From 08448aef30a48c5f0f4f1d04a33885deeacc4313 Mon Sep 17 00:00:00 2001
From: "enzo.decarvalhobittencourt" <ezdecarvalho@gmail.com>
Date: Mon, 11 Dec 2023 11:24:10 +0100
Subject: [PATCH] reformatted apm.c file, fixed 'bug'. TODO : change apm_omp.c
file
---
Projet/CODE/apm/src/.apm.c.swp | Bin 0 -> 16384 bytes
Projet/CODE/apm/src/apm.c | 354 ++++++++++++--------------
Projet/CODE/apm/src/apm_omp.c | 450 +++++++++++++++++----------------
3 files changed, 394 insertions(+), 410 deletions(-)
create mode 100644 Projet/CODE/apm/src/.apm.c.swp
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
GIT binary patch
literal 16384
zcmeI3Yit}>6~}KIC~;_cqvi|Yc7wz2dhOk{n~?eul*F6VO8iJ-hg8N|W_M@3<BVsv
zGqbU`Zc`x?1eHKSLPZF*B~%Sm;{Bm%3#tfhDpl|S6%axoR8+oH<)MlKMG6uBb00Ia
z_BsvUDm0`1yfb(1oVoX$b06nSS}B~InB;d16c~>8Ft+{WGv=k4J?w{HV{FNA`VGf-
z>DILl%Xa%6!)Y4*E5?ekdCjw0V7@eUVq&6{pE*1;S8jUlk{O8e!NTBBenws&oE|Ub
zjplOR_p0<eP~BW`awpM1qJe8`pcT~n_uj&W28&{-?@Zms-~Yb3Yd@3RO*D{bAkjdg
zfkXp|1`-V<8b~ydXyE@!13~jfc0YP_qw3Y?)$a}Kez&OWhWdSE-F<bL{3IGkG>~W@
z(LkbsL<5Ni5)C98NHmaWAkjdgfkXpuK@Au+#^w?1e}w{keE-++|CM($_IvPK@B+9D
zegGZ@4}cX=1(V<?*b6=ewtySJYwu$0CGZRIBk(kM2;2i2paQmoE#N=5Fm?r82Is*!
z@F`FR$G}Gc2OkE1yP2_Pz~kUi@CmRFWWY|40$1P3*q^{3!1G`gEPy+~0k9to0S5lP
zjj=bt%ivewIq*|(3ET~uU^f^7Jzy(%r3dxF&%yKHo8UZn0C->;l)y*88(SIs88`<_
zFc0RyC>REJfW6>W@Ik=9tM7o`z(w#l_$oLHEN}`O1P8zla5K0G{Q4&77kmcX4Nik4
zkOeQjov{bOm%s^-1}U%&Tz(s47r>Xn7r__6F>nNof)9c1U@N!^AGrw51M-*8ffX<g
zPJliz0#1TCFbl3Cv2+>y4m<{)P}fi4_epROFs_dKaMp35%Da?xDWb}r8MHiy7x_q7
zfr{%*&vJr#n)^Y`^t>ETl{^nM@b2q5xU58y=%8jshiB^Z&C2!t>-p`JvEfy+cilS|
z@0;uKm4;=TylHs8<t%c;TWl?xPQZI>pL9|=ZuJdiA~9>M2ZvSXX`7FZ@j`}CTg4wb
zvH2J@=h>!{hMY6=cz7Z9G*ruNDQrzVQ^)Jm)>vVLTYQu|m2%Sv0@HJR6!i6Fcs|Py
zdq#x^4Qimg#j|<o2$2S~F{5@;W5f}Y8Ec5X%TsfXQ9<tmmm9Y2R*k@f20Ww9-MW4w
zo%+^2rqT%04{Kjh>J;UqAJUF$EFT-=Q*%d;X7brXmTkxTfnN0Vgw=Su+Autx&1RNG
zJJPXs^Q?HiTNib*nal{aK)g=;iB}yX`&D^A9~vRunSpqv(^{^WUaU(#b=WrzuiD^b
z12hIAc^!`67|SNCD9kswAf#vugtx1%6Bw35?n0IcP?_Fjt_E6?(Zs*jS}oU&Y5?&N
z7r2&mi6R^#*0h@C2ZmEMxvKiV7+18h5O*-@1RbfGW0Y$~U{nl0^qitL=pY{$7$E0n
zqB8!dQJ<RgjYV^q_xfCRz*;r}%XM@=QsM#Wx@2Xc>rsBY90lmr!G>8q%_DWAf*4GG
z=(IEhvfL>{aJ6Cj(qpO6DOcKoE~vRJ^2%Dv6YrO`FtA!xsM%UJ&lvEfVvYxc@|JWS
zUTM`MfmV($MOU3pQiyJ>x0Jf2Bx;k#Uz62(9ARsWn!XHQNYe@FBgd5|3m3{@LX_iF
zj?r}0wOh;1Jp4@CEgHtr8QH})Ft99R5#Hn4H9C`xpnKhpuznv;`^EWoe{q3^pFcRi
zN~a&^1wPD+7(J}p)4EKxPdweni;;^^1$`5O`Q*gZknT-;fp4g*+KigvQ_-8(n0}v_
z0o$lm9N}%6QlS}~Ve$*BgdH2>=t(3*$t_T8R%Nl2D`c)pnX949RV_18bJ#M}ZEuj!
zy;Y)FEyuSO9ka&C>Z>{4&V}a6Mb?tuVVh@6$8Q8CoJ6{Y56@L+gIHi70-cs8S*0!b
z&CZ%xw;WR{+Q{(=9?I}^+Q^KiD;d~Ro}vt=Mh3=BS2N-Vw?}bK<)|pjAu#TT(NL+{
zu5YI6HRTssG1HGl!;$SYotjk_-PY5@R5+h{rcvW!;9}O03#J;#khc?a#QvGd@_6aM
z+~G~uELt5RlVS>{_viHMJDfGPR#n|*oA=tbe0SQ<@Ve(N%Ndx4EKm1Fw@}$KYnhG-
zulw3XPD%5c>H@!QOtwe*qAnf7=E<l*Ww1%Bo>NsuuCs&m4jiJNvF@#FP}haIv%^?d
zXyU;%gXKExoE!nv3A8O-ei^+|6zGLkud|{Z;R-A7>Nx@v`hLABpv8n1O`-WNi(WT3
zIYgF#YcB>3cn7Q{HdMOjUAzM?oShz@#^9i3MD1#@`>=h}Jgt{jaUrx{$ng`U(vk9s
z(yY>?><uOndZ43DX=+^6i7md-LPf(7Yqjb57>{yM$7(KIY10+C({-<5K(}c|GQ}o?
zkM{ceq&C!+Lp3fkU%f`w>n}>*qbp8w(t1V8@#*sM@#(3fcSZf0-uNQjdYWY-2UfEv
z6$;5}(R1tdGD>I&$}uTtDLGlJF?B`WU$&fPD=1TA)T9<}p7caUQex9sI1zCCv)Y}O
zQ?*+)laKmsKTj+AKx1F5wB=x1RO>9OSDnD_EJ7XIs%$8;-1S8WY8I(X_)wNlOdZ<2
zr@&7Q7K(dNhW{{6%^aUTH8Ht=w!~-l&(4;PPjOrvymMmeFw1ANjN<<%5ZgJ36Dj_0
z$WVv<3o-mpz}LZpfMWbTAP4%u6~yiT1pff9gBQT3!4#MTJ3tSh`2HEh?cW9$z+>Pf
z7y-M%UlFfg0^b7^(|-#*1U?JeU=>tA35<gsU^{pPvHLH<i{MFc5v+iDa17iIUPr9{
zEcgz16nq2R3p_9j_JJ{w2k!-2z>j+v`!1lE{sK4$?gB>u#q)neeEuSM4m=C)1#4gi
z8~`cs0k949fWIR){|opt_zid(JOu*agF~PMhCwgb4sHdn!5*)I?}KyTesC5v0om#i
z@GwY@L<5Ni5)Hf+G|;gV$J#5lXHi&!z1o}CpdFnKMCYvq+A^z{8dqvdAgaiOUMkwN
zt7;<gp%XB)AJIE_Mvuvjh|Eu6>#<peN;VyN8#-hX1&b**TUb0Nrufn6=@}soD<}?G
zTSpPt5%8Le2nRc^UK=?ku_4kiKe`~E)YoW4Iv5-X&Xj!<37(*+PBVRJRo=o4RZgdw
ze9_#ar64~;y9~EpGur800m3ekmXf<1+IHfmht!?h3^NsxJ?fr`U5*IcwLDT$RAJ*4
zmBbCw*C$^^<#b5(%5xcWgoz-;z#Tb>jMA~H9M+>yIf^WmA%!RG!cKpF2`(XHsf{fs
zQTK^VCS@}#*wCFG2`}^cscC*2UqSlC<&GQh6$9HuZ2g7baKBYSB8F05*qFO557xs@
zFvnMd22)K8fAV>10W7C?p8ZJ4@Q!L56%nh8oG1y<S<xsZKyOf@;}zgCv1nB{qti}Q
zsyz_@2W8b1Sziia5y0}a+X|>-y)s_pOWi}!ZU$W9y}Vc`(5@Y6;V#jQZV&Ccsnwkx
zL8UR<svS8!6RAiH$0a!&mndPZa%OyqavMy)ptHl9Cx_E<-SrhSVHilsED8e2JLsT~
z0IoO8TN{(b%jUA{wZ&W_{S2YET|3YjZBxV6$46mnqwZ1Es)Xpgaac>2BV7(fg=yk9
z?LsIZJ{pAvBYg>pD)AB-g-YWJ!b2*xAB{EWh~to5xX#IP-Bg5JQ1_|G@I*FQc0f#@
z(FA*-bQrVi=2L9s0h?Pt{<&d;<*8S6thd_rc>;MrmyAScg3i1|tazPu<4N1_BY^bH
zd{(3;M5wM7G^mGBo4a+Mym+&|kotMkg<LEFB9BB7F3oUaY7>F&K&r#k*T}D|kB*~w
zeU}=p@im0n8|x*KNh%+ZTek>Aeo2p{Y}Y+aEhL}Aw52?f5@A?ONe1QcSMt$}BIdNv
zCVB$gFFsRHmfz$v^7|5>G=c_15AzhZO7yZwpYVUD+HC8uJ7TdBA0g;FR}SCAFp0!_
z7d=UGy1U{At91Dy6)iY4Aa$bARwg0Yas<*DnI;;bk*ARd#LL$w!bIbvaX`5aod+Ya
F?7!h%*zN!T
literal 0
HcmV?d00001
diff --git a/Projet/CODE/apm/src/apm.c b/Projet/CODE/apm/src/apm.c
index 1c3e60c..6dc52b6 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 f0d611a..f5db3e5 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;
}
--
GitLab