diff --git a/Projet/CODE/apm/src/.apm.c.swp b/Projet/CODE/apm/src/.apm.c.swp
new file mode 100644
index 0000000000000000000000000000000000000000..28e989bebdb020ae307b90cfb0a208c9ff1045df
Binary files /dev/null and b/Projet/CODE/apm/src/.apm.c.swp differ
diff --git a/Projet/CODE/apm/src/apm.c b/Projet/CODE/apm/src/apm.c
index 1c3e60c29aaf32be05c7fef5087b4701e1e03a23..6dc52b69bcf486c33aac542794ae841c0bcf551e 100644
--- a/Projet/CODE/apm/src/apm.c
+++ b/Projet/CODE/apm/src/apm.c
@@ -12,248 +12,230 @@
#define APM_DEBUG 0
-char *
-read_input_file( char * filename, int * size )
+char * read_input_file(char * filename, int * size)
{
- char * buf ;
+ char * buf;
off_t fsize;
- int fd = 0 ;
- int n_bytes = 1 ;
+ int fd = 0;
+ int n_bytes = 1;
/* Open the text file */
- fd = open( filename, O_RDONLY ) ;
- if ( fd == -1 )
+ fd = open(filename, O_RDONLY);
+ if (fd == -1)
{
- fprintf( stderr, "Unable to open the text file <%s>\n", filename ) ;
- return NULL ;
+ fprintf(stderr, "Unable to open the text file <%s>\n", filename);
+ return NULL;
}
/* Get the number of characters in the textfile */
fsize = lseek(fd, 0, SEEK_END);
lseek(fd, 0, SEEK_SET);
-
/* TODO check return of lseek */
#if APM_DEBUG
- printf( "File length: %lld\n", fsize ) ;
+ printf("File length: %lld\n", fsize);
#endif
/* Allocate data to copy the target text */
- buf = (char *)malloc( fsize * sizeof ( char ) ) ;
- if ( buf == NULL )
+ buf = (char *)malloc(fsize * sizeof (char));
+ if (buf == NULL)
{
- fprintf( stderr, "Unable to allocate %lld byte(s) for main array\n",
- fsize ) ;
- return NULL ;
+ fprintf(stderr, "Unable to allocate %lld byte(s) for main array\n",
+ fsize);
+ return NULL;
}
- n_bytes = read( fd, buf, fsize ) ;
- if ( n_bytes != fsize )
+ n_bytes = read(fd, buf, fsize);
+ if (n_bytes != fsize)
{
- fprintf( stderr,
- "Unable to copy %lld byte(s) from text file (%d byte(s) copied)\n",
- fsize, n_bytes) ;
- return NULL ;
+ fprintf(stderr,
+ "Unable to copy %lld byte(s) from text file (%d byte(s) copied)\n",
+ fsize, n_bytes);
+ return NULL;
}
#if APM_DEBUG
- printf( "Number of read bytes: %d\n", n_bytes ) ;
+ printf("Number of read bytes: %d\n", n_bytes);
#endif
- *size = n_bytes ;
-
-
- close( fd ) ;
-
-
- return buf ;
+ *size = n_bytes;
+ close(fd);
+ return buf;
}
+#define MIN3(a, b, c) ((a)<(b) ? ((a)<(c) ? (a) : (c)) : ((b)<(c) ? (b) : (c)))
-#define MIN3(a, b, c) ((a) < (b) ? ((a) < (c) ? (a) : (c)) : ((b) < (c) ? (b) : (c)))
-
-int levenshtein(char *s1, char *s2, int len, int * column) {
+int levenshtein(char *s1, char *s2, int len, int * column)
+{
unsigned int x, y, lastdiag, olddiag;
for (y = 1; y <= len; y++)
{
column[y] = y;
}
- for (x = 1; x <= len; x++) {
+ for (x = 1; x <= len; x++)
+ {
column[0] = x;
- lastdiag = x-1 ;
- for (y = 1; y <= len; y++) {
+ lastdiag = x-1;
+ for (y = 1; y <= len; y++)
+ {
olddiag = column[y];
- column[y] = MIN3(
- column[y] + 1,
- column[y-1] + 1,
- lastdiag + (s1[y-1] == s2[x-1] ? 0 : 1)
- );
+ column[y] = MIN3(column[y] + 1,
+ column[y-1] + 1,
+ lastdiag + (s1[y-1] == s2[x-1] ? 0 : 1));
lastdiag = olddiag;
-
}
}
return(column[len]);
}
+int main(int argc, char ** argv)
+{
+ char ** pattern;
+ char * filename;
+ int approx_factor = 0;
+ int nb_patterns = 0;
+ int i, j;
+ char * buf;
+ struct timeval t1, t2;
+ double duration;
+ int n_bytes;
+ int * n_matches;
+
+ /* Check number of arguments */
+ if (argc < 4)
+ {
+ printf("Usage: %s approximation_factor "
+ "dna_database pattern1 pattern2 ...\n",
+ argv[0]);
+ return 1;
+ }
+ approx_factor = atoi(argv[1]);/* Get the distance factor */
+ filename = argv[2];/* Grab the filename containing the target text */
+ nb_patterns = argc - 3;/* Get the number of patterns to search for */
+
+ pattern = (char **)malloc(nb_patterns * sizeof(char*));
+ if (pattern == NULL)/*Fill the pattern*/
+ {
+ fprintf(stderr,
+ "Unable to allocate array of pattern of size %d\n",
+ nb_patterns);
+ return 1;
+ }
-int
-main( int argc, char ** argv )
-{
- char ** pattern ;
- char * filename ;
- int approx_factor = 0 ;
- int nb_patterns = 0 ;
- int i, j ;
- char * buf ;
- struct timeval t1, t2;
- double duration ;
- int n_bytes ;
- int * n_matches ;
-
- /* Check number of arguments */
- if ( argc < 4 )
- {
- printf( "Usage: %s approximation_factor "
- "dna_database pattern1 pattern2 ...\n",
- argv[0] ) ;
- return 1 ;
- }
-
- /* Get the distance factor */
- approx_factor = atoi( argv[1] ) ;
-
- /* Grab the filename containing the target text */
- filename = argv[2] ;
-
- /* Get the number of patterns that the user wants to search for */
- nb_patterns = argc - 3 ;
-
- /* Fill the pattern array */
- pattern = (char **)malloc( nb_patterns * sizeof( char * ) ) ;
- if ( pattern == NULL )
- {
- fprintf( stderr,
- "Unable to allocate array of pattern of size %d\n",
- nb_patterns ) ;
- return 1 ;
- }
-
- /* Grab the patterns */
- for ( i = 0 ; i < nb_patterns ; i++ )
- {
- int l ;
-
- l = strlen(argv[i+3]) ;
- if ( l <= 0 )
- {
- fprintf( stderr, "Error while parsing argument %d\n", i+3 ) ;
- return 1 ;
- }
-
- pattern[i] = (char *)malloc( (l+1) * sizeof( char ) ) ;
- if ( pattern[i] == NULL )
- {
- fprintf( stderr, "Unable to allocate string of size %d\n", l ) ;
- return 1 ;
- }
-
- strncpy( pattern[i], argv[i+3], (l+1) ) ;
-
- }
-
-
- printf( "Approximate Pattern Mathing: "
- "looking for %d pattern(s) in file %s w/ distance of %d\n",
- nb_patterns, filename, approx_factor ) ;
-
- buf = read_input_file( filename, &n_bytes ) ;
- if ( buf == NULL )
- {
- return 1 ;
- }
-
- /* Allocate the array of matches */
- n_matches = (int *)malloc( nb_patterns * sizeof( int ) ) ;
- if ( n_matches == NULL )
- {
- fprintf( stderr, "Error: unable to allocate memory for %ldB\n",
- nb_patterns * sizeof( int ) ) ;
- return 1 ;
- }
-
- /*****
- * BEGIN MAIN LOOP
- ******/
-
- /* Timer start */
- gettimeofday(&t1, NULL);
-
- for ( i = 0 ; i < nb_patterns ; i++ )
- {
-
-
-
- int size_pattern = strlen(pattern[i]) ;
-
- int * column ;
-
- n_matches[i] = 0 ;
-
- column = (int *)malloc( (size_pattern+1) * sizeof( int ) ) ;
- if ( column == NULL )
- {
- fprintf( stderr, "Error: unable to allocate memory for column (%ldB)\n",
- (size_pattern+1) * sizeof( int ) ) ;
- return 1 ;
- }
-
- for ( j = 0 ; j < n_bytes ; j++ )
- {
- int distance = 0 ;
- int size ;
+ for (i=0; i < nb_patterns; i++) /* Grab the patterns */
+ {
+ int l;
+ l = strlen(argv[i+3]);
+
+ if (l <= 0)
+ {
+ fprintf(stderr, "Error while parsing argument %d\n", i+3);
+ return 1;
+ }
+
+ pattern[i] = (char *)malloc((l+1) * sizeof(char));
+ if (pattern[i] == NULL)
+ {
+ fprintf(stderr, "Unable to allocate string of size %d\n", l);
+ return 1;
+ }
+
+ strncpy(pattern[i], argv[i+3], (l+1));
+ }
+
+
+ printf("Approximate Pattern Mathing: "
+ "looking for %d pattern(s) in file %s w/ distance of %d\n",
+ nb_patterns, filename, approx_factor);
+
+ buf = read_input_file(filename, &n_bytes);
+ if (buf == NULL)
+ {
+ fprintf(stderr, "Error: NULL pointer from reading input file.");
+ return 1;
+ }
+
+ n_matches = (int *)malloc(nb_patterns * sizeof(int));/*Alloc the matches*/
+ if (n_matches == NULL)
+ {
+ fprintf(stderr, "Error: unable to allocate memory for %ldB\n",
+ nb_patterns * sizeof(int));
+ return 1;
+ }
+
+ /*****
+ * BEGIN MAIN LOOP
+ ******/
+
+ /* Timer start */
+ gettimeofday(&t1, NULL);
+
+ for (i = 0; i < nb_patterns; i++)
+ {
+ int size_pattern = strlen(pattern[i]);
+ int * column;
+
+ n_matches[i] = 0;
+
+ column = (int *)malloc((size_pattern+1) * sizeof(int));
+ if (column == NULL)
+ {
+ fprintf(stderr,
+ "Error: unable to allocate memory for column (%ldB)\n",
+ (size_pattern+1) * sizeof(int));
+ return 1;
+ }
+
+ for (j = 0; j < n_bytes; j++)
+ {
+ int distance = 0;
+ int size;
#if APM_DEBUG
- if ( j % 100 == 0 )
- {
- printf( "Procesing byte %d (out of %d)\n", j, n_bytes ) ;
- }
+ if (j % 100 == 0)
+ {
+ printf("Procesing byte %d (out of %d)\n", j, n_bytes);
+ }
#endif
- size = size_pattern ;
- if ( n_bytes - j < size_pattern )
- {
- size = n_bytes - j ;
- }
+ size = size_pattern;
+ if (n_bytes - j < size_pattern)
+ {
+ //size = n_bytes - j;
+ //NO ! we do not want to match substring of our input, wth
+ break;
+ }
- distance = levenshtein( pattern[i], &buf[j], size, column ) ;
+ distance = levenshtein(pattern[i], &buf[j], size, column);
- if ( distance <= approx_factor ) {
- n_matches[i]++ ;
- }
- }
+ if (distance <= approx_factor)
+ {
+ n_matches[i]++;
+ }
+ }
- free( column );
- }
+ free(column);
+ }
- /* Timer stop */
- gettimeofday(&t2, NULL);
+ /* Timer stop */
+ gettimeofday(&t2, NULL);
- duration = (t2.tv_sec -t1.tv_sec)+((t2.tv_usec-t1.tv_usec)/1e6);
+ duration = (t2.tv_sec -t1.tv_sec)+((t2.tv_usec-t1.tv_usec)/1e6);
- printf( "APM done in %lf s\n", duration ) ;
+ printf("APM done in %lf s\n", duration);
- /*****
- * END MAIN LOOP
- ******/
+ /*****
+ * END MAIN LOOP
+ ******/
- for ( i = 0 ; i < nb_patterns ; i++ )
- {
- printf( "Number of matches for pattern <%s>: %d\n",
- pattern[i], n_matches[i] ) ;
- }
+ for (i = 0; i < nb_patterns; i++)
+ {
+ printf("Number of matches for pattern <%s>: %d\n",
+ pattern[i], n_matches[i]);
+ }
- return 0 ;
+ return 0;
}
diff --git a/Projet/CODE/apm/src/apm_omp.c b/Projet/CODE/apm/src/apm_omp.c
index f0d611a4ae3ee1f3646c622ba9f5241b3ec61a5f..f5db3e57414d6a84a2d1b472364efaca25ed21e4 100644
--- a/Projet/CODE/apm/src/apm_omp.c
+++ b/Projet/CODE/apm/src/apm_omp.c
@@ -14,56 +14,56 @@
char *
read_input_file(char *filename, int *size)
{
- char *buf;
- off_t fsize;
- int fd = 0;
- int n_bytes = 1;
-
- /* Open the text file */
- fd = open(filename, O_RDONLY);
- if (fd == -1)
- {
- fprintf(stderr, "Unable to open the text file <%s>\n", filename);
- return NULL;
- }
-
- /* Get the number of characters in the textfile */
- fsize = lseek(fd, 0, SEEK_END);
- lseek(fd, 0, SEEK_SET);
-
- /* TODO check return of lseek */
-
- #if APM_DEBUG
- printf("File length: %lld\n", fsize);
- #endif
-
- /* Allocate data to copy the target text */
- buf = (char *) malloc(fsize * sizeof (char));
- if (buf == NULL)
- {
- fprintf(stderr, "Unable to allocate %lld byte(s) for main array\n",
- fsize);
- return NULL;
- }
-
- n_bytes = read(fd, buf, fsize);
- if (n_bytes != fsize)
- {
- fprintf(stderr,
- "Unable to copy %lld byte(s) from text file (%d byte(s) copied)\n",
- fsize, n_bytes);
- return NULL;
- }
-
- #if APM_DEBUG
- printf("Number of read bytes: %d\n", n_bytes);
- #endif
-
- *size = n_bytes;
-
- close(fd);
-
- return buf;
+ char *buf;
+ off_t fsize;
+ int fd = 0;
+ int n_bytes = 1;
+
+ /* Open the text file */
+ fd = open(filename, O_RDONLY);
+ if (fd == -1)
+ {
+ fprintf(stderr, "Unable to open the text file <%s>\n", filename);
+ return NULL;
+ }
+
+ /* Get the number of characters in the textfile */
+ fsize = lseek(fd, 0, SEEK_END);
+ lseek(fd, 0, SEEK_SET);
+
+ /* TODO check return of lseek */
+
+#if APM_DEBUG
+ printf("File length: %lld\n", fsize);
+#endif
+
+ /* Allocate data to copy the target text */
+ buf = (char *) malloc(fsize * sizeof (char));
+ if (buf == NULL)
+ {
+ fprintf(stderr, "Unable to allocate %lld byte(s) for main array\n",
+ fsize);
+ return NULL;
+ }
+
+ n_bytes = read(fd, buf, fsize);
+ if (n_bytes != fsize)
+ {
+ fprintf(stderr,
+ "Unable to copy %lld byte(s) from text file (%d byte(s) copied)\n",
+ fsize, n_bytes);
+ return NULL;
+ }
+
+#if APM_DEBUG
+ printf("Number of read bytes: %d\n", n_bytes);
+#endif
+
+ *size = n_bytes;
+
+ close(fd);
+
+ return buf;
}
@@ -73,183 +73,185 @@ read_input_file(char *filename, int *size)
int
levenshtein(char *s1, char *s2, int len, int * column)
{
- unsigned int x, y, lastdiag, olddiag;
-
- for (y = 1; y <= len; y++)
- {
- column[y] = y;
- }
- for (x = 1; x <= len; x++) {
- column[0] = x;
- lastdiag = x-1 ;
- for (y = 1; y <= len; y++) {
- olddiag = column[y];
- column[y] = MIN3(
- column[y] + 1,
- column[y-1] + 1,
- lastdiag + (s1[y-1] == s2[x-1] ? 0 : 1)
- );
- lastdiag = olddiag;
- }
- }
- return(column[len]);
+ unsigned int x, y, lastdiag, olddiag;
+
+ for (y = 1; y <= len; y++)
+ {
+ column[y] = y;
+ }
+ for (x = 1; x <= len; x++)
+ {
+ column[0] = x;
+ lastdiag = x-1 ;
+ for (y = 1; y <= len; y++)
+ {
+ olddiag = column[y];
+ column[y] = MIN3(
+ column[y] + 1,
+ column[y-1] + 1,
+ lastdiag + (s1[y-1] == s2[x-1] ? 0 : 1)
+ );
+ lastdiag = olddiag;
+ }
+ }
+ return(column[len]);
}
-int
+int
main(int argc, char **argv)
{
- char **pattern;
- char *filename;
- int approx_factor = 0;
- int nb_patterns = 0;
- int i, j;
- char *buf;
- struct timeval t1, t2;
- double duration;
- int n_bytes;
- int *n_matches;
-
- /* Check number of arguments */
- if (argc < 4)
- {
- printf("Usage: %s approximation_factor "
- "dna_database pattern1 pattern2 ...\n",
- argv[0]);
- return 1;
- }
-
- /* Get the distance factor */
- approx_factor = atoi(argv[1]);
-
- /* Grab the filename containing the target text */
- filename = argv[2];
-
- /* Get the number of patterns that the user wants to search for */
- nb_patterns = argc - 3;
-
- /* Fill the pattern array */
- pattern = (char **)malloc(nb_patterns * sizeof(char *));
- if (pattern == NULL)
- {
- fprintf(stderr,
- "Unable to allocate array of pattern of size %d\n",
- nb_patterns );
- return 1;
- }
-
- /* Grab the patterns */
- for (i = 0; i < nb_patterns; i++)
- {
- int l;
-
- l = strlen(argv[i+3]);
- if (l <= 0)
- {
- fprintf(stderr, "Error while parsing argument %d\n", i + 3);
- return 1;
- }
-
- pattern[i] = (char *) malloc((l+1) * sizeof(char));
- if (pattern[i] == NULL)
- {
- fprintf(stderr, "Unable to allocate string of size %d\n", l);
- return 1;
- }
-
- strncpy(pattern[i], argv[i + 3], (l + 1));
- }
-
-
- printf("Approximate Pattern Mathing: "
- "looking for %d pattern(s) in file %s w/ distance of %d\n",
- nb_patterns, filename, approx_factor);
-
- buf = read_input_file(filename, &n_bytes);
- if (buf == NULL)
- {
- return 1;
- }
-
- /* Allocate the array of matches */
- n_matches = (int *) malloc(nb_patterns * sizeof(int));
- if (n_matches == NULL)
- {
- fprintf(stderr, "Error: unable to allocate memory for %ldB\n",
- nb_patterns * sizeof(int));
- return 1;
- }
-
- /*****
- * BEGIN MAIN LOOP
- ******/
-
- /* Timer start */
- gettimeofday(&t1, NULL);
-
- for (i = 0; i < nb_patterns; i++)
- {
-
- int size_pattern = strlen(pattern[i]);
-
- int * column;
-
- n_matches[i] = 0;
-
- column = (int *) malloc((size_pattern + 1) * sizeof(int));
- if (column == NULL)
- {
- fprintf(stderr, "Error: unable to allocate memory for column "
- "(%ldB)\n",
- (size_pattern + 1) * sizeof(int));
- return 1;
- }
-
- for (j = 0; j < n_bytes; j++)
- {
- int distance = 0;
- int size;
-
- #if APM_DEBUG
- if (j % 100 == 0)
- {
- printf("Procesing byte %d (out of %d)\n", j, n_bytes);
- }
- #endif
-
- size = size_pattern;
- if (n_bytes - j < size_pattern)
- {
- size = n_bytes - j;
- }
-
- distance = levenshtein(pattern[i], &buf[j], size, column);
-
- if (distance <= approx_factor)
- {
- n_matches[i]++;
- }
- }
-
- free(column);
- }
-
- /* Timer stop */
- gettimeofday(&t2, NULL);
-
- duration = (t2.tv_sec - t1.tv_sec) + ((t2.tv_usec - t1.tv_usec) / 1e6);
-
- printf("APM done in %lf s\n", duration);
-
- /*****
- * END MAIN LOOP
- ******/
-
- for (i = 0; i < nb_patterns; i++)
- {
- printf("Number of matches for pattern <%s>: %d\n",
- pattern[i], n_matches[i]);
- }
-
- return 0;
+ char **pattern;
+ char *filename;
+ int approx_factor = 0;
+ int nb_patterns = 0;
+ int i, j;
+ char *buf;
+ struct timeval t1, t2;
+ double duration;
+ int n_bytes;
+ int *n_matches;
+
+ /* Check number of arguments */
+ if (argc < 4)
+ {
+ printf("Usage: %s approximation_factor "
+ "dna_database pattern1 pattern2 ...\n",
+ argv[0]);
+ return 1;
+ }
+
+ /* Get the distance factor */
+ approx_factor = atoi(argv[1]);
+
+ /* Grab the filename containing the target text */
+ filename = argv[2];
+
+ /* Get the number of patterns that the user wants to search for */
+ nb_patterns = argc - 3;
+
+ /* Fill the pattern array */
+ pattern = (char **)malloc(nb_patterns * sizeof(char *));
+ if (pattern == NULL)
+ {
+ fprintf(stderr,
+ "Unable to allocate array of pattern of size %d\n",
+ nb_patterns );
+ return 1;
+ }
+
+ /* Grab the patterns */
+ for (i = 0; i < nb_patterns; i++)
+ {
+ int l;
+
+ l = strlen(argv[i+3]);
+ if (l <= 0)
+ {
+ fprintf(stderr, "Error while parsing argument %d\n", i + 3);
+ return 1;
+ }
+
+ pattern[i] = (char *) malloc((l+1) * sizeof(char));
+ if (pattern[i] == NULL)
+ {
+ fprintf(stderr, "Unable to allocate string of size %d\n", l);
+ return 1;
+ }
+
+ strncpy(pattern[i], argv[i + 3], (l + 1));
+ }
+
+
+ printf("Approximate Pattern Mathing: "
+ "looking for %d pattern(s) in file %s w/ distance of %d\n",
+ nb_patterns, filename, approx_factor);
+
+ buf = read_input_file(filename, &n_bytes);
+ if (buf == NULL)
+ {
+ return 1;
+ }
+
+ /* Allocate the array of matches */
+ n_matches = (int *) malloc(nb_patterns * sizeof(int));
+ if (n_matches == NULL)
+ {
+ fprintf(stderr, "Error: unable to allocate memory for %ldB\n",
+ nb_patterns * sizeof(int));
+ return 1;
+ }
+
+ /*****
+ * BEGIN MAIN LOOP
+ ******/
+
+ /* Timer start */
+ gettimeofday(&t1, NULL);
+
+ for (i = 0; i < nb_patterns; i++)
+ {
+
+ int size_pattern = strlen(pattern[i]);
+
+ int * column;
+
+ n_matches[i] = 0;
+
+ column = (int *) malloc((size_pattern + 1) * sizeof(int));
+ if (column == NULL)
+ {
+ fprintf(stderr, "Error: unable to allocate memory for column "
+ "(%ldB)\n",
+ (size_pattern + 1) * sizeof(int));
+ return 1;
+ }
+
+ for (j = 0; j < n_bytes; j++)
+ {
+ int distance = 0;
+ int size;
+
+#if APM_DEBUG
+ if (j % 100 == 0)
+ {
+ printf("Procesing byte %d (out of %d)\n", j, n_bytes);
+ }
+#endif
+
+ size = size_pattern;
+ if (n_bytes - j < size_pattern)
+ {
+ size = n_bytes - j;
+ }
+
+ distance = levenshtein(pattern[i], &buf[j], size, column);
+
+ if (distance <= approx_factor)
+ {
+ n_matches[i]++;
+ }
+ }
+
+ free(column);
+ }
+
+ /* Timer stop */
+ gettimeofday(&t2, NULL);
+
+ duration = (t2.tv_sec - t1.tv_sec) + ((t2.tv_usec - t1.tv_usec) / 1e6);
+
+ printf("APM done in %lf s\n", duration);
+
+ /*****
+ * END MAIN LOOP
+ ******/
+
+ for (i = 0; i < nb_patterns; i++)
+ {
+ printf("Number of matches for pattern <%s>: %d\n",
+ pattern[i], n_matches[i]);
+ }
+
+ return 0;
}