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