1 | /* |
---|
2 | * Definition of all objects belonging to this version of |
---|
3 | * the valid names text file |
---|
4 | * |
---|
5 | * 29. November 2002 |
---|
6 | * |
---|
7 | * coded by Lothar Richter |
---|
8 | * |
---|
9 | * Copyright (C) 2002 Department of Microbiology (Technical University Munich) |
---|
10 | */ |
---|
11 | |
---|
12 | #if defined(DEVEL_LOTHAR) |
---|
13 | #define DUMP |
---|
14 | #endif // DEVEL_LOTHAR |
---|
15 | |
---|
16 | #include "NT_validNameParser.h" |
---|
17 | #include "NT_local.h" |
---|
18 | |
---|
19 | #include <cstdlib> |
---|
20 | #include <cstdlib> |
---|
21 | #include <iostream> |
---|
22 | #include <fstream> |
---|
23 | |
---|
24 | using namespace std; |
---|
25 | |
---|
26 | namespace validNames { |
---|
27 | |
---|
28 | |
---|
29 | TokLPtr tokenize(const std::string& description, TokLPtr tokenLP) { |
---|
30 | size_t tokenEnd = 0; |
---|
31 | size_t tokenBegin = 0; |
---|
32 | |
---|
33 | while (tokenEnd != description.size()) { // CC : warning: comparison between signed and unsigned (tokenEnd sollte nicht 'int' sondern 'unsigned' sein) |
---|
34 | tokenEnd = description.find_first_of(' ', tokenBegin); |
---|
35 | if (tokenEnd == string::npos) tokenEnd = description.size(); |
---|
36 | int tokLength = tokenEnd - tokenBegin; |
---|
37 | if (tokLength != 0) { |
---|
38 | tokenLP->push_back(description.substr(tokenBegin, tokenEnd - tokenBegin)); |
---|
39 | } |
---|
40 | tokenBegin = tokenEnd + 1; |
---|
41 | |
---|
42 | } |
---|
43 | return tokenLP; |
---|
44 | } |
---|
45 | |
---|
46 | |
---|
47 | |
---|
48 | |
---|
49 | |
---|
50 | Desco determineType(const string& descriptionString) |
---|
51 | { // begin determineType |
---|
52 | |
---|
53 | DESCT actType = NOTYPE; |
---|
54 | TokLPtr tokenLP = new TokL; |
---|
55 | tokenLP = tokenize(descriptionString, tokenLP); |
---|
56 | // remove all tokens in parentheses |
---|
57 | { |
---|
58 | TokL::iterator it = tokenLP->begin(); |
---|
59 | while (it != tokenLP->end()) { |
---|
60 | if (((*it).at(0) == '(') && *it != string("(corrig.)")) it = tokenLP->erase(it); |
---|
61 | else ++it; |
---|
62 | } |
---|
63 | } |
---|
64 | |
---|
65 | // check first word for upper case letters |
---|
66 | string descNames[6]; // first the valid genus, species, subsp. then the other names |
---|
67 | // stores occurrence of subsp. which is needed to retrieve the right tokens later on and status flags |
---|
68 | int sspPos[2] = { 0, 0 }; // token subsp. occurs maximum twice |
---|
69 | int ssp = 0; |
---|
70 | bool isValid = true; |
---|
71 | bool isRenamed = false; |
---|
72 | bool isHetero = false; |
---|
73 | bool isHomo = false; |
---|
74 | bool isGenus = false; |
---|
75 | // bool isSee = false; |
---|
76 | bool isCorr = false; |
---|
77 | |
---|
78 | |
---|
79 | |
---|
80 | for (TokL::iterator it = tokenLP->begin(); it != tokenLP->end(); ++it, ++ssp) { |
---|
81 | if (isUpperCase(*it)) { |
---|
82 | isGenus = true; |
---|
83 | #if defined(DUMP) |
---|
84 | std::cout << "genus detected" << std::endl; |
---|
85 | #endif // DUMP |
---|
86 | } |
---|
87 | |
---|
88 | |
---|
89 | else { // begin operators |
---|
90 | if (*it == string("->")) { |
---|
91 | nt_assert(!isHetero); |
---|
92 | nt_assert(!isHomo); |
---|
93 | nt_assert(isValid); // only one operator per line allowed |
---|
94 | isRenamed = true; |
---|
95 | isValid = false; |
---|
96 | #if defined(DUMP) |
---|
97 | std::cout << "renaming detected" << std::endl; |
---|
98 | #endif // DUMP |
---|
99 | } |
---|
100 | else { |
---|
101 | if (*it == string("=>")) { |
---|
102 | nt_assert(!isRenamed); |
---|
103 | nt_assert(!isHomo); |
---|
104 | nt_assert(isValid); |
---|
105 | isHetero = true; |
---|
106 | isValid = false; |
---|
107 | #if defined(DUMP) |
---|
108 | std::cout << "heteronym detected" << std::endl; |
---|
109 | #endif // DUMP |
---|
110 | } |
---|
111 | else { |
---|
112 | if (*it == string("=")) { |
---|
113 | nt_assert(!isRenamed); |
---|
114 | nt_assert(!isHetero); |
---|
115 | nt_assert(isValid); |
---|
116 | isHomo = true; |
---|
117 | isValid = false; |
---|
118 | #if defined(DUMP) |
---|
119 | std::cout << "homonym detected" << std::endl; |
---|
120 | #endif // DUMP |
---|
121 | } |
---|
122 | else { |
---|
123 | if (*it == string("(corrig.)")) { |
---|
124 | isCorr = true; |
---|
125 | #if defined(DUMP) |
---|
126 | std::cout << "correction" << std::endl; |
---|
127 | #endif // DUMP |
---|
128 | } |
---|
129 | else { |
---|
130 | if (*it == string("see:")) { |
---|
131 | // isSee = true; |
---|
132 | isValid = false; |
---|
133 | #if defined(DUMP) |
---|
134 | std::cout << "reference" << std::endl; |
---|
135 | #endif // DUMP |
---|
136 | } |
---|
137 | else { |
---|
138 | if (*it == string("subsp.")) { |
---|
139 | #if defined(DUMP) |
---|
140 | std::cout << "subspecies detected at position: >>>" << ssp << "<<<" << std::endl; |
---|
141 | #endif // DUMP |
---|
142 | ssp == 2 ? sspPos[0] = ssp : sspPos[1] = ssp; |
---|
143 | // max. one subsp. on each operator side |
---|
144 | #if defined(DUMP) |
---|
145 | std::cout << "position of subsp.: " << sspPos[0] << "\tand: " << sspPos[1] << std::endl; |
---|
146 | #endif // DUMP |
---|
147 | } |
---|
148 | } |
---|
149 | } |
---|
150 | } |
---|
151 | } |
---|
152 | } |
---|
153 | } |
---|
154 | } |
---|
155 | |
---|
156 | |
---|
157 | |
---|
158 | if (isGenus) { |
---|
159 | #if defined(DUMP) |
---|
160 | std::cout << " GENUS description found " << std::endl; |
---|
161 | #endif // DUMP |
---|
162 | if (isValid) { |
---|
163 | descNames[0] = (*tokenLP)[0]; |
---|
164 | actType = VALGEN; |
---|
165 | #if defined(DUMP) |
---|
166 | std::cout << "VALIDGEN type set to: " << actType << std::endl; |
---|
167 | #endif// DUMP |
---|
168 | } |
---|
169 | else { |
---|
170 | if (isHetero) { |
---|
171 | descNames[0] = (*tokenLP)[2]; |
---|
172 | descNames[3] = (*tokenLP)[0]; |
---|
173 | actType = HETGEN; |
---|
174 | #if defined(DUMP) |
---|
175 | std::cout << "HETERONYMGEN type set to: " << actType << std::endl; |
---|
176 | #endif // DUMP |
---|
177 | } |
---|
178 | else { |
---|
179 | if (isHomo) { |
---|
180 | descNames[0] = (*tokenLP)[2]; |
---|
181 | descNames[3] = (*tokenLP)[0]; |
---|
182 | actType = HOMGEN; |
---|
183 | #if defined(DUMP) |
---|
184 | std::cout << "HOMONYMGEN type set to: " << actType << std::endl; |
---|
185 | #endif // DUMP |
---|
186 | |
---|
187 | } |
---|
188 | else { |
---|
189 | |
---|
190 | if (isRenamed) { |
---|
191 | descNames[0] = (*tokenLP)[2]; |
---|
192 | descNames[3] = (*tokenLP)[0]; |
---|
193 | actType = RENGEN; |
---|
194 | #if defined(DUMP) |
---|
195 | std::cout << "RENAMEDGEN type set to: " << actType << std::endl; |
---|
196 | #endif // DUMP |
---|
197 | } |
---|
198 | else { |
---|
199 | #if defined(DUMP) |
---|
200 | std::cout << "no meaningful combination of conditions reached" << std::endl |
---|
201 | << "for line: " << descriptionString << std::endl; |
---|
202 | std::cout << "description type is set to NOTYPE: " << NOTYPE << std::endl; |
---|
203 | #endif // DUMP |
---|
204 | isValid = false; |
---|
205 | #if defined(DUMP) |
---|
206 | std::cout << "isValid set to false " << std::endl; |
---|
207 | #endif // DUMP |
---|
208 | actType = NOTYPE; |
---|
209 | } |
---|
210 | } |
---|
211 | } |
---|
212 | } |
---|
213 | } |
---|
214 | else { |
---|
215 | |
---|
216 | // just fancy experimental , maybe not 100% correct but looks good |
---|
217 | if (!(((sspPos[0] == 0) || (sspPos[0] == 2)) && (((sspPos[1] > 4)&&(sspPos[1]< 9))||(sspPos[1]==0)))) { |
---|
218 | #if defined(DUMP) |
---|
219 | std::cout << "subsp. at strange position found in line:" << std::endl << descriptionString << endl; |
---|
220 | std::cout << "description type is set to NOTYPE: " << NOTYPE << std::endl; |
---|
221 | #endif // DUMP |
---|
222 | isValid = false; |
---|
223 | #if defined(DUMP) |
---|
224 | std::cout << "isValid set to false " << std::endl; |
---|
225 | #endif // DUMP |
---|
226 | actType = NOTYPE; |
---|
227 | } |
---|
228 | |
---|
229 | if (isValid) { |
---|
230 | descNames[0] = (*tokenLP)[0]; |
---|
231 | descNames[1] = (*tokenLP)[1]; |
---|
232 | if (sspPos[0] != 0) { descNames[2] = (*tokenLP)[sspPos[0]+1]; } // only if subsp. exists |
---|
233 | actType = VALSPEC; |
---|
234 | } |
---|
235 | else { // begin else isHetero |
---|
236 | if (isHetero) { |
---|
237 | descNames[0] = (*tokenLP)[3 + sspPos[0]]; |
---|
238 | descNames[1] = (*tokenLP)[4 + sspPos[0]]; |
---|
239 | if (sspPos[1]!=0) { descNames[2]=(*tokenLP)[6 + sspPos[0]]; } // only if subsp. exists |
---|
240 | |
---|
241 | descNames[3] = (*tokenLP)[0]; |
---|
242 | descNames[4] = (*tokenLP)[1]; |
---|
243 | if (sspPos[0]!=0) { descNames[5]=(*tokenLP)[sspPos[0]+1]; } // only if subsp. exists |
---|
244 | |
---|
245 | actType = HETSPEC; |
---|
246 | } |
---|
247 | else { |
---|
248 | if (isHomo) { |
---|
249 | descNames[0] = (*tokenLP)[3 + sspPos[0]]; |
---|
250 | descNames[1] = (*tokenLP)[4 + sspPos[0]]; |
---|
251 | if (sspPos[1]!=0) { descNames[2]=(*tokenLP)[6 + sspPos[0]]; } // only if subsp. exists |
---|
252 | |
---|
253 | descNames[3] = (*tokenLP)[0]; |
---|
254 | descNames[4] = (*tokenLP)[1]; |
---|
255 | if (sspPos[0]!=0) { descNames[5]=(*tokenLP)[sspPos[0]+1]; } // only if subsp. exists |
---|
256 | |
---|
257 | actType = HOMSPEC; |
---|
258 | |
---|
259 | } |
---|
260 | else { // else branch isHomo |
---|
261 | if (isRenamed) { |
---|
262 | descNames[0] = (*tokenLP)[3 + sspPos[0]]; |
---|
263 | descNames[1] = (*tokenLP)[4 + sspPos[0]]; |
---|
264 | if (sspPos[1]!=0) { descNames[2]=(*tokenLP)[6 + sspPos[0]]; } // only if subsp. exists |
---|
265 | |
---|
266 | descNames[3] = (*tokenLP)[0]; |
---|
267 | descNames[4] = (*tokenLP)[1]; |
---|
268 | if (sspPos[0]!=0) { descNames[5]=(*tokenLP)[sspPos[0]+1]; } // only if subsp. exists |
---|
269 | |
---|
270 | actType = RENSPEC; |
---|
271 | |
---|
272 | } |
---|
273 | else { // species remaining cases |
---|
274 | #if defined(DUMP) |
---|
275 | std::cout << "not a valid description line detected" << std::endl; |
---|
276 | std::cout << "isValid: " << isValid << std::endl; |
---|
277 | std::cout << "isRenamed: " << isRenamed << std::endl; |
---|
278 | std::cout << "isHetero: " << isHetero << std::endl; |
---|
279 | std::cout << "isHomo: " << isHomo << std::endl; |
---|
280 | std::cout << "isGenus: " << isGenus << std::endl; |
---|
281 | std::cout << "isSee: " << isSee << std::endl; |
---|
282 | std::cout << "isCorr: " << isCorr << std::endl; |
---|
283 | std::cout << "sspPos: " << sspPos[0] << " and " << sspPos[1] << std::endl; |
---|
284 | std::cout << descriptionString << std::endl; |
---|
285 | #endif // DUMP |
---|
286 | actType = NOTYPE; |
---|
287 | } |
---|
288 | |
---|
289 | } |
---|
290 | } |
---|
291 | } |
---|
292 | } |
---|
293 | |
---|
294 | |
---|
295 | #if defined(DUMP) |
---|
296 | std::cout << descriptionString << std::endl; |
---|
297 | std::cout << "classified as " << actType << std::endl; |
---|
298 | #endif // DUMP |
---|
299 | |
---|
300 | Desco actDesc(actType, isCorr, descNames[0], descNames[1], descNames[2], descNames[3], descNames[4], descNames[5]); |
---|
301 | delete tokenLP; |
---|
302 | return actDesc; |
---|
303 | } |
---|
304 | |
---|
305 | |
---|
306 | string Desco::getFirstName() { |
---|
307 | string tmp = firstgen; |
---|
308 | if (!firstspec.empty()) { |
---|
309 | tmp = tmp + " " + firstspec; |
---|
310 | if (!firstsub.empty()) { |
---|
311 | tmp = tmp + " " + "subsp." + " " + firstsub; |
---|
312 | } |
---|
313 | } |
---|
314 | |
---|
315 | |
---|
316 | return tmp; |
---|
317 | } |
---|
318 | |
---|
319 | string Desco::getSecondName() { |
---|
320 | string tmp = secondgen; |
---|
321 | if (!secondspec.empty()) { |
---|
322 | tmp = tmp + " " + firstspec; |
---|
323 | if (!secondsub.empty()) { |
---|
324 | tmp = tmp + " " + "subsp." + " " + secondsub; |
---|
325 | } |
---|
326 | } |
---|
327 | return tmp; |
---|
328 | } |
---|
329 | |
---|
330 | |
---|
331 | bool isUpperCase(const string& input) { |
---|
332 | for (size_t i=0; i<input.length(); ++i) { |
---|
333 | if (input[i]<'A' || input[i]>'Z') return false; |
---|
334 | } |
---|
335 | return true; |
---|
336 | } |
---|
337 | } |
---|