1 | #include "embl.h" |
---|
2 | #include "genbank.h" |
---|
3 | #include "macke.h" |
---|
4 | #include "wrap.h" |
---|
5 | |
---|
6 | static void embl_continue_line(const char *pattern, char*& Str, Reader& reader) { |
---|
7 | // if there are (numb) blanks at the beginning of line, |
---|
8 | // it is a continue line of the current command. |
---|
9 | int ind; |
---|
10 | char key[TOKENSIZE], temp[LINESIZE]; |
---|
11 | |
---|
12 | // check continue lines |
---|
13 | for (++reader; reader.line(); ++reader) { |
---|
14 | if (has_content(reader.line())) { |
---|
15 | embl_key_word(reader.line(), 0, key); |
---|
16 | if (!str_equal(pattern, key)) break; |
---|
17 | |
---|
18 | // remove end-of-line, if there is any |
---|
19 | ind = Skip_white_space(reader.line(), p_nonkey_start); |
---|
20 | strcpy(temp, reader.line() + ind); |
---|
21 | skip_eolnl_and_append_spaced(Str, temp); |
---|
22 | } |
---|
23 | } |
---|
24 | } |
---|
25 | |
---|
26 | static void embl_one_entry(Reader& reader, char*& entry, const char *key) { |
---|
27 | // Read in one embl entry lines. |
---|
28 | int index = Skip_white_space(reader.line(), p_nonkey_start); |
---|
29 | freedup(entry, reader.line() + index); |
---|
30 | embl_continue_line(key, entry, reader); |
---|
31 | } |
---|
32 | |
---|
33 | static void embl_date(Embl& embl, Reader& reader) { |
---|
34 | // Read in embl DATE lines. |
---|
35 | int index = Skip_white_space(reader.line(), p_nonkey_start); |
---|
36 | freedup(embl.dateu, reader.line() + index); |
---|
37 | |
---|
38 | ++reader; |
---|
39 | |
---|
40 | char key[TOKENSIZE]; |
---|
41 | embl_key_word(reader.line(), 0, key); |
---|
42 | if (str_equal(key, "DT")) { |
---|
43 | index = Skip_white_space(reader.line(), p_nonkey_start); |
---|
44 | freedup(embl.datec, reader.line() + index); |
---|
45 | // skip the rest of DT lines |
---|
46 | do { |
---|
47 | ++reader; |
---|
48 | if (!reader.line()) break; |
---|
49 | embl_key_word(reader.line(), 0, key); |
---|
50 | } |
---|
51 | while (str_equal(key, "DT")); |
---|
52 | } |
---|
53 | else { |
---|
54 | // always expect more than two DT lines |
---|
55 | warning(33, "one DT line is missing"); |
---|
56 | } |
---|
57 | } |
---|
58 | |
---|
59 | static void embl_correct_title(Emblref& ref) { |
---|
60 | // Check missing '"' at the both ends |
---|
61 | |
---|
62 | terminate_with(ref.title, ';'); |
---|
63 | |
---|
64 | int len = str0len(ref.title); |
---|
65 | if (len > 2 && (ref.title[0] != '"' || ref.title[len - 3] != '"')) { |
---|
66 | char *temp = NULL; |
---|
67 | if (ref.title[0] != '"') |
---|
68 | temp = ARB_strdup("\""); |
---|
69 | else |
---|
70 | temp = ARB_strdup(""); |
---|
71 | Append(temp, ref.title); |
---|
72 | if ((len > 2 && ref.title[len - 3] |
---|
73 | != '"')) { |
---|
74 | len = str0len(temp); |
---|
75 | temp[len - 2] = '"'; |
---|
76 | terminate_with(temp, ';'); |
---|
77 | } |
---|
78 | freedup(ref.title, temp); |
---|
79 | free(temp); |
---|
80 | } |
---|
81 | } |
---|
82 | |
---|
83 | int comment_subkey(const char *line, char *key) { |
---|
84 | // Get the subkey-word (including delimiting ':') from a comment line |
---|
85 | int len = parse_key_word(line, key, ":\t\n("); |
---|
86 | if (!len) return 0; |
---|
87 | |
---|
88 | if (line[len] == ':') { |
---|
89 | key[len] = ':'; |
---|
90 | key[len+1] = 0; |
---|
91 | } |
---|
92 | return len+1; |
---|
93 | } |
---|
94 | |
---|
95 | inline bool is_embl_comment(const char *line) { return line && line[0] == 'C' && line[1] == 'C'; } |
---|
96 | |
---|
97 | static void embl_one_comment_entry(char*& datastring, int start_index, Reader& reader) { |
---|
98 | // Read in one embl sub-entry in comments lines. |
---|
99 | // If it's not a RDP defined comment, you should not call this function. |
---|
100 | |
---|
101 | int index = Skip_white_space(reader.line(), start_index); |
---|
102 | freedup(datastring, reader.line() + index); |
---|
103 | |
---|
104 | const int expectedIndent = RDP_CONTINUED_INDENT+RDP_SUBKEY_INDENT; |
---|
105 | |
---|
106 | for (++reader; |
---|
107 | is_embl_comment(reader.line()) && count_spaces(reader.line() + 2) >= expectedIndent; |
---|
108 | ++reader) |
---|
109 | { |
---|
110 | index = Skip_white_space(reader.line(), p_nonkey_start + expectedIndent); |
---|
111 | |
---|
112 | char temp[LINESIZE]; |
---|
113 | strcpy(temp, reader.line() + index); |
---|
114 | skip_eolnl_and_append_spaced(datastring, temp); |
---|
115 | } |
---|
116 | } |
---|
117 | |
---|
118 | static void embl_comments(Embl& embl, Reader& reader) { |
---|
119 | // Read in embl comment lines. |
---|
120 | |
---|
121 | for (; is_embl_comment(reader.line());) { |
---|
122 | char key[TOKENSIZE]; |
---|
123 | int index = Skip_white_space(reader.line(), 5); |
---|
124 | int offset = comment_subkey(reader.line() + index, key); |
---|
125 | index = Skip_white_space(reader.line(), index + offset); |
---|
126 | |
---|
127 | RDP_comment_parser one_comment_entry = embl_one_comment_entry; |
---|
128 | RDP_comments& comments = embl.comments; |
---|
129 | |
---|
130 | if (!parse_RDP_comment(comments, one_comment_entry, key, index, reader)) { |
---|
131 | // other comments |
---|
132 | Append(comments.others, reader.line() + 5); |
---|
133 | ++reader; |
---|
134 | } |
---|
135 | } |
---|
136 | } |
---|
137 | |
---|
138 | static void embl_skip_unidentified(const char *pattern, Reader& reader) { |
---|
139 | // if there are (numb) blanks at the beginning of line, |
---|
140 | // it is a continue line of the current command. |
---|
141 | |
---|
142 | for (++reader; reader.line(); ++reader) { |
---|
143 | char key[TOKENSIZE]; |
---|
144 | embl_key_word(reader.line(), 0, key); |
---|
145 | if (!str_equal(key, pattern)) break; |
---|
146 | } |
---|
147 | } |
---|
148 | |
---|
149 | void EmblParser::parse_section() { |
---|
150 | char key[TOKENSIZE]; |
---|
151 | embl_key_word(reader.line(), 0, key); |
---|
152 | state = ENTRY_STARTED; |
---|
153 | parse_keyed_section(key); |
---|
154 | } |
---|
155 | |
---|
156 | static void embl_origin(Seq& seq, Reader& reader) { |
---|
157 | // Read in embl sequence data. |
---|
158 | ca_assert(seq.is_empty()); |
---|
159 | |
---|
160 | // read in whole sequence data |
---|
161 | for (++reader; |
---|
162 | reader.line() && !is_sequence_terminator(reader.line()); |
---|
163 | ++reader |
---|
164 | ) |
---|
165 | { |
---|
166 | const char *line = reader.line(); |
---|
167 | for (int idx = 5; line[idx]; ++idx) { |
---|
168 | char ch = line[idx]; |
---|
169 | if (ch == ' ' || ch == '\n') continue; |
---|
170 | if (idx>70) continue; |
---|
171 | seq.add(ch); |
---|
172 | } |
---|
173 | } |
---|
174 | } |
---|
175 | |
---|
176 | void EmblParser::parse_keyed_section(const char *key) { |
---|
177 | if (str_equal(key, "ID")) { |
---|
178 | embl_one_entry(reader, embl.ID, key); |
---|
179 | } |
---|
180 | else if (str_equal(key, "DT")) { |
---|
181 | embl_date(embl, reader); |
---|
182 | } |
---|
183 | else if (str_equal(key, "DE")) { |
---|
184 | embl_one_entry(reader, embl.description, key); |
---|
185 | } |
---|
186 | else if (str_equal(key, "OS")) { |
---|
187 | embl_one_entry(reader, embl.os, key); |
---|
188 | } |
---|
189 | else if (str_equal(key, "AC")) { |
---|
190 | embl_one_entry(reader, embl.accession, key); |
---|
191 | } |
---|
192 | else if (str_equal(key, "KW")) { |
---|
193 | embl_one_entry(reader, embl.keywords, key); |
---|
194 | |
---|
195 | // correct missing '.' |
---|
196 | if (!has_content(embl.keywords)) freedup(embl.keywords, ".\n"); |
---|
197 | else terminate_with(embl.keywords, '.'); |
---|
198 | } |
---|
199 | else if (str_equal(key, "DR")) { |
---|
200 | embl_one_entry(reader, embl.dr, key); |
---|
201 | } |
---|
202 | else if (str_equal(key, "RA")) { |
---|
203 | Emblref& ref = embl.get_latest_ref(); |
---|
204 | embl_one_entry(reader, ref.author, key); |
---|
205 | terminate_with(ref.author, ';'); |
---|
206 | } |
---|
207 | else if (str_equal(key, "RT")) { |
---|
208 | Emblref& ref = embl.get_latest_ref(); |
---|
209 | embl_one_entry(reader, ref.title, key); |
---|
210 | embl_correct_title(ref); |
---|
211 | } |
---|
212 | else if (str_equal(key, "RL")) { |
---|
213 | Emblref& ref = embl.get_latest_ref(); |
---|
214 | embl_one_entry(reader, ref.journal, key); |
---|
215 | terminate_with(ref.journal, '.'); |
---|
216 | } |
---|
217 | else if (str_equal(key, "RP")) { |
---|
218 | Emblref& ref = embl.get_latest_ref(); |
---|
219 | embl_one_entry(reader, ref.processing, key); |
---|
220 | } |
---|
221 | else if (str_equal(key, "RN")) { |
---|
222 | embl.resize_refs(embl.get_refcount()+1); |
---|
223 | ++reader; |
---|
224 | } |
---|
225 | else if (str_equal(key, "CC")) { |
---|
226 | embl_comments(embl, reader); |
---|
227 | } |
---|
228 | else if (str_equal(key, "SQ")) { |
---|
229 | embl_origin(seq, reader); |
---|
230 | state = ENTRY_COMPLETED; |
---|
231 | } |
---|
232 | else { |
---|
233 | embl_skip_unidentified(key, reader); |
---|
234 | } |
---|
235 | } |
---|
236 | |
---|
237 | void embl_key_word(const char *line, int index, char *key) { |
---|
238 | parse_key_word(line+index, key, " \t\n"); |
---|
239 | } |
---|
240 | |
---|
241 | static void embl_print_lines(Writer& write, const char *key, const char *content, const WrapMode& wrapMode) { |
---|
242 | // Print EMBL entry and wrap around if line over EMBLMAXLINE. |
---|
243 | ca_assert(strlen(key) == 2); |
---|
244 | |
---|
245 | char prefix[TOKENSIZE]; |
---|
246 | sprintf(prefix, "%-*s", EMBLINDENT, key); |
---|
247 | |
---|
248 | wrapMode.print(write, prefix, prefix, content, EMBLMAXLINE); |
---|
249 | } |
---|
250 | |
---|
251 | static bool embl_print_lines_if_content(Writer& write, const char *key, const char *content, const WrapMode& wrapMode, bool followed_by_spacer) { |
---|
252 | if (has_content(content)) { |
---|
253 | embl_print_lines(write, key, content, wrapMode); |
---|
254 | if (followed_by_spacer) write.out("XX\n"); |
---|
255 | return true; |
---|
256 | } |
---|
257 | return false; |
---|
258 | } |
---|
259 | |
---|
260 | static void embl_print_comment_if_content(Writer& write, const char *key, const char *content) { |
---|
261 | // Print one embl comment line, wrap around |
---|
262 | |
---|
263 | if (!has_content(content)) return; |
---|
264 | |
---|
265 | char first[LINESIZE]; sprintf(first, "CC%*s%s", (EMBLINDENT-2)+RDP_SUBKEY_INDENT, "", key); |
---|
266 | char other[LINESIZE]; sprintf(other, "CC%*s", (EMBLINDENT-2)+RDP_SUBKEY_INDENT+RDP_CONTINUED_INDENT, ""); |
---|
267 | WrapMode(true).print(write, first, other, content, EMBLMAXLINE); |
---|
268 | } |
---|
269 | |
---|
270 | inline void embl_print_completeness(Writer& write, char compX, char X) { |
---|
271 | if (compX == ' ') return; |
---|
272 | ca_assert(compX == 'y' || compX == 'n'); |
---|
273 | write.outf("CC %c' end complete: %s\n", X, compX == 'y' ? "Yes" : "No"); |
---|
274 | } |
---|
275 | |
---|
276 | static void embl_out_comments(const Embl& embl, const Seq& seq, Writer& write) { |
---|
277 | // Print out the comments part of EMBL format. |
---|
278 | |
---|
279 | const OrgInfo& orginf = embl.comments.orginf; |
---|
280 | if (orginf.exists()) { |
---|
281 | write.out("CC Organism information\n"); |
---|
282 | |
---|
283 | embl_print_comment_if_content(write, "Source of strain: ", orginf.source); |
---|
284 | embl_print_comment_if_content(write, "Culture collection: ", orginf.cultcoll); |
---|
285 | embl_print_comment_if_content(write, "Former name: ", orginf.formname); |
---|
286 | embl_print_comment_if_content(write, "Alternate name: ", orginf.nickname); |
---|
287 | embl_print_comment_if_content(write, "Common name: ", orginf.commname); |
---|
288 | embl_print_comment_if_content(write, "Host organism: ", orginf.hostorg); |
---|
289 | } |
---|
290 | |
---|
291 | const SeqInfo& seqinf = embl.comments.seqinf; |
---|
292 | if (seqinf.exists()) { |
---|
293 | write.outf("CC Sequence information (bases 1 to %d)\n", seq.get_len()); |
---|
294 | |
---|
295 | embl_print_comment_if_content(write, "RDP ID: ", seqinf.RDPid); |
---|
296 | embl_print_comment_if_content(write, "Corresponding GenBank entry: ", seqinf.gbkentry); |
---|
297 | embl_print_comment_if_content(write, "Sequencing methods: ", seqinf.methods); |
---|
298 | |
---|
299 | embl_print_completeness(write, seqinf.comp5, '5'); |
---|
300 | embl_print_completeness(write, seqinf.comp3, '3'); |
---|
301 | } |
---|
302 | |
---|
303 | embl_print_lines_if_content(write, "CC", embl.comments.others, WrapMode("\n"), true); |
---|
304 | } |
---|
305 | |
---|
306 | static void embl_out_origin(const Seq& seq, Writer& write) { |
---|
307 | // Print out the sequence data of EMBL format. |
---|
308 | BaseCounts bases; |
---|
309 | seq.count(bases); |
---|
310 | write.outf("SQ Sequence %d BP; %d A; %d C; %d G; %d T; %d other;\n", |
---|
311 | seq.get_len(), bases.a, bases.c, bases.g, bases.t, bases.other); |
---|
312 | |
---|
313 | seq.out(write, EMBL); |
---|
314 | } |
---|
315 | |
---|
316 | void embl_out_header(const Embl& embl, const Seq& seq, Writer& write) { |
---|
317 | WrapMode wrapWords(true); |
---|
318 | WrapMode neverWrap(false); |
---|
319 | |
---|
320 | embl_print_lines_if_content(write, "ID", embl.ID, neverWrap, true); |
---|
321 | embl_print_lines_if_content(write, "AC", embl.accession, wrapWords, true); |
---|
322 | |
---|
323 | { |
---|
324 | bool dt1 = embl_print_lines_if_content(write, "DT", embl.dateu, neverWrap, false); |
---|
325 | bool dt2 = embl_print_lines_if_content(write, "DT", embl.datec, neverWrap, false); |
---|
326 | if (dt1 || dt2) write.out("XX\n"); |
---|
327 | } |
---|
328 | |
---|
329 | embl_print_lines_if_content(write, "DE", embl.description, wrapWords, true); |
---|
330 | embl_print_lines_if_content(write, "KW", embl.keywords, WrapMode(";"), true); |
---|
331 | |
---|
332 | if (has_content(embl.os)) { |
---|
333 | embl_print_lines(write, "OS", embl.os, wrapWords); |
---|
334 | write.out("OC No information.\n"); |
---|
335 | write.out("XX\n"); |
---|
336 | } |
---|
337 | |
---|
338 | // GenbankRef |
---|
339 | for (int indi = 0; indi < embl.get_refcount(); indi++) { |
---|
340 | const Emblref& ref = embl.get_ref(indi); |
---|
341 | |
---|
342 | write.outf("RN [%d]\n", indi + 1); |
---|
343 | embl_print_lines_if_content(write, "RP", ref.processing, neverWrap, false); |
---|
344 | embl_print_lines_if_content(write, "RA", ref.author, WrapMode(","), false); |
---|
345 | |
---|
346 | if (has_content(ref.title)) embl_print_lines(write, "RT", ref.title, wrapWords); |
---|
347 | else write.out("RT ;\n"); |
---|
348 | |
---|
349 | embl_print_lines_if_content(write, "RL", ref.journal, wrapWords, false); |
---|
350 | write.out("XX\n"); |
---|
351 | } |
---|
352 | |
---|
353 | if (has_content(embl.dr)) { |
---|
354 | embl_print_lines(write, "DR", embl.dr, wrapWords); |
---|
355 | write.out("XX\n"); |
---|
356 | } |
---|
357 | |
---|
358 | embl_out_comments(embl, seq, write); |
---|
359 | } |
---|
360 | |
---|
361 | void embl_out(const Embl& embl, const Seq& seq, Writer& write) { |
---|
362 | // Output EMBL data. |
---|
363 | embl_out_header(embl, seq, write); |
---|
364 | embl_out_origin(seq, write); |
---|
365 | } |
---|
366 | |
---|
367 | static char *etog_author(char *Str) { |
---|
368 | // Convert EMBL author format to Genbank author format. |
---|
369 | int indi, indk, len, index; |
---|
370 | char token[TOKENSIZE], *author; |
---|
371 | |
---|
372 | author = ARB_strdup(""); |
---|
373 | for (indi = index = 0, len = str0len(Str) - 1; indi < len; indi++, index++) { |
---|
374 | if (Str[indi] == ',' || Str[indi] == ';') { |
---|
375 | token[index--] = '\0'; |
---|
376 | if (has_content(author)) { |
---|
377 | Append(author, (Str[indi] == ',') ? "," : " and"); |
---|
378 | } |
---|
379 | // search backward to find the first blank and replace the blank by ',' |
---|
380 | for (indk = 0; index > 0 && indk == 0; index--) |
---|
381 | if (token[index] == ' ') { |
---|
382 | token[index] = ','; |
---|
383 | indk = 1; |
---|
384 | } |
---|
385 | Append(author, token); |
---|
386 | index = (-1); |
---|
387 | } |
---|
388 | else |
---|
389 | token[index] = Str[indi]; |
---|
390 | } |
---|
391 | Append(author, "\n"); |
---|
392 | return (author); |
---|
393 | } |
---|
394 | static char *etog_journal(const char *eJournal) { |
---|
395 | // Convert journal part from EMBL to GenBank format. |
---|
396 | char *new_journal = 0; |
---|
397 | char token[TOKENSIZE]; |
---|
398 | |
---|
399 | scan_token_or_die(token, eJournal); |
---|
400 | if (str_equal(token, "(in)") == 1 || str_equal(token, "Submitted") || str_equal(token, "Unpublished")) { |
---|
401 | // remove trailing '.' |
---|
402 | int len = str0len(eJournal); |
---|
403 | ca_assert(eJournal[len-2] == '.'); |
---|
404 | new_journal = strndup(eJournal, len-2); |
---|
405 | Append(new_journal, "\n"); |
---|
406 | } |
---|
407 | else { |
---|
408 | const char *colon = strchr(eJournal, ':'); |
---|
409 | |
---|
410 | if (colon) { |
---|
411 | const char *p1 = strchr(colon+1, '('); |
---|
412 | if (p1) { |
---|
413 | const char *p2 = strchr(p1+1, ')'); |
---|
414 | if (p2 && strcmp(p2+1, ".\n") == 0) { |
---|
415 | ARB_realloc(new_journal, str0len(eJournal)+1+1); |
---|
416 | |
---|
417 | int l1 = colon-eJournal; |
---|
418 | int l2 = p1-colon-1; |
---|
419 | int l3 = p2-p1+1; |
---|
420 | |
---|
421 | char *pos = new_journal; |
---|
422 | |
---|
423 | memcpy(pos, eJournal, l1); pos += l1; |
---|
424 | memcpy(pos, ", ", 2); pos += 2; |
---|
425 | memcpy(pos, colon+1, l2); pos += l2; |
---|
426 | memcpy(pos, " ", 1); pos += 1; |
---|
427 | memcpy(pos, p1, l3); pos += l3; |
---|
428 | memcpy(pos, "\n", 2); |
---|
429 | } |
---|
430 | } |
---|
431 | } |
---|
432 | |
---|
433 | if (!new_journal) { |
---|
434 | warningf(148, "Removed unknown journal format: %s", eJournal); |
---|
435 | new_journal = no_content(); |
---|
436 | } |
---|
437 | } |
---|
438 | |
---|
439 | return new_journal; |
---|
440 | } |
---|
441 | static void etog_convert_references(const Embl& embl, GenBank& gbk) { |
---|
442 | // Convert reference from EMBL to GenBank format. |
---|
443 | int indi, len, start, end; |
---|
444 | char temp[LONGTEXT]; |
---|
445 | |
---|
446 | gbk.resize_refs(embl.get_refcount()); |
---|
447 | |
---|
448 | for (indi = 0; indi < embl.get_refcount(); indi++) { |
---|
449 | const Emblref& ref = embl.get_ref(indi); |
---|
450 | GenbankRef& gref = gbk.get_ref(indi); |
---|
451 | |
---|
452 | if (has_content(ref.processing) && |
---|
453 | sscanf(ref.processing, "%d %d", &start, &end) == 2) |
---|
454 | { |
---|
455 | end *= -1; // will get negative from sscanf |
---|
456 | sprintf(temp, "%d (bases %d to %d)\n", (indi + 1), start, end); |
---|
457 | } |
---|
458 | else { |
---|
459 | sprintf(temp, "%d\n", (indi + 1)); |
---|
460 | } |
---|
461 | |
---|
462 | freedup(gref.ref, temp); |
---|
463 | |
---|
464 | if (has_content(ref.title) && ref.title[0] != ';') { |
---|
465 | // remove '"' and ';', if there is any |
---|
466 | len = str0len(ref.title); |
---|
467 | if (len > 2 && ref.title[0] == '"' && ref.title[len - 2] == ';' && ref.title[len - 3] == '"') { |
---|
468 | ref.title[len - 3] = '\n'; |
---|
469 | ref.title[len - 2] = '\0'; |
---|
470 | freedup(gref.title, ref.title+1); |
---|
471 | ref.title[len - 3] = '"'; |
---|
472 | ref.title[len - 2] = ';'; |
---|
473 | } |
---|
474 | else { |
---|
475 | freedup(gref.title, ref.title); |
---|
476 | } |
---|
477 | } |
---|
478 | else { |
---|
479 | freeset(gref.title, no_content()); |
---|
480 | } |
---|
481 | |
---|
482 | freeset(gref.author, has_content(ref.author) ? etog_author(ref.author) : no_content()); |
---|
483 | freeset(gref.journal, has_content(ref.journal) ? etog_journal(ref.journal) : no_content()); |
---|
484 | |
---|
485 | freeset(gref.standard, no_content()); |
---|
486 | } |
---|
487 | } |
---|
488 | |
---|
489 | int etog(const Embl& embl, GenBank& gbk, const Seq& seq) { // __ATTR__USERESULT |
---|
490 | // Convert from embl to genbank format. |
---|
491 | int indi; |
---|
492 | char key[TOKENSIZE], temp[LONGTEXT]; |
---|
493 | char t1[TOKENSIZE], t2[TOKENSIZE], t3[TOKENSIZE]; |
---|
494 | |
---|
495 | embl_key_word(embl.ID, 0, key); |
---|
496 | if (has_content(embl.dr)) { |
---|
497 | // get short_id from DR line if there is RDP def. |
---|
498 | strcpy(t3, "dummy"); |
---|
499 | ASSERT_RESULT(int, 3, sscanf(embl.dr, "%s %s %s", t1, t2, t3)); |
---|
500 | if (str_equal(t1, "RDP;")) { |
---|
501 | if (!str_equal(t3, "dummy")) { |
---|
502 | strcpy(key, t3); |
---|
503 | } |
---|
504 | else |
---|
505 | strcpy(key, t2); |
---|
506 | key[str0len(key) - 1] = '\0'; // remove '.' |
---|
507 | } |
---|
508 | } |
---|
509 | strcpy(temp, key); |
---|
510 | |
---|
511 | // LOCUS |
---|
512 | for (indi = str0len(temp); indi < 13; temp[indi++] = ' ') {} |
---|
513 | { |
---|
514 | const char *date = has_content(embl.dateu) ? embl.dateu : today_date(); |
---|
515 | sprintf((temp + 10), "%7d bp RNA RNA %s\n", |
---|
516 | seq.get_len(), |
---|
517 | genbank_date(date)); |
---|
518 | } |
---|
519 | freedup(gbk.locus, temp); |
---|
520 | |
---|
521 | // DEFINITION |
---|
522 | if (copy_content(gbk.definition, embl.description)) terminate_with(gbk.definition, '.'); |
---|
523 | |
---|
524 | // SOURCE and DEFINITION if not yet defined |
---|
525 | if (copy_content(gbk.source, embl.os)) { |
---|
526 | freedup(gbk.organism, embl.os); |
---|
527 | if (!has_content(embl.description)) { |
---|
528 | freedup(gbk.definition, embl.os); |
---|
529 | } |
---|
530 | } |
---|
531 | |
---|
532 | // COMMENT GenBank entry |
---|
533 | copy_content(gbk.accession, embl.accession); |
---|
534 | if (has_content(embl.keywords) && embl.keywords[0] != '.') { |
---|
535 | freedup(gbk.keywords, embl.keywords); |
---|
536 | } |
---|
537 | |
---|
538 | etog_convert_references(embl, gbk); |
---|
539 | gbk.comments.set_content_from(embl.comments); |
---|
540 | |
---|
541 | return (1); |
---|
542 | } |
---|
543 | |
---|
544 | int etom(const Embl& embl, Macke& macke, const Seq& seq) { // __ATTR__USERESULT |
---|
545 | // Convert from embl format to Macke format. |
---|
546 | GenBank gbk; |
---|
547 | return etog(embl, gbk, seq) && gtom(gbk, macke); |
---|
548 | } |
---|
549 | |
---|
550 | // -------------------------------------------------------------------------------- |
---|
551 | |
---|
552 | #ifdef UNIT_TESTS |
---|
553 | #include <test_unit.h> |
---|
554 | |
---|
555 | #define TEST_EXPECT_ETOG_JOURNAL_PARSES(i,o) \ |
---|
556 | do { \ |
---|
557 | char *dup = ARB_strdup(i); \ |
---|
558 | char *res = etog_journal(dup); \ |
---|
559 | TEST_EXPECT_EQUAL(res, o); \ |
---|
560 | free(res); \ |
---|
561 | free(dup); \ |
---|
562 | } while (0) |
---|
563 | |
---|
564 | void TEST_BASIC_etog_journal() { |
---|
565 | // behavior documented in r6943: |
---|
566 | TEST_EXPECT_ETOG_JOURNAL_PARSES("Gene 134:283-287(1993).\n", |
---|
567 | "Gene 134, 283-287 (1993)\n"); |
---|
568 | TEST_EXPECT_ETOG_JOURNAL_PARSES("J. Exp. Med. 179:1809-1821(1994).\n", |
---|
569 | "J. Exp. Med. 179, 1809-1821 (1994)\n"); |
---|
570 | TEST_EXPECT_ETOG_JOURNAL_PARSES("Unpublished whatever.\n", |
---|
571 | "Unpublished whatever\n"); |
---|
572 | TEST_EXPECT_ETOG_JOURNAL_PARSES("bla bla bla.\n", |
---|
573 | "\n"); // skips if can't parse |
---|
574 | TEST_EXPECT_ETOG_JOURNAL_PARSES("bla bla bla\n", |
---|
575 | "\n"); |
---|
576 | } |
---|
577 | |
---|
578 | #endif // UNIT_TESTS |
---|
579 | |
---|
580 | static char *gtoe_author(char *author) { |
---|
581 | // Convert GenBank author to EMBL author. |
---|
582 | int indi, len, index, odd; |
---|
583 | char *auth, *Str; |
---|
584 | |
---|
585 | // replace " and " by ", " |
---|
586 | auth = nulldup(author); |
---|
587 | if ((index = find_pattern(auth, " and ")) > 0) { |
---|
588 | auth[index] = '\0'; |
---|
589 | Str = nulldup(auth); |
---|
590 | auth[index] = ' '; // remove '\0' for free space later |
---|
591 | Append(Str, ","); |
---|
592 | Append(Str, auth + index + 4); |
---|
593 | } |
---|
594 | else |
---|
595 | Str = nulldup(author); |
---|
596 | |
---|
597 | for (indi = 0, len = str0len(Str), odd = 1; indi < len; indi++) { |
---|
598 | if (Str[indi] == ',') { |
---|
599 | if (odd) { |
---|
600 | Str[indi] = ' '; |
---|
601 | odd = 0; |
---|
602 | } |
---|
603 | else { |
---|
604 | odd = 1; |
---|
605 | } |
---|
606 | } |
---|
607 | } |
---|
608 | |
---|
609 | freenull(auth); |
---|
610 | return (Str); |
---|
611 | } |
---|
612 | static char *gtoe_journal(char *Str) { |
---|
613 | // Convert GenBank journal to EMBL journal. |
---|
614 | char token[TOKENSIZE], *journal; |
---|
615 | int indi, indj, index, len; |
---|
616 | |
---|
617 | if (scan_token(token, Str)) { |
---|
618 | if (str_equal(token, "(in)") == 1 || str_equal(token, "Unpublished") || str_equal(token, "Submitted")) { |
---|
619 | journal = nulldup(Str); |
---|
620 | terminate_with(journal, '.'); |
---|
621 | return (journal); |
---|
622 | } |
---|
623 | } |
---|
624 | |
---|
625 | journal = nulldup(Str); |
---|
626 | for (indi = indj = index = 0, len = str0len(journal); indi < len; indi++, indj++) { |
---|
627 | if (journal[indi] == ',') { |
---|
628 | journal[indi] = ':'; |
---|
629 | indi++; // skip blank after ',' |
---|
630 | index = 1; |
---|
631 | } |
---|
632 | else if (journal[indi] == ' ' && index) { |
---|
633 | indj--; |
---|
634 | } |
---|
635 | else |
---|
636 | journal[indj] = journal[indi]; |
---|
637 | } |
---|
638 | |
---|
639 | journal[indj] = '\0'; |
---|
640 | terminate_with(journal, '.'); |
---|
641 | return (journal); |
---|
642 | } |
---|
643 | static void gtoe_reference(const GenBank& gbk, Embl& embl) { |
---|
644 | // Convert references from GenBank to EMBL. |
---|
645 | if (gbk.has_refs()) { |
---|
646 | embl.resize_refs(gbk.get_refcount()); |
---|
647 | } |
---|
648 | |
---|
649 | for (int indi = 0; indi < gbk.get_refcount(); indi++) { |
---|
650 | Emblref& ref = embl.get_ref(indi); |
---|
651 | const GenbankRef& gref = gbk.get_ref(indi); |
---|
652 | |
---|
653 | freedup(ref.title, gref.title); |
---|
654 | embl_correct_title(ref); |
---|
655 | |
---|
656 | freeset(ref.journal, gtoe_journal(gref.journal)); |
---|
657 | terminate_with(ref.journal, '.'); |
---|
658 | |
---|
659 | freeset(ref.author, gtoe_author(gref.author)); |
---|
660 | terminate_with(ref.author, ';'); |
---|
661 | |
---|
662 | // create processing information |
---|
663 | int refnum, start = 0, end = 0; |
---|
664 | char t1[TOKENSIZE], t2[TOKENSIZE], t3[TOKENSIZE]; |
---|
665 | |
---|
666 | if (!gref.ref || sscanf(gref.ref, "%d %s %d %s %d %s", &refnum, t1, &start, t2, &end, t3) != 6) { |
---|
667 | start = 0; |
---|
668 | end = 0; |
---|
669 | } |
---|
670 | |
---|
671 | freenull(ref.processing); |
---|
672 | if (start || end) ref.processing = strf("%d-%d\n", start, end); |
---|
673 | else ref.processing = no_content(); |
---|
674 | |
---|
675 | } |
---|
676 | } |
---|
677 | |
---|
678 | int gtoe(const GenBank& gbk, Embl& embl, const Seq& seq) { // __ATTR__USERESULT |
---|
679 | // Genbank to EMBL. |
---|
680 | { |
---|
681 | char temp[LONGTEXT]; |
---|
682 | strcpy(temp, gbk.get_id()); |
---|
683 | |
---|
684 | upcase(temp); // Adjust short-id, EMBL short_id always upper case |
---|
685 | for (int indi = min(str0len(temp), 9); indi < 10; indi++) |
---|
686 | temp[indi] = ' '; |
---|
687 | |
---|
688 | sprintf(temp + 10, "preliminary; RNA; UNA; %d BP.\n", seq.get_len()); |
---|
689 | freedup(embl.ID, temp); |
---|
690 | } |
---|
691 | |
---|
692 | // accession number |
---|
693 | if (has_content(gbk.accession)) |
---|
694 | // take just the accession num, no version num. |
---|
695 | freedup(embl.accession, gbk.accession); |
---|
696 | |
---|
697 | // date |
---|
698 | { |
---|
699 | char *date = gbk.get_date(); |
---|
700 | |
---|
701 | freeset(embl.dateu, strf("%s (Rel. 1, Last updated, Version 1)\n", date)); |
---|
702 | freeset(embl.datec, strf("%s (Rel. 1, Created)\n", date)); |
---|
703 | |
---|
704 | free(date); |
---|
705 | } |
---|
706 | |
---|
707 | // description |
---|
708 | copy_content(embl.description, gbk.definition); |
---|
709 | // EMBL KW line |
---|
710 | if (copy_content(embl.keywords, gbk.keywords)) { |
---|
711 | terminate_with(embl.keywords, '.'); |
---|
712 | } |
---|
713 | else { |
---|
714 | freedup(embl.keywords, ".\n"); |
---|
715 | } |
---|
716 | |
---|
717 | copy_content(embl.os, gbk.organism); // EMBL OS line |
---|
718 | // reference |
---|
719 | gtoe_reference(gbk, embl); |
---|
720 | |
---|
721 | // EMBL DR line |
---|
722 | { |
---|
723 | char token[TOKENSIZE]; |
---|
724 | char temp[LONGTEXT]; |
---|
725 | |
---|
726 | scan_token_or_die(token, gbk.locus); // short_id |
---|
727 | if (has_content(gbk.comments.seqinf.RDPid)) { |
---|
728 | char rdpid[TOKENSIZE]; |
---|
729 | scan_token_or_die(rdpid, gbk.comments.seqinf.RDPid); |
---|
730 | sprintf(temp, "RDP; %s; %s.\n", rdpid, token); |
---|
731 | } |
---|
732 | else { |
---|
733 | sprintf(temp, "RDP; %s.\n", token); |
---|
734 | } |
---|
735 | freedup(embl.dr, temp); |
---|
736 | } |
---|
737 | embl.comments.set_content_from(gbk.comments); |
---|
738 | |
---|
739 | return (1); |
---|
740 | } |
---|
741 | |
---|
742 | static int partial_mtoe(const Macke& macke, Embl& embl) { |
---|
743 | // Handle subspecies information when converting from Macke to EMBL. |
---|
744 | char*& others = embl.comments.others; |
---|
745 | |
---|
746 | if (has_content(macke.strain)) { |
---|
747 | int ridx = skip_pattern(others, "*source:"); |
---|
748 | bool have_strain = ridx >= 0 && stristr(others+ridx, "strain="); |
---|
749 | |
---|
750 | if (!have_strain) { |
---|
751 | if (!has_content(others)) freenull(others); |
---|
752 | Append(others, "*source: strain="); |
---|
753 | Append(others, macke.strain); |
---|
754 | if (!is_end_mark(others[str0len(others) - 2])) skip_eolnl_and_append(others, ";\n"); |
---|
755 | } |
---|
756 | } |
---|
757 | |
---|
758 | if (has_content(macke.subspecies)) { |
---|
759 | int ridx = skip_pattern(others, "*source:"); |
---|
760 | bool have_subsp = ridx >= 0 && find_subspecies(others+ridx, '=') >= 0; |
---|
761 | |
---|
762 | if (!have_subsp) { |
---|
763 | if (!has_content(others)) freenull(others); |
---|
764 | Append(others, "*source: subspecies="); |
---|
765 | Append(others, macke.subspecies); |
---|
766 | if (!is_end_mark(others[str0len(others) - 2])) skip_eolnl_and_append(others, ";\n"); |
---|
767 | } |
---|
768 | } |
---|
769 | |
---|
770 | return (1); |
---|
771 | } |
---|
772 | |
---|
773 | int mtoe(const Macke& macke, Embl& embl, const Seq& seq) { // __ATTR__USERESULT |
---|
774 | GenBank gbk; |
---|
775 | return mtog(macke, gbk, seq) && gtoe(gbk, embl, seq) && partial_mtoe(macke, embl); |
---|
776 | } |
---|
777 | |
---|
778 | bool EmblSwissprotReader::read_one_entry(Seq& seq) { |
---|
779 | data.reinit(); |
---|
780 | if (!EmblParser(data, seq, *this).parse_entry()) abort(); |
---|
781 | return ok(); |
---|
782 | } |
---|