diff options
-rw-r--r-- | .gitignore | 11 | ||||
-rw-r--r-- | CMakeLists.txt | 8 | ||||
-rw-r--r-- | furries.cpp | 15 | ||||
-rw-r--r-- | generator.cpp | 451 | ||||
-rw-r--r-- | schema.sql | 121 | ||||
-rw-r--r-- | verbly/adjective.h | 2 | ||||
-rw-r--r-- | verbly/adverb.h | 21 | ||||
-rw-r--r-- | verbly/data.h | 79 | ||||
-rw-r--r-- | verbly/token.h | 21 | ||||
-rw-r--r-- | verbly/verbly.h | 1 |
10 files changed, 707 insertions, 23 deletions
diff --git a/.gitignore b/.gitignore index e9abc7f..461a080 100644 --- a/.gitignore +++ b/.gitignore | |||
@@ -1 +1,10 @@ | |||
1 | config.yml \ No newline at end of file | 1 | config.yml |
2 | .DS_Store | ||
3 | CMakeCache.txt | ||
4 | CMakeFiles/ | ||
5 | Makefile | ||
6 | cmake_install.cmake | ||
7 | furries | ||
8 | furries.dSYM/ | ||
9 | generator | ||
10 | generator.dSYM/ | ||
diff --git a/CMakeLists.txt b/CMakeLists.txt index 054c972..0b6d991 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt | |||
@@ -6,9 +6,15 @@ add_subdirectory(vendor/twitcurl/libtwitcurl) | |||
6 | find_package(PkgConfig) | 6 | find_package(PkgConfig) |
7 | pkg_check_modules(YamlCpp yaml-cpp REQUIRED) | 7 | pkg_check_modules(YamlCpp yaml-cpp REQUIRED) |
8 | pkg_check_modules(sqlite3 sqlite3 REQUIRED) | 8 | pkg_check_modules(sqlite3 sqlite3 REQUIRED) |
9 | find_package(libxml2 REQUIRED) | ||
9 | 10 | ||
10 | include_directories(vendor/twitcurl/libtwitcurl ${sqlite3_INCLUDE_DIR}) | 11 | include_directories(vendor/twitcurl/libtwitcurl ${LIBXML2_INCLUDE_DIR} ${sqlite3_INCLUDE_DIR}) |
11 | add_executable(furries furries.cpp) | 12 | add_executable(furries furries.cpp) |
12 | set_property(TARGET furries PROPERTY CXX_STANDARD 11) | 13 | set_property(TARGET furries PROPERTY CXX_STANDARD 11) |
13 | set_property(TARGET furries PROPERTY CXX_STANDARD_REQUIRED ON) | 14 | set_property(TARGET furries PROPERTY CXX_STANDARD_REQUIRED ON) |
14 | target_link_libraries(furries ${sqlite3_LIBRARIES} ${YamlCpp_LIBRARIES} twitcurl curl) | 15 | target_link_libraries(furries ${sqlite3_LIBRARIES} ${YamlCpp_LIBRARIES} twitcurl curl) |
16 | |||
17 | add_executable(generator generator.cpp) | ||
18 | set_property(TARGET generator PROPERTY CXX_STANDARD 11) | ||
19 | set_property(TARGET generator PROPERTY CXX_STANDARD_REQUIRED ON) | ||
20 | target_link_libraries(generator ${sqlite3_LIBRARIES} ${LIBXML2_LIBRARIES}) | ||
diff --git a/furries.cpp b/furries.cpp index 2d0fb23..0cce8bd 100644 --- a/furries.cpp +++ b/furries.cpp | |||
@@ -62,7 +62,15 @@ class fill_blanks { | |||
62 | case verbly::fillin_type::adjective: | 62 | case verbly::fillin_type::adjective: |
63 | { | 63 | { |
64 | const verbly::adjective& adj = database.adjectives().random(true).limit(1).run().front(); | 64 | const verbly::adjective& adj = database.adjectives().random(true).limit(1).run().front(); |
65 | it = std::make_unique<verbly::string_token>(adj.value); | 65 | it = std::make_unique<verbly::string_token>(adj.form); |
66 | |||
67 | break; | ||
68 | } | ||
69 | |||
70 | case verbly::fillin_type::adverb: | ||
71 | { | ||
72 | const verbly::adverb& adv = database.adverbs().random(true).limit(1).run().front(); | ||
73 | it = std::make_unique<verbly::string_token>(adv.form); | ||
66 | 74 | ||
67 | break; | 75 | break; |
68 | } | 76 | } |
@@ -110,6 +118,11 @@ int main(int argc, char** argv) | |||
110 | new verbly::string_token("the furries are"), | 118 | new verbly::string_token("the furries are"), |
111 | new verbly::fillin_token(verbly::fillin_type::adjective) | 119 | new verbly::fillin_token(verbly::fillin_type::adjective) |
112 | }); | 120 | }); |
121 | forms.push_back({ | ||
122 | new verbly::string_token("the furries are"), | ||
123 | new verbly::fillin_token(verbly::fillin_type::adverb), | ||
124 | new verbly::fillin_token(verbly::fillin_type::adjective) | ||
125 | }); | ||
113 | 126 | ||
114 | verbly::data database {"data.sqlite3"}; | 127 | verbly::data database {"data.sqlite3"}; |
115 | fill_blanks yeah {database}; | 128 | fill_blanks yeah {database}; |
diff --git a/generator.cpp b/generator.cpp new file mode 100644 index 0000000..c389963 --- /dev/null +++ b/generator.cpp | |||
@@ -0,0 +1,451 @@ | |||
1 | #include <libxml/parser.h> | ||
2 | #include <iostream> | ||
3 | #include <dirent.h> | ||
4 | #include <set> | ||
5 | #include <map> | ||
6 | #include <string> | ||
7 | #include <vector> | ||
8 | #include <fstream> | ||
9 | #include <sqlite3.h> | ||
10 | #include <sstream> | ||
11 | #include <regex> | ||
12 | |||
13 | struct verb { | ||
14 | std::string infinitive; | ||
15 | std::string past_tense; | ||
16 | std::string past_participle; | ||
17 | std::string ing_form; | ||
18 | std::string s_form; | ||
19 | }; | ||
20 | |||
21 | struct group { | ||
22 | std::string id; | ||
23 | std::set<std::string> members; | ||
24 | }; | ||
25 | |||
26 | std::map<std::string, group> groups; | ||
27 | std::map<std::string, verb> verbs; | ||
28 | std::map<int, std::map<int, int>> wn; | ||
29 | |||
30 | void print_usage() | ||
31 | { | ||
32 | std::cout << "Verbly Datafile Generator" << std::endl; | ||
33 | std::cout << "-------------------------" << std::endl; | ||
34 | std::cout << "Requires exactly four arguments." << std::endl; | ||
35 | std::cout << "1. The path to a VerbNet data directory." << std::endl; | ||
36 | std::cout << "2. The path to a SemLink vnpbMappings file." << std::endl; | ||
37 | std::cout << "3. The path to an AGID infl.txt file." << std::endl; | ||
38 | std::cout << "4. The path to a WordNet prolog data directory." << std::endl; | ||
39 | std::cout << "5. Datafile output path." << std::endl; | ||
40 | |||
41 | exit(1); | ||
42 | } | ||
43 | /* | ||
44 | void parse_group(xmlNodePtr top, std::string filename) | ||
45 | { | ||
46 | xmlChar* key = xmlGetProp(top, (xmlChar*) "ID"); | ||
47 | if (key == 0) | ||
48 | { | ||
49 | std::cout << "Bad VerbNet file format: " << filename << std::endl; | ||
50 | print_usage(); | ||
51 | } | ||
52 | std::string vnid = key; | ||
53 | vnid = vnid.substr(vnid.find_first_of("-")+1); | ||
54 | xmlFree(key); | ||
55 | |||
56 | group g; | ||
57 | g.id = vnid; | ||
58 | |||
59 | for (xmlNodePtr node = top->xmlChildrenNode; node != nullptr; node = node->next) | ||
60 | { | ||
61 | if (!xmlStrcmp(node->name, (const xmlChar*) "MEMBERS")) | ||
62 | { | ||
63 | for (xmlNodePtr member = node->xmlChildrenNode; member != nullptr; member = member->next) | ||
64 | { | ||
65 | if (!xmlStrcmp(member->name, (const xmlChar*) "MEMBER")) | ||
66 | { | ||
67 | key = xmlGetProp(member, (xmlChar*) "name"); | ||
68 | g.members.insert(key); | ||
69 | xmlFree(key); | ||
70 | } | ||
71 | } | ||
72 | } else if (!xmlStrcmp(node->name, (const xmlChar*) "FRAMES")) | ||
73 | { | ||
74 | for (xmlNodePtr frame = node->xmlChildrenNode; frame != nullptr; frame = frame->next) | ||
75 | { | ||
76 | if (!xmlStrcmp(frame->name, (const xmlChar*) "FRAME")) | ||
77 | { | ||
78 | for (xmlNodePtr framenode = frame->xmlChildrenNode; framenode != nullptr; framenode = framenode->next) | ||
79 | { | ||
80 | |||
81 | } | ||
82 | } | ||
83 | } | ||
84 | } | ||
85 | } | ||
86 | }*/ | ||
87 | |||
88 | int main(int argc, char** argv) | ||
89 | { | ||
90 | if (argc != 6) | ||
91 | { | ||
92 | print_usage(); | ||
93 | } | ||
94 | |||
95 | /*DIR* dir; | ||
96 | if ((dir = opendir(argv[1])) == nullptr) | ||
97 | { | ||
98 | std::cout << "Invalid VerbNet data directory." << std::endl; | ||
99 | |||
100 | print_usage(); | ||
101 | } | ||
102 | |||
103 | struct dirent* ent; | ||
104 | while ((ent = readdir(dir)) != nullptr) | ||
105 | { | ||
106 | std::string filename(argv[1]); | ||
107 | if (filename.back() != '/') | ||
108 | { | ||
109 | filename += '/'; | ||
110 | } | ||
111 | |||
112 | filename += ent->d_name; | ||
113 | //std::cout << ent->d_name << std::endl; | ||
114 | |||
115 | if (filename.rfind(".xml") != filename.size() - 4) | ||
116 | { | ||
117 | continue; | ||
118 | } | ||
119 | |||
120 | xmlDocPtr doc = xmlParseFile(filename.c_str()); | ||
121 | if (doc == nullptr) | ||
122 | { | ||
123 | std::cout << "Error opening " << filename << std::endl; | ||
124 | print_usage(); | ||
125 | } | ||
126 | |||
127 | xmlNodePtr top = xmlDocGetRootElement(doc); | ||
128 | if ((top == nullptr) || (xmlStrcmp(top->name, (xmlChar*) "VNCLASS"))) | ||
129 | { | ||
130 | std::cout << "Bad VerbNet file format: " << filename << std::endl; | ||
131 | print_usage(); | ||
132 | } | ||
133 | |||
134 | parse_group(top, filename); | ||
135 | } | ||
136 | |||
137 | closedir(dir);*/ | ||
138 | |||
139 | // Get verbs from AGID | ||
140 | std::cout << "Reading verb inflection..." << std::endl; | ||
141 | |||
142 | std::ifstream agidfile(argv[3]); | ||
143 | if (!agidfile.is_open()) | ||
144 | { | ||
145 | std::cout << "Could not open AGID file: " << argv[3] << std::endl; | ||
146 | print_usage(); | ||
147 | } | ||
148 | |||
149 | for (;;) | ||
150 | { | ||
151 | std::string line; | ||
152 | if (!getline(agidfile, line)) | ||
153 | { | ||
154 | break; | ||
155 | } | ||
156 | |||
157 | if (line.back() == '\r') | ||
158 | { | ||
159 | line.pop_back(); | ||
160 | } | ||
161 | |||
162 | int divider = line.find_first_of(" "); | ||
163 | std::string word = line.substr(0, divider); | ||
164 | line = line.substr(divider+1); | ||
165 | |||
166 | if (line[0] != 'V') | ||
167 | { | ||
168 | continue; | ||
169 | } | ||
170 | |||
171 | if (line[1] == '?') | ||
172 | { | ||
173 | line.erase(0, 4); | ||
174 | } else { | ||
175 | line.erase(0, 3); | ||
176 | } | ||
177 | |||
178 | std::vector<std::string> forms; | ||
179 | while (!line.empty()) | ||
180 | { | ||
181 | std::string inflection; | ||
182 | if ((divider = line.find(" | ")) != std::string::npos) | ||
183 | { | ||
184 | inflection = line.substr(0, divider); | ||
185 | line = line.substr(divider + 3); | ||
186 | } else { | ||
187 | inflection = line; | ||
188 | line = ""; | ||
189 | } | ||
190 | |||
191 | if ((divider = inflection.find_first_of(",?")) != std::string::npos) | ||
192 | { | ||
193 | inflection = inflection.substr(0, divider); | ||
194 | } | ||
195 | |||
196 | forms.push_back(inflection); | ||
197 | } | ||
198 | |||
199 | verb v; | ||
200 | v.infinitive = word; | ||
201 | if (forms.size() == 4) | ||
202 | { | ||
203 | v.past_tense = forms[0]; | ||
204 | v.past_participle = forms[1]; | ||
205 | v.ing_form = forms[2]; | ||
206 | v.s_form = forms[3]; | ||
207 | } else if (forms.size() == 3) | ||
208 | { | ||
209 | v.past_tense = forms[0]; | ||
210 | v.past_participle = forms[0]; | ||
211 | v.ing_form = forms[1]; | ||
212 | v.s_form = forms[2]; | ||
213 | } else if (forms.size() == 8) | ||
214 | { | ||
215 | // As of AGID 2014.08.11, this is only "to be" | ||
216 | v.past_tense = forms[0]; | ||
217 | v.past_participle = forms[2]; | ||
218 | v.ing_form = forms[3]; | ||
219 | v.s_form = forms[4]; | ||
220 | } else { | ||
221 | // Words that don't fit the cases above as of AGID 2014.08.11: | ||
222 | // - may and shall do not conjugate the way we want them to | ||
223 | // - methinks only has a past tense and is an outlier | ||
224 | // - wit has five forms, and is archaic/obscure enough that we can ignore it for now | ||
225 | std::cout << "Ignoring verb \"" << word << "\" due to non-standard number of forms." << std::endl; | ||
226 | } | ||
227 | |||
228 | verbs[word] = v; | ||
229 | } | ||
230 | |||
231 | // Start writing output | ||
232 | std::cout << "Writing output..." << std::endl; | ||
233 | |||
234 | sqlite3* ppdb; | ||
235 | if (sqlite3_open_v2(argv[5], &ppdb, SQLITE_OPEN_READWRITE | SQLITE_OPEN_CREATE, NULL) != SQLITE_OK) | ||
236 | { | ||
237 | std::cout << "Error opening output datafile: " << sqlite3_errmsg(ppdb) << std::endl; | ||
238 | print_usage(); | ||
239 | } | ||
240 | |||
241 | std::ifstream schemafile("schema.sql"); | ||
242 | if (!schemafile.is_open()) | ||
243 | { | ||
244 | std::cout << "Could not find schema file" << std::endl; | ||
245 | print_usage(); | ||
246 | } | ||
247 | |||
248 | std::stringstream schemabuilder; | ||
249 | for (;;) | ||
250 | { | ||
251 | std::string line; | ||
252 | if (!getline(schemafile, line)) | ||
253 | { | ||
254 | break; | ||
255 | } | ||
256 | |||
257 | if (line.back() == '\r') | ||
258 | { | ||
259 | line.pop_back(); | ||
260 | } | ||
261 | |||
262 | schemabuilder << line << std::endl; | ||
263 | } | ||
264 | |||
265 | std::string schema = schemabuilder.str(); | ||
266 | while (!schema.empty()) | ||
267 | { | ||
268 | std::string query; | ||
269 | int divider = schema.find(";"); | ||
270 | if (divider != std::string::npos) | ||
271 | { | ||
272 | query = schema.substr(0, divider+1); | ||
273 | schema = schema.substr(divider+2); | ||
274 | } else { | ||
275 | break; | ||
276 | } | ||
277 | |||
278 | sqlite3_stmt* schmstmt; | ||
279 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &schmstmt, NULL) != SQLITE_OK) | ||
280 | { | ||
281 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | ||
282 | sqlite3_close_v2(ppdb); | ||
283 | print_usage(); | ||
284 | } | ||
285 | |||
286 | if (sqlite3_step(schmstmt) != SQLITE_DONE) | ||
287 | { | ||
288 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | ||
289 | sqlite3_close_v2(ppdb); | ||
290 | print_usage(); | ||
291 | } | ||
292 | |||
293 | sqlite3_finalize(schmstmt); | ||
294 | } | ||
295 | |||
296 | std::cout << "Writing verbs..." << std::endl; | ||
297 | for (auto& mapping : verbs) | ||
298 | { | ||
299 | sqlite3_stmt* ppstmt; | ||
300 | std::string query("INSERT INTO verbs (infinitive, past_tense, past_participle, ing_form, s_form) VALUES (?, ?, ?, ?, ?)"); | ||
301 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
302 | { | ||
303 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | ||
304 | sqlite3_close_v2(ppdb); | ||
305 | print_usage(); | ||
306 | } | ||
307 | |||
308 | sqlite3_bind_text(ppstmt, 1, mapping.second.infinitive.c_str(), mapping.second.infinitive.length(), SQLITE_STATIC); | ||
309 | sqlite3_bind_text(ppstmt, 2, mapping.second.past_tense.c_str(), mapping.second.past_tense.length(), SQLITE_STATIC); | ||
310 | sqlite3_bind_text(ppstmt, 3, mapping.second.past_participle.c_str(), mapping.second.past_participle.length(), SQLITE_STATIC); | ||
311 | sqlite3_bind_text(ppstmt, 4, mapping.second.ing_form.c_str(), mapping.second.ing_form.length(), SQLITE_STATIC); | ||
312 | sqlite3_bind_text(ppstmt, 5, mapping.second.s_form.c_str(), mapping.second.s_form.length(), SQLITE_STATIC); | ||
313 | |||
314 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
315 | { | ||
316 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | ||
317 | sqlite3_close_v2(ppdb); | ||
318 | print_usage(); | ||
319 | } | ||
320 | |||
321 | sqlite3_finalize(ppstmt); | ||
322 | } | ||
323 | |||
324 | // Get nouns/adjectives/adverbs from WordNet | ||
325 | // Useful relations: | ||
326 | // - s: master list | ||
327 | // - ant: antonymy (e.g. happy/sad, sad/happy, happiness/sadness) | ||
328 | // - at: variation (e.g. a measurement can be standard or nonstandard) | ||
329 | // - hyp: hypernymy/hyponymy (e.g. color/red, color/blue) | ||
330 | // - ins: instantiation (do we need this? let's see) | ||
331 | // - mm: member meronymy/holonymy (e.g. family/mother, family/child) | ||
332 | // - mp: part meronymy/holonymy (e.g. wheel/spoke, wheel/tire) | ||
333 | // - ms: substance meronymy/holonymy (e.g. tire/rubber, doorstop/rubber) | ||
334 | // - per: pertainymy (e.g. something that is Alaskan pertains to Alaska) | ||
335 | // mannernymy (e.g. something done quickly is done in a manner that is quick) | ||
336 | // - sa: specification (e.g. inaccurate (general) can mean imprecise or incorrect (specific)) | ||
337 | // - sim: synonymy (e.g. cheerful/happy, happy/cheerful) | ||
338 | // - syntax: positioning flags for some adjectives | ||
339 | std::string wnpref {argv[4]}; | ||
340 | if (wnpref.back() != '/') | ||
341 | { | ||
342 | wnpref += '/'; | ||
343 | } | ||
344 | |||
345 | std::cout << "Reading words from WordNet..." << std::endl; | ||
346 | std::ifstream wnsfile(wnpref + "wn_s.pl"); | ||
347 | if (!wnsfile.is_open()) | ||
348 | { | ||
349 | std::cout << "Invalid WordNet data directory." << std::endl; | ||
350 | print_usage(); | ||
351 | } | ||
352 | |||
353 | for (;;) | ||
354 | { | ||
355 | std::string line; | ||
356 | if (!getline(wnsfile, line)) | ||
357 | { | ||
358 | break; | ||
359 | } | ||
360 | |||
361 | if (line.back() == '\r') | ||
362 | { | ||
363 | line.pop_back(); | ||
364 | } | ||
365 | |||
366 | std::regex relation("^s\\(([134]\\d{8}),(\\d+),'([\\w ]+)',"); | ||
367 | std::smatch relation_data; | ||
368 | if (!std::regex_search(line, relation_data, relation)) | ||
369 | { | ||
370 | continue; | ||
371 | } | ||
372 | |||
373 | int synset_id = stoi(relation_data[1]); | ||
374 | int wnum = stoi(relation_data[2]); | ||
375 | std::string word = relation_data[3]; | ||
376 | |||
377 | std::string query; | ||
378 | switch (synset_id / 100000000) | ||
379 | { | ||
380 | case 1: // Noun | ||
381 | { | ||
382 | query = "INSERT INTO nouns (form) VALUES (?)"; | ||
383 | |||
384 | break; | ||
385 | } | ||
386 | |||
387 | case 2: // Verb | ||
388 | { | ||
389 | // Ignore | ||
390 | |||
391 | break; | ||
392 | } | ||
393 | |||
394 | case 3: // Adjective | ||
395 | { | ||
396 | query = "INSERT INTO adjectives (form) VALUES (?)"; | ||
397 | |||
398 | break; | ||
399 | } | ||
400 | |||
401 | case 4: // Adverb | ||
402 | { | ||
403 | query = "INSERT INTO adverbs (form) VALUES (?)"; | ||
404 | |||
405 | break; | ||
406 | } | ||
407 | } | ||
408 | |||
409 | sqlite3_stmt* ppstmt; | ||
410 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
411 | { | ||
412 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | ||
413 | sqlite3_close_v2(ppdb); | ||
414 | print_usage(); | ||
415 | } | ||
416 | |||
417 | sqlite3_bind_text(ppstmt, 1, word.c_str(), word.length(), SQLITE_STATIC); | ||
418 | |||
419 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
420 | { | ||
421 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | ||
422 | sqlite3_close_v2(ppdb); | ||
423 | print_usage(); | ||
424 | } | ||
425 | |||
426 | sqlite3_finalize(ppstmt); | ||
427 | |||
428 | query = "SELECT last_insert_rowid()"; | ||
429 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
430 | { | ||
431 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | ||
432 | sqlite3_close_v2(ppdb); | ||
433 | print_usage(); | ||
434 | } | ||
435 | |||
436 | if (sqlite3_step(ppstmt) != SQLITE_ROW) | ||
437 | { | ||
438 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | ||
439 | sqlite3_close_v2(ppdb); | ||
440 | print_usage(); | ||
441 | } | ||
442 | |||
443 | wn[synset_id][wnum] = sqlite3_column_int(ppstmt, 0); | ||
444 | |||
445 | sqlite3_finalize(ppstmt); | ||
446 | } | ||
447 | |||
448 | sqlite3_close_v2(ppdb); | ||
449 | |||
450 | std::cout << "Done." << std::endl; | ||
451 | } \ No newline at end of file | ||
diff --git a/schema.sql b/schema.sql index 7c1b52c..62dd780 100644 --- a/schema.sql +++ b/schema.sql | |||
@@ -34,5 +34,122 @@ CREATE TABLE `verb_groups` ( | |||
34 | DROP TABLE IF EXISTS `adjectives`; | 34 | DROP TABLE IF EXISTS `adjectives`; |
35 | CREATE TABLE `adjectives` ( | 35 | CREATE TABLE `adjectives` ( |
36 | `adjective_id` INTEGER PRIMARY KEY, | 36 | `adjective_id` INTEGER PRIMARY KEY, |
37 | `adjective` VARCHAR(32) NOT NULL | 37 | `form` VARCHAR(32) NOT NULL, |
38 | ); \ No newline at end of file | 38 | `position` CHAR(1) |
39 | ); | ||
40 | |||
41 | DROP TABLE IF EXISTS `adverbs`; | ||
42 | CREATE TABLE `adverbs` ( | ||
43 | `adverb_id` INTEGER PRIMARY KEY, | ||
44 | `form` VARCHAR(32) NOT NULL | ||
45 | ); | ||
46 | |||
47 | DROP TABLE IF EXISTS `nouns`; | ||
48 | CREATE TABLE `nouns` ( | ||
49 | `noun_id` INTEGER PRIMARY KEY, | ||
50 | `form` VARCHAR(32) NOT NULL | ||
51 | ); | ||
52 | |||
53 | DROP TABLE IF EXISTS `hypernymy`; | ||
54 | CREATE TABLE `hypernymy` ( | ||
55 | `hypernym_id` INTEGER NOT NULL, | ||
56 | `hyponym_id` INTEGER NOT NULL, | ||
57 | FOREIGN KEY (`hypernym_id`) REFERENCES `nouns`(`noun_id`), | ||
58 | FOREIGN KEY (`hyponym_id`) REFERENCES `nouns`(`noun_id`) | ||
59 | ); | ||
60 | |||
61 | DROP TABLE IF EXISTS `instantiation`; | ||
62 | CREATE TABLE `instantiation` ( | ||
63 | `class_id` INTEGER NOT NULL, | ||
64 | `instance_id` INTEGER NOT NULL, | ||
65 | FOREIGN KEY (`class_id`) REFERENCES `nouns`(`noun_id`), | ||
66 | FOREIGN KEY (`instance_id`) REFERENCES `nouns`(`noun_id`) | ||
67 | ); | ||
68 | |||
69 | DROP TABLE IF EXISTS `member_meronymy`; | ||
70 | CREATE TABLE `member_meronymy` ( | ||
71 | `meronym_id` INTEGER NOT NULL, | ||
72 | `holonym_id` INTEGER NOT NULL, | ||
73 | FOREIGN KEY (`meronym_id`) REFERENCES `nouns`(`noun_id`), | ||
74 | FOREIGN KEY (`holonym_id`) REFERENCES `nouns`(`noun_id`) | ||
75 | ); | ||
76 | |||
77 | DROP TABLE IF EXISTS `part_meronymy`; | ||
78 | CREATE TABLE `part_meronymy` ( | ||
79 | `meronym_id` INTEGER NOT NULL, | ||
80 | `holonym_id` INTEGER NOT NULL, | ||
81 | FOREIGN KEY (`meronym_id`) REFERENCES `nouns`(`noun_id`), | ||
82 | FOREIGN KEY (`holonym_id`) REFERENCES `nouns`(`noun_id`) | ||
83 | ); | ||
84 | |||
85 | DROP TABLE IF EXISTS `substance_meronymy`; | ||
86 | CREATE TABLE `substance_meronymy` ( | ||
87 | `meronym_id` INTEGER NOT NULL, | ||
88 | `holonym_id` INTEGER NOT NULL, | ||
89 | FOREIGN KEY (`meronym_id`) REFERENCES `nouns`(`noun_id`), | ||
90 | FOREIGN KEY (`holonym_id`) REFERENCES `nouns`(`noun_id`) | ||
91 | ); | ||
92 | |||
93 | DROP TABLE IF EXISTS `variation`; | ||
94 | CREATE TABLE `variation` ( | ||
95 | `noun_id` INTEGER NOT NULL, | ||
96 | `adjective_id` INTEGER NOT NULL, | ||
97 | FOREIGN KEY (`noun_id`) REFERENCES `nouns`(`noun_id`), | ||
98 | FOREIGN KEY (`adjective_id`) REFERENCES `adjectives`(`adjective_id`) | ||
99 | ); | ||
100 | |||
101 | DROP TABLE IF EXISTS `noun_antonymy`; | ||
102 | CREATE TABLE `noun_antonymy` ( | ||
103 | `noun_1_id` INTEGER NOT NULL, | ||
104 | `noun_2_id` INTEGER NOT NULL, | ||
105 | FOREIGN KEY (`noun_1_id`) REFERENCES `nouns`(`noun_id`), | ||
106 | FOREIGN KEY (`noun_2_id`) REFERENCES `nouns`(`noun_id`) | ||
107 | ); | ||
108 | |||
109 | DROP TABLE IF EXISTS `adjective_antonymy`; | ||
110 | CREATE TABLE `adjective_antonymy` ( | ||
111 | `adjective_1_id` INTEGER NOT NULL, | ||
112 | `adjective_2_id` INTEGER NOT NULL, | ||
113 | FOREIGN KEY (`adjective_1_id`) REFERENCES `adjectives`(`adjective_id`), | ||
114 | FOREIGN KEY (`adjective_2_id`) REFERENCES `adjectives`(`adjective_id`) | ||
115 | ); | ||
116 | |||
117 | DROP TABLE IF EXISTS `adverb_antonymy`; | ||
118 | CREATE TABLE `adverb_antonymy` ( | ||
119 | `adverb_1_id` INTEGER NOT NULL, | ||
120 | `adverb_2_id` INTEGER NOT NULL, | ||
121 | FOREIGN KEY (`adverb_1_id`) REFERENCES `adverbs`(`adverb_id`), | ||
122 | FOREIGN KEY (`adverb_2_id`) REFERENCES `adverbs`(`adverb_id`) | ||
123 | ); | ||
124 | |||
125 | DROP TABLE IF EXISTS `specification`; | ||
126 | CREATE TABLE `specification` ( | ||
127 | `general_id` INTEGER NOT NULL, | ||
128 | `specific_id` INTEGER NOT NULL, | ||
129 | FOREIGN KEY (`general_id`) REFERENCES `adjectives`(`adjective_id`), | ||
130 | FOREIGN KEY (`specific_id`) REFERENCES `adjectives`(`adjective_id`) | ||
131 | ); | ||
132 | |||
133 | DROP TABLE IF EXISTS `pertainymy`; | ||
134 | CREATE TABLE `pertainymy` ( | ||
135 | `noun_id` INTEGER NOT NULL, | ||
136 | `pertainym_id` INTEGER NOT NULL, | ||
137 | FOREIGN KEY (`noun_id`) REFERENCES `nouns`(`noun_id`), | ||
138 | FOREIGN KEY (`pertainym_id`) REFERENCES `adjectives`(`adjective_id`) | ||
139 | ); | ||
140 | |||
141 | DROP TABLE IF EXISTS `mannernymy`; | ||
142 | CREATE TABLE `mannernymy` ( | ||
143 | `adjective_id` INTEGER NOT NULL, | ||
144 | `mannernym_id` INTEGER NOT NULL, | ||
145 | FOREIGN KEY (`adjective_id`) REFERENCES `adjectives`(`adjective_id`), | ||
146 | FOREIGN KEY (`mannernym_id`) REFERENCES `adverbs`(`adverb_id`) | ||
147 | ); | ||
148 | |||
149 | DROP TABLE IF EXISTS `synonymy`; | ||
150 | CREATE TABLE `synonymy` ( | ||
151 | `adjective_1_id` INTEGER NOT NULL, | ||
152 | `adjective_2_id` INTEGER NOT NULL, | ||
153 | FOREIGN KEY (`adjective_1_id`) REFERENCES `adjectives`(`adjective_id`), | ||
154 | FOREIGN KEY (`adjective_2_id`) REFERENCES `adjectives`(`adjective_id`) | ||
155 | ); | ||
diff --git a/verbly/adjective.h b/verbly/adjective.h index 58c490e..9d7883f 100644 --- a/verbly/adjective.h +++ b/verbly/adjective.h | |||
@@ -8,7 +8,7 @@ namespace verbly { | |||
8 | int id; | 8 | int id; |
9 | 9 | ||
10 | public: | 10 | public: |
11 | std::string value; | 11 | std::string form; |
12 | 12 | ||
13 | adjective(int id) : id(id) | 13 | adjective(int id) : id(id) |
14 | { | 14 | { |
diff --git a/verbly/adverb.h b/verbly/adverb.h new file mode 100644 index 0000000..6d2466e --- /dev/null +++ b/verbly/adverb.h | |||
@@ -0,0 +1,21 @@ | |||
1 | #ifndef ADVERB_H_86F8302F | ||
2 | #define ADVERB_H_86F8302F | ||
3 | |||
4 | namespace verbly { | ||
5 | |||
6 | class adverb { | ||
7 | private: | ||
8 | int id; | ||
9 | |||
10 | public: | ||
11 | std::string form; | ||
12 | |||
13 | adverb(int id) : id(id) | ||
14 | { | ||
15 | |||
16 | } | ||
17 | }; | ||
18 | |||
19 | }; | ||
20 | |||
21 | #endif /* end of include guard: ADVERB_H_86F8302F */ | ||
diff --git a/verbly/data.h b/verbly/data.h index 2c23c15..e901cba 100644 --- a/verbly/data.h +++ b/verbly/data.h | |||
@@ -121,7 +121,7 @@ namespace verbly { | |||
121 | std::list<adjective> run() const | 121 | std::list<adjective> run() const |
122 | { | 122 | { |
123 | std::stringstream construct; | 123 | std::stringstream construct; |
124 | construct << "SELECT adjective_id, adjective FROM adjectives"; | 124 | construct << "SELECT adjective_id, form FROM adjectives"; |
125 | 125 | ||
126 | if (m_random) | 126 | if (m_random) |
127 | { | 127 | { |
@@ -144,7 +144,77 @@ namespace verbly { | |||
144 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | 144 | while (sqlite3_step(ppstmt) == SQLITE_ROW) |
145 | { | 145 | { |
146 | adjective tnc {sqlite3_column_int(ppstmt, 0)}; | 146 | adjective tnc {sqlite3_column_int(ppstmt, 0)}; |
147 | tnc.value = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 1))); | 147 | tnc.form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 1))); |
148 | |||
149 | output.push_back(tnc); | ||
150 | } | ||
151 | |||
152 | sqlite3_finalize(ppstmt); | ||
153 | |||
154 | return output; | ||
155 | } | ||
156 | |||
157 | }; | ||
158 | |||
159 | class adverb_query { | ||
160 | public: | ||
161 | const static int unlimited = -1; | ||
162 | |||
163 | private: | ||
164 | const data& database; | ||
165 | int m_limit = unlimited; | ||
166 | bool m_random = false; | ||
167 | |||
168 | public: | ||
169 | adverb_query(const data& database) : database(database) | ||
170 | { | ||
171 | |||
172 | } | ||
173 | |||
174 | adverb_query& limit(int m_limit) | ||
175 | { | ||
176 | if ((m_limit > 0) || (m_limit == unlimited)) | ||
177 | { | ||
178 | this->m_limit = m_limit; | ||
179 | } | ||
180 | |||
181 | return *this; | ||
182 | } | ||
183 | |||
184 | adverb_query& random(bool m_random) | ||
185 | { | ||
186 | this->m_random = m_random; | ||
187 | |||
188 | return *this; | ||
189 | } | ||
190 | |||
191 | std::list<adverb> run() const | ||
192 | { | ||
193 | std::stringstream construct; | ||
194 | construct << "SELECT adverb_id, form FROM adverbs"; | ||
195 | |||
196 | if (m_random) | ||
197 | { | ||
198 | construct << " ORDER BY RANDOM()"; | ||
199 | } | ||
200 | |||
201 | if (m_limit != unlimited) | ||
202 | { | ||
203 | construct << " LIMIT " << m_limit; | ||
204 | } | ||
205 | |||
206 | sqlite3_stmt* ppstmt; | ||
207 | std::string query = construct.str(); | ||
208 | if (sqlite3_prepare_v2(database.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
209 | { | ||
210 | throw std::runtime_error(sqlite3_errmsg(database.ppdb)); | ||
211 | } | ||
212 | |||
213 | std::list<adverb> output; | ||
214 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
215 | { | ||
216 | adverb tnc {sqlite3_column_int(ppstmt, 0)}; | ||
217 | tnc.form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 1))); | ||
148 | 218 | ||
149 | output.push_back(tnc); | 219 | output.push_back(tnc); |
150 | } | 220 | } |
@@ -194,6 +264,11 @@ namespace verbly { | |||
194 | return adjective_query(*this); | 264 | return adjective_query(*this); |
195 | } | 265 | } |
196 | 266 | ||
267 | adverb_query adverbs() const | ||
268 | { | ||
269 | return adverb_query(*this); | ||
270 | } | ||
271 | |||
197 | }; | 272 | }; |
198 | 273 | ||
199 | }; | 274 | }; |
diff --git a/verbly/token.h b/verbly/token.h index bbe7c2d..2848fd0 100644 --- a/verbly/token.h +++ b/verbly/token.h | |||
@@ -24,7 +24,8 @@ namespace verbly { | |||
24 | enum class fillin_type { | 24 | enum class fillin_type { |
25 | noun_phrase, | 25 | noun_phrase, |
26 | participle_phrase, | 26 | participle_phrase, |
27 | adjective | 27 | adjective, |
28 | adverb | ||
28 | }; | 29 | }; |
29 | 30 | ||
30 | class token { | 31 | class token { |
@@ -128,14 +129,14 @@ namespace verbly { | |||
128 | return it != other.it; | 129 | return it != other.it; |
129 | } | 130 | } |
130 | 131 | ||
131 | token* operator*() | 132 | token& operator*() |
132 | { | 133 | { |
133 | return *it->get(); | 134 | return **it; |
134 | } | 135 | } |
135 | 136 | ||
136 | token* operator->() | 137 | token& operator->() |
137 | { | 138 | { |
138 | return *it->get(); | 139 | return **it; |
139 | } | 140 | } |
140 | };*/ | 141 | };*/ |
141 | 142 | ||
@@ -189,16 +190,6 @@ namespace verbly { | |||
189 | return std::end(utterance); | 190 | return std::end(utterance); |
190 | } | 191 | } |
191 | 192 | ||
192 | const iterator begin() const | ||
193 | { | ||
194 | return std::begin(utterance); | ||
195 | } | ||
196 | |||
197 | const iterator end() const | ||
198 | { | ||
199 | return std::end(utterance); | ||
200 | } | ||
201 | |||
202 | void erase(iterator it) | 193 | void erase(iterator it) |
203 | { | 194 | { |
204 | utterance.erase(it); | 195 | utterance.erase(it); |
diff --git a/verbly/verbly.h b/verbly/verbly.h index 139d8f8..44fd3a8 100644 --- a/verbly/verbly.h +++ b/verbly/verbly.h | |||
@@ -5,6 +5,7 @@ | |||
5 | #include "token.h" | 5 | #include "token.h" |
6 | #include "verb.h" | 6 | #include "verb.h" |
7 | #include "adjective.h" | 7 | #include "adjective.h" |
8 | #include "adverb.h" | ||
8 | #include "data.h" | 9 | #include "data.h" |
9 | 10 | ||
10 | #endif /* end of include guard: VERBLY_H_5B39CE50 */ | 11 | #endif /* end of include guard: VERBLY_H_5B39CE50 */ |