1 | |
---|
2 | /** |
---|
3 | * Definition of all objects belonging to this version of |
---|
4 | * the valid names text file |
---|
5 | * |
---|
6 | * 29. November 2002 |
---|
7 | * |
---|
8 | * coded by Lothar Richter |
---|
9 | * |
---|
10 | * Copyright (C) 2002 Department of Microbiology (Technical University Munich) |
---|
11 | */ |
---|
12 | |
---|
13 | #if defined(DEVEL_LOTHAR) |
---|
14 | #define DUMP |
---|
15 | #endif // DEVEL_LOTHAR |
---|
16 | |
---|
17 | #include <stdlib.h> |
---|
18 | #include <stdlib.h> |
---|
19 | #include <iostream> |
---|
20 | #include <fstream> |
---|
21 | #include <string> |
---|
22 | #include <list> |
---|
23 | #include <vector> |
---|
24 | #include <cassert> |
---|
25 | |
---|
26 | #include "nt_validNameParser.hxx" |
---|
27 | |
---|
28 | using namespace std; |
---|
29 | |
---|
30 | // Hi Lothar, |
---|
31 | // ich hab ein paar CodeComments (CC : ) fuer Dich eingefuegt, die sich auf die Compiler-Warnungen beziehen. |
---|
32 | |
---|
33 | namespace validNames{ |
---|
34 | |
---|
35 | |
---|
36 | TokLPtr tokenize(const string& description, TokLPtr tokenLP) |
---|
37 | { |
---|
38 | // TokLPtr tokenLP = new TokL; |
---|
39 | size_t tokenEnd = 0; |
---|
40 | size_t tokenBegin = 0; |
---|
41 | // std::cout <<description.size() << std::endl; |
---|
42 | |
---|
43 | while (tokenEnd != description.size()){ // CC : warning: comparison between signed and unsigned (tokenEnd sollte nicht 'int' sondern 'unsigned' sein) |
---|
44 | tokenEnd = description.find_first_of(' ', tokenBegin); |
---|
45 | // std::cout << string("TokenBegin:\t") << tokenBegin << "\t" << |
---|
46 | // string("TokenEnd:\t") << tokenEnd << std::endl; |
---|
47 | if (tokenEnd == string::npos) tokenEnd = description.size(); |
---|
48 | int tokLength = tokenEnd - tokenBegin; |
---|
49 | if (tokLength != 0){ |
---|
50 | tokenLP->push_back(description.substr(tokenBegin,tokenEnd - tokenBegin)); |
---|
51 | // std::cout << string("pushedToken:\t") << description.substr(tokenBegin,tokenEnd - tokenBegin) << std::endl; |
---|
52 | } |
---|
53 | // std::cout << description.substr(tokenBegin,tokenEnd - tokenBegin) << std::endl; |
---|
54 | tokenBegin = tokenEnd + 1; |
---|
55 | |
---|
56 | } |
---|
57 | return tokenLP; |
---|
58 | } // end tokenize |
---|
59 | |
---|
60 | |
---|
61 | |
---|
62 | |
---|
63 | |
---|
64 | Desco determineType(const string& descriptionString) |
---|
65 | {// begin determineType |
---|
66 | |
---|
67 | DESCT actType = NOTYPE; |
---|
68 | TokLPtr tokenLP = new TokL; |
---|
69 | tokenLP = tokenize(descriptionString, tokenLP); |
---|
70 | // remove all tokens in parentheses |
---|
71 | { |
---|
72 | TokL::iterator it = tokenLP->begin(); |
---|
73 | while( it != tokenLP->end()){ |
---|
74 | if(((*it).at(0) == '(') && *it != string("(corrig.)")) it = tokenLP->erase(it); |
---|
75 | else ++it; |
---|
76 | } |
---|
77 | } |
---|
78 | |
---|
79 | // check first word for upper case letters |
---|
80 | string descNames[6]; // first the valid genus, species, subsp. then the other names |
---|
81 | // stores occurrence of subsp. which is needed to retrieve the right tokens later on and status flags |
---|
82 | int sspPos[2] = {0, 0}; // token subsp. occurs maximum twice |
---|
83 | int ssp = 0; |
---|
84 | bool isValid = true; |
---|
85 | bool isRenamed = false; |
---|
86 | bool isHetero = false; |
---|
87 | bool isHomo = false; |
---|
88 | bool isGenus = false; |
---|
89 | bool isSee = false; |
---|
90 | // bool isSpecies = false; |
---|
91 | bool isCorr = false; |
---|
92 | |
---|
93 | |
---|
94 | |
---|
95 | for( TokL::iterator it = tokenLP->begin();it != tokenLP->end(); it ++, ssp++) |
---|
96 | {//begin of token iteration |
---|
97 | // std::cout << "entering analysis loop" << std::endl; |
---|
98 | if(isUpperCase(*it)) { |
---|
99 | isGenus = true; |
---|
100 | #if defined(DUMP) |
---|
101 | std::cout << "genus detected" << std::endl; |
---|
102 | #endif // DUMP |
---|
103 | } // for genus descriptions |
---|
104 | |
---|
105 | |
---|
106 | else{ // begin operators |
---|
107 | if(*it == string("->")) { |
---|
108 | assert(isHetero == false); |
---|
109 | assert(isHomo == false); |
---|
110 | assert(isValid == true); // only one operator per line allowed |
---|
111 | isRenamed = true; |
---|
112 | isValid = false; |
---|
113 | #if defined(DUMP) |
---|
114 | std::cout << "renaming detected" << std::endl; |
---|
115 | #endif // DUMP |
---|
116 | } |
---|
117 | else { |
---|
118 | if(*it == string("=>")){ |
---|
119 | assert(isRenamed == false); |
---|
120 | assert(isHomo == false); |
---|
121 | assert(isValid == true); |
---|
122 | isHetero = true; |
---|
123 | isValid = false; |
---|
124 | #if defined(DUMP) |
---|
125 | std::cout << "heteronym detected" << std::endl; |
---|
126 | #endif // DUMP |
---|
127 | } |
---|
128 | else { |
---|
129 | if(*it == string("=")){ |
---|
130 | assert(isRenamed == false); |
---|
131 | assert(isHetero == false); |
---|
132 | assert(isValid == true); |
---|
133 | isHomo = true; |
---|
134 | isValid = false; |
---|
135 | #if defined(DUMP) |
---|
136 | std::cout << "homonym detected" << std::endl; |
---|
137 | #endif // DUMP |
---|
138 | } |
---|
139 | else{ |
---|
140 | if(*it == string("(corrig.)")) { |
---|
141 | isCorr = true; |
---|
142 | #if defined(DUMP) |
---|
143 | std::cout << "correction" << std::endl; |
---|
144 | #endif // DUMP |
---|
145 | } |
---|
146 | else{ |
---|
147 | if(*it == string("see:")){ |
---|
148 | isSee = true; |
---|
149 | isValid = false; |
---|
150 | #if defined(DUMP) |
---|
151 | std::cout << "reference" << std::endl; |
---|
152 | #endif // DUMP |
---|
153 | } |
---|
154 | else{ |
---|
155 | if(*it == string("subsp.")){ |
---|
156 | #if defined(DUMP) |
---|
157 | std::cout << "subspecies detected at position: >>>"<< ssp << "<<<" << std::endl; |
---|
158 | #endif // DUMP |
---|
159 | ssp == 2 ? sspPos[0] = ssp : sspPos[1] = ssp; |
---|
160 | // : sspPos[1] == 0 ? sspPos[1] = ssp |
---|
161 | // : 10000,exit (102); // bad hack to fake return value |
---|
162 | // max. one subsp. on each operator side |
---|
163 | #if defined(DUMP) |
---|
164 | std::cout << "position of subsp.: " << sspPos[0] << "\tand: " << sspPos[1] << std::endl; |
---|
165 | #endif // DUMP |
---|
166 | } |
---|
167 | } |
---|
168 | } |
---|
169 | } |
---|
170 | } |
---|
171 | } |
---|
172 | } // end operators |
---|
173 | } // end of token iteration |
---|
174 | |
---|
175 | |
---|
176 | |
---|
177 | if(isGenus) { // for genus descriptions |
---|
178 | #if defined(DUMP) |
---|
179 | std::cout << " GENUS description found " << std::endl; |
---|
180 | #endif // DUMP |
---|
181 | if(isValid){ |
---|
182 | descNames[0] = (*tokenLP)[0]; |
---|
183 | actType = VALGEN; |
---|
184 | #if defined(DUMP) |
---|
185 | std::cout << "VALIDGEN type set to: " << actType << std::endl; |
---|
186 | #endif// DUMP |
---|
187 | } |
---|
188 | else{ |
---|
189 | if(isHetero){ |
---|
190 | descNames[0] = (*tokenLP)[2]; |
---|
191 | descNames[3] = (*tokenLP)[0]; |
---|
192 | actType = HETGEN; |
---|
193 | #if defined(DUMP) |
---|
194 | std::cout << "HETERONYMGEN type set to: " << actType << std::endl; |
---|
195 | #endif // DUMP |
---|
196 | } |
---|
197 | else{ |
---|
198 | if(isHomo){ |
---|
199 | descNames[0] = (*tokenLP)[2]; |
---|
200 | descNames[3] = (*tokenLP)[0]; |
---|
201 | actType = HOMGEN; |
---|
202 | #if defined(DUMP) |
---|
203 | std::cout << "HOMONYMGEN type set to: " << actType << std::endl; |
---|
204 | #endif // DUMP |
---|
205 | |
---|
206 | } |
---|
207 | else{ |
---|
208 | |
---|
209 | if(isRenamed){ |
---|
210 | descNames[0] = (*tokenLP)[2]; |
---|
211 | descNames[3] = (*tokenLP)[0]; |
---|
212 | actType = RENGEN; |
---|
213 | #if defined(DUMP) |
---|
214 | std::cout << "RENAMEDGEN type set to: " << actType << std::endl; |
---|
215 | #endif // DUMP |
---|
216 | } |
---|
217 | else{ |
---|
218 | #if defined(DUMP) |
---|
219 | std::cout << "no meaningful combination of conditions reached" << std::endl |
---|
220 | << "for line: " << descriptionString << std::endl; |
---|
221 | std::cout << "description type is set to NOTYPE: " << NOTYPE << std::endl; |
---|
222 | #endif // DUMP |
---|
223 | isValid = false; |
---|
224 | #if defined(DUMP) |
---|
225 | std::cout << "isValid set to false " << std::endl; |
---|
226 | #endif // DUMP |
---|
227 | actType = NOTYPE; |
---|
228 | // exit(25); |
---|
229 | } |
---|
230 | } |
---|
231 | } |
---|
232 | } |
---|
233 | |
---|
234 | } // end of genus part |
---|
235 | else{ // begin of species part |
---|
236 | |
---|
237 | // just fancy experimental , maybe not 100% correct but looks good |
---|
238 | if (!(((sspPos[0] == 0) || (sspPos[0] == 2)) && (((sspPos[1] > 4)&&(sspPos[1]< 9))||(sspPos[1]==0)))) |
---|
239 | { |
---|
240 | #if defined(DUMP) |
---|
241 | std::cout << "subsp. at strange position found in line:" << std::endl<< descriptionString << endl; |
---|
242 | std::cout << "description type is set to NOTYPE: " << NOTYPE << std::endl; |
---|
243 | #endif // DUMP |
---|
244 | isValid = false; |
---|
245 | #if defined(DUMP) |
---|
246 | std::cout << "isValid set to false " << std::endl; |
---|
247 | #endif // DUMP |
---|
248 | actType = NOTYPE; |
---|
249 | } |
---|
250 | |
---|
251 | if(isValid){ |
---|
252 | descNames[0] = (*tokenLP)[0]; |
---|
253 | descNames[1] = (*tokenLP)[1]; |
---|
254 | if(sspPos[0] != 0) {descNames[2] = (*tokenLP)[sspPos[0]+1];} // only if subsp. exists |
---|
255 | actType = VALSPEC; |
---|
256 | } |
---|
257 | else{// begin else isHetero |
---|
258 | if(isHetero){ |
---|
259 | descNames[0] = (*tokenLP)[3 + sspPos[0]]; |
---|
260 | descNames[1] = (*tokenLP)[4 + sspPos[0]]; |
---|
261 | if(sspPos[1]!=0){descNames[2]=(*tokenLP)[6 + sspPos[0]];} // only if subsp. exists |
---|
262 | |
---|
263 | descNames[3] = (*tokenLP)[0]; |
---|
264 | descNames[4] = (*tokenLP)[1]; |
---|
265 | if(sspPos[0]!=0){descNames[5]=(*tokenLP)[sspPos[0]+1];} // only if subsp. exists |
---|
266 | |
---|
267 | actType = HETSPEC; |
---|
268 | } |
---|
269 | else{ |
---|
270 | if(isHomo){ |
---|
271 | descNames[0] = (*tokenLP)[3 + sspPos[0]]; |
---|
272 | descNames[1] = (*tokenLP)[4 + sspPos[0]]; |
---|
273 | if(sspPos[1]!=0){descNames[2]=(*tokenLP)[6 + sspPos[0]];} // only if subsp. exists |
---|
274 | |
---|
275 | descNames[3] = (*tokenLP)[0]; |
---|
276 | descNames[4] = (*tokenLP)[1]; |
---|
277 | if(sspPos[0]!=0){descNames[5]=(*tokenLP)[sspPos[0]+1];} // only if subsp. exists |
---|
278 | |
---|
279 | actType = HOMSPEC; |
---|
280 | |
---|
281 | } |
---|
282 | else{// else branch isHomo |
---|
283 | if(isRenamed){ |
---|
284 | descNames[0] = (*tokenLP)[3 + sspPos[0]]; |
---|
285 | descNames[1] = (*tokenLP)[4 + sspPos[0]]; |
---|
286 | if(sspPos[1]!=0){descNames[2]=(*tokenLP)[6 + sspPos[0]];} // only if subsp. exists |
---|
287 | |
---|
288 | descNames[3] = (*tokenLP)[0]; |
---|
289 | descNames[4] = (*tokenLP)[1]; |
---|
290 | if(sspPos[0]!=0){descNames[5]=(*tokenLP)[sspPos[0]+1];} // only if subsp. exists |
---|
291 | |
---|
292 | actType = RENSPEC; |
---|
293 | |
---|
294 | } |
---|
295 | else{// species remaining cases |
---|
296 | #if defined(DUMP) |
---|
297 | std::cout << "not a valid description line detected" << std::endl; |
---|
298 | std::cout << "isValid: " << isValid << std::endl; |
---|
299 | std::cout << "isRenamed: " << isRenamed << std::endl; |
---|
300 | std::cout << "isHetero: " << isHetero << std::endl; |
---|
301 | std::cout << "isHomo: " << isHomo << std::endl; |
---|
302 | std::cout << "isGenus: " << isGenus << std::endl; |
---|
303 | std::cout << "isSee: " << isSee << std::endl; |
---|
304 | std::cout << "isCorr: " << isCorr << std::endl; |
---|
305 | std::cout << "sspPos: " << sspPos[0]<< " and " << sspPos[1] << std::endl; |
---|
306 | std::cout << descriptionString << std::endl; |
---|
307 | #endif // DUMP |
---|
308 | actType = NOTYPE; |
---|
309 | } |
---|
310 | |
---|
311 | }// end else isHomo |
---|
312 | }// end else isHetero |
---|
313 | }//end else is Valid |
---|
314 | }// end of species part |
---|
315 | |
---|
316 | |
---|
317 | // check line for -> or => or = |
---|
318 | //} |
---|
319 | |
---|
320 | #if defined(DUMP) |
---|
321 | std::cout << descriptionString << std::endl; |
---|
322 | std::cout << "classified as " << actType << std::endl ; |
---|
323 | #endif // DUMP |
---|
324 | |
---|
325 | //Desco actDesc(actType); |
---|
326 | Desco actDesc(actType, isCorr, descNames[0],descNames[1],descNames[2],descNames[3],descNames[4],descNames[5] ); |
---|
327 | delete tokenLP; |
---|
328 | return actDesc; |
---|
329 | // return actType; |
---|
330 | }; // end determineType |
---|
331 | |
---|
332 | |
---|
333 | string Desco::getFirstName(){ |
---|
334 | // return nameParts[0] + nameParts[1] + nameParts[2]; |
---|
335 | string tmp = firstgen; |
---|
336 | if (!firstspec.empty()){ |
---|
337 | tmp = tmp + " " + firstspec; |
---|
338 | if(!firstsub.empty()){ |
---|
339 | tmp = tmp + " " + "subsp." + " " + firstsub; |
---|
340 | } |
---|
341 | } |
---|
342 | |
---|
343 | |
---|
344 | return tmp; |
---|
345 | } // end Desco::getFirstName() |
---|
346 | |
---|
347 | string Desco::getSecondName(){ |
---|
348 | string tmp = secondgen; |
---|
349 | if (!secondspec.empty()){ |
---|
350 | tmp = tmp + " " + firstspec; |
---|
351 | if(!secondsub.empty()){ |
---|
352 | tmp = tmp + " " + "subsp." + " " + secondsub; |
---|
353 | } |
---|
354 | } |
---|
355 | return tmp; |
---|
356 | // return nameParts[3] + nameParts[4] + nameParts[5]; |
---|
357 | } // Desco::getSecondName() |
---|
358 | |
---|
359 | |
---|
360 | bool isUpperCase(const string& input) |
---|
361 | { |
---|
362 | for (size_t i=0;i<input.length(); ++i) |
---|
363 | { |
---|
364 | if(input[i]<'A' || input[i]>'Z'){return false;} |
---|
365 | } |
---|
366 | return true; |
---|
367 | } |
---|
368 | |
---|
369 | |
---|
370 | } // end namespace |
---|
371 | // test |
---|