mirror of
https://github.com/moses-smt/mosesdecoder.git
synced 2024-12-25 04:43:03 +03:00
38d790cac0
The code uses two mechanisms for generating random numbers: srand()/rand(), which is not thread-safe, and srandom()/random(), which is POSIX-specific. Here I add a util/random.cc module that centralizes these calls, and unifies some common usage patterns. If the implementation is not good enough, we can now change it in a single place. To keep things simple, this uses the portable srand()/rand() but protects them with a lock to avoid concurrency problems. The hard part was to keep the regression tests passing: they rely on fixed sequences of random numbers, so a small code change could break them very thoroughly. Util::rand(), for wide types like size_t, calls std::rand() not once but twice. This behaviour was generalized into utils::wide_rand() and friends.
68 lines
1.9 KiB
C++
68 lines
1.9 KiB
C++
#ifndef moses_DynSAInclude_utils_h
|
|
#define moses_DynSAInclude_utils_h
|
|
|
|
#include <cstdlib>
|
|
#include <vector>
|
|
#include <string>
|
|
#include <sstream>
|
|
#include <cctype>
|
|
#include <cmath>
|
|
#include <cstring>
|
|
|
|
//! @todo ask abby2
|
|
class Utils
|
|
{
|
|
public:
|
|
static void trim(std::string& str, const std::string dropChars = " \t\n\r") {
|
|
str.erase(str.find_last_not_of(dropChars)+1);
|
|
str.erase(0, str.find_first_not_of(dropChars));
|
|
}
|
|
static void rtrim(std::string& str, const std::string dropChars = " \t\n\r") {
|
|
str.erase(str.find_last_not_of(dropChars)+1);
|
|
}
|
|
static void ltrim(std::string& str, const std::string dropChars = " \t\n\r") {
|
|
str.erase(0, str.find_first_not_of(dropChars));
|
|
}
|
|
static std::string IntToStr(int integer) {
|
|
std::ostringstream stream;
|
|
stream << integer;
|
|
return stream.str();
|
|
}
|
|
static int splitToStr(const char * str,
|
|
std::vector<std::string> & items,
|
|
const char * delm = "\t") {
|
|
char * buff = const_cast<char *>(str);
|
|
items.clear();
|
|
char * pch = strtok(buff, delm);
|
|
while( pch != NULL ) {
|
|
items.push_back(pch);
|
|
pch = strtok(NULL, delm);
|
|
}
|
|
return items.size();
|
|
}
|
|
static int splitToStr(std::string buff,
|
|
std::vector<std::string> & items,
|
|
std::string delm = "\t") {
|
|
std::string cp = buff.substr();
|
|
return splitToStr(cp.c_str(), items, delm.c_str());
|
|
}
|
|
static int splitToInt(std::string buff, std::vector<int>& items,
|
|
std::string delm = ",") {
|
|
items.clear();
|
|
std::vector<std::string> tmpVector(0);
|
|
int i = 0;
|
|
i = splitToStr(buff.c_str(), tmpVector, delm.c_str());
|
|
if( i > 0 )
|
|
for( int j = 0; j < i; j++ )
|
|
items.push_back(atoi(tmpVector[j].c_str()));
|
|
return i;
|
|
}
|
|
static void strToLowercase(std::string& str) {
|
|
for(unsigned i=0; i < str.length(); i++) {
|
|
str[i] = tolower(str[i]);
|
|
}
|
|
}
|
|
};
|
|
|
|
#endif
|