de-duplicated some cut and paste code

git-svn-id: svn+ssh://svn.corp.yahoo.com/yahoo/yrl/labs/pnuts/code/logstore@526 8dad8b1f-cf64-0410-95b6-bcf113ffbcfe
This commit is contained in:
sears 2010-01-26 03:37:07 +00:00
parent 2fcfafb589
commit 38f2cb3897
9 changed files with 172 additions and 505 deletions

View file

@ -12,76 +12,13 @@
#include <sys/time.h>
#include <time.h>
#include "check_util.h"
#undef begin
#undef end
template class DataPage<datatuple>;
bool mycmp(const std::string & k1,const std::string & k2)
{
//for char* ending with \0
return strcmp(k1.c_str(),k2.c_str()) < 0;
//for int32_t
//printf("%d\t%d\n",(*((int32_t*)k1)) ,(*((int32_t*)k2)));
//return (*((int32_t*)k1)) <= (*((int32_t*)k2));
}
//must be given a sorted array
void removeduplicates(std::vector<std::string> &arr)
{
for(int i=arr.size()-1; i>0; i--)
{
if(! (mycmp(arr[i], arr[i-1]) || mycmp(arr[i-1], arr[i])))
arr.erase(arr.begin()+i);
}
}
void preprandstr(int count, std::vector<std::string> &arr, int avg_len=50, bool duplicates_allowed=false)
{
for ( int j=0; j<count; j++)
{
int str_len = (rand()%(avg_len*2)) + 3;
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
std::string str(rc);
//make sure there is no duplicate key
if(!duplicates_allowed)
{
bool dup = false;
for(int i=0; i<j; i++)
if(! (mycmp(arr[i], str) || mycmp(str, arr[i])))
{
dup=true;
break;
}
if(dup)
{
j--;
continue;
}
}
//printf("keylen-%d\t%d\t%s\n", str_len, str.length(),rc);
free(rc);
arr.push_back(str);
}
}
/**
* REGION ALLOCATION
**/

View file

@ -16,76 +16,11 @@
#undef begin
#undef end
#include "check_util.h"
//template class DataPage<datatuple>;
template class treeIterator<datatuple>;
bool mycmp(const std::string & k1,const std::string & k2)
{
//for char* ending with \0
return strcmp(k1.c_str(),k2.c_str()) < 0;
//for int32_t
//printf("%d\t%d\n",(*((int32_t*)k1)) ,(*((int32_t*)k2)));
//return (*((int32_t*)k1)) <= (*((int32_t*)k2));
}
//must be given a sorted array
void removeduplicates(std::vector<std::string> &arr)
{
for(int i=arr.size()-1; i>0; i--)
{
if(! (mycmp(arr[i], arr[i-1]) || mycmp(arr[i-1], arr[i])))
arr.erase(arr.begin()+i);
}
}
void preprandstr(int count, std::vector<std::string> &arr, int avg_len=50, bool duplicates_allowed=false)
{
for ( int j=0; j<count; j++)
{
int str_len = (rand()%(avg_len*2)) + 3;
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
std::string str(rc);
//make sure there is no duplicate key
if(!duplicates_allowed)
{
bool dup = false;
for(int i=0; i<j; i++)
if(! (mycmp(arr[i], str) || mycmp(str, arr[i])))
{
dup=true;
break;
}
if(dup)
{
j--;
continue;
}
}
//printf("keylen-%d\t%d\t%s\n", str_len, str.length(),rc);
free(rc);
arr.push_back(str);
}
}
void insertProbeIter(int NUM_ENTRIES)
{
srand(1000);

View file

@ -22,55 +22,7 @@
#undef begin
#undef end
bool mycmp(const std::string & k1,const std::string & k2)
{
//for char* ending with \0
return strcmp(k1.c_str(),k2.c_str()) < 0;
//for int32_t
//printf("%d\t%d\n",(*((int32_t*)k1)) ,(*((int32_t*)k2)));
//return (*((int32_t*)k1)) <= (*((int32_t*)k2));
}
void preprandstr(int count, std::vector<std::string> &arr)
{
for ( int j=0; j<count; j++)
{
int str_len = rand()%100 + 3;
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
std::string str(rc);
//make sure there is no duplicate key
bool dup = false;
for(int i=0; i<j; i++)
if(! (mycmp(arr[i], str) || mycmp(str, arr[i])))
{
dup=true;
break;
}
if(dup)
{
j--;
continue;
}
//printf("keylen-%d\t%d\t%s\n", str_len, str.length(),rc);
free(rc);
arr.push_back(str);
}
}
#include "check_util.h"
void insertProbeIter_str(int NUM_ENTRIES)
{
@ -100,7 +52,7 @@ void insertProbeIter_str(int NUM_ENTRIES)
long oldpagenum = -1;
std::vector<std::string> arr;
preprandstr(NUM_ENTRIES, arr);
preprandstr(NUM_ENTRIES, arr, 50, false);
std::sort(arr.begin(), arr.end(), &mycmp);
//for(int i = 0; i < NUM_ENTRIES; i++)

View file

@ -16,54 +16,7 @@
#undef begin
#undef end
bool mycmp(const std::string & k1,const std::string & k2)
{
//for char* ending with \0
return strcmp(k1.c_str(),k2.c_str()) < 0;
//for int32_t
//printf("%d\t%d\n",(*((int32_t*)k1)) ,(*((int32_t*)k2)));
//return (*((int32_t*)k1)) <= (*((int32_t*)k2));
}
//must be given a sorted array
void removeduplicates(std::vector<std::string> *arr)
{
for(int i=arr->size()-1; i>0; i--)
{
if(! (mycmp((*arr)[i], (*arr)[i-1]) || mycmp((*arr)[i-1], (*arr)[i])))
arr->erase(arr->begin()+i);
}
}
void preprandstr(int count, std::vector<std::string> *arr, int avg_len=50)
{
for ( int j=0; j<count; j++)
{
int str_len = (rand()%(avg_len*2)) + 3;
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
std::string str(rc);
free(rc);
arr->push_back(str);
}
}
#include "check_util.h"
void insertProbeIter(int NUM_ENTRIES)
{
@ -77,8 +30,8 @@ void insertProbeIter(int NUM_ENTRIES)
std::vector<std::string> * data_arr = new std::vector<std::string>;
std::vector<std::string> * key_arr = new std::vector<std::string>;
preprandstr(NUM_ENTRIES, data_arr, 10*8192);
preprandstr(NUM_ENTRIES+200, key_arr, 100);
preprandstr(NUM_ENTRIES, data_arr, 10*8192, true);
preprandstr(NUM_ENTRIES+200, key_arr, 100, true);
std::sort(key_arr->begin(), key_arr->end(), &mycmp);

View file

@ -16,73 +16,7 @@
#undef begin
#undef end
bool mycmp(const std::string & k1,const std::string & k2)
{
//for char* ending with \0
return strcmp(k1.c_str(),k2.c_str()) < 0;
//for int32_t
//printf("%d\t%d\n",(*((int32_t*)k1)) ,(*((int32_t*)k2)));
//return (*((int32_t*)k1)) <= (*((int32_t*)k2));
}
//must be given a sorted array
void removeduplicates(std::vector<std::string> *arr)
{
for(int i=arr->size()-1; i>0; i--)
{
if(! (mycmp((*arr)[i], (*arr)[i-1]) || mycmp((*arr)[i-1], (*arr)[i])))
arr->erase(arr->begin()+i);
}
}
void getnextdata(std::string &data, int avg_len)
{
int str_len = (rand()%(avg_len*2)) + 3;
data = std::string(str_len, rand()%10+48);
/*
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
data = std::string(rc);
free(rc);
*/
}
void preprandstr(int count, std::vector<std::string> *arr, int avg_len=50)
{
for ( int j=0; j<count; j++)
{
int str_len = (rand()%(avg_len*2)) + 3;
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
std::string str(rc);
free(rc);
arr->push_back(str);
}
}
#include "check_util.h"
void insertProbeIter(int NUM_ENTRIES)
{
@ -97,7 +31,7 @@ void insertProbeIter(int NUM_ENTRIES)
std::vector<std::string> * key_arr = new std::vector<std::string>;
// preprandstr(NUM_ENTRIES, data_arr, 10*8192);
preprandstr(NUM_ENTRIES+200, key_arr, 100);
preprandstr(NUM_ENTRIES+200, key_arr, 100, true);
std::sort(key_arr->begin(), key_arr->end(), &mycmp);

View file

@ -16,73 +16,7 @@
#undef begin
#undef end
bool mycmp(const std::string & k1,const std::string & k2)
{
//for char* ending with \0
return strcmp(k1.c_str(),k2.c_str()) < 0;
//for int32_t
//printf("%d\t%d\n",(*((int32_t*)k1)) ,(*((int32_t*)k2)));
//return (*((int32_t*)k1)) <= (*((int32_t*)k2));
}
//must be given a sorted array
void removeduplicates(std::vector<std::string> *arr)
{
for(int i=arr->size()-1; i>0; i--)
{
if(! (mycmp((*arr)[i], (*arr)[i-1]) || mycmp((*arr)[i-1], (*arr)[i])))
arr->erase(arr->begin()+i);
}
}
void getnextdata(std::string &data, int avg_len)
{
int str_len = (rand()%(avg_len*2)) + 3;
data = std::string(str_len, rand()%10+48);
/*
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
data = std::string(rc);
free(rc);
*/
}
void preprandstr(int count, std::vector<std::string> *arr, int avg_len=50)
{
for ( int j=0; j<count; j++)
{
int str_len = (rand()%(avg_len*2)) + 3;
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
std::string str(rc);
free(rc);
arr->push_back(str);
}
}
#include "check_util.h"
void insertProbeIter(int NUM_ENTRIES)
{
@ -104,9 +38,9 @@ void insertProbeIter(int NUM_ENTRIES)
{
key_v_t * key_arr = new key_v_t;
if(NUM_ENTRIES < max_partition_size*(i+1))
preprandstr(NUM_ENTRIES-max_partition_size*i, key_arr, KEY_LEN);
preprandstr(NUM_ENTRIES-max_partition_size*i, key_arr, KEY_LEN, true);
else
preprandstr(max_partition_size, key_arr, KEY_LEN);
preprandstr(max_partition_size, key_arr, KEY_LEN, true);
std::sort(key_arr->begin(), key_arr->end(), &mycmp);
key_v_list->push_back(key_arr);

View file

@ -16,73 +16,7 @@
#undef begin
#undef end
bool mycmp(const std::string & k1,const std::string & k2)
{
//for char* ending with \0
return strcmp(k1.c_str(),k2.c_str()) < 0;
//for int32_t
//printf("%d\t%d\n",(*((int32_t*)k1)) ,(*((int32_t*)k2)));
//return (*((int32_t*)k1)) <= (*((int32_t*)k2));
}
//must be given a sorted array
void removeduplicates(std::vector<std::string> &arr)
{
for(int i=arr.size()-1; i>0; i--)
{
if(! (mycmp(arr[i], arr[i-1]) || mycmp(arr[i-1], arr[i])))
arr.erase(arr.begin()+i);
}
}
void preprandstr(int count, std::vector<std::string> &arr, int avg_len=50, bool duplicates_allowed=false)
{
for ( int j=0; j<count; j++)
{
int str_len = (rand()%(avg_len*2)) + 3;
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
std::string str(rc);
//make sure there is no duplicate key
if(!duplicates_allowed)
{
bool dup = false;
for(int i=0; i<j; i++)
if(! (mycmp(arr[i], str) || mycmp(str, arr[i])))
{
dup=true;
break;
}
if(dup)
{
j--;
continue;
}
}
//printf("keylen-%d\t%d\t%s\n", str_len, str.length(),rc);
free(rc);
arr.push_back(str);
}
}
#include "check_util.h"
void insertProbeIter(int NUM_ENTRIES)
{

View file

@ -14,78 +14,11 @@
#include <netinet/in.h>
#include <netdb.h>
#include "check_util.h"
#undef begin
#undef end
bool mycmp(const std::string & k1,const std::string & k2)
{
//for char* ending with \0
return strcmp(k1.c_str(),k2.c_str()) < 0;
//for int32_t
//printf("%d\t%d\n",(*((int32_t*)k1)) ,(*((int32_t*)k2)));
//return (*((int32_t*)k1)) <= (*((int32_t*)k2));
}
//must be given a sorted array
void removeduplicates(std::vector<std::string> *arr)
{
for(int i=arr->size()-1; i>0; i--)
{
if(! (mycmp((*arr)[i], (*arr)[i-1]) || mycmp((*arr)[i-1], (*arr)[i])))
arr->erase(arr->begin()+i);
}
}
void getnextdata(std::string &data, int avg_len)
{
int str_len = (rand()%(avg_len*2)) + 3;
data = std::string(str_len, rand()%10+48);
/*
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
data = std::string(rc);
free(rc);
*/
}
void preprandstr(int count, std::vector<std::string> *arr, int avg_len=50)
{
for ( int j=0; j<count; j++)
{
int str_len = (rand()%(avg_len*2)) + 3;
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
std::string str(rc);
free(rc);
arr->push_back(str);
}
}
inline void readfromsocket(int sockd, byte *buf, int count)
{
@ -210,9 +143,9 @@ void insertProbeIter(int NUM_ENTRIES)
{
key_v_t * key_arr = new key_v_t;
if(NUM_ENTRIES < max_partition_size*(i+1))
preprandstr(NUM_ENTRIES-max_partition_size*i, key_arr, KEY_LEN);
preprandstr(NUM_ENTRIES-max_partition_size*i, key_arr, KEY_LEN, true);
else
preprandstr(max_partition_size, key_arr, KEY_LEN);
preprandstr(max_partition_size, key_arr, KEY_LEN, true);
std::sort(key_arr->begin(), key_arr->end(), &mycmp);
key_v_list->push_back(key_arr);

155
test/check_util.h Normal file
View file

@ -0,0 +1,155 @@
/*
* check_util.h
*
* Created on: Jan 25, 2010
* Author: sears
*/
#ifndef CHECK_UTIL_H_
#define CHECK_UTIL_H_
bool mycmp(const std::string & k1,const std::string & k2)
{
//for char* ending with \0
return strcmp(k1.c_str(),k2.c_str()) < 0;
//for int32_t
//printf("%d\t%d\n",(*((int32_t*)k1)) ,(*((int32_t*)k2)));
//return (*((int32_t*)k1)) <= (*((int32_t*)k2));
}
//must be given a sorted array
void removeduplicates(std::vector<std::string> *arr)
{
for(int i=arr->size()-1; i>0; i--)
{
if(! (mycmp((*arr)[i], (*arr)[i-1]) || mycmp((*arr)[i-1], (*arr)[i])))
arr->erase(arr->begin()+i);
}
}
//must be given a sorted array
// XXX probably don't need two copies of this function.
void removeduplicates(std::vector<std::string> &arr)
{
for(int i=arr.size()-1; i>0; i--)
{
if(! (mycmp(arr[i], arr[i-1]) || mycmp(arr[i-1], arr[i])))
arr.erase(arr.begin()+i);
}
}
void getnextdata(std::string &data, int avg_len)
{
int str_len = (rand()%(avg_len*2)) + 3;
data = std::string(str_len, rand()%10+48);
/*
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
data = std::string(rc);
free(rc);
*/
}
void preprandstr(int count, std::vector<std::string> *arr, int avg_len=50, bool duplicates_allowed=false)
{
for ( int j=0; j<count; j++)
{
int str_len = (rand()%(avg_len*2)) + 3;
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
std::string str(rc);
//make sure there is no duplicate key
if(!duplicates_allowed)
{
bool dup = false;
for(int i=0; i<j; i++)
if(! (mycmp((*arr)[i], str) || mycmp(str, (*arr)[i])))
{
dup=true;
break;
}
if(dup)
{
j--;
continue;
}
}
//printf("keylen-%d\t%d\t%s\n", str_len, str.length(),rc);
free(rc);
arr->push_back(str);
}
}
void preprandstr(int count, std::vector<std::string> &arr, int avg_len=50, bool duplicates_allowed=false)
{
for ( int j=0; j<count; j++)
{
int str_len = (rand()%(avg_len*2)) + 3;
char *rc = (char*)malloc(str_len);
for(int i=0; i<str_len-1; i++)
rc[i] = rand()%10+48;
rc[str_len-1]='\0';
std::string str(rc);
//make sure there is no duplicate key
if(!duplicates_allowed)
{
bool dup = false;
for(int i=0; i<j; i++)
if(! (mycmp(arr[i], str) || mycmp(str, arr[i])))
{
dup=true;
break;
}
if(dup)
{
j--;
continue;
}
}
//printf("keylen-%d\t%d\t%s\n", str_len, str.length(),rc);
free(rc);
arr.push_back(str);
}
}
#endif /* CHECK_UTIL_H_ */