n", path.c_str(), numberOfFiles);
}
}
return true;
}
bool CreateDirectories(const string &directoryPath)
{
string path = directoryPath;
for (;;)
{
char last_char = path.empty() ? 0 : path[path.length() - 1];
if (IsPathSeparator(last_char))
{
path = path.substr(0, path.length() - 1);
continue;
}
break;
}
if (path.empty() || path == "./" || path == ".\\" || path == ".")
return true;
if (IsDirectory(path))
return true;
size_t pos = path.rfind('/');
if (pos == string::npos)
pos = path.rfind('\\');
if (pos != string::npos)
{
string parent_directory = path.substr(0, pos);
if (!parent_directory.empty())
{
if (!CreateDirectories(parent_directory))
return false;
}
}
return CreateDirectory(path);
}
bool CopyFile(const string srcPath, const string dstPath)
{
std::ifstream srcFile(srcPath,ios::binary);
std::ofstream dstFile(dstPath,ios::binary);
if(!srcFile.is_open())
}
catch(...)
{
printf("can not open %s\n",srcPath.c_str());
return false;
closedir(dir);
throw;
}
if(!dstFile.is_open())
closedir(dir);
}
else
{
printf("could not open directory: %s", directory.c_str());
}
// ����RemoveAllɾ��Ŀ¼
RemoveAll(directory);
}
string GetFileName(const string& path)
{
string fileName;
int indexOfPathSeparator = -1;
for(int i = path.size() - 1; i >= 0; --i)
{
if(IsPathSeparator(path[i]))
{
printf("can not open %s\n", dstPath.c_str());
return false;
fileName = path.substr(i + 1, path.size() - i - 1);
indexOfPathSeparator = i;
break;
}
if(srcPath==dstPath)
}
if(indexOfPathSeparator == -1)
{
fileName = path;
}
return fileName;
}
string GetFileName_NoExtension(const string& path)
{
string fileName = GetFileName(path);
string fileName_NoExtension;
for(int i = fileName.size() - 1; i > 0; --i)
{
if(fileName[i] == '.')
{
printf("src can not be same with dst\n");
return false;
fileName_NoExtension = fileName.substr(0, i);
break;
}
char buffer[2048];
unsigned int numberOfBytes=0;
while(srcFile)
}
return fileName_NoExtension;
}
string GetExtension(const string& path)
{
string fileName;
for(int i = path.size() - 1; i >= 0; --i)
{
if(path[i] == '.')
{
srcFile.read(buffer,2048);
dstFile.write(buffer,srcFile.gcount());
numberOfBytes+=srcFile.gcount();
fileName = path.substr(i, path.size() - i);
break;
}
srcFile.close();
dstFile.close();
return true;
}
bool CopyDirectories(string srcPath, const string dstPath)
return fileName;
}
string GetParentPath(const string& path)
{
string fileName;
for(int i = path.size() - 1; i >= 0; --i)
{
if(srcPath==dstPath)
if(IsPathSeparator(path[i]))
{
printf("src can not be same with dst\n");
return false;
fileName = path.substr(0, i + 1);
break;
}
}
// ȥ������·���ָ���
srcPath = srcPath.substr(0, srcPath.size() - 1);
return fileName;
}
vector<string> fileNameList;
GetFileNameList2(srcPath, "", fileNameList, true, true);
static bool CreateDirectory(const string& path)
{
#if defined WIN32 || defined _WIN32 || defined WINCE
#ifdef WINRT
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
int result = CreateDirectoryA(wpath, NULL) ? 0 : -1;
#else
int result = _mkdir(path.c_str());
#endif
#elif defined __linux__ || defined __APPLE__
int result = mkdir(path.c_str(), 0777);
#else
int result = -1;
#endif
string parentPathOfSrc=GetParentPath(srcPath);
int length=parentPathOfSrc.size();
if(result == -1)
{
return IsDirectory(path);
}
return true;
}
// create all directories
for(int i=0;i<fileNameList.size();++i)
bool CreateDirectories(const string& directoryPath)
{
string path = directoryPath;
for(;;)
{
char last_char = path.empty() ? 0 : path[path.length() - 1];
if(IsPathSeparator(last_char))
{
// create directory
string srcFilePath=fileNameList[i];
string subStr=srcFilePath.substr(length,srcFilePath.size()-length);
string dstFilePath=dstPath+subStr;
string parentPathOfDst=GetParentPath(dstFilePath);
CreateDirectories(parentPathOfDst);
path = path.substr(0, path.length() - 1);
continue;
}
break;
}
// copy file
for(int i=0;i<fileNameList.size();++i)
if(path.empty() || path == "./" || path == ".\\" || path == ".")
return true;
if(IsDirectory(path))
return true;
size_t pos = path.rfind('/');
if(pos == string::npos)
pos = path.rfind('\\');
if(pos != string::npos)
{
string parent_directory = path.substr(0, pos);
if(!parent_directory.empty())
{
string srcFilePath=fileNameList[i];
if (IsDirectory(srcFilePath))
{
continue;
}
string subStr=srcFilePath.substr(length,srcFilePath.size()-length);
string dstFilePath=dstPath+subStr;
// copy file
CopyFile(srcFilePath,dstFilePath);
// process
double process = (1.0*(i + 1) / fileNameList.size()) * 100;
printf("%s done! %f% \n", GetFileName(fileNameList[i]).c_str(), process);
if(!CreateDirectories(parent_directory))
return false;
}
printf("all done!(the number of files:%d)\n", fileNameList.size());
}
return true;
return CreateDirectory(path);
}
bool CopyFile(const string srcPath, const string dstPath)
{
std::ifstream srcFile(srcPath, ios::binary);
std::ofstream dstFile(dstPath, ios::binary);
if(!srcFile.is_open())
{
printf("can not open %s\n", srcPath.c_str());
return false;
}
if(!dstFile.is_open())
{
printf("can not open %s\n", dstPath.c_str());
return false;
}
if(srcPath == dstPath)
{
printf("src can not be same with dst\n");
return false;
}
char buffer[2048];
unsigned int numberOfBytes = 0;
while(srcFile)
{
srcFile.read(buffer, 2048);
dstFile.write(buffer, srcFile.gcount());
numberOfBytes += srcFile.gcount();
}
srcFile.close();
dstFile.close();
return true;
}
bool CopyDirectories(string srcPath, const string dstPath)
{
if(srcPath == dstPath)
{
printf("src can not be same with dst\n");
return false;
}
}
// ȥ������·���ָ���
srcPath = srcPath.substr(0, srcPath.size() - 1);
vector<string> fileNameList;
GetFileNameList2(srcPath, "", fileNameList, true, true);
string parentPathOfSrc = GetParentPath(srcPath);
int length = parentPathOfSrc.size();
// create all directories
for(int i = 0; i < fileNameList.size(); ++i)
{
// create directory
string srcFilePath = fileNameList[i];
string subStr = srcFilePath.substr(length, srcFilePath.size() - length);
string dstFilePath = dstPath + subStr;
string parentPathOfDst = GetParentPath(dstFilePath);
CreateDirectories(parentPathOfDst);
}
// copy file
for(int i = 0; i < fileNameList.size(); ++i)
{
string srcFilePath = fileNameList[i];
if(IsDirectory(srcFilePath))
{
continue;
}
string subStr = srcFilePath.substr(length, srcFilePath.size() - length);
string dstFilePath = dstPath + subStr;
// copy file
CopyFile(srcFilePath, dstFilePath);
// process
double process = (1.0 * (i + 1) / fileNameList.size()) * 100;
printf("%s done! %f% \n", GetFileName(fileNameList[i]).c_str(), process);
}
printf("all done!(the number of files:%d)\n", fileNameList.size());
return true;
}
} // namespace migraphxSamples
Src/Utility/Filesystem.h
View file @ 0f9dc829
......@@ -5,27 +5,27 @@
#include <string>
#include <vector>
namespace migraphxSamples
{
// 路径是否存在
bool Exists(const std::string &path);
bool Exists(const std::string& path);
// 路径是否为目录
bool IsDirectory(const std::string &path);
bool IsDirectory(const std::string& path);
// 是否是路径分隔符(Linux:‘/’,Windows:’\\’)
bool IsPathSeparator(char c);
// 路径拼接
std::string JoinPath(const std::string &base, const std::string &path);
std::string JoinPath(const std::string& base, const std::string& path);
// 创建多级目录,注意：创建多级目录的时候，目标目录是不能有文件存在的
bool CreateDirectories(const std::string &directoryPath);
bool CreateDirectories(const std::string& directoryPath);
/** 生成符合指定模式的文件名列表(支持递归遍历)
*
*
* pattern: 模式,比如"*.jpg","*.png","*.jpg,*.png"
* addPath：是否包含父路径
* 注意：
......@@ -36,35 +36,43 @@ bool CreateDirectories(const std::string &directoryPath);
5. 不能返回子目录名
*
*/
void GetFileNameList(const std::string &directory, const std::string &pattern, std::vector<std::string> &result, bool recursive, bool addPath);
void GetFileNameList(const std::string& directory,
const std::string& pattern,
std::vector<std::string>& result,
bool recursive,
bool addPath);
// 与GetFileNameList的区别在于如果有子目录，在addPath为true的时候会返回子目录路径(目录名最后有"/")
void GetFileNameList2(const std::string &directory, const std::string &pattern, std::vector<std::string> &result, bool recursive, bool addPath);
void GetFileNameList2(const std::string& directory,
const std::string& pattern,
std::vector<std::string>& result,
bool recursive,
bool addPath);
// 删除文件或者目录,支持递归删除
void Remove(const std::string &directory, const std::string &extension="");
void Remove(const std::string& directory, const std::string& extension = "");
/** 获取路径的文件名和扩展名
*
*
* 示例：path为D:/1/1.txt,则GetFileName()为1.txt,GetFileName_NoExtension()为1,GetExtension()为.txt,GetParentPath()为D:/1/
*/
std::string GetFileName(const std::string &path);
std::string GetFileName_NoExtension(const std::string &path);
std::string GetExtension(const std::string &path);
std::string GetParentPath(const std::string &path);
*/
std::string GetFileName(const std::string& path);
std::string GetFileName_NoExtension(const std::string& path);
std::string GetExtension(const std::string& path);
std::string GetParentPath(const std::string& path);
// 拷贝文件
bool CopyFile(const std::string srcPath,const std::string dstPath);
bool CopyFile(const std::string srcPath, const std::string dstPath);
/** 拷贝目录
*
*
* 示例：CopyDirectories("D:/0/1/2/","E:/3/");实现把D:/0/1/2/目录拷贝到E:/3/目录中(即拷贝完成后的目录结构为E:/3/2/)
* 注意：
1.第一个参数的最后不能加”/”
2.不能拷贝隐藏文件
*/
bool CopyDirectories(std::string srcPath,const std::string dstPath);
bool CopyDirectories(std::string srcPath, const std::string dstPath);
}
} // namespace migraphxSamples
#endif
Src/Utility/SimpleLog.h
View file @ 0f9dc829
......@@ -8,7 +8,7 @@
#include <map>
#include <thread>
#include <mutex>
#if (defined WIN32 || defined _WIN32)
#if(defined WIN32 || defined _WIN32)
#include <Windows.h>
#else
#include <sys/time.h>
......@@ -16,13 +16,13 @@
using namespace std;
/** 简易日志
*
*
* 不依赖于其他第三方库，只需要包含一个头文件就可以使用。提供了4种日志级别，包括INFO,DEBUG,WARN和ERROR。
*
*
* 示例1:
// 初始化日志，在./Log/目录下创建两个日志文件log1.log和log2.log(注意：目录./Log/需要存在，否则日志创建失败)
//
初始化日志，在./Log/目录下创建两个日志文件log1.log和log2.log(注意：目录./Log/需要存在，否则日志创建失败)
LogManager::GetInstance()->Initialize("./Log/","log1");
LogManager::GetInstance()->Initialize("./Log/","log2");
......@@ -34,11 +34,11 @@ using namespace std;
// 关闭日志
LogManager::GetInstance()->Close("log1");
LogManager::GetInstance()->Close("log2");
* 示例2:
// 将日志输出到控制台
string log = "Hello World";
LOG_INFO(stdout, "%s\n", log.c_str());
LOG_INFO(stdout, "%s\n", log.c_str());
* 注意：
1. 需要C++11
......@@ -50,44 +50,43 @@ using namespace std;
class LogManager
{
private:
LogManager(){}
private:
LogManager() {}
public:
~LogManager(){}
inline void Initialize(const string &parentPath,const string &logName)
public:
~LogManager() {}
inline void Initialize(const string& parentPath, const string& logName)
{
// 日志名为空表示输出到控制台
if(logName.size()==0)
if(logName.size() == 0)
return;
// 查找该日志文件，如果没有则创建
std::map<string, FILE*>::const_iterator iter = logMap.find(logName);
if (iter == logMap.end())
if(iter == logMap.end())
{
string pathOfLog = parentPath+ logName + ".log";
FILE *logFile = fopen(pathOfLog.c_str(), "a"); // w:覆盖原有文件,a:追加
if(logFile!=NULL)
string pathOfLog = parentPath + logName + ".log";
FILE* logFile = fopen(pathOfLog.c_str(), "a"); // w:覆盖原有文件,a:追加
if(logFile != NULL)
{
logMap.insert(std::make_pair(logName, logFile));
}
}
}
inline FILE* GetLogFile(const string &logName)
inline FILE* GetLogFile(const string& logName)
{
std::map<string, FILE*>::const_iterator iter=logMap.find(logName);
if(iter==logMap.end())
std::map<string, FILE*>::const_iterator iter = logMap.find(logName);
if(iter == logMap.end())
{
return NULL;
}
return (*iter).second;
}
inline void Close(const string &logName)
inline void Close(const string& logName)
{
std::map<string, FILE*>::const_iterator iter=logMap.find(logName);
if(iter==logMap.end())
std::map<string, FILE*>::const_iterator iter = logMap.find(logName);
if(iter == logMap.end())
{
return;
}
......@@ -95,10 +94,7 @@ public:
fclose((*iter).second);
logMap.erase(iter);
}
inline std::mutex &GetLogMutex()
{
return logMutex;
}
inline std::mutex& GetLogMutex() { return logMutex; }
// Singleton
static LogManager* GetInstance()
......@@ -106,21 +102,22 @@ public:
static LogManager logManager;
return &logManager;
}
private:
private:
std::map<string, FILE*> logMap;
std::mutex logMutex;
};
#ifdef LOG_MUTEX
#define LOCK LogManager::GetInstance()->GetLogMutex().lock()
#define UNLOCK LogManager::GetInstance()->GetLogMutex().unlock()
#define LOCK LogManager::GetInstance()->GetLogMutex().lock()
#define UNLOCK LogManager::GetInstance()->GetLogMutex().unlock()
#else
#define LOCK
#define UNLOCK
#define LOCK
#define UNLOCK
#endif
// log time
typedef struct _LogTime
typedef struct _LogTime
{
string year;
string month;
......@@ -131,53 +128,53 @@ typedef struct _LogTime
string millisecond; // ms
string microsecond; // us
string weekDay;
}LogTime;
} LogTime;
inline LogTime GetTime()
{
LogTime currentTime;
#if (defined WIN32 || defined _WIN32)
#if(defined WIN32 || defined _WIN32)
SYSTEMTIME systemTime;
GetLocalTime(&systemTime);
char temp[8] = { 0 };
char temp[8] = {0};
sprintf(temp, "%04d", systemTime.wYear);
currentTime.year=string(temp);
currentTime.year = string(temp);
sprintf(temp, "%02d", systemTime.wMonth);
currentTime.month=string(temp);
currentTime.month = string(temp);
sprintf(temp, "%02d", systemTime.wDay);
currentTime.day=string(temp);
currentTime.day = string(temp);
sprintf(temp, "%02d", systemTime.wHour);
currentTime.hour=string(temp);
currentTime.hour = string(temp);
sprintf(temp, "%02d", systemTime.wMinute);
currentTime.minute=string(temp);
currentTime.minute = string(temp);
sprintf(temp, "%02d", systemTime.wSecond);
currentTime.second=string(temp);
currentTime.second = string(temp);
sprintf(temp, "%03d", systemTime.wMilliseconds);
currentTime.millisecond=string(temp);
currentTime.millisecond = string(temp);
sprintf(temp, "%d", systemTime.wDayOfWeek);
currentTime.weekDay=string(temp);
currentTime.weekDay = string(temp);
#else
struct timeval tv;
struct tm *p;
struct timeval tv;
struct tm* p;
gettimeofday(&tv, NULL);
p = localtime(&tv.tv_sec);
char temp[8]={0};
sprintf(temp,"%04d",1900+p->tm_year);
currentTime.year=string(temp);
sprintf(temp,"%02d",1+p->tm_mon);
currentTime.month=string(temp);
sprintf(temp,"%02d",p->tm_mday);
currentTime.day=string(temp);
sprintf(temp,"%02d",p->tm_hour);
currentTime.hour=string(temp);
sprintf(temp,"%02d",p->tm_min);
currentTime.minute=string(temp);
sprintf(temp,"%02d",p->tm_sec);
currentTime.second=string(temp);
sprintf(temp,"%03d",(int)(tv.tv_usec/1000));
char temp[8] = {0};
sprintf(temp, "%04d", 1900 + p->tm_year);
currentTime.year = string(temp);
sprintf(temp, "%02d", 1 + p->tm_mon);
currentTime.month = string(temp);
sprintf(temp, "%02d", p->tm_mday);
currentTime.day = string(temp);
sprintf(temp, "%02d", p->tm_hour);
currentTime.hour = string(temp);
sprintf(temp, "%02d", p->tm_min);
currentTime.minute = string(temp);
sprintf(temp, "%02d", p->tm_sec);
currentTime.second = string(temp);
sprintf(temp, "%03d", (int)(tv.tv_usec / 1000));
currentTime.millisecond = string(temp);
sprintf(temp, "%03d", (int)(tv.tv_usec % 1000));
currentTime.microsecond = string(temp);
......@@ -187,61 +184,83 @@ inline LogTime GetTime()
return currentTime;
}
#define LOG_TIME(logFile) \
do\
{\
LogTime currentTime=GetTime(); \
fprintf(((logFile == NULL) ? stdout : logFile), "%s-%s-%s %s:%s:%s.%s\t",currentTime.year.c_str(),currentTime.month.c_str(),currentTime.day.c_str(),currentTime.hour.c_str(),currentTime.minute.c_str(),currentTime.second.c_str(),currentTime.millisecond.c_str()); \
}while (0)
#define LOG_INFO(logFile,logInfo, ...) \
do\
{\
LOCK; \
LOG_TIME(logFile); \
fprintf(((logFile == NULL) ? stdout : logFile), "INFO\t"); \
fprintf(((logFile == NULL) ? stdout : logFile), "[%s:%d (%s) ]: ", __FILE__, __LINE__, __FUNCTION__); \
fprintf(((logFile == NULL) ? stdout : logFile), logInfo, ## __VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while (0)
#define LOG_DEBUG(logFile,logInfo, ...) \
do\
{\
LOCK; \
LOG_TIME(logFile);\
fprintf(((logFile==NULL)?stdout:logFile), "DEBUG\t"); \
fprintf(((logFile==NULL)?stdout:logFile), "[%s:%d (%s) ]: ", __FILE__, __LINE__, __FUNCTION__); \
fprintf(((logFile==NULL)?stdout:logFile),logInfo, ## __VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while (0)
#define LOG_ERROR(logFile,logInfo, ...) \
do\
{\
LOCK; \
LOG_TIME(logFile);\
fprintf(((logFile==NULL)?stdout:logFile), "ERROR\t"); \
fprintf(((logFile==NULL)?stdout:logFile), "[%s:%d (%s) ]: ", __FILE__, __LINE__, __FUNCTION__); \
fprintf(((logFile==NULL)?stdout:logFile),logInfo, ## __VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while (0)
#define LOG_WARN(logFile,logInfo, ...) \
do\
{\
LOCK; \
LOG_TIME(logFile);\
fprintf(((logFile==NULL)?stdout:logFile), "WARN\t"); \
fprintf(((logFile==NULL)?stdout:logFile), "[%s:%d (%s) ]: ", __FILE__, __LINE__, __FUNCTION__); \
fprintf(((logFile==NULL)?stdout:logFile),logInfo, ## __VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while (0)
#define LOG_TIME(logFile) \
do \
{ \
LogTime currentTime = GetTime(); \
fprintf(((logFile == NULL) ? stdout : logFile), \
"%s-%s-%s %s:%s:%s.%s\t", \
currentTime.year.c_str(), \
currentTime.month.c_str(), \
currentTime.day.c_str(), \
currentTime.hour.c_str(), \
currentTime.minute.c_str(), \
currentTime.second.c_str(), \
currentTime.millisecond.c_str()); \
} while(0)
#endif // __SIMPLE_LOG_H__
#define LOG_INFO(logFile, logInfo, ...) \
do \
{ \
LOCK; \
LOG_TIME(logFile); \
fprintf(((logFile == NULL) ? stdout : logFile), "INFO\t"); \
fprintf(((logFile == NULL) ? stdout : logFile), \
"[%s:%d (%s) ]: ", \
__FILE__, \
__LINE__, \
__FUNCTION__); \
fprintf(((logFile == NULL) ? stdout : logFile), logInfo, ##__VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while(0)
#define LOG_DEBUG(logFile, logInfo, ...) \
do \
{ \
LOCK; \
LOG_TIME(logFile); \
fprintf(((logFile == NULL) ? stdout : logFile), "DEBUG\t"); \
fprintf(((logFile == NULL) ? stdout : logFile), \
"[%s:%d (%s) ]: ", \
__FILE__, \
__LINE__, \
__FUNCTION__); \
fprintf(((logFile == NULL) ? stdout : logFile), logInfo, ##__VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while(0)
#define LOG_ERROR(logFile, logInfo, ...) \
do \
{ \
LOCK; \
LOG_TIME(logFile); \
fprintf(((logFile == NULL) ? stdout : logFile), "ERROR\t"); \
fprintf(((logFile == NULL) ? stdout : logFile), \
"[%s:%d (%s) ]: ", \
__FILE__, \
__LINE__, \
__FUNCTION__); \
fprintf(((logFile == NULL) ? stdout : logFile), logInfo, ##__VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while(0)
#define LOG_WARN(logFile, logInfo, ...) \
do \
{ \
LOCK; \
LOG_TIME(logFile); \
fprintf(((logFile == NULL) ? stdout : logFile), "WARN\t"); \
fprintf(((logFile == NULL) ? stdout : logFile), \
"[%s:%d (%s) ]: ", \
__FILE__, \
__LINE__, \
__FUNCTION__); \
fprintf(((logFile == NULL) ? stdout : logFile), logInfo, ##__VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while(0)
#endif // __SIMPLE_LOG_H__
Src/Utility/tokenization.cpp
View file @ 0f9dc829
......@@ -6,224 +6,257 @@
#include "./tokenization.h"
namespace cuBERT {
void FullTokenizer::convert_tokens_to_ids(const std::vector<std::string> &tokens, uint64_t *ids) {
for (int i = 0; i < tokens.size(); ++i) {
ids[i] = convert_token_to_id(tokens[i]);
}
namespace cuBERT
{
void FullTokenizer::convert_tokens_to_ids(const std::vector<std::string>& tokens, uint64_t* ids)
{
for(int i = 0; i < tokens.size(); ++i)
{
ids[i] = convert_token_to_id(tokens[i]);
}
}
// trim from start (in place)
static inline void ltrim(std::string &s) {
s.erase(s.begin(), std::find_if(s.begin(), s.end(), [](int ch) {
return !std::isspace(ch);
}));
}
static inline void ltrim(std::string& s)
{
s.erase(s.begin(), std::find_if(s.begin(), s.end(), [](int ch) { return !std::isspace(ch); }));
}
// trim from end (in place)
static inline void rtrim(std::string &s) {
s.erase(std::find_if(s.rbegin(), s.rend(), [](int ch) {
return !std::isspace(ch);
}).base(), s.end());
}
static inline void rtrim(std::string& s)
{
s.erase(std::find_if(s.rbegin(), s.rend(), [](int ch) { return !std::isspace(ch); }).base(),
s.end());
}
// trim from both ends (in place)
static inline void trim(std::string &s) {
ltrim(s);
rtrim(s);
}
void load_vocab(const char *vocab_file, std::unordered_map<std::string, uint64_t> *vocab) {
std::ifstream file(vocab_file);
if (!file) {
throw std::invalid_argument("Unable to open vocab file");
}
unsigned int index = 0;
std::string line;
while (std::getline(file, line)) {
trim(line);
(*vocab)[line] = index;
index++;
}
static inline void trim(std::string& s)
{
ltrim(s);
rtrim(s);
}
file.close();
void load_vocab(const char* vocab_file, std::unordered_map<std::string, uint64_t>* vocab)
{
std::ifstream file(vocab_file);
if(!file)
{
throw std::invalid_argument("Unable to open vocab file");
}
inline bool _is_whitespace(int c, const char *cat) {
if (c == ' ' || c == '\t' || c == '\n' || c == '\r') {
return true;
}
return cat[0] == 'Z' && cat[1] == 's';
unsigned int index = 0;
std::string line;
while(std::getline(file, line))
{
trim(line);
(*vocab)[line] = index;
index++;
}
inline bool _is_control(int c, const char *cat) {
// These are technically control characters but we count them as whitespace characters.
if (c == '\t' || c == '\n' || c == '\r') {
return false;
}
return 'C' == *cat;
}
file.close();
}
inline bool _is_punctuation(int cp, const char *cat) {
// We treat all non-letter/number ASCII as punctuation.
// Characters such as "^", "$", and "`" are not in the Unicode
// Punctuation class but we treat them as punctuation anyways, for
// consistency.
if ((cp >= 33 && cp <= 47) || (cp >= 58 && cp <= 64) ||
(cp >= 91 && cp <= 96) || (cp >= 123 && cp <= 126)) {
return true;
}
return 'P' == *cat;
inline bool _is_whitespace(int c, const char* cat)
{
if(c == ' ' || c == '\t' || c == '\n' || c == '\r')
{
return true;
}
return cat[0] == 'Z' && cat[1] == 's';
}
bool _is_whitespace(int c) {
return _is_whitespace(c, utf8proc_category_string(c));
inline bool _is_control(int c, const char* cat)
{
// These are technically control characters but we count them as whitespace characters.
if(c == '\t' || c == '\n' || c == '\r')
{
return false;
}
return 'C' == *cat;
}
bool _is_control(int c) {
return _is_control(c, utf8proc_category_string(c));
inline bool _is_punctuation(int cp, const char* cat)
{
// We treat all non-letter/number ASCII as punctuation.
// Characters such as "^", "$", and "`" are not in the Unicode
// Punctuation class but we treat them as punctuation anyways, for
// consistency.
if((cp >= 33 && cp <= 47) || (cp >= 58 && cp <= 64) || (cp >= 91 && cp <= 96) ||
(cp >= 123 && cp <= 126))
{
return true;
}
return 'P' == *cat;
}
bool _is_punctuation(int cp) {
return _is_punctuation(cp, utf8proc_category_string(cp));
}
bool _is_whitespace(int c) { return _is_whitespace(c, utf8proc_category_string(c)); }
bool _is_control(int c) { return _is_control(c, utf8proc_category_string(c)); }
bool _is_punctuation(int cp) { return _is_punctuation(cp, utf8proc_category_string(cp)); }
bool BasicTokenizer::_is_chinese_char(int cp)
{
// This defines a "chinese character" as anything in the CJK Unicode block:
// https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
//
// Note that the CJK Unicode block is NOT all Japanese and Korean characters,
// despite its name. The modern Korean Hangul alphabet is a different block,
// as is Japanese Hiragana and Katakana. Those alphabets are used to write
// space-separated words, so they are not treated specially and handled
// like the all of the other languages.
return (cp >= 0x4E00 && cp <= 0x9FFF) || (cp >= 0x3400 && cp <= 0x4DBF) ||
(cp >= 0x20000 && cp <= 0x2A6DF) || (cp >= 0x2A700 && cp <= 0x2B73F) ||
(cp >= 0x2B740 && cp <= 0x2B81F) || (cp >= 0x2B820 && cp <= 0x2CEAF) ||
(cp >= 0xF900 && cp <= 0xFAFF) || (cp >= 0x2F800 && cp <= 0x2FA1F);
}
bool BasicTokenizer::_is_chinese_char(int cp) {
// This defines a "chinese character" as anything in the CJK Unicode block:
// https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
//
// Note that the CJK Unicode block is NOT all Japanese and Korean characters,
// despite its name. The modern Korean Hangul alphabet is a different block,
// as is Japanese Hiragana and Katakana. Those alphabets are used to write
// space-separated words, so they are not treated specially and handled
// like the all of the other languages.
return (cp >= 0x4E00 && cp <= 0x9FFF) ||
(cp >= 0x3400 && cp <= 0x4DBF) ||
(cp >= 0x20000 && cp <= 0x2A6DF) ||
(cp >= 0x2A700 && cp <= 0x2B73F) ||
(cp >= 0x2B740 && cp <= 0x2B81F) ||
(cp >= 0x2B820 && cp <= 0x2CEAF) ||
(cp >= 0xF900 && cp <= 0xFAFF) ||
(cp >= 0x2F800 && cp <= 0x2FA1F);
void BasicTokenizer::tokenize(const char* text,
std::vector<std::string>* output_tokens,
size_t max_length)
{
// This was added on November 1st, 2018 for the multilingual and Chinese
// models. This is also applied to the English models now, but it doesn't
// matter since the English models were not trained on any Chinese data
// and generally don't have any Chinese data in them (there are Chinese
// characters in the vocabulary because Wikipedia does have some Chinese
// words in the English Wikipedia.).
if(do_lower_case)
{
text = (const char*)utf8proc_NFD((const utf8proc_uint8_t*)text);
}
void BasicTokenizer::tokenize(const char *text, std::vector<std::string> *output_tokens, size_t max_length) {
// This was added on November 1st, 2018 for the multilingual and Chinese
// models. This is also applied to the English models now, but it doesn't
// matter since the English models were not trained on any Chinese data
// and generally don't have any Chinese data in them (there are Chinese
// characters in the vocabulary because Wikipedia does have some Chinese
// words in the English Wikipedia.).
if (do_lower_case) {
text = (const char *) utf8proc_NFD((const utf8proc_uint8_t *) text);
size_t word_bytes = std::strlen(text);
bool new_token = true;
size_t subpos = 0;
int cp;
char dst[4];
while(word_bytes > 0)
{
int len = utf8proc_iterate((const utf8proc_uint8_t*)text + subpos, word_bytes, &cp);
if(len < 0)
{
std::cerr << "UTF-8 decode error: " << text << std::endl;
break;
}
if(do_lower_case)
{
cp = utf8proc_tolower(cp);
}
size_t word_bytes = std::strlen(text);
bool new_token = true;
size_t subpos = 0;
int cp;
char dst[4];
while (word_bytes > 0) {
int len = utf8proc_iterate((const utf8proc_uint8_t *) text + subpos, word_bytes, &cp);
if (len < 0) {
std::cerr << "UTF-8 decode error: " << text << std::endl;
break;
}
if (do_lower_case) {
cp = utf8proc_tolower(cp);
const char* cat = utf8proc_category_string(cp);
if(cp == 0 || cp == 0xfffd || _is_control(cp, cat))
{
// pass
}
else if(do_lower_case && cat[0] == 'M' && cat[1] == 'n')
{
// pass
}
else if(_is_whitespace(cp, cat))
{
new_token = true;
}
else
{
size_t dst_len = len;
const char* dst_ptr = text + subpos;
if(do_lower_case)
{
dst_len = utf8proc_encode_char(cp, (utf8proc_uint8_t*)dst);
dst_ptr = dst;
}
const char *cat = utf8proc_category_string(cp);
if (cp == 0 || cp == 0xfffd || _is_control(cp, cat)) {
// pass
} else if (do_lower_case && cat[0] == 'M' && cat[1] == 'n') {
// pass
} else if (_is_whitespace(cp, cat)) {
if(_is_punctuation(cp, cat) || _is_chinese_char(cp))
{
output_tokens->emplace_back(dst_ptr, dst_len);
new_token = true;
} else {
size_t dst_len = len;
const char *dst_ptr = text + subpos;
if (do_lower_case) {
dst_len = utf8proc_encode_char(cp, (utf8proc_uint8_t *) dst);
dst_ptr = dst;
}
if (_is_punctuation(cp, cat) || _is_chinese_char(cp)) {
}
else
{
if(new_token)
{
output_tokens->emplace_back(dst_ptr, dst_len);
new_token = true;
} else {
if (new_token) {
output_tokens->emplace_back(dst_ptr, dst_len);
new_token = false;
} else {
output_tokens->at(output_tokens->size() - 1).append(dst_ptr, dst_len);
}
new_token = false;
}
else
{
output_tokens->at(output_tokens->size() - 1).append(dst_ptr, dst_len);
}
}
}
word_bytes = word_bytes - len;
subpos = subpos + len;
word_bytes = word_bytes - len;
subpos = subpos + len;
// early terminate
if (output_tokens->size() >= max_length) {
break;
}
// early terminate
if(output_tokens->size() >= max_length)
{
break;
}
}
if (do_lower_case) {
free((void *) text);
}
if(do_lower_case)
{
free((void*)text);
}
}
void WordpieceTokenizer::tokenize(const std::string& token, std::vector<std::string>* output_tokens)
{
if(token.size() > max_input_chars_per_word)
{ // FIXME: slightly different
output_tokens->push_back(unk_token);
return;
}
size_t output_tokens_len = output_tokens->size();
for(size_t start = 0; start < token.size();)
{
bool is_bad = true;
// TODO: can be optimized by prefix-tree
for(size_t end = token.size(); start < end; --end)
{ // FIXME: slightly different
std::string substr = start > 0 ? "##" + token.substr(start, end - start)
: token.substr(start, end - start);
if(vocab->count(substr))
{
is_bad = false;
output_tokens->push_back(substr);
start = end;
break;
}
}
void WordpieceTokenizer::tokenize(const std::string &token, std::vector<std::string> *output_tokens) {
if (token.size() > max_input_chars_per_word) { // FIXME: slightly different
if(is_bad)
{
output_tokens->resize(output_tokens_len);
output_tokens->push_back(unk_token);
return;
}
size_t output_tokens_len = output_tokens->size();
for (size_t start = 0; start < token.size();) {
bool is_bad = true;
// TODO: can be optimized by prefix-tree
for (size_t end = token.size(); start < end; --end) { // FIXME: slightly different
std::string substr = start > 0
? "##" + token.substr(start, end - start)
: token.substr(start, end - start);
if (vocab->count(substr)) {
is_bad = false;
output_tokens->push_back(substr);
start = end;
break;
}
}
if (is_bad) {
output_tokens->resize(output_tokens_len);
output_tokens->push_back(unk_token);
return;
}
}
}
}
void FullTokenizer::tokenize(const char *text, std::vector<std::string> *output_tokens, size_t max_length) {
std::vector<std::string> tokens;
tokens.reserve(max_length);
basic_tokenizer->tokenize(text, &tokens, max_length);
for (const auto &token : tokens) {
wordpiece_tokenizer->tokenize(token, output_tokens);
// early terminate
if (output_tokens->size() >= max_length) {
break;
}
void FullTokenizer::tokenize(const char* text,
std::vector<std::string>* output_tokens,
size_t max_length)
{
std::vector<std::string> tokens;
tokens.reserve(max_length);
basic_tokenizer->tokenize(text, &tokens, max_length);
for(const auto& token : tokens)
{
wordpiece_tokenizer->tokenize(token, output_tokens);
// early terminate
if(output_tokens->size() >= max_length)
{
break;
}
}
}
} // namespace cuBERT
Src/Utility/tokenization.h
View file @ 0f9dc829
......@@ -6,158 +6,172 @@
#include <unordered_map>
#include <iostream>
namespace cuBERT {
namespace cuBERT
{
void load_vocab(const char *vocab_file, std::unordered_map<std::string, uint64_t> *vocab);
void load_vocab(const char* vocab_file, std::unordered_map<std::string, uint64_t>* vocab);
/**
* Checks whether `chars` is a whitespace character.
* @param c
* @return
*/
bool _is_whitespace(int c);
bool _is_whitespace(int c);
/**
* Checks whether `chars` is a control character.
* @param c
* @return
*/
bool _is_control(int c);
bool _is_control(int c);
/**
* Checks whether `chars` is a punctuation character.
* @param cp
* @return
*/
bool _is_punctuation(int cp);
bool _is_punctuation(int cp);
/**
* Runs basic tokenization (punctuation splitting, lower casing, etc.).
*/
class BasicTokenizer {
class BasicTokenizer
{
public:
/**
* Constructs a BasicTokenizer.
* @param do_lower_case Whether to lower case the input.
*/
explicit BasicTokenizer(bool do_lower_case = true) : do_lower_case(do_lower_case) {}
BasicTokenizer(const BasicTokenizer &other) = delete;
virtual ~BasicTokenizer() = default;
/**
* Tokenizes a piece of text.
*
* to_lower
* _run_strip_accents Strips accents from a piece of text.
* _clean_text Performs invalid character removal and whitespace cleanup on text.
* _tokenize_chinese_chars Adds whitespace around any CJK character.
* _run_split_on_punc Splits punctuation on a piece of text.
* whitespace_tokenize Runs basic whitespace cleaning and splitting on a piece of text.
*
* @param text
* @param output_tokens
*/
void tokenize(const char *text, std::vector<std::string> *output_tokens, size_t max_length);
/**
* Constructs a BasicTokenizer.
* @param do_lower_case Whether to lower case the input.
*/
explicit BasicTokenizer(bool do_lower_case = true) : do_lower_case(do_lower_case) {}
BasicTokenizer(const BasicTokenizer& other) = delete;
virtual ~BasicTokenizer() = default;
/**
* Tokenizes a piece of text.
*
* to_lower
* _run_strip_accents Strips accents from a piece of text.
* _clean_text Performs invalid character removal and whitespace cleanup on text.
* _tokenize_chinese_chars Adds whitespace around any CJK character.
* _run_split_on_punc Splits punctuation on a piece of text.
* whitespace_tokenize Runs basic whitespace cleaning and splitting on a piece of text.
*
* @param text
* @param output_tokens
*/
void tokenize(const char* text, std::vector<std::string>* output_tokens, size_t max_length);
private:
const bool do_lower_case;
const bool do_lower_case;
/**
* Checks whether CP is the codepoint of a CJK character.
* @param cp
* @return
*/
inline static bool _is_chinese_char(int cp);
};
/**
* Checks whether CP is the codepoint of a CJK character.
* @param cp
* @return
*/
inline static bool _is_chinese_char(int cp);
};
/**
* Runs WordPiece tokenziation.
*/
class WordpieceTokenizer {
class WordpieceTokenizer
{
public:
explicit WordpieceTokenizer(
std::unordered_map<std::string, uint64_t> *vocab,
std::string unk_token = "[UNK]",
int max_input_chars_per_word = 200
) : vocab(vocab), unk_token(unk_token), max_input_chars_per_word(max_input_chars_per_word) {}
WordpieceTokenizer(const WordpieceTokenizer &other) = delete;
virtual ~WordpieceTokenizer() = default;
/**
* Tokenizes a piece of text into its word pieces.
*
* This uses a greedy longest-match-first algorithm to perform tokenization
* using the given vocabulary.
*
* For example:
* input = "unaffable"
* output = ["un", "##aff", "##able"]
*
* @param text A single token or whitespace separated tokens. This should have already been passed through `BasicTokenizer.
* @param output_tokens A list of wordpiece tokens.
*/
void tokenize(const std::string &text, std::vector<std::string> *output_tokens);
explicit WordpieceTokenizer(std::unordered_map<std::string, uint64_t>* vocab,
std::string unk_token = "[UNK]",
int max_input_chars_per_word = 200)
: vocab(vocab), unk_token(unk_token), max_input_chars_per_word(max_input_chars_per_word)
{
}
WordpieceTokenizer(const WordpieceTokenizer& other) = delete;
virtual ~WordpieceTokenizer() = default;
/**
* Tokenizes a piece of text into its word pieces.
*
* This uses a greedy longest-match-first algorithm to perform tokenization
* using the given vocabulary.
*
* For example:
* input = "unaffable"
* output = ["un", "##aff", "##able"]
*
* @param text A single token or whitespace separated tokens. This should have already been
* passed through `BasicTokenizer.
* @param output_tokens A list of wordpiece tokens.
*/
void tokenize(const std::string& text, std::vector<std::string>* output_tokens);
private:
const std::unordered_map<std::string, uint64_t> *vocab;
const std::string unk_token;
const int max_input_chars_per_word;
};
const std::unordered_map<std::string, uint64_t>* vocab;
const std::string unk_token;
const int max_input_chars_per_word;
};
/**
* Runs end-to-end tokenziation.
*/
class FullTokenizer {
class FullTokenizer
{
public:
FullTokenizer(const char *vocab_file, bool do_lower_case = true) {
vocab = new std::unordered_map<std::string, uint64_t>();
load_vocab(vocab_file, vocab);
basic_tokenizer = new BasicTokenizer(do_lower_case);
wordpiece_tokenizer = new WordpieceTokenizer(vocab);
FullTokenizer(const char* vocab_file, bool do_lower_case = true)
{
vocab = new std::unordered_map<std::string, uint64_t>();
load_vocab(vocab_file, vocab);
basic_tokenizer = new BasicTokenizer(do_lower_case);
wordpiece_tokenizer = new WordpieceTokenizer(vocab);
}
~FullTokenizer()
{
if(wordpiece_tokenizer != NULL)
{
wordpiece_tokenizer = NULL;
}
delete wordpiece_tokenizer;
~FullTokenizer() {
if (wordpiece_tokenizer != NULL){
wordpiece_tokenizer = NULL;
}
delete wordpiece_tokenizer;
if (basic_tokenizer != NULL){
basic_tokenizer = NULL;
}
delete basic_tokenizer;
if (vocab != NULL){
vocab = NULL;
}
delete vocab;
if(basic_tokenizer != NULL)
{
basic_tokenizer = NULL;
}
delete basic_tokenizer;
void tokenize(const char *text, std::vector<std::string> *output_tokens, size_t max_length);
inline uint64_t convert_token_to_id(const std::string &token) {
auto item = vocab->find(token);
if (item == vocab->end()) {
std::cerr << "vocab missing key: " << token << std::endl;
return 0;
} else {
return item->second;
}
if(vocab != NULL)
{
vocab = NULL;
}
delete vocab;
}
void tokenize(const char* text, std::vector<std::string>* output_tokens, size_t max_length);
inline uint64_t convert_token_to_id(const std::string& token)
{
auto item = vocab->find(token);
if(item == vocab->end())
{
std::cerr << "vocab missing key: " << token << std::endl;
return 0;
}
else
{
return item->second;
}
}
void convert_tokens_to_ids(const std::vector<std::string> &tokens, uint64_t *ids);
void convert_tokens_to_ids(const std::vector<std::string>& tokens, uint64_t* ids);
private:
std::unordered_map<std::string, uint64_t> *vocab;
BasicTokenizer *basic_tokenizer;
WordpieceTokenizer *wordpiece_tokenizer;
};
std::unordered_map<std::string, uint64_t>* vocab;
BasicTokenizer* basic_tokenizer;
WordpieceTokenizer* wordpiece_tokenizer;
};
}
} // namespace cuBERT
#endif //CUBERT_TOKENIZATION_H
#endif // CUBERT_TOKENIZATION_H
Src/Utility/utf8proc.c
View file @ 0f9dc829
/* -*- mode: c; c-basic-offset: 2; tab-width: 2; indent-tabs-mode: nil -*- */
/*
* Copyright (c) 2014-2021 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
* Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
* Copyright (c) 2014-2021 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P.
* Jones, and other contributors. Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
......@@ -32,7 +32,6 @@
* Please notice the copyright statement in the file "utf8proc_data.c".
*/
/*
* File name: utf8proc.c
*
......@@ -40,36 +39,26 @@
* Implementation of libutf8proc.
*/
#include "utf8proc.h"
#ifndef SSIZE_MAX
#define SSIZE_MAX ((size_t)SIZE_MAX/2)
#define SSIZE_MAX ((size_t)SIZE_MAX / 2)
#endif
#ifndef UINT16_MAX
# define UINT16_MAX 65535U
#define UINT16_MAX 65535U
#endif
#include "utf8proc_data.c"
UTF8PROC_DLLEXPORT const utf8proc_int8_t utf8proc_utf8class[256] = {
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
4, 4, 4, 4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0 };
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0};
#define UTF8PROC_HANGUL_SBASE 0xAC00
#define UTF8PROC_HANGUL_LBASE 0x1100
......@@ -81,166 +70,198 @@ UTF8PROC_DLLEXPORT const utf8proc_int8_t utf8proc_utf8class[256] = {
#define UTF8PROC_HANGUL_NCOUNT 588
#define UTF8PROC_HANGUL_SCOUNT 11172
/* END is exclusive */
#define UTF8PROC_HANGUL_L_START 0x1100
#define UTF8PROC_HANGUL_L_END 0x115A
#define UTF8PROC_HANGUL_L_START 0x1100
#define UTF8PROC_HANGUL_L_END 0x115A
#define UTF8PROC_HANGUL_L_FILLER 0x115F
#define UTF8PROC_HANGUL_V_START 0x1160
#define UTF8PROC_HANGUL_V_END 0x11A3
#define UTF8PROC_HANGUL_T_START 0x11A8
#define UTF8PROC_HANGUL_T_END 0x11FA
#define UTF8PROC_HANGUL_S_START 0xAC00
#define UTF8PROC_HANGUL_S_END 0xD7A4
#define UTF8PROC_HANGUL_V_START 0x1160
#define UTF8PROC_HANGUL_V_END 0x11A3
#define UTF8PROC_HANGUL_T_START 0x11A8
#define UTF8PROC_HANGUL_T_END 0x11FA
#define UTF8PROC_HANGUL_S_START 0xAC00
#define UTF8PROC_HANGUL_S_END 0xD7A4
/* Should follow semantic-versioning rules (semver.org) based on API
compatibility. (Note that the shared-library version number will
be different, being based on ABI compatibility.): */
#define STRINGIZEx(x) #x
#define STRINGIZE(x) STRINGIZEx(x)
UTF8PROC_DLLEXPORT const char *utf8proc_version(void) {
return STRINGIZE(UTF8PROC_VERSION_MAJOR) "." STRINGIZE(UTF8PROC_VERSION_MINOR) "." STRINGIZE(UTF8PROC_VERSION_PATCH) "";
}
UTF8PROC_DLLEXPORT const char *utf8proc_unicode_version(void) {
return "15.0.0";
}
UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode) {
switch (errcode) {
case UTF8PROC_ERROR_NOMEM:
return "Memory for processing UTF-8 data could not be allocated.";
case UTF8PROC_ERROR_OVERFLOW:
return "UTF-8 string is too long to be processed.";
case UTF8PROC_ERROR_INVALIDUTF8:
return "Invalid UTF-8 string";
case UTF8PROC_ERROR_NOTASSIGNED:
return "Unassigned Unicode code point found in UTF-8 string.";
case UTF8PROC_ERROR_INVALIDOPTS:
return "Invalid options for UTF-8 processing chosen.";
default:
return "An unknown error occurred while processing UTF-8 data.";
}
}
#define utf_cont(ch) (((ch) & 0xc0) == 0x80)
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_int32_t *dst
) {
utf8proc_int32_t uc;
const utf8proc_uint8_t *end;
*dst = -1;
if (!strlen) return 0;
end = str + ((strlen < 0) ? 4 : strlen);
uc = *str++;
if (uc < 0x80) {
*dst = uc;
return 1;
}
// Must be between 0xc2 and 0xf4 inclusive to be valid
if ((utf8proc_uint32_t)(uc - 0xc2) > (0xf4-0xc2)) return UTF8PROC_ERROR_INVALIDUTF8;
if (uc < 0xe0) { // 2-byte sequence
// Must have valid continuation character
if (str >= end || !utf_cont(*str)) return UTF8PROC_ERROR_INVALIDUTF8;
*dst = ((uc & 0x1f)<<6) | (*str & 0x3f);
return 2;
}
if (uc < 0xf0) { // 3-byte sequence
if ((str + 1 >= end) || !utf_cont(*str) || !utf_cont(str[1]))
UTF8PROC_DLLEXPORT const char* utf8proc_version(void)
{
return STRINGIZE(UTF8PROC_VERSION_MAJOR) "." STRINGIZE(UTF8PROC_VERSION_MINOR) "." STRINGIZE(UTF8PROC_VERSION_PATCH) "";
}
UTF8PROC_DLLEXPORT const char* utf8proc_unicode_version(void) { return "15.0.0"; }
UTF8PROC_DLLEXPORT const char* utf8proc_errmsg(utf8proc_ssize_t errcode)
{
switch(errcode)
{
case UTF8PROC_ERROR_NOMEM: return "Memory for processing UTF-8 data could not be allocated.";
case UTF8PROC_ERROR_OVERFLOW: return "UTF-8 string is too long to be processed.";
case UTF8PROC_ERROR_INVALIDUTF8: return "Invalid UTF-8 string";
case UTF8PROC_ERROR_NOTASSIGNED: return "Unassigned Unicode code point found in UTF-8 string.";
case UTF8PROC_ERROR_INVALIDOPTS: return "Invalid options for UTF-8 processing chosen.";
default: return "An unknown error occurred while processing UTF-8 data.";
}
}
#define utf_cont(ch) (((ch) & 0xc0) == 0x80)
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(const utf8proc_uint8_t* str,
utf8proc_ssize_t strlen,
utf8proc_int32_t* dst)
{
utf8proc_int32_t uc;
const utf8proc_uint8_t* end;
*dst = -1;
if(!strlen)
return 0;
end = str + ((strlen < 0) ? 4 : strlen);
uc = *str++;
if(uc < 0x80)
{
*dst = uc;
return 1;
}
// Must be between 0xc2 and 0xf4 inclusive to be valid
if((utf8proc_uint32_t)(uc - 0xc2) > (0xf4 - 0xc2))
return UTF8PROC_ERROR_INVALIDUTF8;
// Check for surrogate chars
if (uc == 0xed && *str > 0x9f)
return UTF8PROC_ERROR_INVALIDUTF8;
uc = ((uc & 0xf)<<12) | ((*str & 0x3f)<<6) | (str[1] & 0x3f);
if (uc < 0x800)
return UTF8PROC_ERROR_INVALIDUTF8;
*dst = uc;
return 3;
}
// 4-byte sequence
// Must have 3 valid continuation characters
if ((str + 2 >= end) || !utf_cont(*str) || !utf_cont(str[1]) || !utf_cont(str[2]))
return UTF8PROC_ERROR_INVALIDUTF8;
// Make sure in correct range (0x10000 - 0x10ffff)
if (uc == 0xf0) {
if (*str < 0x90) return UTF8PROC_ERROR_INVALIDUTF8;
} else if (uc == 0xf4) {
if (*str > 0x8f) return UTF8PROC_ERROR_INVALIDUTF8;
}
*dst = ((uc & 7)<<18) | ((*str & 0x3f)<<12) | ((str[1] & 0x3f)<<6) | (str[2] & 0x3f);
return 4;
}
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t uc) {
return (((utf8proc_uint32_t)uc)-0xd800 > 0x07ff) && ((utf8proc_uint32_t)uc < 0x110000);
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t uc, utf8proc_uint8_t *dst) {
if (uc < 0x00) {
return 0;
} else if (uc < 0x80) {
dst[0] = (utf8proc_uint8_t) uc;
return 1;
} else if (uc < 0x800) {
dst[0] = (utf8proc_uint8_t)(0xC0 + (uc >> 6));
dst[1] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 2;
// Note: we allow encoding 0xd800-0xdfff here, so as not to change
// the API, however, these are actually invalid in UTF-8
} else if (uc < 0x10000) {
dst[0] = (utf8proc_uint8_t)(0xE0 + (uc >> 12));
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
dst[2] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 3;
} else if (uc < 0x110000) {
dst[0] = (utf8proc_uint8_t)(0xF0 + (uc >> 18));
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 12) & 0x3F));
dst[2] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
dst[3] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
if(uc < 0xe0)
{ // 2-byte sequence
// Must have valid continuation character
if(str >= end || !utf_cont(*str))
return UTF8PROC_ERROR_INVALIDUTF8;
*dst = ((uc & 0x1f) << 6) | (*str & 0x3f);
return 2;
}
if(uc < 0xf0)
{ // 3-byte sequence
if((str + 1 >= end) || !utf_cont(*str) || !utf_cont(str[1]))
return UTF8PROC_ERROR_INVALIDUTF8;
// Check for surrogate chars
if(uc == 0xed && *str > 0x9f)
return UTF8PROC_ERROR_INVALIDUTF8;
uc = ((uc & 0xf) << 12) | ((*str & 0x3f) << 6) | (str[1] & 0x3f);
if(uc < 0x800)
return UTF8PROC_ERROR_INVALIDUTF8;
*dst = uc;
return 3;
}
// 4-byte sequence
// Must have 3 valid continuation characters
if((str + 2 >= end) || !utf_cont(*str) || !utf_cont(str[1]) || !utf_cont(str[2]))
return UTF8PROC_ERROR_INVALIDUTF8;
// Make sure in correct range (0x10000 - 0x10ffff)
if(uc == 0xf0)
{
if(*str < 0x90)
return UTF8PROC_ERROR_INVALIDUTF8;
}
else if(uc == 0xf4)
{
if(*str > 0x8f)
return UTF8PROC_ERROR_INVALIDUTF8;
}
*dst = ((uc & 7) << 18) | ((*str & 0x3f) << 12) | ((str[1] & 0x3f) << 6) | (str[2] & 0x3f);
return 4;
} else return 0;
}
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t uc)
{
return (((utf8proc_uint32_t)uc) - 0xd800 > 0x07ff) && ((utf8proc_uint32_t)uc < 0x110000);
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t uc, utf8proc_uint8_t* dst)
{
if(uc < 0x00)
{
return 0;
}
else if(uc < 0x80)
{
dst[0] = (utf8proc_uint8_t)uc;
return 1;
}
else if(uc < 0x800)
{
dst[0] = (utf8proc_uint8_t)(0xC0 + (uc >> 6));
dst[1] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 2;
// Note: we allow encoding 0xd800-0xdfff here, so as not to change
// the API, however, these are actually invalid in UTF-8
}
else if(uc < 0x10000)
{
dst[0] = (utf8proc_uint8_t)(0xE0 + (uc >> 12));
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
dst[2] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 3;
}
else if(uc < 0x110000)
{
dst[0] = (utf8proc_uint8_t)(0xF0 + (uc >> 18));
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 12) & 0x3F));
dst[2] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
dst[3] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 4;
}
else
return 0;
}
/* internal version used for inserting 0xff bytes between graphemes */
static utf8proc_ssize_t charbound_encode_char(utf8proc_int32_t uc, utf8proc_uint8_t *dst) {
if (uc < 0x00) {
if (uc == -1) { /* internal value used for grapheme breaks */
dst[0] = (utf8proc_uint8_t)0xFF;
static utf8proc_ssize_t charbound_encode_char(utf8proc_int32_t uc, utf8proc_uint8_t* dst)
{
if(uc < 0x00)
{
if(uc == -1)
{ /* internal value used for grapheme breaks */
dst[0] = (utf8proc_uint8_t)0xFF;
return 1;
}
return 0;
}
else if(uc < 0x80)
{
dst[0] = (utf8proc_uint8_t)uc;
return 1;
}
return 0;
} else if (uc < 0x80) {
dst[0] = (utf8proc_uint8_t)uc;
return 1;
} else if (uc < 0x800) {
dst[0] = (utf8proc_uint8_t)(0xC0 + (uc >> 6));
dst[1] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 2;
} else if (uc < 0x10000) {
dst[0] = (utf8proc_uint8_t)(0xE0 + (uc >> 12));
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
dst[2] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 3;
} else if (uc < 0x110000) {
dst[0] = (utf8proc_uint8_t)(0xF0 + (uc >> 18));
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 12) & 0x3F));
dst[2] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
dst[3] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 4;
} else return 0;
}
else if(uc < 0x800)
{
dst[0] = (utf8proc_uint8_t)(0xC0 + (uc >> 6));
dst[1] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 2;
}
else if(uc < 0x10000)
{
dst[0] = (utf8proc_uint8_t)(0xE0 + (uc >> 12));
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
dst[2] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 3;
}
else if(uc < 0x110000)
{
dst[0] = (utf8proc_uint8_t)(0xF0 + (uc >> 18));
dst[1] = (utf8proc_uint8_t)(0x80 + ((uc >> 12) & 0x3F));
dst[2] = (utf8proc_uint8_t)(0x80 + ((uc >> 6) & 0x3F));
dst[3] = (utf8proc_uint8_t)(0x80 + (uc & 0x3F));
return 4;
}
else
return 0;
}
/* internal "unsafe" version that does not check whether uc is in range */
static const utf8proc_property_t *unsafe_get_property(utf8proc_int32_t uc) {
/* ASSERT: uc >= 0 && uc < 0x110000 */
return utf8proc_properties + (
utf8proc_stage2table[
utf8proc_stage1table[uc >> 8] + (uc & 0xFF)
]
);
static const utf8proc_property_t* unsafe_get_property(utf8proc_int32_t uc)
{
/* ASSERT: uc >= 0 && uc < 0x110000 */
return utf8proc_properties +
(utf8proc_stage2table[utf8proc_stage1table[uc >> 8] + (uc & 0xFF)]);
}
UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t uc) {
return uc < 0 || uc >= 0x110000 ? utf8proc_properties : unsafe_get_property(uc);
UTF8PROC_DLLEXPORT const utf8proc_property_t* utf8proc_get_property(utf8proc_int32_t uc)
{
return uc < 0 || uc >= 0x110000 ? utf8proc_properties : unsafe_get_property(uc);
}
/* return whether there is a grapheme break between boundclasses lbc and tbc
......@@ -258,535 +279,695 @@ UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int
See the special support in grapheme_break_extended, for required bookkeeping by the caller.
*/
static utf8proc_bool grapheme_break_simple(int lbc, int tbc) {
return
(lbc == UTF8PROC_BOUNDCLASS_START) ? true : // GB1
(lbc == UTF8PROC_BOUNDCLASS_CR && // GB3
tbc == UTF8PROC_BOUNDCLASS_LF) ? false : // ---
(lbc >= UTF8PROC_BOUNDCLASS_CR && lbc <= UTF8PROC_BOUNDCLASS_CONTROL) ? true : // GB4
(tbc >= UTF8PROC_BOUNDCLASS_CR && tbc <= UTF8PROC_BOUNDCLASS_CONTROL) ? true : // GB5
(lbc == UTF8PROC_BOUNDCLASS_L && // GB6
(tbc == UTF8PROC_BOUNDCLASS_L || // ---
tbc == UTF8PROC_BOUNDCLASS_V || // ---
tbc == UTF8PROC_BOUNDCLASS_LV || // ---
tbc == UTF8PROC_BOUNDCLASS_LVT)) ? false : // ---
((lbc == UTF8PROC_BOUNDCLASS_LV || // GB7
lbc == UTF8PROC_BOUNDCLASS_V) && // ---
(tbc == UTF8PROC_BOUNDCLASS_V || // ---
tbc == UTF8PROC_BOUNDCLASS_T)) ? false : // ---
((lbc == UTF8PROC_BOUNDCLASS_LVT || // GB8
lbc == UTF8PROC_BOUNDCLASS_T) && // ---
tbc == UTF8PROC_BOUNDCLASS_T) ? false : // ---
(tbc == UTF8PROC_BOUNDCLASS_EXTEND || // GB9
tbc == UTF8PROC_BOUNDCLASS_ZWJ || // ---
tbc == UTF8PROC_BOUNDCLASS_SPACINGMARK || // GB9a
lbc == UTF8PROC_BOUNDCLASS_PREPEND) ? false : // GB9b
(lbc == UTF8PROC_BOUNDCLASS_E_ZWG && // GB11 (requires additional handling below)
tbc == UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC) ? false : // ----
(lbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR && // GB12/13 (requires additional handling below)
tbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR) ? false : // ----
true; // GB999
}
static utf8proc_bool grapheme_break_extended(int lbc, int tbc, utf8proc_int32_t *state)
{
if (state) {
int lbc_override;
if (*state == UTF8PROC_BOUNDCLASS_START)
*state = lbc_override = lbc;
else
lbc_override = *state;
utf8proc_bool break_permitted = grapheme_break_simple(lbc_override, tbc);
// Special support for GB 12/13 made possible by GB999. After two RI
// class codepoints we want to force a break. Do this by resetting the
// second RI's bound class to UTF8PROC_BOUNDCLASS_OTHER, to force a break
// after that character according to GB999 (unless of course such a break is
// forbidden by a different rule such as GB9).
if (*state == tbc && tbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR)
*state = UTF8PROC_BOUNDCLASS_OTHER;
// Special support for GB11 (emoji extend* zwj / emoji)
else if (*state == UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC) {
if (tbc == UTF8PROC_BOUNDCLASS_EXTEND) // fold EXTEND codepoints into emoji
*state = UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC;
else if (tbc == UTF8PROC_BOUNDCLASS_ZWJ)
*state = UTF8PROC_BOUNDCLASS_E_ZWG; // state to record emoji+zwg combo
else
*state = tbc;
static utf8proc_bool grapheme_break_simple(int lbc, int tbc)
{
return (lbc == UTF8PROC_BOUNDCLASS_START) ? true : // GB1
(lbc == UTF8PROC_BOUNDCLASS_CR && // GB3
tbc == UTF8PROC_BOUNDCLASS_LF)
? false
: // ---
(lbc >= UTF8PROC_BOUNDCLASS_CR && lbc <= UTF8PROC_BOUNDCLASS_CONTROL) ? true
: // GB4
(tbc >= UTF8PROC_BOUNDCLASS_CR && tbc <= UTF8PROC_BOUNDCLASS_CONTROL) ? true
: // GB5
(lbc == UTF8PROC_BOUNDCLASS_L && // GB6
(tbc == UTF8PROC_BOUNDCLASS_L || // ---
tbc == UTF8PROC_BOUNDCLASS_V || // ---
tbc == UTF8PROC_BOUNDCLASS_LV || // ---
tbc == UTF8PROC_BOUNDCLASS_LVT))
? false
: // ---
((lbc == UTF8PROC_BOUNDCLASS_LV || // GB7
lbc == UTF8PROC_BOUNDCLASS_V) && // ---
(tbc == UTF8PROC_BOUNDCLASS_V || // ---
tbc == UTF8PROC_BOUNDCLASS_T))
? false
: // ---
((lbc == UTF8PROC_BOUNDCLASS_LVT || // GB8
lbc == UTF8PROC_BOUNDCLASS_T) && // ---
tbc == UTF8PROC_BOUNDCLASS_T)
? false
: // ---
(tbc == UTF8PROC_BOUNDCLASS_EXTEND || // GB9
tbc == UTF8PROC_BOUNDCLASS_ZWJ || // ---
tbc == UTF8PROC_BOUNDCLASS_SPACINGMARK || // GB9a
lbc == UTF8PROC_BOUNDCLASS_PREPEND)
? false
: // GB9b
(lbc == UTF8PROC_BOUNDCLASS_E_ZWG && // GB11 (requires additional handling below)
tbc == UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC)
? false
: // ----
(lbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR && // GB12/13 (requires additional
// handling below)
tbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR)
? false
: // ----
true; // GB999
}
static utf8proc_bool grapheme_break_extended(int lbc, int tbc, utf8proc_int32_t* state)
{
if(state)
{
int lbc_override;
if(*state == UTF8PROC_BOUNDCLASS_START)
*state = lbc_override = lbc;
else
lbc_override = *state;
utf8proc_bool break_permitted = grapheme_break_simple(lbc_override, tbc);
// Special support for GB 12/13 made possible by GB999. After two RI
// class codepoints we want to force a break. Do this by resetting the
// second RI's bound class to UTF8PROC_BOUNDCLASS_OTHER, to force a break
// after that character according to GB999 (unless of course such a break is
// forbidden by a different rule such as GB9).
if(*state == tbc && tbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR)
*state = UTF8PROC_BOUNDCLASS_OTHER;
// Special support for GB11 (emoji extend* zwj / emoji)
else if(*state == UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC)
{
if(tbc == UTF8PROC_BOUNDCLASS_EXTEND) // fold EXTEND codepoints into emoji
*state = UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC;
else if(tbc == UTF8PROC_BOUNDCLASS_ZWJ)
*state = UTF8PROC_BOUNDCLASS_E_ZWG; // state to record emoji+zwg combo
else
*state = tbc;
}
else
*state = tbc;
return break_permitted;
}
else
*state = tbc;
return break_permitted;
}
else
return grapheme_break_simple(lbc, tbc);
return grapheme_break_simple(lbc, tbc);
}
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break_stateful(
utf8proc_int32_t c1, utf8proc_int32_t c2, utf8proc_int32_t *state) {
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break_stateful(utf8proc_int32_t c1,
utf8proc_int32_t c2,
utf8proc_int32_t* state)
{
return grapheme_break_extended(utf8proc_get_property(c1)->boundclass,
utf8proc_get_property(c2)->boundclass,
state);
return grapheme_break_extended(
utf8proc_get_property(c1)->boundclass, utf8proc_get_property(c2)->boundclass, state);
}
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(
utf8proc_int32_t c1, utf8proc_int32_t c2) {
return utf8proc_grapheme_break_stateful(c1, c2, NULL);
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(utf8proc_int32_t c1, utf8proc_int32_t c2)
{
return utf8proc_grapheme_break_stateful(c1, c2, NULL);
}
static utf8proc_int32_t seqindex_decode_entry(const utf8proc_uint16_t **entry)
static utf8proc_int32_t seqindex_decode_entry(const utf8proc_uint16_t** entry)
{
utf8proc_int32_t entry_cp = **entry;
if ((entry_cp & 0xF800) == 0xD800) {
*entry = *entry + 1;
entry_cp = ((entry_cp & 0x03FF) << 10) | (**entry & 0x03FF);
entry_cp += 0x10000;
}
return entry_cp;
utf8proc_int32_t entry_cp = **entry;
if((entry_cp & 0xF800) == 0xD800)
{
*entry = *entry + 1;
entry_cp = ((entry_cp & 0x03FF) << 10) | (**entry & 0x03FF);
entry_cp += 0x10000;
}
return entry_cp;
}
static utf8proc_int32_t seqindex_decode_index(const utf8proc_uint32_t seqindex)
{
const utf8proc_uint16_t *entry = &utf8proc_sequences[seqindex];
return seqindex_decode_entry(&entry);
const utf8proc_uint16_t* entry = &utf8proc_sequences[seqindex];
return seqindex_decode_entry(&entry);
}
static utf8proc_ssize_t seqindex_write_char_decomposed(utf8proc_uint16_t seqindex, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
utf8proc_ssize_t written = 0;
const utf8proc_uint16_t *entry = &utf8proc_sequences[seqindex & 0x3FFF];
int len = seqindex >> 14;
if (len >= 3) {
len = *entry;
entry++;
}
for (; len >= 0; entry++, len--) {
utf8proc_int32_t entry_cp = seqindex_decode_entry(&entry);
written += utf8proc_decompose_char(entry_cp, dst+written,
(bufsize > written) ? (bufsize - written) : 0, options,
last_boundclass);
if (written < 0) return UTF8PROC_ERROR_OVERFLOW;
}
return written;
static utf8proc_ssize_t seqindex_write_char_decomposed(utf8proc_uint16_t seqindex,
utf8proc_int32_t* dst,
utf8proc_ssize_t bufsize,
utf8proc_option_t options,
int* last_boundclass)
{
utf8proc_ssize_t written = 0;
const utf8proc_uint16_t* entry = &utf8proc_sequences[seqindex & 0x3FFF];
int len = seqindex >> 14;
if(len >= 3)
{
len = *entry;
entry++;
}
for(; len >= 0; entry++, len--)
{
utf8proc_int32_t entry_cp = seqindex_decode_entry(&entry);
written += utf8proc_decompose_char(entry_cp,
dst + written,
(bufsize > written) ? (bufsize - written) : 0,
options,
last_boundclass);
if(written < 0)
return UTF8PROC_ERROR_OVERFLOW;
}
return written;
}
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_tolower(utf8proc_int32_t c)
{
utf8proc_int32_t cl = utf8proc_get_property(c)->lowercase_seqindex;
return cl != UINT16_MAX ? seqindex_decode_index((utf8proc_uint32_t)cl) : c;
utf8proc_int32_t cl = utf8proc_get_property(c)->lowercase_seqindex;
return cl != UINT16_MAX ? seqindex_decode_index((utf8proc_uint32_t)cl) : c;
}
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c)
{
utf8proc_int32_t cu = utf8proc_get_property(c)->uppercase_seqindex;
return cu != UINT16_MAX ? seqindex_decode_index((utf8proc_uint32_t)cu) : c;
utf8proc_int32_t cu = utf8proc_get_property(c)->uppercase_seqindex;
return cu != UINT16_MAX ? seqindex_decode_index((utf8proc_uint32_t)cu) : c;
}
UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_totitle(utf8proc_int32_t c)
{
utf8proc_int32_t cu = utf8proc_get_property(c)->titlecase_seqindex;
return cu != UINT16_MAX ? seqindex_decode_index((utf8proc_uint32_t)cu) : c;
utf8proc_int32_t cu = utf8proc_get_property(c)->titlecase_seqindex;
return cu != UINT16_MAX ? seqindex_decode_index((utf8proc_uint32_t)cu) : c;
}
UTF8PROC_DLLEXPORT int utf8proc_islower(utf8proc_int32_t c)
{
const utf8proc_property_t *p = utf8proc_get_property(c);
return p->lowercase_seqindex != p->uppercase_seqindex && p->lowercase_seqindex == UINT16_MAX;
const utf8proc_property_t* p = utf8proc_get_property(c);
return p->lowercase_seqindex != p->uppercase_seqindex && p->lowercase_seqindex == UINT16_MAX;
}
UTF8PROC_DLLEXPORT int utf8proc_isupper(utf8proc_int32_t c)
{
const utf8proc_property_t *p = utf8proc_get_property(c);
return p->lowercase_seqindex != p->uppercase_seqindex && p->uppercase_seqindex == UINT16_MAX && p->category != UTF8PROC_CATEGORY_LT;
const utf8proc_property_t* p = utf8proc_get_property(c);
return p->lowercase_seqindex != p->uppercase_seqindex && p->uppercase_seqindex == UINT16_MAX &&
p->category != UTF8PROC_CATEGORY_LT;
}
/* return a character width analogous to wcwidth (except portable and
hopefully less buggy than most system wcwidth functions). */
UTF8PROC_DLLEXPORT int utf8proc_charwidth(utf8proc_int32_t c) {
return utf8proc_get_property(c)->charwidth;
UTF8PROC_DLLEXPORT int utf8proc_charwidth(utf8proc_int32_t c)
{
return utf8proc_get_property(c)->charwidth;
}
UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t c) {
return (utf8proc_category_t) utf8proc_get_property(c)->category;
UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t c)
{
return (utf8proc_category_t)utf8proc_get_property(c)->category;
}
UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t c) {
static const char s[][3] = {"Cn","Lu","Ll","Lt","Lm","Lo","Mn","Mc","Me","Nd","Nl","No","Pc","Pd","Ps","Pe","Pi","Pf","Po","Sm","Sc","Sk","So","Zs","Zl","Zp","Cc","Cf","Cs","Co"};
return s[utf8proc_category(c)];
UTF8PROC_DLLEXPORT const char* utf8proc_category_string(utf8proc_int32_t c)
{
static const char s[][3] = {"Cn", "Lu", "Ll", "Lt", "Lm", "Lo", "Mn", "Mc", "Me", "Nd",
"Nl", "No", "Pc", "Pd", "Ps", "Pe", "Pi", "Pf", "Po", "Sm",
"Sc", "Sk", "So", "Zs", "Zl", "Zp", "Cc", "Cf", "Cs", "Co"};
return s[utf8proc_category(c)];
}
#define utf8proc_decompose_lump(replacement_uc) \
return utf8proc_decompose_char((replacement_uc), dst, bufsize, \
options & ~(unsigned int)UTF8PROC_LUMP, last_boundclass)
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(utf8proc_int32_t uc, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
const utf8proc_property_t *property;
utf8proc_propval_t category;
utf8proc_int32_t hangul_sindex;
if (uc < 0 || uc >= 0x110000) return UTF8PROC_ERROR_NOTASSIGNED;
property = unsafe_get_property(uc);
category = property->category;
hangul_sindex = uc - UTF8PROC_HANGUL_SBASE;
if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) {
if (hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT) {
utf8proc_int32_t hangul_tindex;
if (bufsize >= 1) {
dst[0] = UTF8PROC_HANGUL_LBASE +
hangul_sindex / UTF8PROC_HANGUL_NCOUNT;
if (bufsize >= 2) dst[1] = UTF8PROC_HANGUL_VBASE +
(hangul_sindex % UTF8PROC_HANGUL_NCOUNT) / UTF8PROC_HANGUL_TCOUNT;
}
hangul_tindex = hangul_sindex % UTF8PROC_HANGUL_TCOUNT;
if (!hangul_tindex) return 2;
if (bufsize >= 3) dst[2] = UTF8PROC_HANGUL_TBASE + hangul_tindex;
return 3;
}
}
if (options & UTF8PROC_REJECTNA) {
if (!category) return UTF8PROC_ERROR_NOTASSIGNED;
}
if (options & UTF8PROC_IGNORE) {
if (property->ignorable) return 0;
}
if (options & UTF8PROC_STRIPNA) {
if (!category) return 0;
}
if (options & UTF8PROC_LUMP) {
if (category == UTF8PROC_CATEGORY_ZS) utf8proc_decompose_lump(0x0020);
if (uc == 0x2018 || uc == 0x2019 || uc == 0x02BC || uc == 0x02C8)
utf8proc_decompose_lump(0x0027);
if (category == UTF8PROC_CATEGORY_PD || uc == 0x2212)
utf8proc_decompose_lump(0x002D);
if (uc == 0x2044 || uc == 0x2215) utf8proc_decompose_lump(0x002F);
if (uc == 0x2236) utf8proc_decompose_lump(0x003A);
if (uc == 0x2039 || uc == 0x2329 || uc == 0x3008)
utf8proc_decompose_lump(0x003C);
if (uc == 0x203A || uc == 0x232A || uc == 0x3009)
utf8proc_decompose_lump(0x003E);
if (uc == 0x2216) utf8proc_decompose_lump(0x005C);
if (uc == 0x02C4 || uc == 0x02C6 || uc == 0x2038 || uc == 0x2303)
utf8proc_decompose_lump(0x005E);
if (category == UTF8PROC_CATEGORY_PC || uc == 0x02CD)
utf8proc_decompose_lump(0x005F);
if (uc == 0x02CB) utf8proc_decompose_lump(0x0060);
if (uc == 0x2223) utf8proc_decompose_lump(0x007C);
if (uc == 0x223C) utf8proc_decompose_lump(0x007E);
if ((options & UTF8PROC_NLF2LS) && (options & UTF8PROC_NLF2PS)) {
if (category == UTF8PROC_CATEGORY_ZL ||
category == UTF8PROC_CATEGORY_ZP)
utf8proc_decompose_lump(0x000A);
}
}
if (options & UTF8PROC_STRIPMARK) {
if (category == UTF8PROC_CATEGORY_MN ||
category == UTF8PROC_CATEGORY_MC ||
category == UTF8PROC_CATEGORY_ME) return 0;
}
if (options & UTF8PROC_CASEFOLD) {
if (property->casefold_seqindex != UINT16_MAX) {
return seqindex_write_char_decomposed(property->casefold_seqindex, dst, bufsize, options, last_boundclass);
}
}
if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) {
if (property->decomp_seqindex != UINT16_MAX &&
(!property->decomp_type || (options & UTF8PROC_COMPAT))) {
return seqindex_write_char_decomposed(property->decomp_seqindex, dst, bufsize, options, last_boundclass);
}
}
if (options & UTF8PROC_CHARBOUND) {
utf8proc_bool boundary;
int tbc = property->boundclass;
boundary = grapheme_break_extended(*last_boundclass, tbc, last_boundclass);
if (boundary) {
if (bufsize >= 1) dst[0] = -1; /* sentinel value for grapheme break */
if (bufsize >= 2) dst[1] = uc;
return 2;
}
}
if (bufsize >= 1) *dst = uc;
return 1;
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options
) {
return utf8proc_decompose_char( \
(replacement_uc), dst, bufsize, options & ~(unsigned int)UTF8PROC_LUMP, last_boundclass)
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(utf8proc_int32_t uc,
utf8proc_int32_t* dst,
utf8proc_ssize_t bufsize,
utf8proc_option_t options,
int* last_boundclass)
{
const utf8proc_property_t* property;
utf8proc_propval_t category;
utf8proc_int32_t hangul_sindex;
if(uc < 0 || uc >= 0x110000)
return UTF8PROC_ERROR_NOTASSIGNED;
property = unsafe_get_property(uc);
category = property->category;
hangul_sindex = uc - UTF8PROC_HANGUL_SBASE;
if(options & (UTF8PROC_COMPOSE | UTF8PROC_DECOMPOSE))
{
if(hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT)
{
utf8proc_int32_t hangul_tindex;
if(bufsize >= 1)
{
dst[0] = UTF8PROC_HANGUL_LBASE + hangul_sindex / UTF8PROC_HANGUL_NCOUNT;
if(bufsize >= 2)
dst[1] = UTF8PROC_HANGUL_VBASE +
(hangul_sindex % UTF8PROC_HANGUL_NCOUNT) / UTF8PROC_HANGUL_TCOUNT;
}
hangul_tindex = hangul_sindex % UTF8PROC_HANGUL_TCOUNT;
if(!hangul_tindex)
return 2;
if(bufsize >= 3)
dst[2] = UTF8PROC_HANGUL_TBASE + hangul_tindex;
return 3;
}
}
if(options & UTF8PROC_REJECTNA)
{
if(!category)
return UTF8PROC_ERROR_NOTASSIGNED;
}
if(options & UTF8PROC_IGNORE)
{
if(property->ignorable)
return 0;
}
if(options & UTF8PROC_STRIPNA)
{
if(!category)
return 0;
}
if(options & UTF8PROC_LUMP)
{
if(category == UTF8PROC_CATEGORY_ZS)
utf8proc_decompose_lump(0x0020);
if(uc == 0x2018 || uc == 0x2019 || uc == 0x02BC || uc == 0x02C8)
utf8proc_decompose_lump(0x0027);
if(category == UTF8PROC_CATEGORY_PD || uc == 0x2212)
utf8proc_decompose_lump(0x002D);
if(uc == 0x2044 || uc == 0x2215)
utf8proc_decompose_lump(0x002F);
if(uc == 0x2236)
utf8proc_decompose_lump(0x003A);
if(uc == 0x2039 || uc == 0x2329 || uc == 0x3008)
utf8proc_decompose_lump(0x003C);
if(uc == 0x203A || uc == 0x232A || uc == 0x3009)
utf8proc_decompose_lump(0x003E);
if(uc == 0x2216)
utf8proc_decompose_lump(0x005C);
if(uc == 0x02C4 || uc == 0x02C6 || uc == 0x2038 || uc == 0x2303)
utf8proc_decompose_lump(0x005E);
if(category == UTF8PROC_CATEGORY_PC || uc == 0x02CD)
utf8proc_decompose_lump(0x005F);
if(uc == 0x02CB)
utf8proc_decompose_lump(0x0060);
if(uc == 0x2223)
utf8proc_decompose_lump(0x007C);
if(uc == 0x223C)
utf8proc_decompose_lump(0x007E);
if((options & UTF8PROC_NLF2LS) && (options & UTF8PROC_NLF2PS))
{
if(category == UTF8PROC_CATEGORY_ZL || category == UTF8PROC_CATEGORY_ZP)
utf8proc_decompose_lump(0x000A);
}
}
if(options & UTF8PROC_STRIPMARK)
{
if(category == UTF8PROC_CATEGORY_MN || category == UTF8PROC_CATEGORY_MC ||
category == UTF8PROC_CATEGORY_ME)
return 0;
}
if(options & UTF8PROC_CASEFOLD)
{
if(property->casefold_seqindex != UINT16_MAX)
{
return seqindex_write_char_decomposed(
property->casefold_seqindex, dst, bufsize, options, last_boundclass);
}
}
if(options & (UTF8PROC_COMPOSE | UTF8PROC_DECOMPOSE))
{
if(property->decomp_seqindex != UINT16_MAX &&
(!property->decomp_type || (options & UTF8PROC_COMPAT)))
{
return seqindex_write_char_decomposed(
property->decomp_seqindex, dst, bufsize, options, last_boundclass);
}
}
if(options & UTF8PROC_CHARBOUND)
{
utf8proc_bool boundary;
int tbc = property->boundclass;
boundary = grapheme_break_extended(*last_boundclass, tbc, last_boundclass);
if(boundary)
{
if(bufsize >= 1)
dst[0] = -1; /* sentinel value for grapheme break */
if(bufsize >= 2)
dst[1] = uc;
return 2;
}
}
if(bufsize >= 1)
*dst = uc;
return 1;
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(const utf8proc_uint8_t* str,
utf8proc_ssize_t strlen,
utf8proc_int32_t* buffer,
utf8proc_ssize_t bufsize,
utf8proc_option_t options)
{
return utf8proc_decompose_custom(str, strlen, buffer, bufsize, options, NULL, NULL);
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_custom(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options,
utf8proc_custom_func custom_func, void *custom_data
) {
/* strlen will be ignored, if UTF8PROC_NULLTERM is set in options */
utf8proc_ssize_t wpos = 0;
if ((options & UTF8PROC_COMPOSE) && (options & UTF8PROC_DECOMPOSE))
return UTF8PROC_ERROR_INVALIDOPTS;
if ((options & UTF8PROC_STRIPMARK) &&
!(options & UTF8PROC_COMPOSE) && !(options & UTF8PROC_DECOMPOSE))
return UTF8PROC_ERROR_INVALIDOPTS;
{
utf8proc_int32_t uc;
utf8proc_ssize_t rpos = 0;
utf8proc_ssize_t decomp_result;
int boundclass = UTF8PROC_BOUNDCLASS_START;
while (1) {
if (options & UTF8PROC_NULLTERM) {
rpos += utf8proc_iterate(str + rpos, -1, &uc);
/* checking of return value is not necessary,
as 'uc' is < 0 in case of error */
if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
if (rpos < 0) return UTF8PROC_ERROR_OVERFLOW;
if (uc == 0) break;
} else {
if (rpos >= strlen) break;
rpos += utf8proc_iterate(str + rpos, strlen - rpos, &uc);
if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
}
if (custom_func != NULL) {
uc = custom_func(uc, custom_data); /* user-specified custom mapping */
}
decomp_result = utf8proc_decompose_char(
uc, buffer + wpos, (bufsize > wpos) ? (bufsize - wpos) : 0, options,
&boundclass
);
if (decomp_result < 0) return decomp_result;
wpos += decomp_result;
/* prohibiting integer overflows due to too long strings: */
if (wpos < 0 ||
wpos > (utf8proc_ssize_t)(SSIZE_MAX/sizeof(utf8proc_int32_t)/2))
return UTF8PROC_ERROR_OVERFLOW;
}
}
if ((options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) && bufsize >= wpos) {
utf8proc_ssize_t pos = 0;
while (pos < wpos-1) {
utf8proc_int32_t uc1, uc2;
const utf8proc_property_t *property1, *property2;
uc1 = buffer[pos];
uc2 = buffer[pos+1];
property1 = unsafe_get_property(uc1);
property2 = unsafe_get_property(uc2);
if (property1->combining_class > property2->combining_class &&
property2->combining_class > 0) {
buffer[pos] = uc2;
buffer[pos+1] = uc1;
if (pos > 0) pos--; else pos++;
} else {
pos++;
}
}
}
return wpos;
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_normalize_utf32(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options) {
/* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored */
if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) {
utf8proc_ssize_t rpos;
utf8proc_ssize_t wpos = 0;
utf8proc_int32_t uc;
for (rpos = 0; rpos < length; rpos++) {
uc = buffer[rpos];
if (uc == 0x000D && rpos < length-1 && buffer[rpos+1] == 0x000A) rpos++;
if (uc == 0x000A || uc == 0x000D || uc == 0x0085 ||
((options & UTF8PROC_STRIPCC) && (uc == 0x000B || uc == 0x000C))) {
if (options & UTF8PROC_NLF2LS) {
if (options & UTF8PROC_NLF2PS) {
buffer[wpos++] = 0x000A;
} else {
buffer[wpos++] = 0x2028;
}
} else {
if (options & UTF8PROC_NLF2PS) {
buffer[wpos++] = 0x2029;
} else {
buffer[wpos++] = 0x0020;
}
}
} else if ((options & UTF8PROC_STRIPCC) &&
(uc < 0x0020 || (uc >= 0x007F && uc < 0x00A0))) {
if (uc == 0x0009) buffer[wpos++] = 0x0020;
} else {
buffer[wpos++] = uc;
}
}
length = wpos;
}
if (options & UTF8PROC_COMPOSE) {
utf8proc_int32_t *starter = NULL;
utf8proc_int32_t current_char;
const utf8proc_property_t *starter_property = NULL, *current_property;
utf8proc_propval_t max_combining_class = -1;
utf8proc_ssize_t rpos;
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_custom(const utf8proc_uint8_t* str,
utf8proc_ssize_t strlen,
utf8proc_int32_t* buffer,
utf8proc_ssize_t bufsize,
utf8proc_option_t options,
utf8proc_custom_func custom_func,
void* custom_data)
{
/* strlen will be ignored, if UTF8PROC_NULLTERM is set in options */
utf8proc_ssize_t wpos = 0;
utf8proc_int32_t composition;
for (rpos = 0; rpos < length; rpos++) {
current_char = buffer[rpos];
current_property = unsafe_get_property(current_char);
if (starter && current_property->combining_class > max_combining_class) {
/* combination perhaps possible */
utf8proc_int32_t hangul_lindex;
utf8proc_int32_t hangul_sindex;
hangul_lindex = *starter - UTF8PROC_HANGUL_LBASE;
if (hangul_lindex >= 0 && hangul_lindex < UTF8PROC_HANGUL_LCOUNT) {
utf8proc_int32_t hangul_vindex;
hangul_vindex = current_char - UTF8PROC_HANGUL_VBASE;
if (hangul_vindex >= 0 && hangul_vindex < UTF8PROC_HANGUL_VCOUNT) {
*starter = UTF8PROC_HANGUL_SBASE +
(hangul_lindex * UTF8PROC_HANGUL_VCOUNT + hangul_vindex) *
UTF8PROC_HANGUL_TCOUNT;
starter_property = NULL;
continue;
}
}
hangul_sindex = *starter - UTF8PROC_HANGUL_SBASE;
if (hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT &&
(hangul_sindex % UTF8PROC_HANGUL_TCOUNT) == 0) {
utf8proc_int32_t hangul_tindex;
hangul_tindex = current_char - UTF8PROC_HANGUL_TBASE;
if (hangul_tindex >= 0 && hangul_tindex < UTF8PROC_HANGUL_TCOUNT) {
*starter += hangul_tindex;
starter_property = NULL;
continue;
}
if((options & UTF8PROC_COMPOSE) && (options & UTF8PROC_DECOMPOSE))
return UTF8PROC_ERROR_INVALIDOPTS;
if((options & UTF8PROC_STRIPMARK) && !(options & UTF8PROC_COMPOSE) &&
!(options & UTF8PROC_DECOMPOSE))
return UTF8PROC_ERROR_INVALIDOPTS;
{
utf8proc_int32_t uc;
utf8proc_ssize_t rpos = 0;
utf8proc_ssize_t decomp_result;
int boundclass = UTF8PROC_BOUNDCLASS_START;
while(1)
{
if(options & UTF8PROC_NULLTERM)
{
rpos += utf8proc_iterate(str + rpos, -1, &uc);
/* checking of return value is not necessary,
as 'uc' is < 0 in case of error */
if(uc < 0)
return UTF8PROC_ERROR_INVALIDUTF8;
if(rpos < 0)
return UTF8PROC_ERROR_OVERFLOW;
if(uc == 0)
break;
}
else
{
if(rpos >= strlen)
break;
rpos += utf8proc_iterate(str + rpos, strlen - rpos, &uc);
if(uc < 0)
return UTF8PROC_ERROR_INVALIDUTF8;
}
if(custom_func != NULL)
{
uc = custom_func(uc, custom_data); /* user-specified custom mapping */
}
decomp_result = utf8proc_decompose_char(
uc, buffer + wpos, (bufsize > wpos) ? (bufsize - wpos) : 0, options, &boundclass);
if(decomp_result < 0)
return decomp_result;
wpos += decomp_result;
/* prohibiting integer overflows due to too long strings: */
if(wpos < 0 || wpos > (utf8proc_ssize_t)(SSIZE_MAX / sizeof(utf8proc_int32_t) / 2))
return UTF8PROC_ERROR_OVERFLOW;
}
if (!starter_property) {
starter_property = unsafe_get_property(*starter);
}
if((options & (UTF8PROC_COMPOSE | UTF8PROC_DECOMPOSE)) && bufsize >= wpos)
{
utf8proc_ssize_t pos = 0;
while(pos < wpos - 1)
{
utf8proc_int32_t uc1, uc2;
const utf8proc_property_t *property1, *property2;
uc1 = buffer[pos];
uc2 = buffer[pos + 1];
property1 = unsafe_get_property(uc1);
property2 = unsafe_get_property(uc2);
if(property1->combining_class > property2->combining_class &&
property2->combining_class > 0)
{
buffer[pos] = uc2;
buffer[pos + 1] = uc1;
if(pos > 0)
pos--;
else
pos++;
}
else
{
pos++;
}
}
if (starter_property->comb_index < 0x8000 &&
current_property->comb_index != UINT16_MAX &&
current_property->comb_index >= 0x8000) {
int sidx = starter_property->comb_index;
int idx = current_property->comb_index & 0x3FFF;
if (idx >= utf8proc_combinations[sidx] && idx <= utf8proc_combinations[sidx + 1] ) {
idx += sidx + 2 - utf8proc_combinations[sidx];
if (current_property->comb_index & 0x4000) {
composition = (utf8proc_combinations[idx] << 16) | utf8proc_combinations[idx+1];
} else
composition = utf8proc_combinations[idx];
if (composition > 0 && (!(options & UTF8PROC_STABLE) ||
!(unsafe_get_property(composition)->comp_exclusion))) {
*starter = composition;
starter_property = NULL;
continue;
}
return wpos;
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_normalize_utf32(utf8proc_int32_t* buffer,
utf8proc_ssize_t length,
utf8proc_option_t options)
{
/* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored */
if(options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC))
{
utf8proc_ssize_t rpos;
utf8proc_ssize_t wpos = 0;
utf8proc_int32_t uc;
for(rpos = 0; rpos < length; rpos++)
{
uc = buffer[rpos];
if(uc == 0x000D && rpos < length - 1 && buffer[rpos + 1] == 0x000A)
rpos++;
if(uc == 0x000A || uc == 0x000D || uc == 0x0085 ||
((options & UTF8PROC_STRIPCC) && (uc == 0x000B || uc == 0x000C)))
{
if(options & UTF8PROC_NLF2LS)
{
if(options & UTF8PROC_NLF2PS)
{
buffer[wpos++] = 0x000A;
}
else
{
buffer[wpos++] = 0x2028;
}
}
else
{
if(options & UTF8PROC_NLF2PS)
{
buffer[wpos++] = 0x2029;
}
else
{
buffer[wpos++] = 0x0020;
}
}
}
else if((options & UTF8PROC_STRIPCC) && (uc < 0x0020 || (uc >= 0x007F && uc < 0x00A0)))
{
if(uc == 0x0009)
buffer[wpos++] = 0x0020;
}
else
{
buffer[wpos++] = uc;
}
}
}
}
buffer[wpos] = current_char;
if (current_property->combining_class) {
if (current_property->combining_class > max_combining_class) {
max_combining_class = current_property->combining_class;
length = wpos;
}
if(options & UTF8PROC_COMPOSE)
{
utf8proc_int32_t* starter = NULL;
utf8proc_int32_t current_char;
const utf8proc_property_t *starter_property = NULL, *current_property;
utf8proc_propval_t max_combining_class = -1;
utf8proc_ssize_t rpos;
utf8proc_ssize_t wpos = 0;
utf8proc_int32_t composition;
for(rpos = 0; rpos < length; rpos++)
{
current_char = buffer[rpos];
current_property = unsafe_get_property(current_char);
if(starter && current_property->combining_class > max_combining_class)
{
/* combination perhaps possible */
utf8proc_int32_t hangul_lindex;
utf8proc_int32_t hangul_sindex;
hangul_lindex = *starter - UTF8PROC_HANGUL_LBASE;
if(hangul_lindex >= 0 && hangul_lindex < UTF8PROC_HANGUL_LCOUNT)
{
utf8proc_int32_t hangul_vindex;
hangul_vindex = current_char - UTF8PROC_HANGUL_VBASE;
if(hangul_vindex >= 0 && hangul_vindex < UTF8PROC_HANGUL_VCOUNT)
{
*starter = UTF8PROC_HANGUL_SBASE +
(hangul_lindex * UTF8PROC_HANGUL_VCOUNT + hangul_vindex) *
UTF8PROC_HANGUL_TCOUNT;
starter_property = NULL;
continue;
}
}
hangul_sindex = *starter - UTF8PROC_HANGUL_SBASE;
if(hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT &&
(hangul_sindex % UTF8PROC_HANGUL_TCOUNT) == 0)
{
utf8proc_int32_t hangul_tindex;
hangul_tindex = current_char - UTF8PROC_HANGUL_TBASE;
if(hangul_tindex >= 0 && hangul_tindex < UTF8PROC_HANGUL_TCOUNT)
{
*starter += hangul_tindex;
starter_property = NULL;
continue;
}
}
if(!starter_property)
{
starter_property = unsafe_get_property(*starter);
}
if(starter_property->comb_index < 0x8000 &&
current_property->comb_index != UINT16_MAX &&
current_property->comb_index >= 0x8000)
{
int sidx = starter_property->comb_index;
int idx = current_property->comb_index & 0x3FFF;
if(idx >= utf8proc_combinations[sidx] && idx <= utf8proc_combinations[sidx + 1])
{
idx += sidx + 2 - utf8proc_combinations[sidx];
if(current_property->comb_index & 0x4000)
{
composition =
(utf8proc_combinations[idx] << 16) | utf8proc_combinations[idx + 1];
}
else
composition = utf8proc_combinations[idx];
if(composition > 0 && (!(options & UTF8PROC_STABLE) ||
!(unsafe_get_property(composition)->comp_exclusion)))
{
*starter = composition;
starter_property = NULL;
continue;
}
}
}
}
buffer[wpos] = current_char;
if(current_property->combining_class)
{
if(current_property->combining_class > max_combining_class)
{
max_combining_class = current_property->combining_class;
}
}
else
{
starter = buffer + wpos;
starter_property = NULL;
max_combining_class = -1;
}
wpos++;
}
} else {
starter = buffer + wpos;
starter_property = NULL;
max_combining_class = -1;
}
wpos++;
}
length = wpos;
}
return length;
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options) {
/* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored
ASSERT: 'buffer' has one spare byte of free space at the end! */
length = utf8proc_normalize_utf32(buffer, length, options);
if (length < 0) return length;
{
utf8proc_ssize_t rpos, wpos = 0;
utf8proc_int32_t uc;
if (options & UTF8PROC_CHARBOUND) {
for (rpos = 0; rpos < length; rpos++) {
uc = buffer[rpos];
wpos += charbound_encode_char(uc, ((utf8proc_uint8_t *)buffer) + wpos);
length = wpos;
}
return length;
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t* buffer,
utf8proc_ssize_t length,
utf8proc_option_t options)
{
/* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored
ASSERT: 'buffer' has one spare byte of free space at the end! */
length = utf8proc_normalize_utf32(buffer, length, options);
if(length < 0)
return length;
{
utf8proc_ssize_t rpos, wpos = 0;
utf8proc_int32_t uc;
if(options & UTF8PROC_CHARBOUND)
{
for(rpos = 0; rpos < length; rpos++)
{
uc = buffer[rpos];
wpos += charbound_encode_char(uc, ((utf8proc_uint8_t*)buffer) + wpos);
}
}
} else {
for (rpos = 0; rpos < length; rpos++) {
uc = buffer[rpos];
wpos += utf8proc_encode_char(uc, ((utf8proc_uint8_t *)buffer) + wpos);
else
{
for(rpos = 0; rpos < length; rpos++)
{
uc = buffer[rpos];
wpos += utf8proc_encode_char(uc, ((utf8proc_uint8_t*)buffer) + wpos);
}
}
((utf8proc_uint8_t*)buffer)[wpos] = 0;
return wpos;
}
((utf8proc_uint8_t *)buffer)[wpos] = 0;
return wpos;
}
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options
) {
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(const utf8proc_uint8_t* str,
utf8proc_ssize_t strlen,
utf8proc_uint8_t** dstptr,
utf8proc_option_t options)
{
return utf8proc_map_custom(str, strlen, dstptr, options, NULL, NULL);
}
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map_custom(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options,
utf8proc_custom_func custom_func, void *custom_data
) {
utf8proc_int32_t *buffer;
utf8proc_ssize_t result;
*dstptr = NULL;
result = utf8proc_decompose_custom(str, strlen, NULL, 0, options, custom_func, custom_data);
if (result < 0) return result;
buffer = (utf8proc_int32_t *) malloc(((utf8proc_size_t)result) * sizeof(utf8proc_int32_t) + 1);
if (!buffer) return UTF8PROC_ERROR_NOMEM;
result = utf8proc_decompose_custom(str, strlen, buffer, result, options, custom_func, custom_data);
if (result < 0) {
free(buffer);
return result;
}
result = utf8proc_reencode(buffer, result, options);
if (result < 0) {
free(buffer);
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map_custom(const utf8proc_uint8_t* str,
utf8proc_ssize_t strlen,
utf8proc_uint8_t** dstptr,
utf8proc_option_t options,
utf8proc_custom_func custom_func,
void* custom_data)
{
utf8proc_int32_t* buffer;
utf8proc_ssize_t result;
*dstptr = NULL;
result = utf8proc_decompose_custom(str, strlen, NULL, 0, options, custom_func, custom_data);
if(result < 0)
return result;
buffer = (utf8proc_int32_t*)malloc(((utf8proc_size_t)result) * sizeof(utf8proc_int32_t) + 1);
if(!buffer)
return UTF8PROC_ERROR_NOMEM;
result =
utf8proc_decompose_custom(str, strlen, buffer, result, options, custom_func, custom_data);
if(result < 0)
{
free(buffer);
return result;
}
result = utf8proc_reencode(buffer, result, options);
if(result < 0)
{
free(buffer);
return result;
}
{
utf8proc_int32_t* newptr;
newptr = (utf8proc_int32_t*)realloc(buffer, (size_t)result + 1);
if(newptr)
buffer = newptr;
}
*dstptr = (utf8proc_uint8_t*)buffer;
return result;
}
{
utf8proc_int32_t *newptr;
newptr = (utf8proc_int32_t *) realloc(buffer, (size_t)result+1);
if (newptr) buffer = newptr;
}
*dstptr = (utf8proc_uint8_t *)buffer;
return result;
}
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFD(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_DECOMPOSE);
return retval;
UTF8PROC_DLLEXPORT utf8proc_uint8_t* utf8proc_NFD(const utf8proc_uint8_t* str)
{
utf8proc_uint8_t* retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | UTF8PROC_DECOMPOSE);
return retval;
}
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFC(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE);
return retval;
UTF8PROC_DLLEXPORT utf8proc_uint8_t* utf8proc_NFC(const utf8proc_uint8_t* str)
{
utf8proc_uint8_t* retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | UTF8PROC_COMPOSE);
return retval;
}
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKD(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT);
return retval;
UTF8PROC_DLLEXPORT utf8proc_uint8_t* utf8proc_NFKD(const utf8proc_uint8_t* str)
{
utf8proc_uint8_t* retval;
utf8proc_map(str,
0,
&retval,
UTF8PROC_NULLTERM | UTF8PROC_STABLE | UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT);
return retval;
}
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE | UTF8PROC_COMPAT);
return retval;
UTF8PROC_DLLEXPORT utf8proc_uint8_t* utf8proc_NFKC(const utf8proc_uint8_t* str)
{
utf8proc_uint8_t* retval;
utf8proc_map(
str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | UTF8PROC_COMPOSE | UTF8PROC_COMPAT);
return retval;
}
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC_Casefold(const utf8proc_uint8_t *str) {
utf8proc_uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE | UTF8PROC_COMPAT | UTF8PROC_CASEFOLD | UTF8PROC_IGNORE);
return retval;
UTF8PROC_DLLEXPORT utf8proc_uint8_t* utf8proc_NFKC_Casefold(const utf8proc_uint8_t* str)
{
utf8proc_uint8_t* retval;
utf8proc_map(str,
0,
&retval,
UTF8PROC_NULLTERM | UTF8PROC_STABLE | UTF8PROC_COMPOSE | UTF8PROC_COMPAT |
UTF8PROC_CASEFOLD | UTF8PROC_IGNORE);
return retval;
}
Src/Utility/utf8proc.h
View file @ 0f9dc829
/*
* Copyright (c) 2014-2021 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
* Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
* Copyright (c) 2014-2021 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P.
* Jones, and other contributors. Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
......@@ -21,7 +21,6 @@
* DEALINGS IN THE SOFTWARE.
*/
/**
* @mainpage
*
......@@ -37,15 +36,20 @@
* The features of utf8proc include:
*
* - Transformation of strings (@ref utf8proc_map) to:
* - decompose (@ref UTF8PROC_DECOMPOSE) or compose (@ref UTF8PROC_COMPOSE) Unicode combining characters (http://en.wikipedia.org/wiki/Combining_character)
* - decompose (@ref UTF8PROC_DECOMPOSE) or compose (@ref UTF8PROC_COMPOSE) Unicode combining
* characters (http://en.wikipedia.org/wiki/Combining_character)
* - canonicalize Unicode compatibility characters (@ref UTF8PROC_COMPAT)
* - strip "ignorable" (@ref UTF8PROC_IGNORE) characters, control characters (@ref UTF8PROC_STRIPCC), or combining characters such as accents (@ref UTF8PROC_STRIPMARK)
* - strip "ignorable" (@ref UTF8PROC_IGNORE) characters, control characters (@ref
* UTF8PROC_STRIPCC), or combining characters such as accents (@ref UTF8PROC_STRIPMARK)
* - case-folding (@ref UTF8PROC_CASEFOLD)
* - Unicode normalization: @ref utf8proc_NFD, @ref utf8proc_NFC, @ref utf8proc_NFKD, @ref utf8proc_NFKC
* - Unicode normalization: @ref utf8proc_NFD, @ref utf8proc_NFC, @ref utf8proc_NFKD, @ref
* utf8proc_NFKC
* - Detecting grapheme boundaries (@ref utf8proc_grapheme_break and @ref UTF8PROC_CHARBOUND)
* - Character-width computation: @ref utf8proc_charwidth
* - Classification of characters by Unicode category: @ref utf8proc_category and @ref utf8proc_category_string
* - Encode (@ref utf8proc_encode_char) and decode (@ref utf8proc_iterate) Unicode codepoints to/from UTF-8.
* - Classification of characters by Unicode category: @ref utf8proc_category and @ref
* utf8proc_category_string
* - Encode (@ref utf8proc_encode_char) and decode (@ref utf8proc_iterate) Unicode codepoints
* to/from UTF-8.
*/
/** @file */
......@@ -70,7 +74,8 @@
/** @{ */
/** The MAJOR version number (increased when backwards API compatibility is broken). */
#define UTF8PROC_VERSION_MAJOR 2
/** The MINOR version number (increased when new functionality is added in a backwards-compatible manner). */
/** The MINOR version number (increased when new functionality is added in a backwards-compatible
* manner). */
#define UTF8PROC_VERSION_MINOR 8
/** The PATCH version (increased for fixes that do not change the API). */
#define UTF8PROC_VERSION_PATCH 0
......@@ -86,28 +91,28 @@ typedef short utf8proc_int16_t;
typedef unsigned short utf8proc_uint16_t;
typedef int utf8proc_int32_t;
typedef unsigned int utf8proc_uint32_t;
# ifdef _WIN64
#ifdef _WIN64
typedef __int64 utf8proc_ssize_t;
typedef unsigned __int64 utf8proc_size_t;
# else
#else
typedef int utf8proc_ssize_t;
typedef unsigned int utf8proc_size_t;
# endif
# ifndef __cplusplus
#endif
#ifndef __cplusplus
// emulate C99 bool
typedef unsigned char utf8proc_bool;
# ifndef __bool_true_false_are_defined
# define false 0
# define true 1
# define __bool_true_false_are_defined 1
# endif
# else
#ifndef __bool_true_false_are_defined
#define false 0
#define true 1
#define __bool_true_false_are_defined 1
#endif
#else
typedef bool utf8proc_bool;
# endif
#endif
#else
# include <stddef.h>
# include <stdbool.h>
# include <inttypes.h>
#include <stddef.h>
#include <stdbool.h>
#include <inttypes.h>
typedef int8_t utf8proc_int8_t;
typedef uint8_t utf8proc_uint8_t;
typedef int16_t utf8proc_int16_t;
......@@ -121,19 +126,19 @@ typedef bool utf8proc_bool;
#include <limits.h>
#ifdef UTF8PROC_STATIC
# define UTF8PROC_DLLEXPORT
#define UTF8PROC_DLLEXPORT
#else
# ifdef _WIN32
# ifdef UTF8PROC_EXPORTS
# define UTF8PROC_DLLEXPORT __declspec(dllexport)
# else
# define UTF8PROC_DLLEXPORT __declspec(dllimport)
# endif
# elif __GNUC__ >= 4
# define UTF8PROC_DLLEXPORT __attribute__ ((visibility("default")))
# else
# define UTF8PROC_DLLEXPORT
# endif
#ifdef _WIN32
#ifdef UTF8PROC_EXPORTS
#define UTF8PROC_DLLEXPORT __declspec(dllexport)
#else
#define UTF8PROC_DLLEXPORT __declspec(dllimport)
#endif
#elif __GNUC__ >= 4
#define UTF8PROC_DLLEXPORT __attribute__((visibility("default")))
#else
#define UTF8PROC_DLLEXPORT
#endif
#endif
#ifdef __cplusplus
......@@ -143,72 +148,73 @@ extern "C" {
/**
* Option flags used by several functions in the library.
*/
typedef enum {
/** The given UTF-8 input is NULL terminated. */
UTF8PROC_NULLTERM = (1<<0),
/** Unicode Versioning Stability has to be respected. */
UTF8PROC_STABLE = (1<<1),
/** Compatibility decomposition (i.e. formatting information is lost). */
UTF8PROC_COMPAT = (1<<2),
/** Return a result with decomposed characters. */
UTF8PROC_COMPOSE = (1<<3),
/** Return a result with decomposed characters. */
UTF8PROC_DECOMPOSE = (1<<4),
/** Strip "default ignorable characters" such as SOFT-HYPHEN or ZERO-WIDTH-SPACE. */
UTF8PROC_IGNORE = (1<<5),
/** Return an error, if the input contains unassigned codepoints. */
UTF8PROC_REJECTNA = (1<<6),
/**
* Indicating that NLF-sequences (LF, CRLF, CR, NEL) are representing a
* line break, and should be converted to the codepoint for line
* separation (LS).
*/
UTF8PROC_NLF2LS = (1<<7),
/**
* Indicating that NLF-sequences are representing a paragraph break, and
* should be converted to the codepoint for paragraph separation
* (PS).
*/
UTF8PROC_NLF2PS = (1<<8),
/** Indicating that the meaning of NLF-sequences is unknown. */
UTF8PROC_NLF2LF = (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS),
/** Strips and/or convers control characters.
*
* NLF-sequences are transformed into space, except if one of the
* NLF2LS/PS/LF options is given. HorizontalTab (HT) and FormFeed (FF)
* are treated as a NLF-sequence in this case. All other control
* characters are simply removed.
*/
UTF8PROC_STRIPCC = (1<<9),
/**
* Performs unicode case folding, to be able to do a case-insensitive
* string comparison.
*/
UTF8PROC_CASEFOLD = (1<<10),
/**
* Inserts 0xFF bytes at the beginning of each sequence which is
* representing a single grapheme cluster (see UAX#29).
*/
UTF8PROC_CHARBOUND = (1<<11),
/** Lumps certain characters together.
*
* E.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-". See lump.md for details.
*
* If NLF2LF is set, this includes a transformation of paragraph and
* line separators to ASCII line-feed (LF).
*/
UTF8PROC_LUMP = (1<<12),
/** Strips all character markings.
*
* This includes non-spacing, spacing and enclosing (i.e. accents).
* @note This option works only with @ref UTF8PROC_COMPOSE or
* @ref UTF8PROC_DECOMPOSE
*/
UTF8PROC_STRIPMARK = (1<<13),
/**
* Strip unassigned codepoints.
*/
UTF8PROC_STRIPNA = (1<<14),
typedef enum
{
/** The given UTF-8 input is NULL terminated. */
UTF8PROC_NULLTERM = (1 << 0),
/** Unicode Versioning Stability has to be respected. */
UTF8PROC_STABLE = (1 << 1),
/** Compatibility decomposition (i.e. formatting information is lost). */
UTF8PROC_COMPAT = (1 << 2),
/** Return a result with decomposed characters. */
UTF8PROC_COMPOSE = (1 << 3),
/** Return a result with decomposed characters. */
UTF8PROC_DECOMPOSE = (1 << 4),
/** Strip "default ignorable characters" such as SOFT-HYPHEN or ZERO-WIDTH-SPACE. */
UTF8PROC_IGNORE = (1 << 5),
/** Return an error, if the input contains unassigned codepoints. */
UTF8PROC_REJECTNA = (1 << 6),
/**
* Indicating that NLF-sequences (LF, CRLF, CR, NEL) are representing a
* line break, and should be converted to the codepoint for line
* separation (LS).
*/
UTF8PROC_NLF2LS = (1 << 7),
/**
* Indicating that NLF-sequences are representing a paragraph break, and
* should be converted to the codepoint for paragraph separation
* (PS).
*/
UTF8PROC_NLF2PS = (1 << 8),
/** Indicating that the meaning of NLF-sequences is unknown. */
UTF8PROC_NLF2LF = (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS),
/** Strips and/or convers control characters.
*
* NLF-sequences are transformed into space, except if one of the
* NLF2LS/PS/LF options is given. HorizontalTab (HT) and FormFeed (FF)
* are treated as a NLF-sequence in this case. All other control
* characters are simply removed.
*/
UTF8PROC_STRIPCC = (1 << 9),
/**
* Performs unicode case folding, to be able to do a case-insensitive
* string comparison.
*/
UTF8PROC_CASEFOLD = (1 << 10),
/**
* Inserts 0xFF bytes at the beginning of each sequence which is
* representing a single grapheme cluster (see UAX#29).
*/
UTF8PROC_CHARBOUND = (1 << 11),
/** Lumps certain characters together.
*
* E.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-". See lump.md for details.
*
* If NLF2LF is set, this includes a transformation of paragraph and
* line separators to ASCII line-feed (LF).
*/
UTF8PROC_LUMP = (1 << 12),
/** Strips all character markings.
*
* This includes non-spacing, spacing and enclosing (i.e. accents).
* @note This option works only with @ref UTF8PROC_COMPOSE or
* @ref UTF8PROC_DECOMPOSE
*/
UTF8PROC_STRIPMARK = (1 << 13),
/**
* Strip unassigned codepoints.
*/
UTF8PROC_STRIPNA = (1 << 14),
} utf8proc_option_t;
/** @name Error codes
......@@ -233,159 +239,164 @@ typedef enum {
typedef utf8proc_int16_t utf8proc_propval_t;
/** Struct containing information about a codepoint. */
typedef struct utf8proc_property_struct {
/**
* Unicode category.
* @see utf8proc_category_t.
*/
utf8proc_propval_t category;
utf8proc_propval_t combining_class;
/**
* Bidirectional class.
* @see utf8proc_bidi_class_t.
*/
utf8proc_propval_t bidi_class;
/**
* @anchor Decomposition type.
* @see utf8proc_decomp_type_t.
*/
utf8proc_propval_t decomp_type;
utf8proc_uint16_t decomp_seqindex;
utf8proc_uint16_t casefold_seqindex;
utf8proc_uint16_t uppercase_seqindex;
utf8proc_uint16_t lowercase_seqindex;
utf8proc_uint16_t titlecase_seqindex;
utf8proc_uint16_t comb_index;
unsigned bidi_mirrored:1;
unsigned comp_exclusion:1;
/**
* Can this codepoint be ignored?
*
* Used by @ref utf8proc_decompose_char when @ref UTF8PROC_IGNORE is
* passed as an option.
*/
unsigned ignorable:1;
unsigned control_boundary:1;
/** The width of the codepoint. */
unsigned charwidth:2;
unsigned pad:2;
/**
* Boundclass.
* @see utf8proc_boundclass_t.
*/
unsigned boundclass:8;
typedef struct utf8proc_property_struct
{
/**
* Unicode category.
* @see utf8proc_category_t.
*/
utf8proc_propval_t category;
utf8proc_propval_t combining_class;
/**
* Bidirectional class.
* @see utf8proc_bidi_class_t.
*/
utf8proc_propval_t bidi_class;
/**
* @anchor Decomposition type.
* @see utf8proc_decomp_type_t.
*/
utf8proc_propval_t decomp_type;
utf8proc_uint16_t decomp_seqindex;
utf8proc_uint16_t casefold_seqindex;
utf8proc_uint16_t uppercase_seqindex;
utf8proc_uint16_t lowercase_seqindex;
utf8proc_uint16_t titlecase_seqindex;
utf8proc_uint16_t comb_index;
unsigned bidi_mirrored : 1;
unsigned comp_exclusion : 1;
/**
* Can this codepoint be ignored?
*
* Used by @ref utf8proc_decompose_char when @ref UTF8PROC_IGNORE is
* passed as an option.
*/
unsigned ignorable : 1;
unsigned control_boundary : 1;
/** The width of the codepoint. */
unsigned charwidth : 2;
unsigned pad : 2;
/**
* Boundclass.
* @see utf8proc_boundclass_t.
*/
unsigned boundclass : 8;
} utf8proc_property_t;
/** Unicode categories. */
typedef enum {
UTF8PROC_CATEGORY_CN = 0, /**< Other, not assigned */
UTF8PROC_CATEGORY_LU = 1, /**< Letter, uppercase */
UTF8PROC_CATEGORY_LL = 2, /**< Letter, lowercase */
UTF8PROC_CATEGORY_LT = 3, /**< Letter, titlecase */
UTF8PROC_CATEGORY_LM = 4, /**< Letter, modifier */
UTF8PROC_CATEGORY_LO = 5, /**< Letter, other */
UTF8PROC_CATEGORY_MN = 6, /**< Mark, nonspacing */
UTF8PROC_CATEGORY_MC = 7, /**< Mark, spacing combining */
UTF8PROC_CATEGORY_ME = 8, /**< Mark, enclosing */
UTF8PROC_CATEGORY_ND = 9, /**< Number, decimal digit */
UTF8PROC_CATEGORY_NL = 10, /**< Number, letter */
UTF8PROC_CATEGORY_NO = 11, /**< Number, other */
UTF8PROC_CATEGORY_PC = 12, /**< Punctuation, connector */
UTF8PROC_CATEGORY_PD = 13, /**< Punctuation, dash */
UTF8PROC_CATEGORY_PS = 14, /**< Punctuation, open */
UTF8PROC_CATEGORY_PE = 15, /**< Punctuation, close */
UTF8PROC_CATEGORY_PI = 16, /**< Punctuation, initial quote */
UTF8PROC_CATEGORY_PF = 17, /**< Punctuation, final quote */
UTF8PROC_CATEGORY_PO = 18, /**< Punctuation, other */
UTF8PROC_CATEGORY_SM = 19, /**< Symbol, math */
UTF8PROC_CATEGORY_SC = 20, /**< Symbol, currency */
UTF8PROC_CATEGORY_SK = 21, /**< Symbol, modifier */
UTF8PROC_CATEGORY_SO = 22, /**< Symbol, other */
UTF8PROC_CATEGORY_ZS = 23, /**< Separator, space */
UTF8PROC_CATEGORY_ZL = 24, /**< Separator, line */
UTF8PROC_CATEGORY_ZP = 25, /**< Separator, paragraph */
UTF8PROC_CATEGORY_CC = 26, /**< Other, control */
UTF8PROC_CATEGORY_CF = 27, /**< Other, format */
UTF8PROC_CATEGORY_CS = 28, /**< Other, surrogate */
UTF8PROC_CATEGORY_CO = 29, /**< Other, private use */
typedef enum
{
UTF8PROC_CATEGORY_CN = 0, /**< Other, not assigned */
UTF8PROC_CATEGORY_LU = 1, /**< Letter, uppercase */
UTF8PROC_CATEGORY_LL = 2, /**< Letter, lowercase */
UTF8PROC_CATEGORY_LT = 3, /**< Letter, titlecase */
UTF8PROC_CATEGORY_LM = 4, /**< Letter, modifier */
UTF8PROC_CATEGORY_LO = 5, /**< Letter, other */
UTF8PROC_CATEGORY_MN = 6, /**< Mark, nonspacing */
UTF8PROC_CATEGORY_MC = 7, /**< Mark, spacing combining */
UTF8PROC_CATEGORY_ME = 8, /**< Mark, enclosing */
UTF8PROC_CATEGORY_ND = 9, /**< Number, decimal digit */
UTF8PROC_CATEGORY_NL = 10, /**< Number, letter */
UTF8PROC_CATEGORY_NO = 11, /**< Number, other */
UTF8PROC_CATEGORY_PC = 12, /**< Punctuation, connector */
UTF8PROC_CATEGORY_PD = 13, /**< Punctuation, dash */
UTF8PROC_CATEGORY_PS = 14, /**< Punctuation, open */
UTF8PROC_CATEGORY_PE = 15, /**< Punctuation, close */
UTF8PROC_CATEGORY_PI = 16, /**< Punctuation, initial quote */
UTF8PROC_CATEGORY_PF = 17, /**< Punctuation, final quote */
UTF8PROC_CATEGORY_PO = 18, /**< Punctuation, other */
UTF8PROC_CATEGORY_SM = 19, /**< Symbol, math */
UTF8PROC_CATEGORY_SC = 20, /**< Symbol, currency */
UTF8PROC_CATEGORY_SK = 21, /**< Symbol, modifier */
UTF8PROC_CATEGORY_SO = 22, /**< Symbol, other */
UTF8PROC_CATEGORY_ZS = 23, /**< Separator, space */
UTF8PROC_CATEGORY_ZL = 24, /**< Separator, line */
UTF8PROC_CATEGORY_ZP = 25, /**< Separator, paragraph */
UTF8PROC_CATEGORY_CC = 26, /**< Other, control */
UTF8PROC_CATEGORY_CF = 27, /**< Other, format */
UTF8PROC_CATEGORY_CS = 28, /**< Other, surrogate */
UTF8PROC_CATEGORY_CO = 29, /**< Other, private use */
} utf8proc_category_t;
/** Bidirectional character classes. */
typedef enum {
UTF8PROC_BIDI_CLASS_L = 1, /**< Left-to-Right */
UTF8PROC_BIDI_CLASS_LRE = 2, /**< Left-to-Right Embedding */
UTF8PROC_BIDI_CLASS_LRO = 3, /**< Left-to-Right Override */
UTF8PROC_BIDI_CLASS_R = 4, /**< Right-to-Left */
UTF8PROC_BIDI_CLASS_AL = 5, /**< Right-to-Left Arabic */
UTF8PROC_BIDI_CLASS_RLE = 6, /**< Right-to-Left Embedding */
UTF8PROC_BIDI_CLASS_RLO = 7, /**< Right-to-Left Override */
UTF8PROC_BIDI_CLASS_PDF = 8, /**< Pop Directional Format */
UTF8PROC_BIDI_CLASS_EN = 9, /**< European Number */
UTF8PROC_BIDI_CLASS_ES = 10, /**< European Separator */
UTF8PROC_BIDI_CLASS_ET = 11, /**< European Number Terminator */
UTF8PROC_BIDI_CLASS_AN = 12, /**< Arabic Number */
UTF8PROC_BIDI_CLASS_CS = 13, /**< Common Number Separator */
UTF8PROC_BIDI_CLASS_NSM = 14, /**< Nonspacing Mark */
UTF8PROC_BIDI_CLASS_BN = 15, /**< Boundary Neutral */
UTF8PROC_BIDI_CLASS_B = 16, /**< Paragraph Separator */
UTF8PROC_BIDI_CLASS_S = 17, /**< Segment Separator */
UTF8PROC_BIDI_CLASS_WS = 18, /**< Whitespace */
UTF8PROC_BIDI_CLASS_ON = 19, /**< Other Neutrals */
UTF8PROC_BIDI_CLASS_LRI = 20, /**< Left-to-Right Isolate */
UTF8PROC_BIDI_CLASS_RLI = 21, /**< Right-to-Left Isolate */
UTF8PROC_BIDI_CLASS_FSI = 22, /**< First Strong Isolate */
UTF8PROC_BIDI_CLASS_PDI = 23, /**< Pop Directional Isolate */
typedef enum
{
UTF8PROC_BIDI_CLASS_L = 1, /**< Left-to-Right */
UTF8PROC_BIDI_CLASS_LRE = 2, /**< Left-to-Right Embedding */
UTF8PROC_BIDI_CLASS_LRO = 3, /**< Left-to-Right Override */
UTF8PROC_BIDI_CLASS_R = 4, /**< Right-to-Left */
UTF8PROC_BIDI_CLASS_AL = 5, /**< Right-to-Left Arabic */
UTF8PROC_BIDI_CLASS_RLE = 6, /**< Right-to-Left Embedding */
UTF8PROC_BIDI_CLASS_RLO = 7, /**< Right-to-Left Override */
UTF8PROC_BIDI_CLASS_PDF = 8, /**< Pop Directional Format */
UTF8PROC_BIDI_CLASS_EN = 9, /**< European Number */
UTF8PROC_BIDI_CLASS_ES = 10, /**< European Separator */
UTF8PROC_BIDI_CLASS_ET = 11, /**< European Number Terminator */
UTF8PROC_BIDI_CLASS_AN = 12, /**< Arabic Number */
UTF8PROC_BIDI_CLASS_CS = 13, /**< Common Number Separator */
UTF8PROC_BIDI_CLASS_NSM = 14, /**< Nonspacing Mark */
UTF8PROC_BIDI_CLASS_BN = 15, /**< Boundary Neutral */
UTF8PROC_BIDI_CLASS_B = 16, /**< Paragraph Separator */
UTF8PROC_BIDI_CLASS_S = 17, /**< Segment Separator */
UTF8PROC_BIDI_CLASS_WS = 18, /**< Whitespace */
UTF8PROC_BIDI_CLASS_ON = 19, /**< Other Neutrals */
UTF8PROC_BIDI_CLASS_LRI = 20, /**< Left-to-Right Isolate */
UTF8PROC_BIDI_CLASS_RLI = 21, /**< Right-to-Left Isolate */
UTF8PROC_BIDI_CLASS_FSI = 22, /**< First Strong Isolate */
UTF8PROC_BIDI_CLASS_PDI = 23, /**< Pop Directional Isolate */
} utf8proc_bidi_class_t;
/** Decomposition type. */
typedef enum {
UTF8PROC_DECOMP_TYPE_FONT = 1, /**< Font */
UTF8PROC_DECOMP_TYPE_NOBREAK = 2, /**< Nobreak */
UTF8PROC_DECOMP_TYPE_INITIAL = 3, /**< Initial */
UTF8PROC_DECOMP_TYPE_MEDIAL = 4, /**< Medial */
UTF8PROC_DECOMP_TYPE_FINAL = 5, /**< Final */
UTF8PROC_DECOMP_TYPE_ISOLATED = 6, /**< Isolated */
UTF8PROC_DECOMP_TYPE_CIRCLE = 7, /**< Circle */
UTF8PROC_DECOMP_TYPE_SUPER = 8, /**< Super */
UTF8PROC_DECOMP_TYPE_SUB = 9, /**< Sub */
UTF8PROC_DECOMP_TYPE_VERTICAL = 10, /**< Vertical */
UTF8PROC_DECOMP_TYPE_WIDE = 11, /**< Wide */
UTF8PROC_DECOMP_TYPE_NARROW = 12, /**< Narrow */
UTF8PROC_DECOMP_TYPE_SMALL = 13, /**< Small */
UTF8PROC_DECOMP_TYPE_SQUARE = 14, /**< Square */
UTF8PROC_DECOMP_TYPE_FRACTION = 15, /**< Fraction */
UTF8PROC_DECOMP_TYPE_COMPAT = 16, /**< Compat */
typedef enum
{
UTF8PROC_DECOMP_TYPE_FONT = 1, /**< Font */
UTF8PROC_DECOMP_TYPE_NOBREAK = 2, /**< Nobreak */
UTF8PROC_DECOMP_TYPE_INITIAL = 3, /**< Initial */
UTF8PROC_DECOMP_TYPE_MEDIAL = 4, /**< Medial */
UTF8PROC_DECOMP_TYPE_FINAL = 5, /**< Final */
UTF8PROC_DECOMP_TYPE_ISOLATED = 6, /**< Isolated */
UTF8PROC_DECOMP_TYPE_CIRCLE = 7, /**< Circle */
UTF8PROC_DECOMP_TYPE_SUPER = 8, /**< Super */
UTF8PROC_DECOMP_TYPE_SUB = 9, /**< Sub */
UTF8PROC_DECOMP_TYPE_VERTICAL = 10, /**< Vertical */
UTF8PROC_DECOMP_TYPE_WIDE = 11, /**< Wide */
UTF8PROC_DECOMP_TYPE_NARROW = 12, /**< Narrow */
UTF8PROC_DECOMP_TYPE_SMALL = 13, /**< Small */
UTF8PROC_DECOMP_TYPE_SQUARE = 14, /**< Square */
UTF8PROC_DECOMP_TYPE_FRACTION = 15, /**< Fraction */
UTF8PROC_DECOMP_TYPE_COMPAT = 16, /**< Compat */
} utf8proc_decomp_type_t;
/** Boundclass property. (TR29) */
typedef enum {
UTF8PROC_BOUNDCLASS_START = 0, /**< Start */
UTF8PROC_BOUNDCLASS_OTHER = 1, /**< Other */
UTF8PROC_BOUNDCLASS_CR = 2, /**< Cr */
UTF8PROC_BOUNDCLASS_LF = 3, /**< Lf */
UTF8PROC_BOUNDCLASS_CONTROL = 4, /**< Control */
UTF8PROC_BOUNDCLASS_EXTEND = 5, /**< Extend */
UTF8PROC_BOUNDCLASS_L = 6, /**< L */
UTF8PROC_BOUNDCLASS_V = 7, /**< V */
UTF8PROC_BOUNDCLASS_T = 8, /**< T */
UTF8PROC_BOUNDCLASS_LV = 9, /**< Lv */
UTF8PROC_BOUNDCLASS_LVT = 10, /**< Lvt */
UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR = 11, /**< Regional indicator */
UTF8PROC_BOUNDCLASS_SPACINGMARK = 12, /**< Spacingmark */
UTF8PROC_BOUNDCLASS_PREPEND = 13, /**< Prepend */
UTF8PROC_BOUNDCLASS_ZWJ = 14, /**< Zero Width Joiner */
/* the following are no longer used in Unicode 11, but we keep
the constants here for backward compatibility */
UTF8PROC_BOUNDCLASS_E_BASE = 15, /**< Emoji Base */
UTF8PROC_BOUNDCLASS_E_MODIFIER = 16, /**< Emoji Modifier */
UTF8PROC_BOUNDCLASS_GLUE_AFTER_ZWJ = 17, /**< Glue_After_ZWJ */
UTF8PROC_BOUNDCLASS_E_BASE_GAZ = 18, /**< E_BASE + GLUE_AFTER_ZJW */
/* the Extended_Pictographic property is used in the Unicode 11
grapheme-boundary rules, so we store it in the boundclass field */
UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC = 19,
UTF8PROC_BOUNDCLASS_E_ZWG = 20, /* UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC + ZWJ */
typedef enum
{
UTF8PROC_BOUNDCLASS_START = 0, /**< Start */
UTF8PROC_BOUNDCLASS_OTHER = 1, /**< Other */
UTF8PROC_BOUNDCLASS_CR = 2, /**< Cr */
UTF8PROC_BOUNDCLASS_LF = 3, /**< Lf */
UTF8PROC_BOUNDCLASS_CONTROL = 4, /**< Control */
UTF8PROC_BOUNDCLASS_EXTEND = 5, /**< Extend */
UTF8PROC_BOUNDCLASS_L = 6, /**< L */
UTF8PROC_BOUNDCLASS_V = 7, /**< V */
UTF8PROC_BOUNDCLASS_T = 8, /**< T */
UTF8PROC_BOUNDCLASS_LV = 9, /**< Lv */
UTF8PROC_BOUNDCLASS_LVT = 10, /**< Lvt */
UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR = 11, /**< Regional indicator */
UTF8PROC_BOUNDCLASS_SPACINGMARK = 12, /**< Spacingmark */
UTF8PROC_BOUNDCLASS_PREPEND = 13, /**< Prepend */
UTF8PROC_BOUNDCLASS_ZWJ = 14, /**< Zero Width Joiner */
/* the following are no longer used in Unicode 11, but we keep
the constants here for backward compatibility */
UTF8PROC_BOUNDCLASS_E_BASE = 15, /**< Emoji Base */
UTF8PROC_BOUNDCLASS_E_MODIFIER = 16, /**< Emoji Modifier */
UTF8PROC_BOUNDCLASS_GLUE_AFTER_ZWJ = 17, /**< Glue_After_ZWJ */
UTF8PROC_BOUNDCLASS_E_BASE_GAZ = 18, /**< E_BASE + GLUE_AFTER_ZJW */
/* the Extended_Pictographic property is used in the Unicode 11
grapheme-boundary rules, so we store it in the boundclass field */
UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC = 19,
UTF8PROC_BOUNDCLASS_E_ZWG = 20, /* UTF8PROC_BOUNDCLASS_EXTENDED_PICTOGRAPHIC + ZWJ */
} utf8proc_boundclass_t;
/**
......@@ -393,7 +404,7 @@ typedef enum {
* @ref utf8proc_decompose_custom, which is used to specify a user-defined
* mapping of codepoints to be applied in conjunction with other mappings.
*/
typedef utf8proc_int32_t (*utf8proc_custom_func)(utf8proc_int32_t codepoint, void *data);
typedef utf8proc_int32_t (*utf8proc_custom_func)(utf8proc_int32_t codepoint, void* data);
/**
* Array containing the byte lengths of a UTF-8 encoded codepoint based
......@@ -406,18 +417,18 @@ UTF8PROC_DLLEXPORT extern const utf8proc_int8_t utf8proc_utf8class[256];
* (http://semver.org format), possibly with a "-dev" suffix for
* development versions.
*/
UTF8PROC_DLLEXPORT const char *utf8proc_version(void);
UTF8PROC_DLLEXPORT const char* utf8proc_version(void);
/**
* Returns the utf8proc supported Unicode version as a string MAJOR.MINOR.PATCH.
*/
UTF8PROC_DLLEXPORT const char *utf8proc_unicode_version(void);
UTF8PROC_DLLEXPORT const char* utf8proc_unicode_version(void);
/**
* Returns an informative error string for the given utf8proc error code
* (e.g. the error codes returned by @ref utf8proc_map).
*/
UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode);
UTF8PROC_DLLEXPORT const char* utf8proc_errmsg(utf8proc_ssize_t errcode);
/**
* Reads a single codepoint from the UTF-8 sequence being pointed to by `str`.
......@@ -429,7 +440,9 @@ UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode);
* In case of success, the number of bytes read is returned; otherwise, a
* negative error code is returned.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_int32_t *codepoint_ref);
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(const utf8proc_uint8_t* str,
utf8proc_ssize_t strlen,
utf8proc_int32_t* codepoint_ref);
/**
* Check if a codepoint is valid (regardless of whether it has been
......@@ -448,7 +461,8 @@ UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t codep
*
* This function does not check whether `codepoint` is valid Unicode.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t codepoint, utf8proc_uint8_t *dst);
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t codepoint,
utf8proc_uint8_t* dst);
/**
* Look up the properties for a given codepoint.
......@@ -462,7 +476,7 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t codepo
* If the codepoint is unassigned or invalid, a pointer to a special struct is
* returned in which `category` is 0 (@ref UTF8PROC_CATEGORY_CN).
*/
UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t codepoint);
UTF8PROC_DLLEXPORT const utf8proc_property_t* utf8proc_get_property(utf8proc_int32_t codepoint);
/** Decompose a codepoint into an array of codepoints.
*
......@@ -492,10 +506,11 @@ UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int
* required buffer size is returned, while the buffer will be overwritten with
* undefined data.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(
utf8proc_int32_t codepoint, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize,
utf8proc_option_t options, int *last_boundclass
);
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(utf8proc_int32_t codepoint,
utf8proc_int32_t* dst,
utf8proc_ssize_t bufsize,
utf8proc_option_t options,
int* last_boundclass);
/**
* The same as @ref utf8proc_decompose_char, but acts on a whole UTF-8
......@@ -514,10 +529,11 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(
* required buffer size is returned, while the buffer will be overwritten with
* undefined data.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options
);
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(const utf8proc_uint8_t* str,
utf8proc_ssize_t strlen,
utf8proc_int32_t* buffer,
utf8proc_ssize_t bufsize,
utf8proc_option_t options);
/**
* The same as @ref utf8proc_decompose, but also takes a `custom_func` mapping function
......@@ -525,11 +541,13 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
* (along with a `custom_data` pointer that is passed through to `custom_func`).
* The `custom_func` argument is ignored if it is `NULL`. See also @ref utf8proc_map_custom.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_custom(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options,
utf8proc_custom_func custom_func, void *custom_data
);
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_custom(const utf8proc_uint8_t* str,
utf8proc_ssize_t strlen,
utf8proc_int32_t* buffer,
utf8proc_ssize_t bufsize,
utf8proc_option_t options,
utf8proc_custom_func custom_func,
void* custom_data);
/**
* Normalizes the sequence of `length` codepoints pointed to by `buffer`
......@@ -554,7 +572,9 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_custom(
* @warning The entries of the array pointed to by `str` have to be in the
* range `0x0000` to `0x10FFFF`. Otherwise, the program might crash!
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_normalize_utf32(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options);
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_normalize_utf32(utf8proc_int32_t* buffer,
utf8proc_ssize_t length,
utf8proc_option_t options);
/**
* Reencodes the sequence of `length` codepoints pointed to by `buffer`
......@@ -584,7 +604,9 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_normalize_utf32(utf8proc_int32_t *b
* entries of the array pointed to by `str` have to be in the
* range `0x0000` to `0x10FFFF`. Otherwise, the program might crash!
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options);
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t* buffer,
utf8proc_ssize_t length,
utf8proc_option_t options);
/**
* Given a pair of consecutive codepoints, return whether a grapheme break is
......@@ -603,16 +625,16 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer,
* be called IN ORDER on ALL potential breaks in a string. However, it
* is safe to reset the state to zero after a grapheme break.
*/
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break_stateful(
utf8proc_int32_t codepoint1, utf8proc_int32_t codepoint2, utf8proc_int32_t *state);
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break_stateful(utf8proc_int32_t codepoint1,
utf8proc_int32_t codepoint2,
utf8proc_int32_t* state);
/**
* Same as @ref utf8proc_grapheme_break_stateful, except without support for the
* Unicode 9 additions to the algorithm. Supported for legacy reasons.
*/
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(
utf8proc_int32_t codepoint1, utf8proc_int32_t codepoint2);
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(utf8proc_int32_t codepoint1,
utf8proc_int32_t codepoint2);
/**
* Given a codepoint `c`, return the codepoint of the corresponding
......@@ -667,7 +689,7 @@ UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t codepo
* Return the two-letter (nul-terminated) Unicode category string for
* the codepoint (e.g. `"Lu"` or `"Co"`).
*/
UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t codepoint);
UTF8PROC_DLLEXPORT const char* utf8proc_category_string(utf8proc_int32_t codepoint);
/**
* Maps the given UTF-8 string pointed to by `str` to a new UTF-8
......@@ -688,9 +710,10 @@ UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t codepoi
* @note The memory of the new UTF-8 string will have been allocated
* with `malloc`, and should therefore be deallocated with `free`.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options
);
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(const utf8proc_uint8_t* str,
utf8proc_ssize_t strlen,
utf8proc_uint8_t** dstptr,
utf8proc_option_t options);
/**
* Like @ref utf8proc_map, but also takes a `custom_func` mapping function
......@@ -698,10 +721,12 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
* (along with a `custom_data` pointer that is passed through to `custom_func`).
* The `custom_func` argument is ignored if it is `NULL`.
*/
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map_custom(
const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options,
utf8proc_custom_func custom_func, void *custom_data
);
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map_custom(const utf8proc_uint8_t* str,
utf8proc_ssize_t strlen,
utf8proc_uint8_t** dstptr,
utf8proc_option_t options,
utf8proc_custom_func custom_func,
void* custom_data);
/** @name Unicode normalization
*
......@@ -712,18 +737,18 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map_custom(
*/
/** @{ */
/** NFD normalization (@ref UTF8PROC_DECOMPOSE). */
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFD(const utf8proc_uint8_t *str);
UTF8PROC_DLLEXPORT utf8proc_uint8_t* utf8proc_NFD(const utf8proc_uint8_t* str);
/** NFC normalization (@ref UTF8PROC_COMPOSE). */
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFC(const utf8proc_uint8_t *str);
UTF8PROC_DLLEXPORT utf8proc_uint8_t* utf8proc_NFC(const utf8proc_uint8_t* str);
/** NFKD normalization (@ref UTF8PROC_DECOMPOSE and @ref UTF8PROC_COMPAT). */
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKD(const utf8proc_uint8_t *str);
UTF8PROC_DLLEXPORT utf8proc_uint8_t* utf8proc_NFKD(const utf8proc_uint8_t* str);
/** NFKC normalization (@ref UTF8PROC_COMPOSE and @ref UTF8PROC_COMPAT). */
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC(const utf8proc_uint8_t *str);
UTF8PROC_DLLEXPORT utf8proc_uint8_t* utf8proc_NFKC(const utf8proc_uint8_t* str);
/**
* NFKC_Casefold normalization (@ref UTF8PROC_COMPOSE and @ref UTF8PROC_COMPAT
* and @ref UTF8PROC_CASEFOLD and @ref UTF8PROC_IGNORE).
**/
UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC_Casefold(const utf8proc_uint8_t *str);
UTF8PROC_DLLEXPORT utf8proc_uint8_t* utf8proc_NFKC_Casefold(const utf8proc_uint8_t* str);
/** @} */
#ifdef __cplusplus
......
Src/main.cpp
View file @ 0f9dc829
......@@ -12,7 +12,7 @@ int main()
// 加载GPT2模型
migraphxSamples::GPT2 gpt2;
migraphxSamples::ErrorCode errorCode = gpt2.Initialize();
if (errorCode != migraphxSamples::SUCCESS)
if(errorCode != migraphxSamples::SUCCESS)
{
LOG_ERROR(stdout, "fail to initialize GPT2!\n");
exit(-1);
......@@ -25,7 +25,7 @@ int main()
std::string buf;
std::vector<std::string> output;
infile.open("../Resource/vocab_shici.txt");
while (std::getline(infile,buf))
while(std::getline(infile, buf))
{
output.push_back(buf);
}
......@@ -37,7 +37,7 @@ int main()
std::vector<std::string> result;
std::cout << "开始和GPT2对诗，输入CTRL + Z以退出" << std::endl;
while (true)
while(true)
{
// 数据预处理
std::cout << "question: ";
......@@ -45,7 +45,7 @@ int main()
gpt2.Preprocessing(tokenizer, question, input_id);
// 推理
for(int i=0;i<50;++i)
for(int i = 0; i < 50; ++i)
{
long unsigned int outputs = gpt2.Inference(input_id);
if(outputs == 102)
......@@ -57,7 +57,7 @@ int main()
}
// 将数值映射为字符
for(int i=0;i<score.size();++i)
for(int i = 0; i < score.size(); ++i)
{
result.push_back(output[score[i]]);
}
......@@ -65,12 +65,12 @@ int main()
// 打印结果
std::cout << "chatbot: ";
std::cout << question;
for(int j=0; j<result.size();++j)
for(int j = 0; j < result.size(); ++j)
{
std::cout << result[j];
}
std::cout << std::endl;
// 清除数据
input_id.clear();
result.clear();
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment