*** empty log message ***
This commit is contained in:
fc_botelho
parent
124e0dfe68
commit
b8ac6fb0c1
7
FAQ.t2t
7
FAQ.t2t
|
|
@ -25,7 +25,12 @@ one is executed?
|
|||
the cmph_config_set_hashfuncs. Therefore, the default hash function
|
||||
is reset when you call the cmph_config_set_algo function.
|
||||
|
||||
|
||||
- What do I do when the following error is got?
|
||||
- Error: **error while loading shared libraries: libcmph.so.0: cannot open shared object file: No such file ordirectory**
|
||||
|
||||
- Solution: type **export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib/** at the shell or put that shell command
|
||||
in your .profile file or in the /etc/profile file.
|
||||
|
||||
%!include: ALGORITHMS.t2t
|
||||
|
||||
%!include: FOOTER.t2t
|
||||
|
|
|
|||
89
README.t2t
89
README.t2t
|
|
@ -51,7 +51,7 @@ The CMPH Library encapsulates the newest and more efficient algorithms in an eas
|
|||
%txt% - BMZ Algorithm.
|
||||
A very fast external memory based algorithm for constructing minimal perfect hash functions
|
||||
for sets in the order of billion of keys in linear time. The resulting functions are not order preserving and
|
||||
can be stored using just 8.1 bits per key. **This algorithm is available just in the CVS for while**.
|
||||
can be stored using just 8.1 bits per key.
|
||||
%html% - [CHM Algorithm chm.html].
|
||||
%txt% - CHM Algorithm.
|
||||
An algorithm based on acyclic random graphs to construct minimal
|
||||
|
|
@ -61,6 +61,15 @@ The CMPH Library encapsulates the newest and more efficient algorithms in an eas
|
|||
%html% [Click Here comparison.html] to see a comparison of the supported algorithms.
|
||||
|
||||
|
||||
----------------------------------------
|
||||
|
||||
==News for version 0.5==
|
||||
|
||||
- A thread safe vector adapter has been added.
|
||||
- [A new algorithm for sets in the order of billion of keys that requires approximately 8.1 bits per key to store the resulting MPHFs. brz.html]
|
||||
- All reported bugs and suggestions have been corrected and included as well.
|
||||
|
||||
|
||||
----------------------------------------
|
||||
|
||||
==News for version 0.4==
|
||||
|
|
@ -88,29 +97,29 @@ Using cmph is quite simple. Take a look.
|
|||
|
||||
```
|
||||
#include <cmph.h>
|
||||
|
||||
#include <string.h>
|
||||
// Create minimal perfect hash function from in-memory vector
|
||||
int main(int argc, char **argv)
|
||||
{
|
||||
{
|
||||
// Creating a filled vector
|
||||
const char *vector[] = {"aaaaaaaaaa", "bbbbbbbbbb", "cccccccccc", "dddddddddd", "eeeeeeeeee",
|
||||
const char *vector[] = {"aaaaaaaaaa", "bbbbbbbbbb", "cccccccccc", "dddddddddd", "eeeeeeeeee",
|
||||
"ffffffffff", "gggggggggg", "hhhhhhhhhh", "iiiiiiiiii", "jjjjjjjjjj"};
|
||||
unsigned int nkeys = 10;
|
||||
// Source of keys
|
||||
cmph_io_adapter_t *source = cmph_io_vector_adapter(vector, nkeys);
|
||||
|
||||
cmph_io_adapter_t *source = cmph_io_vector_adapter((char **)vector, nkeys);
|
||||
|
||||
//Create minimal perfect hash function using the default (chm) algorithm.
|
||||
cmph_config_t *config = cmph_config_new(source);
|
||||
cmph_t *hash = cmph_new(config);
|
||||
cmph_config_destroy(config);
|
||||
|
||||
|
||||
//Find key
|
||||
const char *key = "jjjjjjjjjj";
|
||||
unsigned int id = cmph_search(hash, key, strlen(key));
|
||||
fprintf(stderr, "Id:%u\n", id);
|
||||
//Destroy hash
|
||||
cmph_destroy(hash);
|
||||
free(source);
|
||||
cmph_io_vector_adapter_destroy(source);
|
||||
return 0;
|
||||
}
|
||||
```
|
||||
|
|
@ -120,33 +129,33 @@ Download [vector_adapter_ex1.c examples/vector_adapter_ex1.c]. This example does
|
|||
```
|
||||
#include <cmph.h>
|
||||
#include <stdio.h>
|
||||
|
||||
// Create minimal perfect hash function from in-disk keys using BMZ algorithm
|
||||
#include <string.h>
|
||||
// Create minimal perfect hash function from in-disk keys using BMZ algorithm
|
||||
int main(int argc, char **argv)
|
||||
{
|
||||
//Open file with newline separated list of keys
|
||||
{
|
||||
//Open file with newline separated list of keys
|
||||
FILE * keys_fd = fopen("keys.txt", "r");
|
||||
cmph_t *hash = NULL;
|
||||
if (keys_fd == NULL)
|
||||
if (keys_fd == NULL)
|
||||
{
|
||||
fprintf(stderr, "File \"keys.txt\" not found\n");
|
||||
exit(1);
|
||||
}
|
||||
fprintf(stderr, "File \"keys.txt\" not found\n");
|
||||
exit(1);
|
||||
}
|
||||
// Source of keys
|
||||
cmph_io_adapter_t *source = cmph_io_nlfile_adapter(keys_fd);
|
||||
|
||||
|
||||
cmph_config_t *config = cmph_config_new(source);
|
||||
cmph_config_set_algo(config, CMPH_BMZ);
|
||||
hash = cmph_new(config);
|
||||
cmph_config_destroy(config);
|
||||
|
||||
|
||||
//Find key
|
||||
const char *key = "jjjjjjjjjj";
|
||||
unsigned int id = cmph_search(hash, key, strlen(key));
|
||||
fprintf(stderr, "Id:%u\n", id);
|
||||
//Destroy hash
|
||||
cmph_destroy(hash);
|
||||
free(source);
|
||||
cmph_io_nlfile_adapter_destroy(source);
|
||||
fclose(keys_fd);
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -176,26 +185,32 @@ utility.
|
|||
|
||||
|
||||
```
|
||||
usage: cmph [-v] [-h] [-V] [-k nkeys] [-f hash_function] [-g [-c value][-s seed] ] [-m file.mph] [-a algorithm] keysfile
|
||||
usage: cmph [-v] [-h] [-V] [-k nkeys] [-f hash_function] [-g [-c value][-s seed] ] [-a algorithm] [-M memory_in_MB] [-b BRZ_parameter] [-d tmp_dir] [-m file.mph] keysfile
|
||||
Minimum perfect hashing tool
|
||||
|
||||
-h print this help message
|
||||
-c c value that determines the number of vertices in the graph
|
||||
-a algorithm - valid values are
|
||||
* bmz
|
||||
* chm
|
||||
-f hash function (may be used multiple times) - valid values are
|
||||
* djb2
|
||||
* fnv
|
||||
* jenkins
|
||||
* sdbm
|
||||
-V print version number and exit
|
||||
-v increase verbosity (may be used multiple times)
|
||||
-k number of keys
|
||||
-g generation mode
|
||||
-s random seed
|
||||
-m minimum perfect hash function file
|
||||
keysfile line separated file with keys
|
||||
-h print this help message
|
||||
-c c value that determines the number of vertices in the graph
|
||||
-a algorithm - valid values are
|
||||
* bmz
|
||||
* bmz8
|
||||
* chm
|
||||
* brz
|
||||
-f hash function (may be used multiple times) - valid values are
|
||||
* djb2
|
||||
* fnv
|
||||
* jenkins
|
||||
* sdbm
|
||||
-V print version number and exit
|
||||
-v increase verbosity (may be used multiple times)
|
||||
-k number of keys
|
||||
-g generation mode
|
||||
-s random seed
|
||||
-m minimum perfect hash function file
|
||||
-M main memory availability (in MB)
|
||||
-d temporary directory used in brz algorithm
|
||||
-b parmeter of BRZ algorithm to make the maximal number of keys in a bucket lower than 256
|
||||
keysfile line separated file with keys
|
||||
|
||||
```
|
||||
|
||||
==Additional Documentation==
|
||||
|
|
|
|||
Loading…
Reference in New Issue