1 | #include <sys/time.h> |
---|
2 | #include <stdio.h> |
---|
3 | // #include <malloc.h> |
---|
4 | #include <string.h> |
---|
5 | #include <time.h> |
---|
6 | |
---|
7 | //#include <xview/xview.h> |
---|
8 | //#include <xview/panel.h> |
---|
9 | |
---|
10 | #include <arbdb.h> |
---|
11 | #include <aw_root.hxx> |
---|
12 | #include <aw_device.hxx> |
---|
13 | #include <aw_window.hxx> |
---|
14 | #include <awt.hxx> |
---|
15 | |
---|
16 | #include "gde.hxx" |
---|
17 | #include "GDE_menu.h" |
---|
18 | #include "GDE_def.h" |
---|
19 | #include "GDE_extglob.h" |
---|
20 | |
---|
21 | /* |
---|
22 | Copyright (c) 1989-1990, University of Illinois board of trustees. All |
---|
23 | rights reserved. Written by Steven Smith at the Center for Prokaryote Genome |
---|
24 | Analysis. Design and implementation guidance by Dr. Gary Olsen and Dr. |
---|
25 | Carl Woese. |
---|
26 | |
---|
27 | Copyright (c) 1990,1991,1992 Steven Smith at the Harvard Genome Laboratory. |
---|
28 | all rights reserved. |
---|
29 | |
---|
30 | Copyright (c) 1993, Steven Smith, all rights reserved. |
---|
31 | |
---|
32 | */ |
---|
33 | |
---|
34 | /* |
---|
35 | * CheckType: Check base composition to see if the sequence |
---|
36 | * appears to be an amino acid sequence. If it is, pass back |
---|
37 | * TRUE, else FALSE. |
---|
38 | */ |
---|
39 | static int CheckType(char *seq,int len) |
---|
40 | { |
---|
41 | |
---|
42 | int j,count1 = 0,count2 = 0; |
---|
43 | |
---|
44 | for(j=0;j<len;j++) |
---|
45 | if(((seq[j]|32) < 'z') && ((seq[j]|32) > 'a')) |
---|
46 | { |
---|
47 | count1++; |
---|
48 | if(strchr("ACGTUNacgtun",seq[j]) == NULL) |
---|
49 | count2++; |
---|
50 | } |
---|
51 | |
---|
52 | return( (count2 > count1/4)?TRUE:FALSE); |
---|
53 | } |
---|
54 | |
---|
55 | // ARB |
---|
56 | typedef struct ARB_TIME_STRUCT |
---|
57 | { |
---|
58 | int yy; |
---|
59 | int mm; |
---|
60 | int dd; |
---|
61 | int hr; |
---|
62 | int mn; |
---|
63 | int sc; |
---|
64 | } ARB_TIME; |
---|
65 | |
---|
66 | static void AsciiTime(void *b,char *asciitime) |
---|
67 | { |
---|
68 | ARB_TIME *a=(ARB_TIME*)b; |
---|
69 | int j; |
---|
70 | char temp[GBUFSIZ]; |
---|
71 | //extern char month[12][6]; |
---|
72 | |
---|
73 | a->dd = 0; |
---|
74 | a->yy = 0; |
---|
75 | a->mm = 0; |
---|
76 | sscanf(asciitime,"%d%5c%d",&(a->dd),temp,&(a->yy)); |
---|
77 | temp[5] = '\0'; |
---|
78 | for(j=0;j<12;j++) |
---|
79 | if(strcmp(temp,GDEmonth[j]) == 0) |
---|
80 | a->mm = j+1; |
---|
81 | if(a->dd <0 || a->dd > 31 || a->yy < 0 || a->mm > 11) |
---|
82 | SetTime(a); |
---|
83 | return; |
---|
84 | } |
---|
85 | // ENDARB |
---|
86 | |
---|
87 | |
---|
88 | |
---|
89 | void ReadGen(char *filename,NA_Alignment *dataset,int type) |
---|
90 | { |
---|
91 | int done = FALSE; |
---|
92 | size_t len = 0; |
---|
93 | size_t j = 0; |
---|
94 | int count,IS_REALLY_AA = FALSE; |
---|
95 | char in_line[GBUFSIZ],c; |
---|
96 | char *buffer = 0,*gencomments = NULL,fields[8][GBUFSIZ]; |
---|
97 | size_t buflen = 0; |
---|
98 | int genclen = 0,curelem = 0,n = 0; |
---|
99 | int start_col = -1; |
---|
100 | |
---|
101 | type=0;count=0; |
---|
102 | |
---|
103 | NA_Sequence *this_elem =0; |
---|
104 | FILE *file; |
---|
105 | |
---|
106 | ErrorOut5(0 != (file = fopen(filename,"r")),"No such file"); |
---|
107 | |
---|
108 | for(;fgets(in_line,GBUFSIZ,file) != 0;) |
---|
109 | { |
---|
110 | if(in_line[strlen(in_line)-1] == '\n') |
---|
111 | in_line[strlen(in_line)-1] = '\0'; |
---|
112 | if(Find(in_line,"LOCUS")) |
---|
113 | { |
---|
114 | curelem = dataset->numelements++; |
---|
115 | if(curelem == 0) |
---|
116 | { |
---|
117 | dataset->element=(NA_Sequence*) |
---|
118 | Calloc(5,sizeof(NA_Sequence)); |
---|
119 | dataset->maxnumelements = 5; |
---|
120 | } |
---|
121 | else if (curelem==dataset->maxnumelements) |
---|
122 | { |
---|
123 | (dataset->maxnumelements) *= 2; |
---|
124 | dataset->element =(NA_Sequence*) |
---|
125 | Realloc((char*)dataset->element, |
---|
126 | dataset->maxnumelements * sizeof(NA_Sequence)); |
---|
127 | } |
---|
128 | this_elem = &(dataset->element[curelem]); |
---|
129 | n = sscanf(in_line,"%s %s %s %s %s %s %s %s", |
---|
130 | fields[0],fields[1],fields[2],fields[3],fields[4], |
---|
131 | fields[5],fields[6],fields[7]); |
---|
132 | if(IS_REALLY_AA) |
---|
133 | { |
---|
134 | InitNASeq(this_elem,PROTEIN); |
---|
135 | } |
---|
136 | else if(Find(in_line,"DNA")) |
---|
137 | { |
---|
138 | InitNASeq(this_elem,DNA); |
---|
139 | } |
---|
140 | else if(Find(in_line,"RNA")) |
---|
141 | { |
---|
142 | InitNASeq(this_elem,RNA); |
---|
143 | } |
---|
144 | else if(Find(in_line,"MASK")) |
---|
145 | { |
---|
146 | InitNASeq(this_elem,MASK); |
---|
147 | } |
---|
148 | else if(Find(in_line,"TEXT")) |
---|
149 | { |
---|
150 | InitNASeq(this_elem,TEXT); |
---|
151 | } |
---|
152 | else if(Find(in_line,"PROT")) |
---|
153 | { |
---|
154 | InitNASeq(this_elem,PROTEIN); |
---|
155 | } |
---|
156 | else |
---|
157 | InitNASeq(this_elem,DNA); |
---|
158 | |
---|
159 | strncpy(this_elem->short_name,fields[1],31); |
---|
160 | AsciiTime(&(this_elem->t_stamp.origin),fields[n-1]); |
---|
161 | this_elem->attr = DEFAULT_X_ATTR; |
---|
162 | |
---|
163 | if( Find(in_line, "Circular") ) |
---|
164 | this_elem->attr |= IS_CIRCULAR; |
---|
165 | |
---|
166 | gencomments = NULL; |
---|
167 | genclen = 0; |
---|
168 | } |
---|
169 | else if(Find(in_line,"DEFINITION")) |
---|
170 | strncpy(this_elem->description,&(in_line[12]),79); |
---|
171 | |
---|
172 | else if(Find(in_line,"AUTHOR")) |
---|
173 | strncpy(this_elem->authority,&(in_line[12]),79); |
---|
174 | |
---|
175 | else if(Find(in_line," ORGANISM")) |
---|
176 | strncpy(this_elem->seq_name,&(in_line[12]),79); |
---|
177 | |
---|
178 | else if(Find(in_line,"ACCESSION")) |
---|
179 | strncpy(this_elem->id,&(in_line[12]),79); |
---|
180 | |
---|
181 | else if(Find(in_line,"ORIGIN")) |
---|
182 | { |
---|
183 | done = FALSE; |
---|
184 | len = 0; |
---|
185 | for(;done == FALSE && fgets(in_line,GBUFSIZ,file) != 0;) |
---|
186 | { |
---|
187 | if(in_line[0] != '/') |
---|
188 | { |
---|
189 | if(buflen == 0) |
---|
190 | { |
---|
191 | buflen = GBUFSIZ; |
---|
192 | buffer = Calloc(sizeof(char) , |
---|
193 | buflen); |
---|
194 | } |
---|
195 | |
---|
196 | else if (len+strlen(in_line) >= buflen) |
---|
197 | { |
---|
198 | buflen += GBUFSIZ; |
---|
199 | buffer = Realloc((char*)buffer, |
---|
200 | sizeof(char)*buflen); |
---|
201 | for(j=buflen-GBUFSIZ |
---|
202 | ;j<buflen;j++) |
---|
203 | buffer[j] = '\0'; |
---|
204 | } |
---|
205 | /* |
---|
206 | * Search for the fist column of data (whitespace-number-whitespace)data |
---|
207 | */ |
---|
208 | if(start_col == -1) |
---|
209 | { |
---|
210 | for(start_col=0; in_line[start_col] == ' ' || in_line[start_col] == '\t';start_col++) ; |
---|
211 | for(start_col++;strchr("1234567890", in_line[start_col]) != NULL;start_col++) ; |
---|
212 | for(start_col++; in_line[start_col] == ' ' || in_line[start_col] == '\t';start_col++) ; |
---|
213 | } |
---|
214 | for(j=start_col;(c = in_line[j]) != '\0';j++) |
---|
215 | { |
---|
216 | if ((c != '\n') && ((j-start_col + 1) % 11 !=0)) { |
---|
217 | buffer[len++] = c; |
---|
218 | } |
---|
219 | } |
---|
220 | } |
---|
221 | else |
---|
222 | { |
---|
223 | AppendNA((NA_Base*)buffer,len,&(dataset-> |
---|
224 | element[curelem])); |
---|
225 | for(j=0;j<len;j++) |
---|
226 | buffer[j] = '\0'; |
---|
227 | len = 0; |
---|
228 | done = TRUE; |
---|
229 | dataset->element[curelem].comments |
---|
230 | = gencomments; |
---|
231 | dataset->element[curelem].comments_len= |
---|
232 | genclen - 1; |
---|
233 | dataset->element[curelem]. |
---|
234 | comments_maxlen = genclen; |
---|
235 | |
---|
236 | gencomments = NULL; |
---|
237 | genclen = 0; |
---|
238 | } |
---|
239 | } |
---|
240 | /* |
---|
241 | * Test if sequence should be converted by the translation table |
---|
242 | * If it looks like a protein... |
---|
243 | */ |
---|
244 | if(dataset->element[curelem].rmatrix && |
---|
245 | IS_REALLY_AA == FALSE) |
---|
246 | { |
---|
247 | IS_REALLY_AA = CheckType((char*)dataset->element[curelem]. |
---|
248 | sequence,dataset->element[curelem].seqlen); |
---|
249 | |
---|
250 | if(IS_REALLY_AA == FALSE) |
---|
251 | Ascii2NA((char*)dataset->element[curelem].sequence, |
---|
252 | dataset->element[curelem].seqlen, |
---|
253 | dataset->element[curelem].rmatrix); |
---|
254 | else |
---|
255 | /* |
---|
256 | * Force the sequence to be AA |
---|
257 | */ |
---|
258 | { |
---|
259 | dataset->element[curelem].elementtype = PROTEIN; |
---|
260 | dataset->element[curelem].rmatrix = NULL; |
---|
261 | dataset->element[curelem].tmatrix = NULL; |
---|
262 | dataset->element[curelem].col_lut = |
---|
263 | Default_PROColor_LKUP; |
---|
264 | } |
---|
265 | } |
---|
266 | } |
---|
267 | else if (Find(in_line,"ZZZZZ")) |
---|
268 | { |
---|
269 | Cfree(gencomments); |
---|
270 | genclen = 0; |
---|
271 | } |
---|
272 | else |
---|
273 | { |
---|
274 | if (gencomments == NULL) |
---|
275 | { |
---|
276 | gencomments = strdup(in_line); |
---|
277 | genclen = strlen(gencomments)+1; |
---|
278 | } |
---|
279 | else |
---|
280 | { |
---|
281 | genclen += strlen(in_line)+1; |
---|
282 | gencomments = Realloc((char*)gencomments,genclen * |
---|
283 | sizeof(char)); |
---|
284 | strncat(gencomments,in_line,GBUFSIZ); |
---|
285 | strncat(gencomments,"\n",GBUFSIZ); |
---|
286 | } |
---|
287 | } |
---|
288 | } |
---|
289 | Cfree(buffer); |
---|
290 | fclose(file); |
---|
291 | for(j=0;j<dataset->numelements;j++) |
---|
292 | dataset->maxlen = MAX(dataset->maxlen, |
---|
293 | dataset->element[j].seqlen+dataset->element[j].offset); |
---|
294 | //return; |
---|
295 | } |
---|
296 | |
---|
297 | int WriteGen(NA_Alignment *aln,char *filename,int method,int maskable) |
---|
298 | { |
---|
299 | int i; |
---|
300 | size_t j; |
---|
301 | int k,mask = -1; |
---|
302 | FILE *file; |
---|
303 | //extern char month[12][6]; |
---|
304 | NA_Sequence *this_elem; |
---|
305 | char c; |
---|
306 | if(aln == NULL) |
---|
307 | return(1); |
---|
308 | // ARB |
---|
309 | //if(aln->na_ddata == NULL) |
---|
310 | // return(1); |
---|
311 | |
---|
312 | file = fopen(filename,"w"); |
---|
313 | if(file == NULL) |
---|
314 | { |
---|
315 | Warning("Cannot open file for output"); |
---|
316 | return(1); |
---|
317 | } |
---|
318 | |
---|
319 | if(maskable && method != SELECT_REGION) |
---|
320 | for(j=0;j<aln->numelements;j++) |
---|
321 | if(aln->element[j].elementtype == MASK && |
---|
322 | aln->element[j].selected) |
---|
323 | mask = j; |
---|
324 | |
---|
325 | for(j=0;j<aln->numelements;j++) |
---|
326 | { |
---|
327 | this_elem = &(aln->element[j]); |
---|
328 | if ((aln->element[j].selected && (int)j!=mask && method != SELECT_REGION) |
---|
329 | ||(aln->element[j].subselected && method == SELECT_REGION) |
---|
330 | || (method == ALL)) |
---|
331 | { |
---|
332 | fprintf(file, |
---|
333 | "LOCUS %10s%8d bp %4s %10s %2d%5s%4d\n", |
---|
334 | this_elem->short_name,this_elem->seqlen+this_elem->offset, |
---|
335 | (this_elem->elementtype == DNA) ? "DNA": |
---|
336 | (this_elem->elementtype ==RNA)?"RNA": |
---|
337 | (this_elem->elementtype == MASK)?"MASK": |
---|
338 | (this_elem->elementtype == PROTEIN)?"PROT":"TEXT", |
---|
339 | this_elem->attr & IS_CIRCULAR?"Circular":"", |
---|
340 | this_elem->t_stamp.origin.dd, |
---|
341 | GDEmonth[this_elem->t_stamp.origin.mm-1], |
---|
342 | (this_elem->t_stamp.origin.yy>1900)?this_elem->t_stamp.origin.yy: |
---|
343 | this_elem->t_stamp.origin.yy+1900); |
---|
344 | |
---|
345 | if(this_elem->description[0]) |
---|
346 | fprintf(file,"DEFINITION %s\n",this_elem->description); |
---|
347 | if(this_elem->seq_name[0]) |
---|
348 | fprintf(file," ORGANISM %s\n",this_elem->seq_name); |
---|
349 | if(this_elem->id[0]) |
---|
350 | fprintf(file," ACCESSION %s\n",this_elem->id); |
---|
351 | if(this_elem->authority[0]) |
---|
352 | fprintf(file," AUTHORS %s\n",this_elem->authority); |
---|
353 | if(this_elem->comments) |
---|
354 | fprintf(file,"%s\n",this_elem->comments); |
---|
355 | fprintf(file,"ORIGIN"); |
---|
356 | if(this_elem->tmatrix) |
---|
357 | { |
---|
358 | if(mask == -1) |
---|
359 | { |
---|
360 | for(i=0,k=0;k<this_elem->seqlen+this_elem->offset;k++) |
---|
361 | { |
---|
362 | if(method == SELECT_REGION) |
---|
363 | { |
---|
364 | if(aln->selection_mask[k] == '1') |
---|
365 | { |
---|
366 | if(i%60 == 0) |
---|
367 | fprintf(file,"\n%9d",i+1); |
---|
368 | if(i%10 == 0) |
---|
369 | fprintf(file," "); |
---|
370 | fprintf(file,"%c",this_elem->tmatrix |
---|
371 | [getelem(this_elem,k)]); |
---|
372 | i++; |
---|
373 | } |
---|
374 | } |
---|
375 | else |
---|
376 | { |
---|
377 | if(i%60 == 0) |
---|
378 | fprintf(file,"\n%9d",i+1); |
---|
379 | if(i%10 == 0) |
---|
380 | fprintf(file," "); |
---|
381 | fprintf(file,"%c",this_elem->tmatrix |
---|
382 | [getelem(this_elem,k)]); |
---|
383 | i++; |
---|
384 | } |
---|
385 | } |
---|
386 | } |
---|
387 | else |
---|
388 | { |
---|
389 | for(k=0;k<this_elem->seqlen+this_elem->offset;k++) |
---|
390 | { |
---|
391 | c =(char)getelem(&(aln->element[mask]),k); |
---|
392 | if(c != '0' && c!= '-') |
---|
393 | { |
---|
394 | if(k%60 == 0) |
---|
395 | fprintf(file,"\n%9d",k+1); |
---|
396 | if(k%10 == 0) |
---|
397 | fprintf(file," "); |
---|
398 | fprintf(file,"%c",this_elem->tmatrix |
---|
399 | [getelem(this_elem,k)]); |
---|
400 | } |
---|
401 | } |
---|
402 | } |
---|
403 | } |
---|
404 | else |
---|
405 | { |
---|
406 | if(mask == -1) |
---|
407 | { |
---|
408 | for(i=0,k=0;k<this_elem->seqlen+this_elem->offset;k++) |
---|
409 | { |
---|
410 | if(method == SELECT_REGION) |
---|
411 | { |
---|
412 | if(aln->selection_mask[k] == '1') |
---|
413 | { |
---|
414 | if(i%60 == 0) |
---|
415 | fprintf(file,"\n%9d",i+1); |
---|
416 | if(i%10 == 0) |
---|
417 | fprintf(file," "); |
---|
418 | fprintf(file,"%c", getelem(this_elem,k)); |
---|
419 | i++; |
---|
420 | } |
---|
421 | } |
---|
422 | else |
---|
423 | { |
---|
424 | if(i%60 == 0) |
---|
425 | fprintf(file,"\n%9d",i+1); |
---|
426 | if(i%10 == 0) |
---|
427 | fprintf(file," "); |
---|
428 | fprintf(file,"%c",getelem(this_elem,k)); |
---|
429 | i++; |
---|
430 | } |
---|
431 | } |
---|
432 | } |
---|
433 | else |
---|
434 | { |
---|
435 | for(k=0;k<this_elem->seqlen+this_elem->offset;k++) |
---|
436 | { |
---|
437 | c =(char)getelem(&(aln->element[mask]),k); |
---|
438 | if(c != '0' && c!= '-') |
---|
439 | { |
---|
440 | if(k%60 == 0) |
---|
441 | fprintf(file,"\n%9d",k+1); |
---|
442 | if(k%10 == 0) |
---|
443 | fprintf(file," "); |
---|
444 | fprintf(file,"%c",getelem(this_elem,k)); |
---|
445 | } |
---|
446 | } |
---|
447 | } |
---|
448 | } |
---|
449 | fprintf(file,"\n//\n"); |
---|
450 | } |
---|
451 | } |
---|
452 | fclose(file); |
---|
453 | return(0); |
---|
454 | } |
---|
455 | |
---|
456 | |
---|
457 | void SetTime(void *b) |
---|
458 | { |
---|
459 | ARB_TIME *a=(ARB_TIME*)b; |
---|
460 | struct tm *tim; //*localtime(); |
---|
461 | time_t clock; |
---|
462 | |
---|
463 | clock = time(0); |
---|
464 | tim = localtime(&clock); |
---|
465 | |
---|
466 | a->yy = tim->tm_year; |
---|
467 | a->mm = tim->tm_mon+1; |
---|
468 | a->dd = tim->tm_mday; |
---|
469 | a->hr = tim->tm_hour; |
---|
470 | a->mn = tim->tm_min; |
---|
471 | a->sc = tim->tm_sec; |
---|
472 | return; |
---|
473 | } |
---|
474 | |
---|