diff options
| -rw-r--r-- | CMakeLists.txt | 6 | ||||
| -rw-r--r-- | furries.cpp | 16 | ||||
| -rw-r--r-- | generator.cpp | 1303 | ||||
| -rw-r--r-- | progress.h | 50 | ||||
| -rw-r--r-- | schema.sql | 59 | ||||
| -rw-r--r-- | verbly/adjective.cpp | 586 | ||||
| -rw-r--r-- | verbly/adjective.h | 126 | ||||
| -rw-r--r-- | verbly/adverb.cpp | 364 | ||||
| -rw-r--r-- | verbly/adverb.h | 75 | ||||
| -rw-r--r-- | verbly/data.cpp | 50 | ||||
| -rw-r--r-- | verbly/data.h | 275 | ||||
| -rw-r--r-- | verbly/noun.cpp | 916 | ||||
| -rw-r--r-- | verbly/noun.h | 171 | ||||
| -rw-r--r-- | verbly/token.cpp | 53 | ||||
| -rw-r--r-- | verbly/token.h | 82 | ||||
| -rw-r--r-- | verbly/util.h | 53 | ||||
| -rw-r--r-- | verbly/verb.cpp | 193 | ||||
| -rw-r--r-- | verbly/verb.h | 68 | ||||
| -rw-r--r-- | verbly/verbly.h | 7 | ||||
| -rw-r--r-- | verbly/word.cpp | 32 | ||||
| -rw-r--r-- | verbly/word.h | 35 |
21 files changed, 4043 insertions, 477 deletions
| diff --git a/CMakeLists.txt b/CMakeLists.txt index 0b6d991..3a884b5 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt | |||
| @@ -8,11 +8,15 @@ 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 | find_package(libxml2 REQUIRED) |
| 10 | 10 | ||
| 11 | add_library(verbly verbly/data.cpp verbly/adjective.cpp verbly/noun.cpp verbly/verb.cpp verbly/adverb.cpp verbly/token.cpp verbly/word.cpp) | ||
| 12 | set_property(TARGET verbly PROPERTY CXX_STANDARD 11) | ||
| 13 | set_property(TARGET verbly PROPERTY CXX_STANDARD_REQUIRED ON) | ||
| 14 | |||
| 11 | include_directories(vendor/twitcurl/libtwitcurl ${LIBXML2_INCLUDE_DIR} ${sqlite3_INCLUDE_DIR}) | 15 | include_directories(vendor/twitcurl/libtwitcurl ${LIBXML2_INCLUDE_DIR} ${sqlite3_INCLUDE_DIR}) |
| 12 | add_executable(furries furries.cpp) | 16 | add_executable(furries furries.cpp) |
| 13 | set_property(TARGET furries PROPERTY CXX_STANDARD 11) | 17 | set_property(TARGET furries PROPERTY CXX_STANDARD 11) |
| 14 | set_property(TARGET furries PROPERTY CXX_STANDARD_REQUIRED ON) | 18 | set_property(TARGET furries PROPERTY CXX_STANDARD_REQUIRED ON) |
| 15 | target_link_libraries(furries ${sqlite3_LIBRARIES} ${YamlCpp_LIBRARIES} twitcurl curl) | 19 | target_link_libraries(furries ${sqlite3_LIBRARIES} ${YamlCpp_LIBRARIES} twitcurl curl verbly) |
| 16 | 20 | ||
| 17 | add_executable(generator generator.cpp) | 21 | add_executable(generator generator.cpp) |
| 18 | set_property(TARGET generator PROPERTY CXX_STANDARD 11) | 22 | set_property(TARGET generator PROPERTY CXX_STANDARD 11) |
| diff --git a/furries.cpp b/furries.cpp index 0cce8bd..55dfb7b 100644 --- a/furries.cpp +++ b/furries.cpp | |||
| @@ -20,7 +20,7 @@ class fill_blanks { | |||
| 20 | { | 20 | { |
| 21 | switch (it->token_type()) | 21 | switch (it->token_type()) |
| 22 | { | 22 | { |
| 23 | case verbly::type::utterance: | 23 | case verbly::token::type::utterance: |
| 24 | { | 24 | { |
| 25 | auto& action = *dynamic_cast<verbly::utterance_token*>(it.get()); | 25 | auto& action = *dynamic_cast<verbly::utterance_token*>(it.get()); |
| 26 | for (auto& tkn : action) | 26 | for (auto& tkn : action) |
| @@ -36,14 +36,14 @@ class fill_blanks { | |||
| 36 | break; | 36 | break; |
| 37 | } | 37 | } |
| 38 | 38 | ||
| 39 | case verbly::type::fillin: | 39 | case verbly::token::type::fillin: |
| 40 | { | 40 | { |
| 41 | auto& tkn = *dynamic_cast<verbly::fillin_token*>(it.get()); | 41 | auto& tkn = *dynamic_cast<verbly::fillin_token*>(it.get()); |
| 42 | switch (tkn.fillin_type()) | 42 | switch (tkn.fillin_type()) |
| 43 | { | 43 | { |
| 44 | case verbly::fillin_type::participle_phrase: | 44 | case verbly::fillin_type::participle_phrase: |
| 45 | { | 45 | { |
| 46 | const verbly::verb& v = database.verbs().random(true).limit(1).run().front(); | 46 | verbly::verb v = database.verbs().random(true).limit(1).run().front(); |
| 47 | /*verbly::utterance_token phrase = verbly::random(v.frames).make_utterance(); | 47 | /*verbly::utterance_token phrase = verbly::random(v.frames).make_utterance(); |
| 48 | while (std::begin(phrase)->token_type() != verbly::type::verb) | 48 | while (std::begin(phrase)->token_type() != verbly::type::verb) |
| 49 | { | 49 | { |
| @@ -53,7 +53,7 @@ class fill_blanks { | |||
| 53 | *std::begin(phrase) = verbly::verb_token(v).conjugate(verbly::conjugation::present_participle); | 53 | *std::begin(phrase) = verbly::verb_token(v).conjugate(verbly::conjugation::present_participle); |
| 54 | *it = phrase;*/ | 54 | *it = phrase;*/ |
| 55 | auto avt = std::make_unique<verbly::verb_token>(v); | 55 | auto avt = std::make_unique<verbly::verb_token>(v); |
| 56 | avt->conjugate(verbly::conjugation::present_participle); | 56 | avt->inflect(verbly::verb_token::inflection::ing_form); |
| 57 | it = std::move(avt); | 57 | it = std::move(avt); |
| 58 | 58 | ||
| 59 | break; | 59 | break; |
| @@ -61,16 +61,16 @@ class fill_blanks { | |||
| 61 | 61 | ||
| 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 | verbly::adjective adj = database.adjectives().random(true).limit(1).run().front(); |
| 65 | it = std::make_unique<verbly::string_token>(adj.form); | 65 | it = std::make_unique<verbly::string_token>(adj.base_form()); |
| 66 | 66 | ||
| 67 | break; | 67 | break; |
| 68 | } | 68 | } |
| 69 | 69 | ||
| 70 | case verbly::fillin_type::adverb: | 70 | case verbly::fillin_type::adverb: |
| 71 | { | 71 | { |
| 72 | const verbly::adverb& adv = database.adverbs().random(true).limit(1).run().front(); | 72 | verbly::adverb adv = database.adverbs().random(true).limit(1).run().front(); |
| 73 | it = std::make_unique<verbly::string_token>(adv.form); | 73 | it = std::make_unique<verbly::string_token>(adv.base_form()); |
| 74 | 74 | ||
| 75 | break; | 75 | break; |
| 76 | } | 76 | } |
| diff --git a/generator.cpp b/generator.cpp index c389963..305d121 100644 --- a/generator.cpp +++ b/generator.cpp | |||
| @@ -9,6 +9,8 @@ | |||
| 9 | #include <sqlite3.h> | 9 | #include <sqlite3.h> |
| 10 | #include <sstream> | 10 | #include <sstream> |
| 11 | #include <regex> | 11 | #include <regex> |
| 12 | #include <list> | ||
| 13 | #include "progress.h" | ||
| 12 | 14 | ||
| 13 | struct verb { | 15 | struct verb { |
| 14 | std::string infinitive; | 16 | std::string infinitive; |
| @@ -18,6 +20,17 @@ struct verb { | |||
| 18 | std::string s_form; | 20 | std::string s_form; |
| 19 | }; | 21 | }; |
| 20 | 22 | ||
| 23 | struct adjective { | ||
| 24 | std::string base; | ||
| 25 | std::string comparative; | ||
| 26 | std::string superlative; | ||
| 27 | }; | ||
| 28 | |||
| 29 | struct noun { | ||
| 30 | std::string singular; | ||
| 31 | std::string plural; | ||
| 32 | }; | ||
| 33 | |||
| 21 | struct group { | 34 | struct group { |
| 22 | std::string id; | 35 | std::string id; |
| 23 | std::set<std::string> members; | 36 | std::set<std::string> members; |
| @@ -25,21 +38,33 @@ struct group { | |||
| 25 | 38 | ||
| 26 | std::map<std::string, group> groups; | 39 | std::map<std::string, group> groups; |
| 27 | std::map<std::string, verb> verbs; | 40 | std::map<std::string, verb> verbs; |
| 41 | std::map<std::string, adjective> adjectives; | ||
| 42 | std::map<std::string, noun> nouns; | ||
| 28 | std::map<int, std::map<int, int>> wn; | 43 | std::map<int, std::map<int, int>> wn; |
| 44 | std::map<std::string, std::set<std::string>> pronunciations; | ||
| 29 | 45 | ||
| 30 | void print_usage() | 46 | void print_usage() |
| 31 | { | 47 | { |
| 32 | std::cout << "Verbly Datafile Generator" << std::endl; | 48 | std::cout << "Verbly Datafile Generator" << std::endl; |
| 33 | std::cout << "-------------------------" << std::endl; | 49 | std::cout << "-------------------------" << std::endl; |
| 34 | std::cout << "Requires exactly four arguments." << std::endl; | 50 | std::cout << "Requires exactly six arguments." << std::endl; |
| 35 | std::cout << "1. The path to a VerbNet data directory." << std::endl; | 51 | 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; | 52 | 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; | 53 | 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; | 54 | std::cout << "4. The path to a WordNet prolog data directory." << std::endl; |
| 39 | std::cout << "5. Datafile output path." << std::endl; | 55 | std::cout << "5. The path to a CMUDICT pronunciation file." << std::endl; |
| 56 | std::cout << "6. Datafile output path." << std::endl; | ||
| 40 | 57 | ||
| 41 | exit(1); | 58 | exit(1); |
| 42 | } | 59 | } |
| 60 | |||
| 61 | void db_error(sqlite3* ppdb, std::string) | ||
| 62 | { | ||
| 63 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | ||
| 64 | sqlite3_close_v2(ppdb); | ||
| 65 | print_usage(); | ||
| 66 | } | ||
| 67 | |||
| 43 | /* | 68 | /* |
| 44 | void parse_group(xmlNodePtr top, std::string filename) | 69 | void parse_group(xmlNodePtr top, std::string filename) |
| 45 | { | 70 | { |
| @@ -87,7 +112,7 @@ void parse_group(xmlNodePtr top, std::string filename) | |||
| 87 | 112 | ||
| 88 | int main(int argc, char** argv) | 113 | int main(int argc, char** argv) |
| 89 | { | 114 | { |
| 90 | if (argc != 6) | 115 | if (argc != 7) |
| 91 | { | 116 | { |
| 92 | print_usage(); | 117 | print_usage(); |
| 93 | } | 118 | } |
| @@ -137,7 +162,7 @@ int main(int argc, char** argv) | |||
| 137 | closedir(dir);*/ | 162 | closedir(dir);*/ |
| 138 | 163 | ||
| 139 | // Get verbs from AGID | 164 | // Get verbs from AGID |
| 140 | std::cout << "Reading verb inflection..." << std::endl; | 165 | std::cout << "Reading inflections..." << std::endl; |
| 141 | 166 | ||
| 142 | std::ifstream agidfile(argv[3]); | 167 | std::ifstream agidfile(argv[3]); |
| 143 | if (!agidfile.is_open()) | 168 | if (!agidfile.is_open()) |
| @@ -162,11 +187,7 @@ int main(int argc, char** argv) | |||
| 162 | int divider = line.find_first_of(" "); | 187 | int divider = line.find_first_of(" "); |
| 163 | std::string word = line.substr(0, divider); | 188 | std::string word = line.substr(0, divider); |
| 164 | line = line.substr(divider+1); | 189 | line = line.substr(divider+1); |
| 165 | 190 | char type = line[0]; | |
| 166 | if (line[0] != 'V') | ||
| 167 | { | ||
| 168 | continue; | ||
| 169 | } | ||
| 170 | 191 | ||
| 171 | if (line[1] == '?') | 192 | if (line[1] == '?') |
| 172 | { | 193 | { |
| @@ -174,7 +195,7 @@ int main(int argc, char** argv) | |||
| 174 | } else { | 195 | } else { |
| 175 | line.erase(0, 3); | 196 | line.erase(0, 3); |
| 176 | } | 197 | } |
| 177 | 198 | ||
| 178 | std::vector<std::string> forms; | 199 | std::vector<std::string> forms; |
| 179 | while (!line.empty()) | 200 | while (!line.empty()) |
| 180 | { | 201 | { |
| @@ -187,52 +208,129 @@ int main(int argc, char** argv) | |||
| 187 | inflection = line; | 208 | inflection = line; |
| 188 | line = ""; | 209 | line = ""; |
| 189 | } | 210 | } |
| 190 | 211 | ||
| 191 | if ((divider = inflection.find_first_of(",?")) != std::string::npos) | 212 | if ((divider = inflection.find_first_of(",?")) != std::string::npos) |
| 192 | { | 213 | { |
| 193 | inflection = inflection.substr(0, divider); | 214 | inflection = inflection.substr(0, divider); |
| 194 | } | 215 | } |
| 195 | 216 | ||
| 196 | forms.push_back(inflection); | 217 | forms.push_back(inflection); |
| 197 | } | 218 | } |
| 198 | 219 | ||
| 199 | verb v; | 220 | switch (type) |
| 200 | v.infinitive = word; | ||
| 201 | if (forms.size() == 4) | ||
| 202 | { | 221 | { |
| 203 | v.past_tense = forms[0]; | 222 | case 'V': |
| 204 | v.past_participle = forms[1]; | 223 | { |
| 205 | v.ing_form = forms[2]; | 224 | verb v; |
| 206 | v.s_form = forms[3]; | 225 | v.infinitive = word; |
| 207 | } else if (forms.size() == 3) | 226 | if (forms.size() == 4) |
| 227 | { | ||
| 228 | v.past_tense = forms[0]; | ||
| 229 | v.past_participle = forms[1]; | ||
| 230 | v.ing_form = forms[2]; | ||
| 231 | v.s_form = forms[3]; | ||
| 232 | } else if (forms.size() == 3) | ||
| 233 | { | ||
| 234 | v.past_tense = forms[0]; | ||
| 235 | v.past_participle = forms[0]; | ||
| 236 | v.ing_form = forms[1]; | ||
| 237 | v.s_form = forms[2]; | ||
| 238 | } else if (forms.size() == 8) | ||
| 239 | { | ||
| 240 | // As of AGID 2014.08.11, this is only "to be" | ||
| 241 | v.past_tense = forms[0]; | ||
| 242 | v.past_participle = forms[2]; | ||
| 243 | v.ing_form = forms[3]; | ||
| 244 | v.s_form = forms[4]; | ||
| 245 | } else { | ||
| 246 | // Words that don't fit the cases above as of AGID 2014.08.11: | ||
| 247 | // - may and shall do not conjugate the way we want them to | ||
| 248 | // - methinks only has a past tense and is an outlier | ||
| 249 | // - wit has five forms, and is archaic/obscure enough that we can ignore it for now | ||
| 250 | std::cout << "Ignoring verb \"" << word << "\" due to non-standard number of forms." << std::endl; | ||
| 251 | } | ||
| 252 | |||
| 253 | verbs[word] = v; | ||
| 254 | |||
| 255 | break; | ||
| 256 | } | ||
| 257 | |||
| 258 | case 'A': | ||
| 259 | { | ||
| 260 | adjective adj; | ||
| 261 | adj.base = word; | ||
| 262 | if (forms.size() == 2) | ||
| 263 | { | ||
| 264 | adj.comparative = forms[0]; | ||
| 265 | adj.superlative = forms[1]; | ||
| 266 | } else { | ||
| 267 | // As of AGID 2014.08.11, this is only "only", which has only the form "onliest" | ||
| 268 | std::cout << "Ignoring adjective/adverb \"" << word << "\" due to non-standard number of forms." << std::endl; | ||
| 269 | } | ||
| 270 | |||
| 271 | adjectives[word] = adj; | ||
| 272 | |||
| 273 | break; | ||
| 274 | } | ||
| 275 | |||
| 276 | case 'N': | ||
| 277 | { | ||
| 278 | noun n; | ||
| 279 | n.singular = word; | ||
| 280 | if (forms.size() == 1) | ||
| 281 | { | ||
| 282 | n.plural = forms[0]; | ||
| 283 | } else { | ||
| 284 | // As of AGID 2014.08.11, this is non-existent. | ||
| 285 | std::cout << "Ignoring noun \"" << word << "\" due to non-standard number of forms." << std::endl; | ||
| 286 | } | ||
| 287 | |||
| 288 | nouns[word] = n; | ||
| 289 | |||
| 290 | break; | ||
| 291 | } | ||
| 292 | } | ||
| 293 | } | ||
| 294 | |||
| 295 | // Pronounciations | ||
| 296 | std::cout << "Reading pronunciations..." << std::endl; | ||
| 297 | |||
| 298 | std::ifstream pronfile(argv[5]); | ||
| 299 | if (!pronfile.is_open()) | ||
| 300 | { | ||
| 301 | std::cout << "Could not open CMUDICT file: " << argv[5] << std::endl; | ||
| 302 | print_usage(); | ||
| 303 | } | ||
| 304 | |||
| 305 | for (;;) | ||
| 306 | { | ||
| 307 | std::string line; | ||
| 308 | if (!getline(pronfile, line)) | ||
| 208 | { | 309 | { |
| 209 | v.past_tense = forms[0]; | 310 | break; |
| 210 | v.past_participle = forms[0]; | 311 | } |
| 211 | v.ing_form = forms[1]; | 312 | |
| 212 | v.s_form = forms[2]; | 313 | if (line.back() == '\r') |
| 213 | } else if (forms.size() == 8) | ||
| 214 | { | 314 | { |
| 215 | // As of AGID 2014.08.11, this is only "to be" | 315 | line.pop_back(); |
| 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 | } | 316 | } |
| 227 | 317 | ||
| 228 | verbs[word] = v; | 318 | std::regex phoneme("([A-Z][^ \\(]*)(?:\\(\\d+\\))? ([A-Z 0-9]+)"); |
| 319 | std::smatch phoneme_data; | ||
| 320 | if (std::regex_search(line, phoneme_data, phoneme)) | ||
| 321 | { | ||
| 322 | std::string canonical(phoneme_data[1]); | ||
| 323 | std::transform(std::begin(canonical), std::end(canonical), std::begin(canonical), ::tolower); | ||
| 324 | |||
| 325 | pronunciations[canonical].insert(phoneme_data[2]); | ||
| 326 | } | ||
| 229 | } | 327 | } |
| 230 | 328 | ||
| 231 | // Start writing output | 329 | // Start writing output |
| 232 | std::cout << "Writing output..." << std::endl; | 330 | std::cout << "Writing schema..." << std::endl; |
| 233 | 331 | ||
| 234 | sqlite3* ppdb; | 332 | sqlite3* ppdb; |
| 235 | if (sqlite3_open_v2(argv[5], &ppdb, SQLITE_OPEN_READWRITE | SQLITE_OPEN_CREATE, NULL) != SQLITE_OK) | 333 | if (sqlite3_open_v2(argv[6], &ppdb, SQLITE_OPEN_READWRITE | SQLITE_OPEN_CREATE, NULL) != SQLITE_OK) |
| 236 | { | 334 | { |
| 237 | std::cout << "Error opening output datafile: " << sqlite3_errmsg(ppdb) << std::endl; | 335 | std::cout << "Error opening output datafile: " << sqlite3_errmsg(ppdb) << std::endl; |
| 238 | print_usage(); | 336 | print_usage(); |
| @@ -278,47 +376,82 @@ int main(int argc, char** argv) | |||
| 278 | sqlite3_stmt* schmstmt; | 376 | sqlite3_stmt* schmstmt; |
| 279 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &schmstmt, NULL) != SQLITE_OK) | 377 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &schmstmt, NULL) != SQLITE_OK) |
| 280 | { | 378 | { |
| 281 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | 379 | db_error(ppdb, query); |
| 282 | sqlite3_close_v2(ppdb); | ||
| 283 | print_usage(); | ||
| 284 | } | 380 | } |
| 285 | 381 | ||
| 286 | if (sqlite3_step(schmstmt) != SQLITE_DONE) | 382 | if (sqlite3_step(schmstmt) != SQLITE_DONE) |
| 287 | { | 383 | { |
| 288 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | 384 | db_error(ppdb, query); |
| 289 | sqlite3_close_v2(ppdb); | ||
| 290 | print_usage(); | ||
| 291 | } | 385 | } |
| 292 | 386 | ||
| 293 | sqlite3_finalize(schmstmt); | 387 | sqlite3_finalize(schmstmt); |
| 294 | } | 388 | } |
| 295 | 389 | ||
| 296 | std::cout << "Writing verbs..." << std::endl; | ||
| 297 | for (auto& mapping : verbs) | ||
| 298 | { | 390 | { |
| 299 | sqlite3_stmt* ppstmt; | 391 | progress ppgs("Writing verbs...", verbs.size()); |
| 300 | std::string query("INSERT INTO verbs (infinitive, past_tense, past_participle, ing_form, s_form) VALUES (?, ?, ?, ?, ?)"); | 392 | for (auto& mapping : verbs) |
| 301 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 302 | { | 393 | { |
| 303 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | 394 | sqlite3_stmt* ppstmt; |
| 304 | sqlite3_close_v2(ppdb); | 395 | std::string query("INSERT INTO verbs (infinitive, past_tense, past_participle, ing_form, s_form) VALUES (?, ?, ?, ?, ?)"); |
| 305 | print_usage(); | 396 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) |
| 306 | } | 397 | { |
| 398 | db_error(ppdb, query); | ||
| 399 | } | ||
| 307 | 400 | ||
| 308 | sqlite3_bind_text(ppstmt, 1, mapping.second.infinitive.c_str(), mapping.second.infinitive.length(), SQLITE_STATIC); | 401 | 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); | 402 | 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); | 403 | 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); | 404 | 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); | 405 | sqlite3_bind_text(ppstmt, 5, mapping.second.s_form.c_str(), mapping.second.s_form.length(), SQLITE_STATIC); |
| 313 | 406 | ||
| 314 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | 407 | if (sqlite3_step(ppstmt) != SQLITE_DONE) |
| 315 | { | 408 | { |
| 316 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | 409 | db_error(ppdb, query); |
| 317 | sqlite3_close_v2(ppdb); | 410 | } |
| 318 | print_usage(); | ||
| 319 | } | ||
| 320 | 411 | ||
| 321 | sqlite3_finalize(ppstmt); | 412 | sqlite3_finalize(ppstmt); |
| 413 | |||
| 414 | std::string canonical(mapping.second.infinitive); | ||
| 415 | std::transform(std::begin(canonical), std::end(canonical), std::begin(canonical), ::tolower); | ||
| 416 | if (pronunciations.count(canonical) == 1) | ||
| 417 | { | ||
| 418 | query = "SELECT last_insert_rowid()"; | ||
| 419 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 420 | { | ||
| 421 | db_error(ppdb, query); | ||
| 422 | } | ||
| 423 | |||
| 424 | if (sqlite3_step(ppstmt) != SQLITE_ROW) | ||
| 425 | { | ||
| 426 | db_error(ppdb, query); | ||
| 427 | } | ||
| 428 | |||
| 429 | int rowid = sqlite3_column_int(ppstmt, 0); | ||
| 430 | |||
| 431 | sqlite3_finalize(ppstmt); | ||
| 432 | |||
| 433 | for (auto pronunciation : pronunciations[canonical]) | ||
| 434 | { | ||
| 435 | query = "INSERT INTO verb_pronunciations (verb_id, pronunciation) VALUES (?, ?)"; | ||
| 436 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 437 | { | ||
| 438 | db_error(ppdb, query); | ||
| 439 | } | ||
| 440 | |||
| 441 | sqlite3_bind_int(ppstmt, 1, rowid); | ||
| 442 | sqlite3_bind_text(ppstmt, 2, pronunciation.c_str(), pronunciation.length(), SQLITE_STATIC); | ||
| 443 | |||
| 444 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 445 | { | ||
| 446 | db_error(ppdb, query); | ||
| 447 | } | ||
| 448 | |||
| 449 | sqlite3_finalize(ppstmt); | ||
| 450 | } | ||
| 451 | } | ||
| 452 | |||
| 453 | ppgs.update(); | ||
| 454 | } | ||
| 322 | } | 455 | } |
| 323 | 456 | ||
| 324 | // Get nouns/adjectives/adverbs from WordNet | 457 | // Get nouns/adjectives/adverbs from WordNet |
| @@ -342,110 +475,1046 @@ int main(int argc, char** argv) | |||
| 342 | wnpref += '/'; | 475 | wnpref += '/'; |
| 343 | } | 476 | } |
| 344 | 477 | ||
| 345 | std::cout << "Reading words from WordNet..." << std::endl; | 478 | // s table |
| 346 | std::ifstream wnsfile(wnpref + "wn_s.pl"); | ||
| 347 | if (!wnsfile.is_open()) | ||
| 348 | { | 479 | { |
| 349 | std::cout << "Invalid WordNet data directory." << std::endl; | 480 | std::ifstream wnsfile(wnpref + "wn_s.pl"); |
| 350 | print_usage(); | 481 | if (!wnsfile.is_open()) |
| 482 | { | ||
| 483 | std::cout << "Invalid WordNet data directory." << std::endl; | ||
| 484 | print_usage(); | ||
| 485 | } | ||
| 486 | |||
| 487 | std::list<std::string> lines; | ||
| 488 | for (;;) | ||
| 489 | { | ||
| 490 | std::string line; | ||
| 491 | if (!getline(wnsfile, line)) | ||
| 492 | { | ||
| 493 | break; | ||
| 494 | } | ||
| 495 | |||
| 496 | if (line.back() == '\r') | ||
| 497 | { | ||
| 498 | line.pop_back(); | ||
| 499 | } | ||
| 500 | |||
| 501 | lines.push_back(line); | ||
| 502 | } | ||
| 503 | |||
| 504 | progress ppgs("Writing nouns, adjectives, and adverbs...", lines.size()); | ||
| 505 | for (auto line : lines) | ||
| 506 | { | ||
| 507 | ppgs.update(); | ||
| 508 | |||
| 509 | std::regex relation("^s\\(([134]\\d{8}),(\\d+),'([\\w ]+)',"); | ||
| 510 | std::smatch relation_data; | ||
| 511 | if (!std::regex_search(line, relation_data, relation)) | ||
| 512 | { | ||
| 513 | continue; | ||
| 514 | } | ||
| 515 | |||
| 516 | int synset_id = stoi(relation_data[1]); | ||
| 517 | int wnum = stoi(relation_data[2]); | ||
| 518 | std::string word = relation_data[3]; | ||
| 519 | |||
| 520 | std::string query; | ||
| 521 | switch (synset_id / 100000000) | ||
| 522 | { | ||
| 523 | case 1: // Noun | ||
| 524 | { | ||
| 525 | if (nouns.count(word) == 1) | ||
| 526 | { | ||
| 527 | query = "INSERT INTO nouns (singular, plural) VALUES (?, ?)"; | ||
| 528 | } else { | ||
| 529 | query = "INSERT INTO nouns (singular) VALUES (?)"; | ||
| 530 | } | ||
| 531 | |||
| 532 | break; | ||
| 533 | } | ||
| 534 | |||
| 535 | case 2: // Verb | ||
| 536 | { | ||
| 537 | // Ignore | ||
| 538 | |||
| 539 | break; | ||
| 540 | } | ||
| 541 | |||
| 542 | case 3: // Adjective | ||
| 543 | { | ||
| 544 | if (adjectives.count(word) == 1) | ||
| 545 | { | ||
| 546 | query = "INSERT INTO adjectives (base_form, comparative, superlative) VALUES (?, ?, ?)"; | ||
| 547 | } else { | ||
| 548 | query = "INSERT INTO adjectives (base_form) VALUES (?)"; | ||
| 549 | } | ||
| 550 | |||
| 551 | break; | ||
| 552 | } | ||
| 553 | |||
| 554 | case 4: // Adverb | ||
| 555 | { | ||
| 556 | if (adjectives.count(word) == 1) | ||
| 557 | { | ||
| 558 | query = "INSERT INTO adverbs (base_form, comparative, superlative) VALUES (?, ?, ?)"; | ||
| 559 | } else { | ||
| 560 | query = "INSERT INTO adverbs (base_form) VALUES (?)"; | ||
| 561 | } | ||
| 562 | |||
| 563 | break; | ||
| 564 | } | ||
| 565 | } | ||
| 566 | |||
| 567 | sqlite3_stmt* ppstmt; | ||
| 568 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 569 | { | ||
| 570 | db_error(ppdb, query); | ||
| 571 | } | ||
| 572 | |||
| 573 | sqlite3_bind_text(ppstmt, 1, word.c_str(), word.length(), SQLITE_STATIC); | ||
| 574 | switch (synset_id / 100000000) | ||
| 575 | { | ||
| 576 | case 1: // Noun | ||
| 577 | { | ||
| 578 | if (nouns.count(word) == 1) | ||
| 579 | { | ||
| 580 | sqlite3_bind_text(ppstmt, 2, nouns[word].plural.c_str(), nouns[word].plural.length(), SQLITE_STATIC); | ||
| 581 | } | ||
| 582 | |||
| 583 | break; | ||
| 584 | } | ||
| 585 | |||
| 586 | case 3: // Adjective | ||
| 587 | case 4: // Adverb | ||
| 588 | { | ||
| 589 | if (adjectives.count(word) == 1) | ||
| 590 | { | ||
| 591 | sqlite3_bind_text(ppstmt, 2, adjectives[word].comparative.c_str(), adjectives[word].comparative.length(), SQLITE_STATIC); | ||
| 592 | sqlite3_bind_text(ppstmt, 3, adjectives[word].superlative.c_str(), adjectives[word].superlative.length(), SQLITE_STATIC); | ||
| 593 | } | ||
| 594 | |||
| 595 | break; | ||
| 596 | } | ||
| 597 | } | ||
| 598 | |||
| 599 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 600 | { | ||
| 601 | db_error(ppdb, query); | ||
| 602 | } | ||
| 603 | |||
| 604 | sqlite3_finalize(ppstmt); | ||
| 605 | |||
| 606 | query = "SELECT last_insert_rowid()"; | ||
| 607 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 608 | { | ||
| 609 | db_error(ppdb, query); | ||
| 610 | } | ||
| 611 | |||
| 612 | if (sqlite3_step(ppstmt) != SQLITE_ROW) | ||
| 613 | { | ||
| 614 | db_error(ppdb, query); | ||
| 615 | } | ||
| 616 | |||
| 617 | int rowid = sqlite3_column_int(ppstmt, 0); | ||
| 618 | wn[synset_id][wnum] = rowid; | ||
| 619 | |||
| 620 | sqlite3_finalize(ppstmt); | ||
| 621 | |||
| 622 | std::string canonical(word); | ||
| 623 | std::transform(std::begin(canonical), std::end(canonical), std::begin(canonical), ::tolower); | ||
| 624 | if (pronunciations.count(canonical) == 1) | ||
| 625 | { | ||
| 626 | for (auto pronunciation : pronunciations[canonical]) | ||
| 627 | { | ||
| 628 | switch (synset_id / 100000000) | ||
| 629 | { | ||
| 630 | case 1: // Noun | ||
| 631 | { | ||
| 632 | query = "INSERT INTO noun_pronunciations (noun_id, pronunciation) VALUES (?, ?)"; | ||
| 633 | |||
| 634 | break; | ||
| 635 | } | ||
| 636 | |||
| 637 | case 3: // Adjective | ||
| 638 | { | ||
| 639 | query = "INSERT INTO adjective_pronunciations (adjective_id, pronunciation) VALUES (?, ?)"; | ||
| 640 | |||
| 641 | break; | ||
| 642 | } | ||
| 643 | |||
| 644 | case 4: // Adverb | ||
| 645 | { | ||
| 646 | query = "INSERT INTO adverb_pronunciations (adverb_id, pronunciation) VALUES (?, ?)"; | ||
| 647 | |||
| 648 | break; | ||
| 649 | } | ||
| 650 | } | ||
| 651 | |||
| 652 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 653 | { | ||
| 654 | db_error(ppdb, query); | ||
| 655 | } | ||
| 656 | |||
| 657 | sqlite3_bind_int(ppstmt, 1, rowid); | ||
| 658 | sqlite3_bind_text(ppstmt, 2, pronunciation.c_str(), pronunciation.length(), SQLITE_STATIC); | ||
| 659 | |||
| 660 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 661 | { | ||
| 662 | db_error(ppdb, query); | ||
| 663 | } | ||
| 664 | |||
| 665 | sqlite3_finalize(ppstmt); | ||
| 666 | } | ||
| 667 | } | ||
| 668 | } | ||
| 351 | } | 669 | } |
| 352 | 670 | ||
| 353 | for (;;) | 671 | // While we're working on s |
| 354 | { | 672 | { |
| 355 | std::string line; | 673 | progress ppgs("Writing word synonyms...", wn.size()); |
| 356 | if (!getline(wnsfile, line)) | 674 | for (auto sense : wn) |
| 357 | { | 675 | { |
| 358 | break; | 676 | ppgs.update(); |
| 677 | |||
| 678 | for (auto word1 : sense.second) | ||
| 679 | { | ||
| 680 | for (auto word2 : sense.second) | ||
| 681 | { | ||
| 682 | if (word1 != word2) | ||
| 683 | { | ||
| 684 | std::string query; | ||
| 685 | switch (sense.first / 100000000) | ||
| 686 | { | ||
| 687 | case 1: // Noun | ||
| 688 | { | ||
| 689 | query = "INSERT INTO noun_synonymy (noun_1_id, noun_2_id) VALUES (?, ?)"; | ||
| 690 | |||
| 691 | break; | ||
| 692 | } | ||
| 693 | |||
| 694 | case 2: // Verb | ||
| 695 | { | ||
| 696 | // Ignore | ||
| 697 | |||
| 698 | break; | ||
| 699 | } | ||
| 700 | |||
| 701 | case 3: // Adjective | ||
| 702 | { | ||
| 703 | query = "INSERT INTO adjective_synonymy (adjective_1_id, adjective_2_id) VALUES (?, ?)"; | ||
| 704 | |||
| 705 | break; | ||
| 706 | } | ||
| 707 | |||
| 708 | case 4: // Adverb | ||
| 709 | { | ||
| 710 | query = "INSERT INTO adverb_synonymy (adverb_1_id, adverb_2_id) VALUES (?, ?)"; | ||
| 711 | |||
| 712 | break; | ||
| 713 | } | ||
| 714 | } | ||
| 715 | |||
| 716 | sqlite3_stmt* ppstmt; | ||
| 717 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 718 | { | ||
| 719 | db_error(ppdb, query); | ||
| 720 | } | ||
| 721 | |||
| 722 | sqlite3_bind_int(ppstmt, 1, word1.second); | ||
| 723 | sqlite3_bind_int(ppstmt, 2, word2.second); | ||
| 724 | |||
| 725 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 726 | { | ||
| 727 | db_error(ppdb, query); | ||
| 728 | } | ||
| 729 | |||
| 730 | sqlite3_finalize(ppstmt); | ||
| 731 | } | ||
| 732 | } | ||
| 733 | } | ||
| 734 | } | ||
| 735 | } | ||
| 736 | |||
| 737 | // ant table | ||
| 738 | { | ||
| 739 | std::ifstream wnantfile(wnpref + "wn_ant.pl"); | ||
| 740 | if (!wnantfile.is_open()) | ||
| 741 | { | ||
| 742 | std::cout << "Invalid WordNet data directory." << std::endl; | ||
| 743 | print_usage(); | ||
| 359 | } | 744 | } |
| 745 | |||
| 746 | std::list<std::string> lines; | ||
| 747 | for (;;) | ||
| 748 | { | ||
| 749 | std::string line; | ||
| 750 | if (!getline(wnantfile, line)) | ||
| 751 | { | ||
| 752 | break; | ||
| 753 | } | ||
| 360 | 754 | ||
| 361 | if (line.back() == '\r') | 755 | if (line.back() == '\r') |
| 756 | { | ||
| 757 | line.pop_back(); | ||
| 758 | } | ||
| 759 | |||
| 760 | lines.push_back(line); | ||
| 761 | } | ||
| 762 | |||
| 763 | progress ppgs("Writing antonyms...", lines.size()); | ||
| 764 | for (auto line : lines) | ||
| 362 | { | 765 | { |
| 363 | line.pop_back(); | 766 | ppgs.update(); |
| 767 | |||
| 768 | std::regex relation("^ant\\(([134]\\d{8}),(\\d+),([134]\\d{8}),(\\d+)\\)\\."); | ||
| 769 | std::smatch relation_data; | ||
| 770 | if (!std::regex_search(line, relation_data, relation)) | ||
| 771 | { | ||
| 772 | continue; | ||
| 773 | } | ||
| 774 | |||
| 775 | int synset_id_1 = stoi(relation_data[1]); | ||
| 776 | int wnum_1 = stoi(relation_data[2]); | ||
| 777 | int synset_id_2 = stoi(relation_data[3]); | ||
| 778 | int wnum_2 = stoi(relation_data[4]); | ||
| 779 | |||
| 780 | std::string query; | ||
| 781 | switch (synset_id_1 / 100000000) | ||
| 782 | { | ||
| 783 | case 1: // Noun | ||
| 784 | { | ||
| 785 | query = "INSERT INTO noun_antonymy (noun_1_id, noun_2_id) VALUES (?, ?)"; | ||
| 786 | |||
| 787 | break; | ||
| 788 | } | ||
| 789 | |||
| 790 | case 2: // Verb | ||
| 791 | { | ||
| 792 | // Ignore | ||
| 793 | |||
| 794 | break; | ||
| 795 | } | ||
| 796 | |||
| 797 | case 3: // Adjective | ||
| 798 | { | ||
| 799 | query = "INSERT INTO adjective_antonymy (adjective_1_id, adjective_2_id) VALUES (?, ?)"; | ||
| 800 | |||
| 801 | break; | ||
| 802 | } | ||
| 803 | |||
| 804 | case 4: // Adverb | ||
| 805 | { | ||
| 806 | query = "INSERT INTO adverb_antonymy (adverb_1_id, adverb_2_id) VALUES (?, ?)"; | ||
| 807 | |||
| 808 | break; | ||
| 809 | } | ||
| 810 | } | ||
| 811 | |||
| 812 | sqlite3_stmt* ppstmt; | ||
| 813 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 814 | { | ||
| 815 | db_error(ppdb, query); | ||
| 816 | } | ||
| 817 | |||
| 818 | sqlite3_bind_int(ppstmt, 1, wn[synset_id_1][wnum_1]); | ||
| 819 | sqlite3_bind_int(ppstmt, 2, wn[synset_id_2][wnum_2]); | ||
| 820 | |||
| 821 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 822 | { | ||
| 823 | db_error(ppdb, query); | ||
| 824 | } | ||
| 825 | |||
| 826 | sqlite3_finalize(ppstmt); | ||
| 827 | } | ||
| 828 | } | ||
| 829 | |||
| 830 | // at table | ||
| 831 | { | ||
| 832 | std::ifstream wnatfile(wnpref + "wn_at.pl"); | ||
| 833 | if (!wnatfile.is_open()) | ||
| 834 | { | ||
| 835 | std::cout << "Invalid WordNet data directory." << std::endl; | ||
| 836 | print_usage(); | ||
| 364 | } | 837 | } |
| 838 | |||
| 839 | std::list<std::string> lines; | ||
| 840 | for (;;) | ||
| 841 | { | ||
| 842 | std::string line; | ||
| 843 | if (!getline(wnatfile, line)) | ||
| 844 | { | ||
| 845 | break; | ||
| 846 | } | ||
| 365 | 847 | ||
| 366 | std::regex relation("^s\\(([134]\\d{8}),(\\d+),'([\\w ]+)',"); | 848 | if (line.back() == '\r') |
| 367 | std::smatch relation_data; | 849 | { |
| 368 | if (!std::regex_search(line, relation_data, relation)) | 850 | line.pop_back(); |
| 851 | } | ||
| 852 | |||
| 853 | lines.push_back(line); | ||
| 854 | } | ||
| 855 | |||
| 856 | progress ppgs("Writing variations...", lines.size()); | ||
| 857 | for (auto line : lines) | ||
| 369 | { | 858 | { |
| 370 | continue; | 859 | ppgs.update(); |
| 860 | |||
| 861 | std::regex relation("^at\\((1\\d{8}),(3\\d{8})\\)\\."); | ||
| 862 | std::smatch relation_data; | ||
| 863 | if (!std::regex_search(line, relation_data, relation)) | ||
| 864 | { | ||
| 865 | continue; | ||
| 866 | } | ||
| 867 | |||
| 868 | int synset_id_1 = stoi(relation_data[1]); | ||
| 869 | int synset_id_2 = stoi(relation_data[2]); | ||
| 870 | std::string query("INSERT INTO variation (noun_id, adjective_id) VALUES (?, ?)"); | ||
| 871 | |||
| 872 | for (auto mapping1 : wn[synset_id_1]) | ||
| 873 | { | ||
| 874 | for (auto mapping2 : wn[synset_id_2]) | ||
| 875 | { | ||
| 876 | sqlite3_stmt* ppstmt; | ||
| 877 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.size(), &ppstmt, NULL) != SQLITE_OK) | ||
| 878 | { | ||
| 879 | db_error(ppdb, query); | ||
| 880 | } | ||
| 881 | |||
| 882 | sqlite3_bind_int(ppstmt, 1, mapping1.second); | ||
| 883 | sqlite3_bind_int(ppstmt, 2, mapping2.second); | ||
| 884 | |||
| 885 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 886 | { | ||
| 887 | db_error(ppdb, query); | ||
| 888 | } | ||
| 889 | |||
| 890 | sqlite3_finalize(ppstmt); | ||
| 891 | } | ||
| 892 | } | ||
| 371 | } | 893 | } |
| 894 | } | ||
| 895 | |||
| 896 | // hyp table | ||
| 897 | { | ||
| 898 | std::ifstream wnhypfile(wnpref + "wn_hyp.pl"); | ||
| 899 | if (!wnhypfile.is_open()) | ||
| 900 | { | ||
| 901 | std::cout << "Invalid WordNet data directory." << std::endl; | ||
| 902 | print_usage(); | ||
| 903 | } | ||
| 904 | |||
| 905 | std::list<std::string> lines; | ||
| 906 | for (;;) | ||
| 907 | { | ||
| 908 | std::string line; | ||
| 909 | if (!getline(wnhypfile, line)) | ||
| 910 | { | ||
| 911 | break; | ||
| 912 | } | ||
| 372 | 913 | ||
| 373 | int synset_id = stoi(relation_data[1]); | 914 | if (line.back() == '\r') |
| 374 | int wnum = stoi(relation_data[2]); | 915 | { |
| 375 | std::string word = relation_data[3]; | 916 | line.pop_back(); |
| 917 | } | ||
| 918 | |||
| 919 | lines.push_back(line); | ||
| 920 | } | ||
| 376 | 921 | ||
| 377 | std::string query; | 922 | progress ppgs("Writing hypernyms...", lines.size()); |
| 378 | switch (synset_id / 100000000) | 923 | for (auto line : lines) |
| 379 | { | 924 | { |
| 380 | case 1: // Noun | 925 | ppgs.update(); |
| 926 | |||
| 927 | std::regex relation("^hyp\\((1\\d{8}),(1\\d{8})\\)\\."); | ||
| 928 | std::smatch relation_data; | ||
| 929 | if (!std::regex_search(line, relation_data, relation)) | ||
| 930 | { | ||
| 931 | continue; | ||
| 932 | } | ||
| 933 | |||
| 934 | int synset_id_1 = stoi(relation_data[1]); | ||
| 935 | int synset_id_2 = stoi(relation_data[2]); | ||
| 936 | std::string query("INSERT INTO hypernymy (hyponym_id, hypernym_id) VALUES (?, ?)"); | ||
| 937 | |||
| 938 | for (auto mapping1 : wn[synset_id_1]) | ||
| 939 | { | ||
| 940 | for (auto mapping2 : wn[synset_id_2]) | ||
| 941 | { | ||
| 942 | sqlite3_stmt* ppstmt; | ||
| 943 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.size(), &ppstmt, NULL) != SQLITE_OK) | ||
| 944 | { | ||
| 945 | db_error(ppdb, query); | ||
| 946 | } | ||
| 947 | |||
| 948 | sqlite3_bind_int(ppstmt, 1, mapping1.second); | ||
| 949 | sqlite3_bind_int(ppstmt, 2, mapping2.second); | ||
| 950 | |||
| 951 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 952 | { | ||
| 953 | db_error(ppdb, query); | ||
| 954 | } | ||
| 955 | |||
| 956 | sqlite3_finalize(ppstmt); | ||
| 957 | } | ||
| 958 | } | ||
| 959 | } | ||
| 960 | } | ||
| 961 | |||
| 962 | // ins table | ||
| 963 | { | ||
| 964 | std::ifstream wninsfile(wnpref + "wn_ins.pl"); | ||
| 965 | if (!wninsfile.is_open()) | ||
| 966 | { | ||
| 967 | std::cout << "Invalid WordNet data directory." << std::endl; | ||
| 968 | print_usage(); | ||
| 969 | } | ||
| 970 | |||
| 971 | std::list<std::string> lines; | ||
| 972 | for (;;) | ||
| 973 | { | ||
| 974 | std::string line; | ||
| 975 | if (!getline(wninsfile, line)) | ||
| 381 | { | 976 | { |
| 382 | query = "INSERT INTO nouns (form) VALUES (?)"; | ||
| 383 | |||
| 384 | break; | 977 | break; |
| 385 | } | 978 | } |
| 979 | |||
| 980 | if (line.back() == '\r') | ||
| 981 | { | ||
| 982 | line.pop_back(); | ||
| 983 | } | ||
| 386 | 984 | ||
| 387 | case 2: // Verb | 985 | lines.push_back(line); |
| 986 | } | ||
| 987 | |||
| 988 | progress ppgs("Writing instantiations...", lines.size()); | ||
| 989 | for (auto line : lines) | ||
| 990 | { | ||
| 991 | ppgs.update(); | ||
| 992 | |||
| 993 | std::regex relation("^ins\\((1\\d{8}),(1\\d{8})\\)\\."); | ||
| 994 | std::smatch relation_data; | ||
| 995 | if (!std::regex_search(line, relation_data, relation)) | ||
| 996 | { | ||
| 997 | continue; | ||
| 998 | } | ||
| 999 | |||
| 1000 | int synset_id_1 = stoi(relation_data[1]); | ||
| 1001 | int synset_id_2 = stoi(relation_data[2]); | ||
| 1002 | std::string query("INSERT INTO instantiation (instance_id, class_id) VALUES (?, ?)"); | ||
| 1003 | |||
| 1004 | for (auto mapping1 : wn[synset_id_1]) | ||
| 1005 | { | ||
| 1006 | for (auto mapping2 : wn[synset_id_2]) | ||
| 1007 | { | ||
| 1008 | sqlite3_stmt* ppstmt; | ||
| 1009 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.size(), &ppstmt, NULL) != SQLITE_OK) | ||
| 1010 | { | ||
| 1011 | db_error(ppdb, query); | ||
| 1012 | } | ||
| 1013 | |||
| 1014 | sqlite3_bind_int(ppstmt, 1, mapping1.second); | ||
| 1015 | sqlite3_bind_int(ppstmt, 2, mapping2.second); | ||
| 1016 | |||
| 1017 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 1018 | { | ||
| 1019 | db_error(ppdb, query); | ||
| 1020 | } | ||
| 1021 | |||
| 1022 | sqlite3_finalize(ppstmt); | ||
| 1023 | } | ||
| 1024 | } | ||
| 1025 | } | ||
| 1026 | } | ||
| 1027 | |||
| 1028 | // mm table | ||
| 1029 | { | ||
| 1030 | std::ifstream wnmmfile(wnpref + "wn_mm.pl"); | ||
| 1031 | if (!wnmmfile.is_open()) | ||
| 1032 | { | ||
| 1033 | std::cout << "Invalid WordNet data directory." << std::endl; | ||
| 1034 | print_usage(); | ||
| 1035 | } | ||
| 1036 | |||
| 1037 | std::list<std::string> lines; | ||
| 1038 | for (;;) | ||
| 1039 | { | ||
| 1040 | std::string line; | ||
| 1041 | if (!getline(wnmmfile, line)) | ||
| 388 | { | 1042 | { |
| 389 | // Ignore | ||
| 390 | |||
| 391 | break; | 1043 | break; |
| 392 | } | 1044 | } |
| 1045 | |||
| 1046 | if (line.back() == '\r') | ||
| 1047 | { | ||
| 1048 | line.pop_back(); | ||
| 1049 | } | ||
| 1050 | |||
| 1051 | lines.push_back(line); | ||
| 1052 | } | ||
| 1053 | |||
| 1054 | progress ppgs("Writing member meronyms...", lines.size()); | ||
| 1055 | for (auto line : lines) | ||
| 1056 | { | ||
| 1057 | ppgs.update(); | ||
| 393 | 1058 | ||
| 394 | case 3: // Adjective | 1059 | std::regex relation("^mm\\((1\\d{8}),(1\\d{8})\\)\\."); |
| 1060 | std::smatch relation_data; | ||
| 1061 | if (!std::regex_search(line, relation_data, relation)) | ||
| 1062 | { | ||
| 1063 | continue; | ||
| 1064 | } | ||
| 1065 | |||
| 1066 | int synset_id_1 = stoi(relation_data[1]); | ||
| 1067 | int synset_id_2 = stoi(relation_data[2]); | ||
| 1068 | std::string query("INSERT INTO member_meronymy (holonym_id, meronym_id) VALUES (?, ?)"); | ||
| 1069 | |||
| 1070 | for (auto mapping1 : wn[synset_id_1]) | ||
| 1071 | { | ||
| 1072 | for (auto mapping2 : wn[synset_id_2]) | ||
| 1073 | { | ||
| 1074 | sqlite3_stmt* ppstmt; | ||
| 1075 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.size(), &ppstmt, NULL) != SQLITE_OK) | ||
| 1076 | { | ||
| 1077 | db_error(ppdb, query); | ||
| 1078 | } | ||
| 1079 | |||
| 1080 | sqlite3_bind_int(ppstmt, 1, mapping1.second); | ||
| 1081 | sqlite3_bind_int(ppstmt, 2, mapping2.second); | ||
| 1082 | |||
| 1083 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 1084 | { | ||
| 1085 | db_error(ppdb, query); | ||
| 1086 | } | ||
| 1087 | |||
| 1088 | sqlite3_finalize(ppstmt); | ||
| 1089 | } | ||
| 1090 | } | ||
| 1091 | } | ||
| 1092 | } | ||
| 1093 | |||
| 1094 | // ms table | ||
| 1095 | { | ||
| 1096 | std::ifstream wnmsfile(wnpref + "wn_ms.pl"); | ||
| 1097 | if (!wnmsfile.is_open()) | ||
| 1098 | { | ||
| 1099 | std::cout << "Invalid WordNet data directory." << std::endl; | ||
| 1100 | print_usage(); | ||
| 1101 | } | ||
| 1102 | |||
| 1103 | std::list<std::string> lines; | ||
| 1104 | for (;;) | ||
| 1105 | { | ||
| 1106 | std::string line; | ||
| 1107 | if (!getline(wnmsfile, line)) | ||
| 395 | { | 1108 | { |
| 396 | query = "INSERT INTO adjectives (form) VALUES (?)"; | ||
| 397 | |||
| 398 | break; | 1109 | break; |
| 399 | } | 1110 | } |
| 1111 | |||
| 1112 | if (line.back() == '\r') | ||
| 1113 | { | ||
| 1114 | line.pop_back(); | ||
| 1115 | } | ||
| 400 | 1116 | ||
| 401 | case 4: // Adverb | 1117 | lines.push_back(line); |
| 1118 | } | ||
| 1119 | |||
| 1120 | progress ppgs("Writing substance meronyms...", lines.size()); | ||
| 1121 | for (auto line : lines) | ||
| 1122 | { | ||
| 1123 | ppgs.update(); | ||
| 1124 | |||
| 1125 | std::regex relation("^ms\\((1\\d{8}),(1\\d{8})\\)\\."); | ||
| 1126 | std::smatch relation_data; | ||
| 1127 | if (!std::regex_search(line, relation_data, relation)) | ||
| 1128 | { | ||
| 1129 | continue; | ||
| 1130 | } | ||
| 1131 | |||
| 1132 | int synset_id_1 = stoi(relation_data[1]); | ||
| 1133 | int synset_id_2 = stoi(relation_data[2]); | ||
| 1134 | std::string query("INSERT INTO substance_meronymy (holonym_id, meronym_id) VALUES (?, ?)"); | ||
| 1135 | |||
| 1136 | for (auto mapping1 : wn[synset_id_1]) | ||
| 1137 | { | ||
| 1138 | for (auto mapping2 : wn[synset_id_2]) | ||
| 1139 | { | ||
| 1140 | sqlite3_stmt* ppstmt; | ||
| 1141 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.size(), &ppstmt, NULL) != SQLITE_OK) | ||
| 1142 | { | ||
| 1143 | db_error(ppdb, query); | ||
| 1144 | } | ||
| 1145 | |||
| 1146 | sqlite3_bind_int(ppstmt, 1, mapping1.second); | ||
| 1147 | sqlite3_bind_int(ppstmt, 2, mapping2.second); | ||
| 1148 | |||
| 1149 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 1150 | { | ||
| 1151 | db_error(ppdb, query); | ||
| 1152 | } | ||
| 1153 | |||
| 1154 | sqlite3_finalize(ppstmt); | ||
| 1155 | } | ||
| 1156 | } | ||
| 1157 | } | ||
| 1158 | } | ||
| 1159 | |||
| 1160 | // mm table | ||
| 1161 | { | ||
| 1162 | std::ifstream wnmpfile(wnpref + "wn_mp.pl"); | ||
| 1163 | if (!wnmpfile.is_open()) | ||
| 1164 | { | ||
| 1165 | std::cout << "Invalid WordNet data directory." << std::endl; | ||
| 1166 | print_usage(); | ||
| 1167 | } | ||
| 1168 | |||
| 1169 | std::list<std::string> lines; | ||
| 1170 | for (;;) | ||
| 1171 | { | ||
| 1172 | std::string line; | ||
| 1173 | if (!getline(wnmpfile, line)) | ||
| 402 | { | 1174 | { |
| 403 | query = "INSERT INTO adverbs (form) VALUES (?)"; | ||
| 404 | |||
| 405 | break; | 1175 | break; |
| 406 | } | 1176 | } |
| 1177 | |||
| 1178 | if (line.back() == '\r') | ||
| 1179 | { | ||
| 1180 | line.pop_back(); | ||
| 1181 | } | ||
| 1182 | |||
| 1183 | lines.push_back(line); | ||
| 407 | } | 1184 | } |
| 408 | 1185 | ||
| 409 | sqlite3_stmt* ppstmt; | 1186 | progress ppgs("Writing part meronyms...", lines.size()); |
| 410 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | 1187 | for (auto line : lines) |
| 1188 | { | ||
| 1189 | ppgs.update(); | ||
| 1190 | |||
| 1191 | std::regex relation("^mp\\((1\\d{8}),(1\\d{8})\\)\\."); | ||
| 1192 | std::smatch relation_data; | ||
| 1193 | if (!std::regex_search(line, relation_data, relation)) | ||
| 1194 | { | ||
| 1195 | continue; | ||
| 1196 | } | ||
| 1197 | |||
| 1198 | int synset_id_1 = stoi(relation_data[1]); | ||
| 1199 | int synset_id_2 = stoi(relation_data[2]); | ||
| 1200 | std::string query("INSERT INTO part_meronymy (holonym_id, meronym_id) VALUES (?, ?)"); | ||
| 1201 | |||
| 1202 | for (auto mapping1 : wn[synset_id_1]) | ||
| 1203 | { | ||
| 1204 | for (auto mapping2 : wn[synset_id_2]) | ||
| 1205 | { | ||
| 1206 | sqlite3_stmt* ppstmt; | ||
| 1207 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.size(), &ppstmt, NULL) != SQLITE_OK) | ||
| 1208 | { | ||
| 1209 | db_error(ppdb, query); | ||
| 1210 | } | ||
| 1211 | |||
| 1212 | sqlite3_bind_int(ppstmt, 1, mapping1.second); | ||
| 1213 | sqlite3_bind_int(ppstmt, 2, mapping2.second); | ||
| 1214 | |||
| 1215 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 1216 | { | ||
| 1217 | db_error(ppdb, query); | ||
| 1218 | } | ||
| 1219 | |||
| 1220 | sqlite3_finalize(ppstmt); | ||
| 1221 | } | ||
| 1222 | } | ||
| 1223 | } | ||
| 1224 | } | ||
| 1225 | |||
| 1226 | // per table | ||
| 1227 | { | ||
| 1228 | std::ifstream wnperfile(wnpref + "wn_per.pl"); | ||
| 1229 | if (!wnperfile.is_open()) | ||
| 411 | { | 1230 | { |
| 412 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | 1231 | std::cout << "Invalid WordNet data directory." << std::endl; |
| 413 | sqlite3_close_v2(ppdb); | ||
| 414 | print_usage(); | 1232 | print_usage(); |
| 415 | } | 1233 | } |
| 1234 | |||
| 1235 | std::list<std::string> lines; | ||
| 1236 | for (;;) | ||
| 1237 | { | ||
| 1238 | std::string line; | ||
| 1239 | if (!getline(wnperfile, line)) | ||
| 1240 | { | ||
| 1241 | break; | ||
| 1242 | } | ||
| 1243 | |||
| 1244 | if (line.back() == '\r') | ||
| 1245 | { | ||
| 1246 | line.pop_back(); | ||
| 1247 | } | ||
| 1248 | |||
| 1249 | lines.push_back(line); | ||
| 1250 | } | ||
| 1251 | |||
| 1252 | progress ppgs("Writing pertainyms and mannernyms...", lines.size()); | ||
| 1253 | for (auto line : lines) | ||
| 1254 | { | ||
| 1255 | ppgs.update(); | ||
| 1256 | |||
| 1257 | std::regex relation("^per\\(([34]\\d{8}),(\\d+),([13]\\d{8}),(\\d+)\\)\\."); | ||
| 1258 | std::smatch relation_data; | ||
| 1259 | if (!std::regex_search(line, relation_data, relation)) | ||
| 1260 | { | ||
| 1261 | continue; | ||
| 1262 | } | ||
| 1263 | |||
| 1264 | int synset_id_1 = stoi(relation_data[1]); | ||
| 1265 | int wnum_1 = stoi(relation_data[2]); | ||
| 1266 | int synset_id_2 = stoi(relation_data[3]); | ||
| 1267 | int wnum_2 = stoi(relation_data[4]); | ||
| 1268 | std::string query; | ||
| 1269 | switch (synset_id_1 / 100000000) | ||
| 1270 | { | ||
| 1271 | case 3: // Adjective | ||
| 1272 | { | ||
| 1273 | // This is a pertainym, the second word should be a noun | ||
| 1274 | // Technically it can be an adjective but we're ignoring that | ||
| 1275 | if (synset_id_2 / 100000000 != 1) | ||
| 1276 | { | ||
| 1277 | continue; | ||
| 1278 | } | ||
| 1279 | |||
| 1280 | query = "INSERT INTO pertainymy (pertainym_id, noun_id) VALUES (?, ?)"; | ||
| 1281 | |||
| 1282 | break; | ||
| 1283 | } | ||
| 1284 | |||
| 1285 | case 4: // Adverb | ||
| 1286 | { | ||
| 1287 | // This is a mannernym, the second word should be an adjective | ||
| 1288 | if (synset_id_2 / 100000000 != 3) | ||
| 1289 | { | ||
| 1290 | continue; | ||
| 1291 | } | ||
| 1292 | |||
| 1293 | query = "INSERT INTO mannernymy (mannernym_id, adjective_id) VALUES (?, ?)"; | ||
| 1294 | |||
| 1295 | break; | ||
| 1296 | } | ||
| 1297 | } | ||
| 1298 | |||
| 1299 | sqlite3_stmt* ppstmt; | ||
| 1300 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 1301 | { | ||
| 1302 | db_error(ppdb, query); | ||
| 1303 | } | ||
| 416 | 1304 | ||
| 417 | sqlite3_bind_text(ppstmt, 1, word.c_str(), word.length(), SQLITE_STATIC); | 1305 | sqlite3_bind_int(ppstmt, 1, wn[synset_id_1][wnum_1]); |
| 1306 | sqlite3_bind_int(ppstmt, 2, wn[synset_id_2][wnum_2]); | ||
| 418 | 1307 | ||
| 419 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | 1308 | if (sqlite3_step(ppstmt) != SQLITE_DONE) |
| 1309 | { | ||
| 1310 | db_error(ppdb, query); | ||
| 1311 | } | ||
| 1312 | |||
| 1313 | sqlite3_finalize(ppstmt); | ||
| 1314 | } | ||
| 1315 | } | ||
| 1316 | |||
| 1317 | // sa table | ||
| 1318 | { | ||
| 1319 | std::ifstream wnsafile(wnpref + "wn_sa.pl"); | ||
| 1320 | if (!wnsafile.is_open()) | ||
| 420 | { | 1321 | { |
| 421 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | 1322 | std::cout << "Invalid WordNet data directory." << std::endl; |
| 422 | sqlite3_close_v2(ppdb); | ||
| 423 | print_usage(); | 1323 | print_usage(); |
| 424 | } | 1324 | } |
| 1325 | |||
| 1326 | std::list<std::string> lines; | ||
| 1327 | for (;;) | ||
| 1328 | { | ||
| 1329 | std::string line; | ||
| 1330 | if (!getline(wnsafile, line)) | ||
| 1331 | { | ||
| 1332 | break; | ||
| 1333 | } | ||
| 1334 | |||
| 1335 | if (line.back() == '\r') | ||
| 1336 | { | ||
| 1337 | line.pop_back(); | ||
| 1338 | } | ||
| 1339 | |||
| 1340 | lines.push_back(line); | ||
| 1341 | } | ||
| 425 | 1342 | ||
| 426 | sqlite3_finalize(ppstmt); | 1343 | progress ppgs("Writing specifications...", lines.size()); |
| 1344 | for (auto line : lines) | ||
| 1345 | { | ||
| 1346 | ppgs.update(); | ||
| 1347 | |||
| 1348 | std::regex relation("^per\\((3\\d{8}),(\\d+),(3\\d{8}),(\\d+)\\)\\."); | ||
| 1349 | std::smatch relation_data; | ||
| 1350 | if (!std::regex_search(line, relation_data, relation)) | ||
| 1351 | { | ||
| 1352 | continue; | ||
| 1353 | } | ||
| 1354 | |||
| 1355 | int synset_id_1 = stoi(relation_data[1]); | ||
| 1356 | int wnum_1 = stoi(relation_data[2]); | ||
| 1357 | int synset_id_2 = stoi(relation_data[3]); | ||
| 1358 | int wnum_2 = stoi(relation_data[4]); | ||
| 1359 | std::string query("INSERT INTO specification (general_id, specific_id) VALUES (?, ?)"); | ||
| 1360 | |||
| 1361 | sqlite3_stmt* ppstmt; | ||
| 1362 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 1363 | { | ||
| 1364 | db_error(ppdb, query); | ||
| 1365 | } | ||
| 1366 | |||
| 1367 | sqlite3_bind_int(ppstmt, 1, wn[synset_id_1][wnum_1]); | ||
| 1368 | sqlite3_bind_int(ppstmt, 2, wn[synset_id_2][wnum_2]); | ||
| 427 | 1369 | ||
| 428 | query = "SELECT last_insert_rowid()"; | 1370 | if (sqlite3_step(ppstmt) != SQLITE_DONE) |
| 429 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | 1371 | { |
| 1372 | db_error(ppdb, query); | ||
| 1373 | } | ||
| 1374 | |||
| 1375 | sqlite3_finalize(ppstmt); | ||
| 1376 | } | ||
| 1377 | } | ||
| 1378 | /* | ||
| 1379 | // sim table | ||
| 1380 | { | ||
| 1381 | std::ifstream wnsimfile(wnpref + "wn_sim.pl"); | ||
| 1382 | if (!wnsimfile.is_open()) | ||
| 430 | { | 1383 | { |
| 431 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | 1384 | std::cout << "Invalid WordNet data directory." << std::endl; |
| 432 | sqlite3_close_v2(ppdb); | ||
| 433 | print_usage(); | 1385 | print_usage(); |
| 434 | } | 1386 | } |
| 1387 | |||
| 1388 | std::list<std::string> lines; | ||
| 1389 | for (;;) | ||
| 1390 | { | ||
| 1391 | std::string line; | ||
| 1392 | if (!getline(wnsimfile, line)) | ||
| 1393 | { | ||
| 1394 | break; | ||
| 1395 | } | ||
| 1396 | |||
| 1397 | if (line.back() == '\r') | ||
| 1398 | { | ||
| 1399 | line.pop_back(); | ||
| 1400 | } | ||
| 1401 | |||
| 1402 | lines.push_back(line); | ||
| 1403 | } | ||
| 435 | 1404 | ||
| 436 | if (sqlite3_step(ppstmt) != SQLITE_ROW) | 1405 | progress ppgs("Writing sense synonyms...", lines.size()); |
| 1406 | for (auto line : lines) | ||
| 1407 | { | ||
| 1408 | ppgs.update(); | ||
| 1409 | |||
| 1410 | std::regex relation("^sim\\((3\\d{8}),(3\\d{8})\\)\\."); | ||
| 1411 | std::smatch relation_data; | ||
| 1412 | if (!std::regex_search(line, relation_data, relation)) | ||
| 1413 | { | ||
| 1414 | continue; | ||
| 1415 | } | ||
| 1416 | |||
| 1417 | int synset_id_1 = stoi(relation_data[1]); | ||
| 1418 | int synset_id_2 = stoi(relation_data[2]); | ||
| 1419 | std::string query("INSERT INTO adjective_synonymy (adjective_1_id, adjective_2_id) VALUES (?, ?)"); | ||
| 1420 | |||
| 1421 | for (auto mapping1 : wn[synset_id_1]) | ||
| 1422 | { | ||
| 1423 | for (auto mapping2 : wn[synset_id_2]) | ||
| 1424 | { | ||
| 1425 | sqlite3_stmt* ppstmt; | ||
| 1426 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.size(), &ppstmt, NULL) != SQLITE_OK) | ||
| 1427 | { | ||
| 1428 | db_error(ppdb, query); | ||
| 1429 | } | ||
| 1430 | |||
| 1431 | sqlite3_bind_int(ppstmt, 1, mapping1.second); | ||
| 1432 | sqlite3_bind_int(ppstmt, 2, mapping2.second); | ||
| 1433 | |||
| 1434 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 1435 | { | ||
| 1436 | db_error(ppdb, query); | ||
| 1437 | } | ||
| 1438 | |||
| 1439 | sqlite3_reset(ppstmt); | ||
| 1440 | sqlite3_clear_bindings(ppstmt); | ||
| 1441 | |||
| 1442 | sqlite3_bind_int(ppstmt, 1, mapping2.second); | ||
| 1443 | sqlite3_bind_int(ppstmt, 2, mapping1.second); | ||
| 1444 | |||
| 1445 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 1446 | { | ||
| 1447 | db_error(ppdb, query); | ||
| 1448 | } | ||
| 1449 | |||
| 1450 | sqlite3_finalize(ppstmt); | ||
| 1451 | } | ||
| 1452 | } | ||
| 1453 | } | ||
| 1454 | } | ||
| 1455 | */ | ||
| 1456 | // syntax table | ||
| 1457 | { | ||
| 1458 | std::ifstream wnsyntaxfile(wnpref + "wn_syntax.pl"); | ||
| 1459 | if (!wnsyntaxfile.is_open()) | ||
| 437 | { | 1460 | { |
| 438 | std::cout << "Error writing to output database: " << sqlite3_errmsg(ppdb) << std::endl; | 1461 | std::cout << "Invalid WordNet data directory." << std::endl; |
| 439 | sqlite3_close_v2(ppdb); | ||
| 440 | print_usage(); | 1462 | print_usage(); |
| 441 | } | 1463 | } |
| 1464 | |||
| 1465 | std::list<std::string> lines; | ||
| 1466 | for (;;) | ||
| 1467 | { | ||
| 1468 | std::string line; | ||
| 1469 | if (!getline(wnsyntaxfile, line)) | ||
| 1470 | { | ||
| 1471 | break; | ||
| 1472 | } | ||
| 442 | 1473 | ||
| 443 | wn[synset_id][wnum] = sqlite3_column_int(ppstmt, 0); | 1474 | if (line.back() == '\r') |
| 1475 | { | ||
| 1476 | line.pop_back(); | ||
| 1477 | } | ||
| 1478 | |||
| 1479 | lines.push_back(line); | ||
| 1480 | } | ||
| 444 | 1481 | ||
| 445 | sqlite3_finalize(ppstmt); | 1482 | progress ppgs("Writing adjective syntax markers...", lines.size()); |
| 1483 | for (auto line : lines) | ||
| 1484 | { | ||
| 1485 | ppgs.update(); | ||
| 1486 | |||
| 1487 | std::regex relation("^syntax\\((3\\d{8}),(\\d+),([ipa])p?\\)\\."); | ||
| 1488 | std::smatch relation_data; | ||
| 1489 | if (!std::regex_search(line, relation_data, relation)) | ||
| 1490 | { | ||
| 1491 | continue; | ||
| 1492 | } | ||
| 1493 | |||
| 1494 | int synset_id = stoi(relation_data[1]); | ||
| 1495 | int wnum = stoi(relation_data[2]); | ||
| 1496 | std::string syn = relation_data[3]; | ||
| 1497 | std::string query("UPDATE adjectives SET position = ? WHERE adjective_id = ?"); | ||
| 1498 | |||
| 1499 | sqlite3_stmt* ppstmt; | ||
| 1500 | if (sqlite3_prepare_v2(ppdb, query.c_str(), query.size(), &ppstmt, NULL) != SQLITE_OK) | ||
| 1501 | { | ||
| 1502 | db_error(ppdb, query); | ||
| 1503 | } | ||
| 1504 | |||
| 1505 | sqlite3_bind_text(ppstmt, 1, syn.c_str(), 1, SQLITE_STATIC); | ||
| 1506 | sqlite3_bind_int(ppstmt, 2, wn[synset_id][wnum]); | ||
| 1507 | |||
| 1508 | if (sqlite3_step(ppstmt) != SQLITE_DONE) | ||
| 1509 | { | ||
| 1510 | db_error(ppdb, query); | ||
| 1511 | } | ||
| 1512 | |||
| 1513 | sqlite3_finalize(ppstmt); | ||
| 1514 | } | ||
| 446 | } | 1515 | } |
| 447 | 1516 | ||
| 448 | sqlite3_close_v2(ppdb); | 1517 | sqlite3_close_v2(ppdb); |
| 449 | 1518 | ||
| 450 | std::cout << "Done." << std::endl; | 1519 | std::cout << "Done." << std::endl; |
| 451 | } \ No newline at end of file | 1520 | } |
| diff --git a/progress.h b/progress.h new file mode 100644 index 0000000..81f07a3 --- /dev/null +++ b/progress.h | |||
| @@ -0,0 +1,50 @@ | |||
| 1 | #ifndef PROGRESS_H_A34EF856 | ||
| 2 | #define PROGRESS_H_A34EF856 | ||
| 3 | |||
| 4 | #include <string> | ||
| 5 | |||
| 6 | class progress { | ||
| 7 | private: | ||
| 8 | std::string message; | ||
| 9 | int total; | ||
| 10 | int cur = 0; | ||
| 11 | int lprint = 0; | ||
| 12 | |||
| 13 | public: | ||
| 14 | progress(std::string message, int total) : message(message), total(total) | ||
| 15 | { | ||
| 16 | std::cout << message << " 0%" << std::flush; | ||
| 17 | } | ||
| 18 | |||
| 19 | void update(int val) | ||
| 20 | { | ||
| 21 | if (val <= total) | ||
| 22 | { | ||
| 23 | cur = val; | ||
| 24 | } else { | ||
| 25 | cur = total; | ||
| 26 | } | ||
| 27 | |||
| 28 | int pp = cur * 100 / total; | ||
| 29 | if (pp != lprint) | ||
| 30 | { | ||
| 31 | lprint = pp; | ||
| 32 | |||
| 33 | std::cout << "\b\b\b\b" << std::right; | ||
| 34 | std::cout.width(3); | ||
| 35 | std::cout << pp << "%" << std::flush; | ||
| 36 | } | ||
| 37 | } | ||
| 38 | |||
| 39 | void update() | ||
| 40 | { | ||
| 41 | update(cur+1); | ||
| 42 | } | ||
| 43 | |||
| 44 | ~progress() | ||
| 45 | { | ||
| 46 | std::cout << "\b\b\b\b100%" << std::endl; | ||
| 47 | } | ||
| 48 | }; | ||
| 49 | |||
| 50 | #endif /* end of include guard: PROGRESS_H_A34EF856 */ | ||
| diff --git a/schema.sql b/schema.sql index 62dd780..fd55734 100644 --- a/schema.sql +++ b/schema.sql | |||
| @@ -34,20 +34,25 @@ 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 | `form` VARCHAR(32) NOT NULL, | 37 | `base_form` VARCHAR(32) NOT NULL, |
| 38 | `comparative` VARCHAR(32), | ||
| 39 | `superlative` VARCHAR(32), | ||
| 38 | `position` CHAR(1) | 40 | `position` CHAR(1) |
| 39 | ); | 41 | ); |
| 40 | 42 | ||
| 41 | DROP TABLE IF EXISTS `adverbs`; | 43 | DROP TABLE IF EXISTS `adverbs`; |
| 42 | CREATE TABLE `adverbs` ( | 44 | CREATE TABLE `adverbs` ( |
| 43 | `adverb_id` INTEGER PRIMARY KEY, | 45 | `adverb_id` INTEGER PRIMARY KEY, |
| 44 | `form` VARCHAR(32) NOT NULL | 46 | `base_form` VARCHAR(32) NOT NULL, |
| 47 | `comparative` VARCHAR(32), | ||
| 48 | `superlative` VARCHAR(32) | ||
| 45 | ); | 49 | ); |
| 46 | 50 | ||
| 47 | DROP TABLE IF EXISTS `nouns`; | 51 | DROP TABLE IF EXISTS `nouns`; |
| 48 | CREATE TABLE `nouns` ( | 52 | CREATE TABLE `nouns` ( |
| 49 | `noun_id` INTEGER PRIMARY KEY, | 53 | `noun_id` INTEGER PRIMARY KEY, |
| 50 | `form` VARCHAR(32) NOT NULL | 54 | `singular` VARCHAR(32) NOT NULL, |
| 55 | `plural` VARCHAR(32) | ||
| 51 | ); | 56 | ); |
| 52 | 57 | ||
| 53 | DROP TABLE IF EXISTS `hypernymy`; | 58 | DROP TABLE IF EXISTS `hypernymy`; |
| @@ -146,10 +151,54 @@ CREATE TABLE `mannernymy` ( | |||
| 146 | FOREIGN KEY (`mannernym_id`) REFERENCES `adverbs`(`adverb_id`) | 151 | FOREIGN KEY (`mannernym_id`) REFERENCES `adverbs`(`adverb_id`) |
| 147 | ); | 152 | ); |
| 148 | 153 | ||
| 149 | DROP TABLE IF EXISTS `synonymy`; | 154 | DROP TABLE IF EXISTS `noun_synonymy`; |
| 150 | CREATE TABLE `synonymy` ( | 155 | CREATE TABLE `noun_synonymy` ( |
| 156 | `noun_1_id` INTEGER NOT NULL, | ||
| 157 | `noun_2_id` INTEGER NOT NULL, | ||
| 158 | FOREIGN KEY (`noun_1_id`) REFERENCES `nouns`(`nouns_id`), | ||
| 159 | FOREIGN KEY (`noun_2_id`) REFERENCES `nouns`(`nouns_id`) | ||
| 160 | ); | ||
| 161 | |||
| 162 | DROP TABLE IF EXISTS `adjective_synonymy`; | ||
| 163 | CREATE TABLE `adjective_synonymy` ( | ||
| 151 | `adjective_1_id` INTEGER NOT NULL, | 164 | `adjective_1_id` INTEGER NOT NULL, |
| 152 | `adjective_2_id` INTEGER NOT NULL, | 165 | `adjective_2_id` INTEGER NOT NULL, |
| 153 | FOREIGN KEY (`adjective_1_id`) REFERENCES `adjectives`(`adjective_id`), | 166 | FOREIGN KEY (`adjective_1_id`) REFERENCES `adjectives`(`adjective_id`), |
| 154 | FOREIGN KEY (`adjective_2_id`) REFERENCES `adjectives`(`adjective_id`) | 167 | FOREIGN KEY (`adjective_2_id`) REFERENCES `adjectives`(`adjective_id`) |
| 155 | ); | 168 | ); |
| 169 | |||
| 170 | DROP TABLE IF EXISTS `adverb_synonymy`; | ||
| 171 | CREATE TABLE `adverb_synonymy` ( | ||
| 172 | `adverb_1_id` INTEGER NOT NULL, | ||
| 173 | `adverb_2_id` INTEGER NOT NULL, | ||
| 174 | FOREIGN KEY (`adverb_1_id`) REFERENCES `adverbs`(`adverb_id`), | ||
| 175 | FOREIGN KEY (`adverb_2_id`) REFERENCES `adverbs`(`adverb_id`) | ||
| 176 | ); | ||
| 177 | |||
| 178 | DROP TABLE IF EXISTS `noun_pronunciations`; | ||
| 179 | CREATE TABLE `noun_pronunciations` ( | ||
| 180 | `noun_id` INTEGER NOT NULL, | ||
| 181 | `pronunciation` VARCHAR(64) NOT NULL, | ||
| 182 | FOREIGN KEY (`noun_id`) REFERENCES `nouns`(`noun_id`) | ||
| 183 | ); | ||
| 184 | |||
| 185 | DROP TABLE IF EXISTS `verb_pronunciations`; | ||
| 186 | CREATE TABLE `verb_pronunciations` ( | ||
| 187 | `verb_id` INTEGER NOT NULL, | ||
| 188 | `pronunciation` VARCHAR(64) NOT NULL, | ||
| 189 | FOREIGN KEY (`verb_id`) REFERENCES `verbs`(`verb_id`) | ||
| 190 | ); | ||
| 191 | |||
| 192 | DROP TABLE IF EXISTS `adjective_pronunciations`; | ||
| 193 | CREATE TABLE `adjective_pronunciations` ( | ||
| 194 | `adjective_id` INTEGER NOT NULL, | ||
| 195 | `pronunciation` VARCHAR(64) NOT NULL, | ||
| 196 | FOREIGN KEY (`adjective_id`) REFERENCES `adjectives`(`adjective_id`) | ||
| 197 | ); | ||
| 198 | |||
| 199 | DROP TABLE IF EXISTS `adverb_pronunciations`; | ||
| 200 | CREATE TABLE `adverb_pronunciations` ( | ||
| 201 | `adverb_id` INTEGER NOT NULL, | ||
| 202 | `pronunciation` VARCHAR(64) NOT NULL, | ||
| 203 | FOREIGN KEY (`adverb_id`) REFERENCES `adverbs`(`adverb_id`) | ||
| 204 | ); | ||
| diff --git a/verbly/adjective.cpp b/verbly/adjective.cpp new file mode 100644 index 0000000..0f4087f --- /dev/null +++ b/verbly/adjective.cpp | |||
| @@ -0,0 +1,586 @@ | |||
| 1 | #include "verbly.h" | ||
| 2 | |||
| 3 | namespace verbly { | ||
| 4 | |||
| 5 | adjective::adjective(const data& _data, int _id) : word(_data, _id) | ||
| 6 | { | ||
| 7 | |||
| 8 | } | ||
| 9 | |||
| 10 | std::string adjective::base_form() const | ||
| 11 | { | ||
| 12 | return _base_form; | ||
| 13 | } | ||
| 14 | |||
| 15 | std::string adjective::comparative_form() const | ||
| 16 | { | ||
| 17 | return _comparative_form; | ||
| 18 | } | ||
| 19 | |||
| 20 | std::string adjective::superlative_form() const | ||
| 21 | { | ||
| 22 | return _superlative_form; | ||
| 23 | } | ||
| 24 | |||
| 25 | adjective::positioning adjective::position() const | ||
| 26 | { | ||
| 27 | return _position; | ||
| 28 | } | ||
| 29 | |||
| 30 | bool adjective::has_comparative_form() const | ||
| 31 | { | ||
| 32 | return !_comparative_form.empty(); | ||
| 33 | } | ||
| 34 | |||
| 35 | bool adjective::has_superlative_form() const | ||
| 36 | { | ||
| 37 | return !_superlative_form.empty(); | ||
| 38 | } | ||
| 39 | |||
| 40 | bool adjective::has_position() const | ||
| 41 | { | ||
| 42 | return _position != adjective::positioning::undefined; | ||
| 43 | } | ||
| 44 | |||
| 45 | adjective_query adjective::antonyms() const | ||
| 46 | { | ||
| 47 | return _data.adjectives().antonym_of(*this); | ||
| 48 | } | ||
| 49 | |||
| 50 | adjective_query adjective::synonyms() const | ||
| 51 | { | ||
| 52 | return _data.adjectives().synonym_of(*this); | ||
| 53 | } | ||
| 54 | |||
| 55 | adjective_query adjective::generalizations() const | ||
| 56 | { | ||
| 57 | return _data.adjectives().generalization_of(*this); | ||
| 58 | } | ||
| 59 | |||
| 60 | adjective_query adjective::specifications() const | ||
| 61 | { | ||
| 62 | return _data.adjectives().specification_of(*this); | ||
| 63 | } | ||
| 64 | |||
| 65 | noun_query adjective::anti_pertainyms() const | ||
| 66 | { | ||
| 67 | return _data.nouns().anti_pertainym_of(*this); | ||
| 68 | } | ||
| 69 | |||
| 70 | adverb_query adjective::mannernyms() const | ||
| 71 | { | ||
| 72 | return _data.adverbs().mannernym_of(*this); | ||
| 73 | } | ||
| 74 | |||
| 75 | noun_query adjective::attributes() const | ||
| 76 | { | ||
| 77 | return _data.nouns().attribute_of(*this); | ||
| 78 | } | ||
| 79 | |||
| 80 | adjective_query::adjective_query(const data& _data) : _data(_data) | ||
| 81 | { | ||
| 82 | |||
| 83 | } | ||
| 84 | |||
| 85 | adjective_query& adjective_query::limit(int _limit) | ||
| 86 | { | ||
| 87 | if ((_limit > 0) || (_limit == unlimited)) | ||
| 88 | { | ||
| 89 | this->_limit = _limit; | ||
| 90 | } | ||
| 91 | |||
| 92 | return *this; | ||
| 93 | } | ||
| 94 | |||
| 95 | adjective_query& adjective_query::random(bool _random) | ||
| 96 | { | ||
| 97 | this->_random = _random; | ||
| 98 | |||
| 99 | return *this; | ||
| 100 | } | ||
| 101 | |||
| 102 | adjective_query& adjective_query::except(const adjective& _word) | ||
| 103 | { | ||
| 104 | _except.push_back(_word); | ||
| 105 | |||
| 106 | return *this; | ||
| 107 | } | ||
| 108 | |||
| 109 | adjective_query& adjective_query::rhymes_with(const word& _word) | ||
| 110 | { | ||
| 111 | for (auto rhyme : _word.rhyme_phonemes()) | ||
| 112 | { | ||
| 113 | _rhymes.push_back(rhyme); | ||
| 114 | } | ||
| 115 | |||
| 116 | if (dynamic_cast<const adjective*>(&_word) != nullptr) | ||
| 117 | { | ||
| 118 | _except.push_back(dynamic_cast<const adjective&>(_word)); | ||
| 119 | } | ||
| 120 | |||
| 121 | return *this; | ||
| 122 | } | ||
| 123 | |||
| 124 | adjective_query& adjective_query::has_pronunciation(bool _has_prn) | ||
| 125 | { | ||
| 126 | this->_has_prn = _has_prn; | ||
| 127 | |||
| 128 | return *this; | ||
| 129 | } | ||
| 130 | |||
| 131 | adjective_query& adjective_query::is_variant(bool _is_variant) | ||
| 132 | { | ||
| 133 | this->_is_variant = _is_variant; | ||
| 134 | |||
| 135 | return *this; | ||
| 136 | } | ||
| 137 | |||
| 138 | adjective_query& adjective_query::variant_of(const noun& _noun) | ||
| 139 | { | ||
| 140 | _variant_of.push_back(_noun); | ||
| 141 | |||
| 142 | return *this; | ||
| 143 | } | ||
| 144 | |||
| 145 | adjective_query& adjective_query::not_variant_of(const noun& _noun) | ||
| 146 | { | ||
| 147 | _not_variant_of.push_back(_noun); | ||
| 148 | |||
| 149 | return *this; | ||
| 150 | } | ||
| 151 | |||
| 152 | adjective_query& adjective_query::has_antonyms(bool _is_antonymic) | ||
| 153 | { | ||
| 154 | this->_is_antonymic = _is_antonymic; | ||
| 155 | |||
| 156 | return *this; | ||
| 157 | } | ||
| 158 | |||
| 159 | adjective_query& adjective_query::antonym_of(const adjective& _adj) | ||
| 160 | { | ||
| 161 | _antonym_of.push_back(_adj); | ||
| 162 | |||
| 163 | return *this; | ||
| 164 | } | ||
| 165 | |||
| 166 | adjective_query& adjective_query::not_antonym_of(const adjective& _adj) | ||
| 167 | { | ||
| 168 | _not_antonym_of.push_back(_adj); | ||
| 169 | |||
| 170 | return *this; | ||
| 171 | } | ||
| 172 | |||
| 173 | adjective_query& adjective_query::has_synonyms(bool _is_synonymic) | ||
| 174 | { | ||
| 175 | this->_is_synonymic = _is_synonymic; | ||
| 176 | |||
| 177 | return *this; | ||
| 178 | } | ||
| 179 | |||
| 180 | adjective_query& adjective_query::synonym_of(const adjective& _adj) | ||
| 181 | { | ||
| 182 | _synonym_of.push_back(_adj); | ||
| 183 | |||
| 184 | return *this; | ||
| 185 | } | ||
| 186 | |||
| 187 | adjective_query& adjective_query::not_synonym_of(const adjective& _adj) | ||
| 188 | { | ||
| 189 | _not_synonym_of.push_back(_adj); | ||
| 190 | |||
| 191 | return *this; | ||
| 192 | } | ||
| 193 | |||
| 194 | adjective_query& adjective_query::is_generalization(bool _is_generalization) | ||
| 195 | { | ||
| 196 | this->_is_generalization = _is_generalization; | ||
| 197 | |||
| 198 | return *this; | ||
| 199 | } | ||
| 200 | |||
| 201 | adjective_query& adjective_query::generalization_of(const adjective& _adj) | ||
| 202 | { | ||
| 203 | _generalization_of.push_back(_adj); | ||
| 204 | |||
| 205 | return *this; | ||
| 206 | } | ||
| 207 | |||
| 208 | adjective_query& adjective_query::not_generalization_of(const adjective& _adj) | ||
| 209 | { | ||
| 210 | _not_generalization_of.push_back(_adj); | ||
| 211 | |||
| 212 | return *this; | ||
| 213 | } | ||
| 214 | |||
| 215 | adjective_query& adjective_query::is_specification(bool _is_specification) | ||
| 216 | { | ||
| 217 | this->_is_specification = _is_specification; | ||
| 218 | |||
| 219 | return *this; | ||
| 220 | } | ||
| 221 | |||
| 222 | adjective_query& adjective_query::specification_of(const adjective& _adj) | ||
| 223 | { | ||
| 224 | _specification_of.push_back(_adj); | ||
| 225 | |||
| 226 | return *this; | ||
| 227 | } | ||
| 228 | |||
| 229 | adjective_query& adjective_query::not_specification_of(const adjective& _adj) | ||
| 230 | { | ||
| 231 | _not_specification_of.push_back(_adj); | ||
| 232 | |||
| 233 | return *this; | ||
| 234 | } | ||
| 235 | |||
| 236 | adjective_query& adjective_query::is_pertainymic(bool _is_pertainymic) | ||
| 237 | { | ||
| 238 | this->_is_pertainymic = _is_pertainymic; | ||
| 239 | |||
| 240 | return *this; | ||
| 241 | } | ||
| 242 | |||
| 243 | adjective_query& adjective_query::pertainym_of(const noun& _noun) | ||
| 244 | { | ||
| 245 | _pertainym_of.push_back(_noun); | ||
| 246 | |||
| 247 | return *this; | ||
| 248 | } | ||
| 249 | |||
| 250 | adjective_query& adjective_query::is_mannernymic(bool _is_mannernymic) | ||
| 251 | { | ||
| 252 | this->_is_mannernymic = _is_mannernymic; | ||
| 253 | |||
| 254 | return *this; | ||
| 255 | } | ||
| 256 | |||
| 257 | adjective_query& adjective_query::anti_mannernym_of(const adverb& _adv) | ||
| 258 | { | ||
| 259 | _anti_mannernym_of.push_back(_adv); | ||
| 260 | |||
| 261 | return *this; | ||
| 262 | } | ||
| 263 | |||
| 264 | std::list<adjective> adjective_query::run() const | ||
| 265 | { | ||
| 266 | std::stringstream construct; | ||
| 267 | construct << "SELECT adjective_id, base_form, comparative, superlative, position FROM adjectives"; | ||
| 268 | std::list<std::string> conditions; | ||
| 269 | |||
| 270 | if (_has_prn) | ||
| 271 | { | ||
| 272 | conditions.push_back("adjective_id IN (SELECT adjective_id FROM adjective_pronunciations)"); | ||
| 273 | } | ||
| 274 | |||
| 275 | if (!_rhymes.empty()) | ||
| 276 | { | ||
| 277 | std::list<std::string> clauses(_rhymes.size(), "pronunciation LIKE @RHMPRN"); | ||
| 278 | std::string cond = "adjective_id IN (SELECT adjective_id FROM adjective_pronunciations WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 279 | conditions.push_back(cond); | ||
| 280 | } | ||
| 281 | |||
| 282 | for (auto except : _except) | ||
| 283 | { | ||
| 284 | conditions.push_back("adjective_id != @EXCID"); | ||
| 285 | } | ||
| 286 | |||
| 287 | if (_requires_comparative_form) | ||
| 288 | { | ||
| 289 | conditions.push_back("comparative IS NOT NULL"); | ||
| 290 | } | ||
| 291 | |||
| 292 | if (_requires_superlative_form) | ||
| 293 | { | ||
| 294 | conditions.push_back("superlative IS NOT NULL"); | ||
| 295 | } | ||
| 296 | |||
| 297 | if (_position != adjective::positioning::undefined) | ||
| 298 | { | ||
| 299 | switch (_position) | ||
| 300 | { | ||
| 301 | case adjective::positioning::predicate: conditions.push_back("position = 'p'"); break; | ||
| 302 | case adjective::positioning::attributive: conditions.push_back("position = 'a'"); break; | ||
| 303 | case adjective::positioning::postnominal: conditions.push_back("position = 'i'"); break; | ||
| 304 | } | ||
| 305 | } | ||
| 306 | |||
| 307 | if (_is_variant) | ||
| 308 | { | ||
| 309 | conditions.push_back("adjective_id IN (SELECT adjective_id FROM variation)"); | ||
| 310 | } | ||
| 311 | |||
| 312 | if (!_variant_of.empty()) | ||
| 313 | { | ||
| 314 | std::list<std::string> clauses(_variant_of.size(), "noun_id = @ATTRID"); | ||
| 315 | std::string cond = "adjective_id IN (SELECT adjective_id FROM variation WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 316 | conditions.push_back(cond); | ||
| 317 | } | ||
| 318 | |||
| 319 | if (!_not_variant_of.empty()) | ||
| 320 | { | ||
| 321 | std::list<std::string> clauses(_not_variant_of.size(), "noun_id = @NATTRID"); | ||
| 322 | std::string cond = "adjective_id NOT IN (SELECT adjective_id FROM variation WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 323 | conditions.push_back(cond); | ||
| 324 | } | ||
| 325 | |||
| 326 | if (_is_antonymic) | ||
| 327 | { | ||
| 328 | conditions.push_back("adjective_id IN (SELECT adjective_2_id FROM adjective_antonymy)"); | ||
| 329 | } | ||
| 330 | |||
| 331 | if (!_antonym_of.empty()) | ||
| 332 | { | ||
| 333 | std::list<std::string> clauses(_antonym_of.size(), "adjective_1_id = @ANTID"); | ||
| 334 | std::string cond = "adjective_id IN (SELECT adjective_2_id FROM adjective_antonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 335 | conditions.push_back(cond); | ||
| 336 | } | ||
| 337 | |||
| 338 | if (!_not_antonym_of.empty()) | ||
| 339 | { | ||
| 340 | std::list<std::string> clauses(_not_antonym_of.size(), "adjective_1_id = @NANTID"); | ||
| 341 | std::string cond = "adjective_id NOT IN (SELECT adjective_2_id FROM adjective_antonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 342 | conditions.push_back(cond); | ||
| 343 | } | ||
| 344 | |||
| 345 | if (_is_synonymic) | ||
| 346 | { | ||
| 347 | conditions.push_back("adjective_id IN (SELECT adjective_2_id FROM adjective_synonymy)"); | ||
| 348 | } | ||
| 349 | |||
| 350 | if (!_synonym_of.empty()) | ||
| 351 | { | ||
| 352 | std::list<std::string> clauses(_synonym_of.size(), "adjective_1_id = @SYNID"); | ||
| 353 | std::string cond = "adjective_id IN (SELECT adjective_2_id FROM adjective_synonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 354 | conditions.push_back(cond); | ||
| 355 | } | ||
| 356 | |||
| 357 | if (!_not_synonym_of.empty()) | ||
| 358 | { | ||
| 359 | std::list<std::string> clauses(_not_synonym_of.size(), "adjective_1_id = @NSYNID"); | ||
| 360 | std::string cond = "adjective_id NOT IN (SELECT adjective_2_id FROM adjective_synonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 361 | conditions.push_back(cond); | ||
| 362 | } | ||
| 363 | |||
| 364 | if (_is_generalization) | ||
| 365 | { | ||
| 366 | conditions.push_back("adjective_id IN (SELECT general_id FROM specification)"); | ||
| 367 | } | ||
| 368 | |||
| 369 | if (!_generalization_of.empty()) | ||
| 370 | { | ||
| 371 | std::list<std::string> clauses(_generalization_of.size(), "specific_id = @SPECID"); | ||
| 372 | std::string cond = "adjective_id IN (SELECT general_id FROM specification WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 373 | conditions.push_back(cond); | ||
| 374 | } | ||
| 375 | |||
| 376 | if (!_not_generalization_of.empty()) | ||
| 377 | { | ||
| 378 | std::list<std::string> clauses(_not_generalization_of.size(), "specific_id = @NSPECID"); | ||
| 379 | std::string cond = "adjective_id NOT IN (SELECT general_id FROM specification WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 380 | conditions.push_back(cond); | ||
| 381 | } | ||
| 382 | |||
| 383 | if (_is_specification) | ||
| 384 | { | ||
| 385 | conditions.push_back("adjective_id IN (SELECT specific_id FROM specification)"); | ||
| 386 | } | ||
| 387 | |||
| 388 | if (!_specification_of.empty()) | ||
| 389 | { | ||
| 390 | std::list<std::string> clauses(_specification_of.size(), "general_id = @GENID"); | ||
| 391 | std::string cond = "adjective_id IN (SELECT specific_id FROM specification WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 392 | conditions.push_back(cond); | ||
| 393 | } | ||
| 394 | |||
| 395 | if (!_not_specification_of.empty()) | ||
| 396 | { | ||
| 397 | std::list<std::string> clauses(_not_specification_of.size(), "general_id = @NGENID"); | ||
| 398 | std::string cond = "adjective_id NOT IN (SELECT specific_id FROM specification WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 399 | conditions.push_back(cond); | ||
| 400 | } | ||
| 401 | |||
| 402 | if (_is_pertainymic) | ||
| 403 | { | ||
| 404 | conditions.push_back("adjective_id IN (SELECT pertainym_id FROM pertainymy)"); | ||
| 405 | } | ||
| 406 | |||
| 407 | if (!_pertainym_of.empty()) | ||
| 408 | { | ||
| 409 | std::list<std::string> clauses(_pertainym_of.size(), "noun_id = @APERID"); | ||
| 410 | std::string cond = "adjective_id IN (SELECT pertainym_id FROM pertainymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 411 | conditions.push_back(cond); | ||
| 412 | } | ||
| 413 | |||
| 414 | if (_is_mannernymic) | ||
| 415 | { | ||
| 416 | conditions.push_back("adjective_id IN (SELECT adjective_id FROM mannernymy)"); | ||
| 417 | } | ||
| 418 | |||
| 419 | if (!_anti_mannernym_of.empty()) | ||
| 420 | { | ||
| 421 | std::list<std::string> clauses(_anti_mannernym_of.size(), "mannernym_id = @MANID"); | ||
| 422 | std::string cond = "adjective_id IN (SELECT adjective_id FROM mannernymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 423 | conditions.push_back(cond); | ||
| 424 | } | ||
| 425 | |||
| 426 | if (!conditions.empty()) | ||
| 427 | { | ||
| 428 | construct << " WHERE "; | ||
| 429 | construct << verbly::implode(std::begin(conditions), std::end(conditions), " AND "); | ||
| 430 | } | ||
| 431 | |||
| 432 | if (_random) | ||
| 433 | { | ||
| 434 | construct << " ORDER BY RANDOM()"; | ||
| 435 | } | ||
| 436 | |||
| 437 | if (_limit != unlimited) | ||
| 438 | { | ||
| 439 | construct << " LIMIT " << _limit; | ||
| 440 | } | ||
| 441 | |||
| 442 | sqlite3_stmt* ppstmt; | ||
| 443 | std::string query = construct.str(); | ||
| 444 | if (sqlite3_prepare_v2(_data.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 445 | { | ||
| 446 | throw std::runtime_error(sqlite3_errmsg(_data.ppdb)); | ||
| 447 | } | ||
| 448 | |||
| 449 | if (!_rhymes.empty()) | ||
| 450 | { | ||
| 451 | int i = 0; | ||
| 452 | for (auto rhyme : _rhymes) | ||
| 453 | { | ||
| 454 | std::string rhymer = "%" + rhyme; | ||
| 455 | sqlite3_bind_text(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@RHMPRN"), rhymer.c_str(), rhymer.length(), SQLITE_STATIC); | ||
| 456 | |||
| 457 | i++; | ||
| 458 | } | ||
| 459 | } | ||
| 460 | |||
| 461 | for (auto except : _except) | ||
| 462 | { | ||
| 463 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@EXCID"), except._id); | ||
| 464 | } | ||
| 465 | |||
| 466 | for (auto attribute : _variant_of) | ||
| 467 | { | ||
| 468 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@ATTRID"), attribute._id); | ||
| 469 | } | ||
| 470 | |||
| 471 | for (auto attribute : _not_variant_of) | ||
| 472 | { | ||
| 473 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NATTRID"), attribute._id); | ||
| 474 | } | ||
| 475 | |||
| 476 | for (auto antonym : _antonym_of) | ||
| 477 | { | ||
| 478 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@ANTID"), antonym._id); | ||
| 479 | } | ||
| 480 | |||
| 481 | for (auto antonym : _not_antonym_of) | ||
| 482 | { | ||
| 483 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NANTID"), antonym._id); | ||
| 484 | } | ||
| 485 | |||
| 486 | for (auto synonym : _synonym_of) | ||
| 487 | { | ||
| 488 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@SYNID"), synonym._id); | ||
| 489 | } | ||
| 490 | |||
| 491 | for (auto synonym : _not_synonym_of) | ||
| 492 | { | ||
| 493 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NSYNID"), synonym._id); | ||
| 494 | } | ||
| 495 | |||
| 496 | for (auto specific : _generalization_of) | ||
| 497 | { | ||
| 498 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@SPECID"), specific._id); | ||
| 499 | } | ||
| 500 | |||
| 501 | for (auto specific : _not_generalization_of) | ||
| 502 | { | ||
| 503 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NSPECID"), specific._id); | ||
| 504 | } | ||
| 505 | |||
| 506 | for (auto general : _specification_of) | ||
| 507 | { | ||
| 508 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@GENID"), general._id); | ||
| 509 | } | ||
| 510 | |||
| 511 | for (auto general : _not_specification_of) | ||
| 512 | { | ||
| 513 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NGENID"), general._id); | ||
| 514 | } | ||
| 515 | |||
| 516 | for (auto n : _pertainym_of) | ||
| 517 | { | ||
| 518 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@APERID"), n._id); | ||
| 519 | } | ||
| 520 | |||
| 521 | for (auto mannernym : _anti_mannernym_of) | ||
| 522 | { | ||
| 523 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@MANID"), mannernym._id); | ||
| 524 | } | ||
| 525 | |||
| 526 | std::list<adjective> output; | ||
| 527 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
| 528 | { | ||
| 529 | adjective tnc {_data, sqlite3_column_int(ppstmt, 0)}; | ||
| 530 | tnc._base_form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 1))); | ||
| 531 | |||
| 532 | if (sqlite3_column_type(ppstmt, 2) != SQLITE_NULL) | ||
| 533 | { | ||
| 534 | tnc._comparative_form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 2))); | ||
| 535 | } | ||
| 536 | |||
| 537 | if (sqlite3_column_type(ppstmt, 3) != SQLITE_NULL) | ||
| 538 | { | ||
| 539 | tnc._superlative_form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 3))); | ||
| 540 | } | ||
| 541 | |||
| 542 | if (sqlite3_column_type(ppstmt, 4) != SQLITE_NULL) | ||
| 543 | { | ||
| 544 | std::string adjpos(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 4))); | ||
| 545 | if (adjpos == "p") | ||
| 546 | { | ||
| 547 | tnc._position = adjective::positioning::predicate; | ||
| 548 | } else if (adjpos == "a") | ||
| 549 | { | ||
| 550 | tnc._position = adjective::positioning::attributive; | ||
| 551 | } else if (adjpos == "i") | ||
| 552 | { | ||
| 553 | tnc._position = adjective::positioning::postnominal; | ||
| 554 | } | ||
| 555 | } | ||
| 556 | |||
| 557 | output.push_back(tnc); | ||
| 558 | } | ||
| 559 | |||
| 560 | sqlite3_finalize(ppstmt); | ||
| 561 | |||
| 562 | for (auto& adjective : output) | ||
| 563 | { | ||
| 564 | query = "SELECT pronunciation FROM adjective_pronunciations WHERE adjective_id = ?"; | ||
| 565 | if (sqlite3_prepare_v2(_data.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 566 | { | ||
| 567 | throw std::runtime_error(sqlite3_errmsg(_data.ppdb)); | ||
| 568 | } | ||
| 569 | |||
| 570 | sqlite3_bind_int(ppstmt, 1, adjective._id); | ||
| 571 | |||
| 572 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
| 573 | { | ||
| 574 | std::string pronunciation(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 0))); | ||
| 575 | auto phonemes = verbly::split<std::list<std::string>>(pronunciation, " "); | ||
| 576 | |||
| 577 | adjective.pronunciations.push_back(phonemes); | ||
| 578 | } | ||
| 579 | |||
| 580 | sqlite3_finalize(ppstmt); | ||
| 581 | } | ||
| 582 | |||
| 583 | return output; | ||
| 584 | } | ||
| 585 | |||
| 586 | }; | ||
| diff --git a/verbly/adjective.h b/verbly/adjective.h index 9d7883f..4927d59 100644 --- a/verbly/adjective.h +++ b/verbly/adjective.h | |||
| @@ -3,17 +3,129 @@ | |||
| 3 | 3 | ||
| 4 | namespace verbly { | 4 | namespace verbly { |
| 5 | 5 | ||
| 6 | class adjective { | 6 | class adjective_query; |
| 7 | class adverb_query; | ||
| 8 | class noun_query; | ||
| 9 | |||
| 10 | class adjective : public word { | ||
| 11 | public: | ||
| 12 | enum class positioning { | ||
| 13 | undefined, | ||
| 14 | predicate, | ||
| 15 | attributive, | ||
| 16 | postnominal | ||
| 17 | }; | ||
| 18 | |||
| 7 | private: | 19 | private: |
| 8 | int id; | 20 | std::string _base_form; |
| 21 | std::string _comparative_form; | ||
| 22 | std::string _superlative_form; | ||
| 23 | positioning _position = positioning::undefined; | ||
| 24 | |||
| 25 | friend class adjective_query; | ||
| 26 | |||
| 27 | public: | ||
| 28 | adjective(const data& _data, int _id); | ||
| 29 | |||
| 30 | std::string base_form() const; | ||
| 31 | std::string comparative_form() const; | ||
| 32 | std::string superlative_form() const; | ||
| 33 | positioning position() const; | ||
| 34 | |||
| 35 | bool has_comparative_form() const; | ||
| 36 | bool has_superlative_form() const; | ||
| 37 | bool has_position() const; | ||
| 9 | 38 | ||
| 39 | adjective_query antonyms() const; | ||
| 40 | adjective_query synonyms() const; | ||
| 41 | adjective_query generalizations() const; | ||
| 42 | adjective_query specifications() const; | ||
| 43 | noun_query anti_pertainyms() const; | ||
| 44 | adverb_query mannernyms() const; | ||
| 45 | noun_query attributes() const; | ||
| 46 | }; | ||
| 47 | |||
| 48 | class adjective_query { | ||
| 10 | public: | 49 | public: |
| 11 | std::string form; | 50 | adjective_query(const data& _data); |
| 51 | |||
| 52 | adjective_query& limit(int _limit); | ||
| 53 | adjective_query& random(bool _random); | ||
| 54 | adjective_query& except(const adjective& _word); | ||
| 55 | adjective_query& rhymes_with(const word& _word); | ||
| 56 | adjective_query& has_pronunciation(bool _has_prn); | ||
| 57 | |||
| 58 | adjective_query& requires_comparative_form(bool req); | ||
| 59 | adjective_query& requires_superlative_form(bool req); | ||
| 60 | adjective_query& position(adjective::positioning pos); | ||
| 61 | |||
| 62 | adjective_query& is_variant(bool _is_variant); | ||
| 63 | adjective_query& variant_of(const noun& _noun); | ||
| 64 | adjective_query& not_variant_of(const noun& _noun); | ||
| 65 | |||
| 66 | adjective_query& has_antonyms(bool _is_antonymic); | ||
| 67 | adjective_query& antonym_of(const adjective& _adj); | ||
| 68 | adjective_query& not_antonym_of(const adjective& _adj); | ||
| 69 | |||
| 70 | adjective_query& has_synonyms(bool _is_synonymic); | ||
| 71 | adjective_query& synonym_of(const adjective& _adj); | ||
| 72 | adjective_query& not_synonym_of(const adjective& _adj); | ||
| 73 | |||
| 74 | adjective_query& is_generalization(bool _is_generalization); | ||
| 75 | adjective_query& generalization_of(const adjective& _adj); | ||
| 76 | adjective_query& not_generalization_of(const adjective& _adj); | ||
| 77 | |||
| 78 | adjective_query& is_specification(bool _is_specification); | ||
| 79 | adjective_query& specification_of(const adjective& _adj); | ||
| 80 | adjective_query& not_specification_of(const adjective& _adj); | ||
| 81 | |||
| 82 | adjective_query& is_pertainymic(bool _is_pertainymic); | ||
| 83 | adjective_query& pertainym_of(const noun& _noun); | ||
| 84 | |||
| 85 | adjective_query& is_mannernymic(bool _is_mannernymic); | ||
| 86 | adjective_query& anti_mannernym_of(const adverb& _adv); | ||
| 87 | |||
| 88 | std::list<adjective> run() const; | ||
| 89 | |||
| 90 | const static int unlimited = -1; | ||
| 91 | |||
| 92 | protected: | ||
| 93 | const data& _data; | ||
| 94 | int _limit = unlimited; | ||
| 95 | bool _random = false; | ||
| 96 | std::list<std::string> _rhymes; | ||
| 97 | std::list<adjective> _except; | ||
| 98 | bool _has_prn = false; | ||
| 99 | |||
| 100 | bool _requires_comparative_form = false; | ||
| 101 | bool _requires_superlative_form = false; | ||
| 102 | adjective::positioning _position = adjective::positioning::undefined; | ||
| 103 | |||
| 104 | bool _is_variant = false; | ||
| 105 | std::list<noun> _variant_of; | ||
| 106 | std::list<noun> _not_variant_of; | ||
| 107 | |||
| 108 | bool _is_antonymic = false; | ||
| 109 | std::list<adjective> _antonym_of; | ||
| 110 | std::list<adjective> _not_antonym_of; | ||
| 111 | |||
| 112 | bool _is_synonymic = false; | ||
| 113 | std::list<adjective> _synonym_of; | ||
| 114 | std::list<adjective> _not_synonym_of; | ||
| 115 | |||
| 116 | bool _is_generalization = false; | ||
| 117 | std::list<adjective> _generalization_of; | ||
| 118 | std::list<adjective> _not_generalization_of; | ||
| 119 | |||
| 120 | bool _is_specification = false; | ||
| 121 | std::list<adjective> _specification_of; | ||
| 122 | std::list<adjective> _not_specification_of; | ||
| 123 | |||
| 124 | bool _is_pertainymic = false; | ||
| 125 | std::list<noun> _pertainym_of; | ||
| 12 | 126 | ||
| 13 | adjective(int id) : id(id) | 127 | bool _is_mannernymic = false; |
| 14 | { | 128 | std::list<adverb> _anti_mannernym_of; |
| 15 | |||
| 16 | } | ||
| 17 | }; | 129 | }; |
| 18 | 130 | ||
| 19 | }; | 131 | }; |
| diff --git a/verbly/adverb.cpp b/verbly/adverb.cpp new file mode 100644 index 0000000..9bb5a0d --- /dev/null +++ b/verbly/adverb.cpp | |||
| @@ -0,0 +1,364 @@ | |||
| 1 | #include "verbly.h" | ||
| 2 | |||
| 3 | namespace verbly { | ||
| 4 | |||
| 5 | adverb::adverb(const data& _data, int _id) : word(_data, _id) | ||
| 6 | { | ||
| 7 | |||
| 8 | } | ||
| 9 | |||
| 10 | std::string adverb::base_form() const | ||
| 11 | { | ||
| 12 | return _base_form; | ||
| 13 | } | ||
| 14 | |||
| 15 | std::string adverb::comparative_form() const | ||
| 16 | { | ||
| 17 | return _comparative_form; | ||
| 18 | } | ||
| 19 | |||
| 20 | std::string adverb::superlative_form() const | ||
| 21 | { | ||
| 22 | return _superlative_form; | ||
| 23 | } | ||
| 24 | |||
| 25 | bool adverb::has_comparative_form() const | ||
| 26 | { | ||
| 27 | return !_comparative_form.empty(); | ||
| 28 | } | ||
| 29 | |||
| 30 | bool adverb::has_superlative_form() const | ||
| 31 | { | ||
| 32 | return !_superlative_form.empty(); | ||
| 33 | } | ||
| 34 | |||
| 35 | adverb_query adverb::antonyms() const | ||
| 36 | { | ||
| 37 | return _data.adverbs().antonym_of(*this); | ||
| 38 | } | ||
| 39 | |||
| 40 | adverb_query adverb::synonyms() const | ||
| 41 | { | ||
| 42 | return _data.adverbs().synonym_of(*this); | ||
| 43 | } | ||
| 44 | |||
| 45 | adjective_query adverb::anti_mannernyms() const | ||
| 46 | { | ||
| 47 | return _data.adjectives().anti_mannernym_of(*this); | ||
| 48 | } | ||
| 49 | |||
| 50 | adverb_query::adverb_query(const data& _data) : _data(_data) | ||
| 51 | { | ||
| 52 | |||
| 53 | } | ||
| 54 | |||
| 55 | adverb_query& adverb_query::limit(int _limit) | ||
| 56 | { | ||
| 57 | if ((_limit > 0) || (_limit == unlimited)) | ||
| 58 | { | ||
| 59 | this->_limit = _limit; | ||
| 60 | } | ||
| 61 | |||
| 62 | return *this; | ||
| 63 | } | ||
| 64 | |||
| 65 | adverb_query& adverb_query::random(bool _random) | ||
| 66 | { | ||
| 67 | this->_random = _random; | ||
| 68 | |||
| 69 | return *this; | ||
| 70 | } | ||
| 71 | |||
| 72 | adverb_query& adverb_query::except(const adverb& _word) | ||
| 73 | { | ||
| 74 | _except.push_back(_word); | ||
| 75 | |||
| 76 | return *this; | ||
| 77 | } | ||
| 78 | |||
| 79 | adverb_query& adverb_query::rhymes_with(const word& _word) | ||
| 80 | { | ||
| 81 | for (auto rhyme : _word.rhyme_phonemes()) | ||
| 82 | { | ||
| 83 | _rhymes.push_back(rhyme); | ||
| 84 | } | ||
| 85 | |||
| 86 | if (dynamic_cast<const adverb*>(&_word) != nullptr) | ||
| 87 | { | ||
| 88 | _except.push_back(dynamic_cast<const adverb&>(_word)); | ||
| 89 | } | ||
| 90 | |||
| 91 | return *this; | ||
| 92 | } | ||
| 93 | |||
| 94 | adverb_query& adverb_query::has_pronunciation(bool _has_prn) | ||
| 95 | { | ||
| 96 | this->_has_prn = _has_prn; | ||
| 97 | |||
| 98 | return *this; | ||
| 99 | } | ||
| 100 | |||
| 101 | adverb_query& adverb_query::requires_comparative_form(bool _arg) | ||
| 102 | { | ||
| 103 | _requires_comparative_form = _arg; | ||
| 104 | |||
| 105 | return *this; | ||
| 106 | } | ||
| 107 | |||
| 108 | adverb_query& adverb_query::requires_superlative_form(bool _arg) | ||
| 109 | { | ||
| 110 | _requires_superlative_form = _arg; | ||
| 111 | |||
| 112 | return *this; | ||
| 113 | } | ||
| 114 | |||
| 115 | adverb_query& adverb_query::has_antonyms(bool _arg) | ||
| 116 | { | ||
| 117 | _has_antonyms = _arg; | ||
| 118 | |||
| 119 | return *this; | ||
| 120 | } | ||
| 121 | |||
| 122 | adverb_query& adverb_query::antonym_of(const adverb& _adv) | ||
| 123 | { | ||
| 124 | _antonym_of.push_back(_adv); | ||
| 125 | |||
| 126 | return *this; | ||
| 127 | } | ||
| 128 | |||
| 129 | adverb_query& adverb_query::not_antonym_of(const adverb& _adv) | ||
| 130 | { | ||
| 131 | _not_antonym_of.push_back(_adv); | ||
| 132 | |||
| 133 | return *this; | ||
| 134 | } | ||
| 135 | |||
| 136 | adverb_query& adverb_query::has_synonyms(bool _arg) | ||
| 137 | { | ||
| 138 | _has_synonyms = _arg; | ||
| 139 | |||
| 140 | return *this; | ||
| 141 | } | ||
| 142 | |||
| 143 | adverb_query& adverb_query::synonym_of(const adverb& _adv) | ||
| 144 | { | ||
| 145 | _synonym_of.push_back(_adv); | ||
| 146 | |||
| 147 | return *this; | ||
| 148 | } | ||
| 149 | |||
| 150 | adverb_query& adverb_query::not_synonym_of(const adverb& _adv) | ||
| 151 | { | ||
| 152 | _not_synonym_of.push_back(_adv); | ||
| 153 | |||
| 154 | return *this; | ||
| 155 | } | ||
| 156 | |||
| 157 | adverb_query& adverb_query::is_mannernymic(bool _arg) | ||
| 158 | { | ||
| 159 | _is_mannernymic = _arg; | ||
| 160 | |||
| 161 | return *this; | ||
| 162 | } | ||
| 163 | |||
| 164 | adverb_query& adverb_query::mannernym_of(const adjective& _adj) | ||
| 165 | { | ||
| 166 | _mannernym_of.push_back(_adj); | ||
| 167 | |||
| 168 | return *this; | ||
| 169 | } | ||
| 170 | |||
| 171 | std::list<adverb> adverb_query::run() const | ||
| 172 | { | ||
| 173 | std::stringstream construct; | ||
| 174 | construct << "SELECT adverb_id, base_form, comparative, superlative FROM adverbs"; | ||
| 175 | std::list<std::string> conditions; | ||
| 176 | |||
| 177 | if (_has_prn) | ||
| 178 | { | ||
| 179 | conditions.push_back("adverb_id IN (SELECT adverb_id FROM adverb_pronunciations)"); | ||
| 180 | } | ||
| 181 | |||
| 182 | if (!_rhymes.empty()) | ||
| 183 | { | ||
| 184 | std::list<std::string> clauses(_rhymes.size(), "pronunciation LIKE @RHMPRN"); | ||
| 185 | std::string cond = "adverb_id IN (SELECT adverb_id FROM adverb_pronunciations WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 186 | conditions.push_back(cond); | ||
| 187 | } | ||
| 188 | |||
| 189 | for (auto except : _except) | ||
| 190 | { | ||
| 191 | conditions.push_back("adverb_id != @EXCID"); | ||
| 192 | } | ||
| 193 | |||
| 194 | if (_requires_comparative_form) | ||
| 195 | { | ||
| 196 | conditions.push_back("comparative IS NOT NULL"); | ||
| 197 | } | ||
| 198 | |||
| 199 | if (_requires_superlative_form) | ||
| 200 | { | ||
| 201 | conditions.push_back("superlative IS NOT NULL"); | ||
| 202 | } | ||
| 203 | |||
| 204 | if (_has_antonyms) | ||
| 205 | { | ||
| 206 | conditions.push_back("adverb_id IN (SELECT adverb_2_id FROM adverb_antonymy)"); | ||
| 207 | } | ||
| 208 | |||
| 209 | if (!_antonym_of.empty()) | ||
| 210 | { | ||
| 211 | std::list<std::string> clauses(_antonym_of.size(), "adverb_1_id = @ANTID"); | ||
| 212 | std::string cond = "adverb_id IN (SELECT adverb_2_id FROM adverb_antonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 213 | conditions.push_back(cond); | ||
| 214 | } | ||
| 215 | |||
| 216 | if (!_not_antonym_of.empty()) | ||
| 217 | { | ||
| 218 | std::list<std::string> clauses(_not_antonym_of.size(), "adverb_1_id = @NANTID"); | ||
| 219 | std::string cond = "adverb_id NOT IN (SELECT adverb_2_id FROM adverb_antonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 220 | conditions.push_back(cond); | ||
| 221 | } | ||
| 222 | |||
| 223 | if (_has_synonyms) | ||
| 224 | { | ||
| 225 | conditions.push_back("adverb_id IN (SELECT adverb_2_id FROM adverb_synonymy)"); | ||
| 226 | } | ||
| 227 | |||
| 228 | if (!_synonym_of.empty()) | ||
| 229 | { | ||
| 230 | std::list<std::string> clauses(_synonym_of.size(), "adverb_1_id = @SYNID"); | ||
| 231 | std::string cond = "adverb_id IN (SELECT adverb_2_id FROM adverb_synonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 232 | conditions.push_back(cond); | ||
| 233 | } | ||
| 234 | |||
| 235 | if (!_not_synonym_of.empty()) | ||
| 236 | { | ||
| 237 | std::list<std::string> clauses(_not_synonym_of.size(), "adverb_1_id = @NSYNID"); | ||
| 238 | std::string cond = "adverb_id NOT IN (SELECT adverb_2_id FROM adverb_synonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 239 | conditions.push_back(cond); | ||
| 240 | } | ||
| 241 | |||
| 242 | if (_is_mannernymic) | ||
| 243 | { | ||
| 244 | conditions.push_back("adverb_id IN (SELECT mannernym_id FROM mannernymy)"); | ||
| 245 | } | ||
| 246 | |||
| 247 | if (!_mannernym_of.empty()) | ||
| 248 | { | ||
| 249 | std::list<std::string> clauses(_mannernym_of.size(), "adjective_id = @AMANID"); | ||
| 250 | std::string cond = "adverb_id IN (SELECT mannernym_id FROM mannernymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 251 | conditions.push_back(cond); | ||
| 252 | } | ||
| 253 | |||
| 254 | if (!conditions.empty()) | ||
| 255 | { | ||
| 256 | construct << " WHERE "; | ||
| 257 | construct << verbly::implode(std::begin(conditions), std::end(conditions), " AND "); | ||
| 258 | } | ||
| 259 | |||
| 260 | if (_random) | ||
| 261 | { | ||
| 262 | construct << " ORDER BY RANDOM()"; | ||
| 263 | } | ||
| 264 | |||
| 265 | if (_limit != unlimited) | ||
| 266 | { | ||
| 267 | construct << " LIMIT " << _limit; | ||
| 268 | } | ||
| 269 | |||
| 270 | sqlite3_stmt* ppstmt; | ||
| 271 | std::string query = construct.str(); | ||
| 272 | if (sqlite3_prepare_v2(_data.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 273 | { | ||
| 274 | throw std::runtime_error(sqlite3_errmsg(_data.ppdb)); | ||
| 275 | } | ||
| 276 | |||
| 277 | if (!_rhymes.empty()) | ||
| 278 | { | ||
| 279 | int i = 0; | ||
| 280 | for (auto rhyme : _rhymes) | ||
| 281 | { | ||
| 282 | std::string rhymer = "%" + rhyme; | ||
| 283 | sqlite3_bind_text(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@RHMPRN"), rhymer.c_str(), rhymer.length(), SQLITE_STATIC); | ||
| 284 | |||
| 285 | i++; | ||
| 286 | } | ||
| 287 | } | ||
| 288 | |||
| 289 | for (auto except : _except) | ||
| 290 | { | ||
| 291 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@EXCID"), except._id); | ||
| 292 | } | ||
| 293 | |||
| 294 | for (auto antonym : _antonym_of) | ||
| 295 | { | ||
| 296 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@ANTID"), antonym._id); | ||
| 297 | } | ||
| 298 | |||
| 299 | for (auto antonym : _not_antonym_of) | ||
| 300 | { | ||
| 301 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NANTID"), antonym._id); | ||
| 302 | } | ||
| 303 | |||
| 304 | for (auto synonym : _synonym_of) | ||
| 305 | { | ||
| 306 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@SYNID"), synonym._id); | ||
| 307 | } | ||
| 308 | |||
| 309 | for (auto synonym : _not_synonym_of) | ||
| 310 | { | ||
| 311 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NSYNID"), synonym._id); | ||
| 312 | } | ||
| 313 | |||
| 314 | for (auto adj : _mannernym_of) | ||
| 315 | { | ||
| 316 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@AMANID"), adj._id); | ||
| 317 | } | ||
| 318 | |||
| 319 | std::list<adverb> output; | ||
| 320 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
| 321 | { | ||
| 322 | adverb tnc {_data, sqlite3_column_int(ppstmt, 0)}; | ||
| 323 | tnc._base_form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 1))); | ||
| 324 | |||
| 325 | if (sqlite3_column_type(ppstmt, 2) != SQLITE_NULL) | ||
| 326 | { | ||
| 327 | tnc._comparative_form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 2))); | ||
| 328 | } | ||
| 329 | |||
| 330 | if (sqlite3_column_type(ppstmt, 3) != SQLITE_NULL) | ||
| 331 | { | ||
| 332 | tnc._superlative_form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 3))); | ||
| 333 | } | ||
| 334 | |||
| 335 | output.push_back(tnc); | ||
| 336 | } | ||
| 337 | |||
| 338 | sqlite3_finalize(ppstmt); | ||
| 339 | |||
| 340 | for (auto& adverb : output) | ||
| 341 | { | ||
| 342 | query = "SELECT pronunciation FROM adverb_pronunciations WHERE adverb_id = ?"; | ||
| 343 | if (sqlite3_prepare_v2(_data.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 344 | { | ||
| 345 | throw std::runtime_error(sqlite3_errmsg(_data.ppdb)); | ||
| 346 | } | ||
| 347 | |||
| 348 | sqlite3_bind_int(ppstmt, 1, adverb._id); | ||
| 349 | |||
| 350 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
| 351 | { | ||
| 352 | std::string pronunciation(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 0))); | ||
| 353 | auto phonemes = verbly::split<std::list<std::string>>(pronunciation, " "); | ||
| 354 | |||
| 355 | adverb.pronunciations.push_back(phonemes); | ||
| 356 | } | ||
| 357 | |||
| 358 | sqlite3_finalize(ppstmt); | ||
| 359 | } | ||
| 360 | |||
| 361 | return output; | ||
| 362 | } | ||
| 363 | |||
| 364 | }; | ||
| diff --git a/verbly/adverb.h b/verbly/adverb.h index 6d2466e..42c3492 100644 --- a/verbly/adverb.h +++ b/verbly/adverb.h | |||
| @@ -3,17 +3,78 @@ | |||
| 3 | 3 | ||
| 4 | namespace verbly { | 4 | namespace verbly { |
| 5 | 5 | ||
| 6 | class adverb { | 6 | class adverb : public word { |
| 7 | private: | 7 | private: |
| 8 | int id; | 8 | std::string _base_form; |
| 9 | std::string _comparative_form; | ||
| 10 | std::string _superlative_form; | ||
| 9 | 11 | ||
| 12 | friend class adverb_query; | ||
| 13 | |||
| 14 | public: | ||
| 15 | adverb(const data& _data, int _id); | ||
| 16 | |||
| 17 | std::string base_form() const; | ||
| 18 | std::string comparative_form() const; | ||
| 19 | std::string superlative_form() const; | ||
| 20 | |||
| 21 | bool has_comparative_form() const; | ||
| 22 | bool has_superlative_form() const; | ||
| 23 | |||
| 24 | adverb_query antonyms() const; | ||
| 25 | adverb_query synonyms() const; | ||
| 26 | adjective_query anti_mannernyms() const; | ||
| 27 | }; | ||
| 28 | |||
| 29 | class adverb_query { | ||
| 10 | public: | 30 | public: |
| 11 | std::string form; | 31 | adverb_query(const data& _data); |
| 32 | |||
| 33 | adverb_query& limit(int _limit); | ||
| 34 | adverb_query& random(bool _random); | ||
| 35 | adverb_query& except(const adverb& _word); | ||
| 36 | adverb_query& rhymes_with(const word& _word); | ||
| 37 | adverb_query& has_pronunciation(bool _has_prn); | ||
| 38 | |||
| 39 | adverb_query& requires_comparative_form(bool _arg); | ||
| 40 | adverb_query& requires_superlative_form(bool _arg); | ||
| 41 | |||
| 42 | adverb_query& has_antonyms(bool _arg); | ||
| 43 | adverb_query& antonym_of(const adverb& _adv); | ||
| 44 | adverb_query& not_antonym_of(const adverb& _adv); | ||
| 45 | |||
| 46 | adverb_query& has_synonyms(bool _arg); | ||
| 47 | adverb_query& synonym_of(const adverb& _adv); | ||
| 48 | adverb_query& not_synonym_of(const adverb& _adv); | ||
| 49 | |||
| 50 | adverb_query& is_mannernymic(bool _arg); | ||
| 51 | adverb_query& mannernym_of(const adjective& _adj); | ||
| 52 | |||
| 53 | std::list<adverb> run() const; | ||
| 54 | |||
| 55 | const static int unlimited = -1; | ||
| 56 | |||
| 57 | private: | ||
| 58 | const data& _data; | ||
| 59 | int _limit = unlimited; | ||
| 60 | bool _random = false; | ||
| 61 | std::list<std::string> _rhymes; | ||
| 62 | std::list<adverb> _except; | ||
| 63 | bool _has_prn = false; | ||
| 64 | |||
| 65 | bool _requires_comparative_form = false; | ||
| 66 | bool _requires_superlative_form = false; | ||
| 67 | |||
| 68 | bool _has_antonyms = false; | ||
| 69 | std::list<adverb> _antonym_of; | ||
| 70 | std::list<adverb> _not_antonym_of; | ||
| 71 | |||
| 72 | bool _has_synonyms = false; | ||
| 73 | std::list<adverb> _synonym_of; | ||
| 74 | std::list<adverb> _not_synonym_of; | ||
| 12 | 75 | ||
| 13 | adverb(int id) : id(id) | 76 | bool _is_mannernymic = false; |
| 14 | { | 77 | std::list<adjective> _mannernym_of; |
| 15 | |||
| 16 | } | ||
| 17 | }; | 78 | }; |
| 18 | 79 | ||
| 19 | }; | 80 | }; |
| diff --git a/verbly/data.cpp b/verbly/data.cpp new file mode 100644 index 0000000..57a8850 --- /dev/null +++ b/verbly/data.cpp | |||
| @@ -0,0 +1,50 @@ | |||
| 1 | #include "verbly.h" | ||
| 2 | |||
| 3 | namespace verbly { | ||
| 4 | |||
| 5 | data::data(std::string datafile) | ||
| 6 | { | ||
| 7 | if (sqlite3_open_v2(datafile.c_str(), &ppdb, SQLITE_OPEN_READONLY, NULL) != SQLITE_OK) | ||
| 8 | { | ||
| 9 | throw std::invalid_argument(sqlite3_errmsg(ppdb)); | ||
| 10 | } | ||
| 11 | } | ||
| 12 | |||
| 13 | data::data(data&& other) | ||
| 14 | { | ||
| 15 | ppdb = other.ppdb; | ||
| 16 | } | ||
| 17 | |||
| 18 | data& data::operator=(data&& other) | ||
| 19 | { | ||
| 20 | ppdb = other.ppdb; | ||
| 21 | |||
| 22 | return *this; | ||
| 23 | } | ||
| 24 | |||
| 25 | data::~data() | ||
| 26 | { | ||
| 27 | sqlite3_close_v2(ppdb); | ||
| 28 | } | ||
| 29 | |||
| 30 | verb_query data::verbs() const | ||
| 31 | { | ||
| 32 | return verb_query(*this); | ||
| 33 | } | ||
| 34 | |||
| 35 | adjective_query data::adjectives() const | ||
| 36 | { | ||
| 37 | return adjective_query(*this); | ||
| 38 | } | ||
| 39 | |||
| 40 | adverb_query data::adverbs() const | ||
| 41 | { | ||
| 42 | return adverb_query(*this); | ||
| 43 | } | ||
| 44 | |||
| 45 | noun_query data::nouns() const | ||
| 46 | { | ||
| 47 | return noun_query(*this); | ||
| 48 | } | ||
| 49 | |||
| 50 | }; | ||
| diff --git a/verbly/data.h b/verbly/data.h index e901cba..37092d7 100644 --- a/verbly/data.h +++ b/verbly/data.h | |||
| @@ -1,273 +1,46 @@ | |||
| 1 | #ifndef DATA_H_C4AEC3DD | 1 | #ifndef DATA_H_C4AEC3DD |
| 2 | #define DATA_H_C4AEC3DD | 2 | #define DATA_H_C4AEC3DD |
| 3 | 3 | ||
| 4 | #include "verb.h" | ||
| 5 | #include <sqlite3.h> | 4 | #include <sqlite3.h> |
| 6 | #include <stdexcept> | 5 | #include <stdexcept> |
| 7 | 6 | ||
| 8 | namespace verbly { | 7 | namespace verbly { |
| 9 | 8 | ||
| 9 | class data; | ||
| 10 | class word; | ||
| 11 | class adjective; | ||
| 12 | class noun; | ||
| 13 | class verb; | ||
| 14 | class adverb; | ||
| 15 | class adjective_query; | ||
| 16 | class adverb_query; | ||
| 17 | class noun_query; | ||
| 18 | class verb_query; | ||
| 19 | |||
| 10 | class data { | 20 | class data { |
| 11 | private: | 21 | private: |
| 12 | sqlite3* ppdb; | 22 | sqlite3* ppdb; |
| 13 | 23 | ||
| 14 | public: | 24 | friend class adjective_query; |
| 15 | class verb_query { | 25 | friend class noun_query; |
| 16 | public: | 26 | friend class verb_query; |
| 17 | const static int unlimited = -1; | 27 | friend class adverb_query; |
| 18 | |||
| 19 | private: | ||
| 20 | const data& database; | ||
| 21 | int m_limit = unlimited; | ||
| 22 | bool m_random = false; | ||
| 23 | |||
| 24 | public: | ||
| 25 | verb_query(const data& database) : database(database) | ||
| 26 | { | ||
| 27 | |||
| 28 | } | ||
| 29 | |||
| 30 | verb_query& limit(int m_limit) | ||
| 31 | { | ||
| 32 | if ((m_limit > 0) || (m_limit == unlimited)) | ||
| 33 | { | ||
| 34 | this->m_limit = m_limit; | ||
| 35 | } | ||
| 36 | |||
| 37 | return *this; | ||
| 38 | } | ||
| 39 | |||
| 40 | verb_query& random(bool m_random) | ||
| 41 | { | ||
| 42 | this->m_random = m_random; | ||
| 43 | |||
| 44 | return *this; | ||
| 45 | } | ||
| 46 | |||
| 47 | std::list<verb> run() const | ||
| 48 | { | ||
| 49 | std::stringstream construct; | ||
| 50 | construct << "SELECT verb_id, infinitive, past_tense, past_participle, ing_form, s_form FROM verbs"; | ||
| 51 | |||
| 52 | if (m_random) | ||
| 53 | { | ||
| 54 | construct << " ORDER BY RANDOM()"; | ||
| 55 | } | ||
| 56 | |||
| 57 | if (m_limit != unlimited) | ||
| 58 | { | ||
| 59 | construct << " LIMIT " << m_limit; | ||
| 60 | } | ||
| 61 | |||
| 62 | sqlite3_stmt* ppstmt; | ||
| 63 | std::string query = construct.str(); | ||
| 64 | if (sqlite3_prepare_v2(database.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 65 | { | ||
| 66 | throw std::runtime_error(sqlite3_errmsg(database.ppdb)); | ||
| 67 | } | ||
| 68 | |||
| 69 | std::list<verb> output; | ||
| 70 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
| 71 | { | ||
| 72 | verb tnc {sqlite3_column_int(ppstmt, 0)}; | ||
| 73 | tnc.infinitive = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 1))); | ||
| 74 | tnc.past_tense = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 2))); | ||
| 75 | tnc.past_participle = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 3))); | ||
| 76 | tnc.ing_form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 4))); | ||
| 77 | tnc.s_form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 5))); | ||
| 78 | |||
| 79 | output.push_back(tnc); | ||
| 80 | } | ||
| 81 | |||
| 82 | sqlite3_finalize(ppstmt); | ||
| 83 | |||
| 84 | return output; | ||
| 85 | } | ||
| 86 | |||
| 87 | }; | ||
| 88 | |||
| 89 | class adjective_query { | ||
| 90 | public: | ||
| 91 | const static int unlimited = -1; | ||
| 92 | |||
| 93 | private: | ||
| 94 | const data& database; | ||
| 95 | int m_limit = unlimited; | ||
| 96 | bool m_random = false; | ||
| 97 | |||
| 98 | public: | ||
| 99 | adjective_query(const data& database) : database(database) | ||
| 100 | { | ||
| 101 | |||
| 102 | } | ||
| 103 | |||
| 104 | adjective_query& limit(int m_limit) | ||
| 105 | { | ||
| 106 | if ((m_limit > 0) || (m_limit == unlimited)) | ||
| 107 | { | ||
| 108 | this->m_limit = m_limit; | ||
| 109 | } | ||
| 110 | |||
| 111 | return *this; | ||
| 112 | } | ||
| 113 | |||
| 114 | adjective_query& random(bool m_random) | ||
| 115 | { | ||
| 116 | this->m_random = m_random; | ||
| 117 | |||
| 118 | return *this; | ||
| 119 | } | ||
| 120 | |||
| 121 | std::list<adjective> run() const | ||
| 122 | { | ||
| 123 | std::stringstream construct; | ||
| 124 | construct << "SELECT adjective_id, form FROM adjectives"; | ||
| 125 | |||
| 126 | if (m_random) | ||
| 127 | { | ||
| 128 | construct << " ORDER BY RANDOM()"; | ||
| 129 | } | ||
| 130 | |||
| 131 | if (m_limit != unlimited) | ||
| 132 | { | ||
| 133 | construct << " LIMIT " << m_limit; | ||
| 134 | } | ||
| 135 | |||
| 136 | sqlite3_stmt* ppstmt; | ||
| 137 | std::string query = construct.str(); | ||
| 138 | if (sqlite3_prepare_v2(database.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 139 | { | ||
| 140 | throw std::runtime_error(sqlite3_errmsg(database.ppdb)); | ||
| 141 | } | ||
| 142 | |||
| 143 | std::list<adjective> output; | ||
| 144 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
| 145 | { | ||
| 146 | adjective tnc {sqlite3_column_int(ppstmt, 0)}; | ||
| 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))); | ||
| 218 | |||
| 219 | output.push_back(tnc); | ||
| 220 | } | ||
| 221 | |||
| 222 | sqlite3_finalize(ppstmt); | ||
| 223 | |||
| 224 | return output; | ||
| 225 | } | ||
| 226 | |||
| 227 | }; | ||
| 228 | 28 | ||
| 229 | data(std::string datafile) | 29 | public: |
| 230 | { | 30 | data(std::string datafile); |
| 231 | if (sqlite3_open_v2(datafile.c_str(), &ppdb, SQLITE_OPEN_READONLY, NULL) != SQLITE_OK) | ||
| 232 | { | ||
| 233 | throw std::invalid_argument(sqlite3_errmsg(ppdb)); | ||
| 234 | } | ||
| 235 | } | ||
| 236 | 31 | ||
| 237 | data(const data& other) = delete; | 32 | data(const data& other) = delete; |
| 238 | data& operator=(const data& other) = delete; | 33 | data& operator=(const data& other) = delete; |
| 239 | 34 | ||
| 240 | data(data&& other) | 35 | data(data&& other); |
| 241 | { | 36 | data& operator=(data&& other); |
| 242 | ppdb = other.ppdb; | ||
| 243 | } | ||
| 244 | |||
| 245 | data& operator=(data&& other) | ||
| 246 | { | ||
| 247 | ppdb = other.ppdb; | ||
| 248 | |||
| 249 | return *this; | ||
| 250 | } | ||
| 251 | |||
| 252 | ~data() | ||
| 253 | { | ||
| 254 | sqlite3_close_v2(ppdb); | ||
| 255 | } | ||
| 256 | |||
| 257 | verb_query verbs() const | ||
| 258 | { | ||
| 259 | return verb_query(*this); | ||
| 260 | } | ||
| 261 | 37 | ||
| 262 | adjective_query adjectives() const | 38 | ~data(); |
| 263 | { | ||
| 264 | return adjective_query(*this); | ||
| 265 | } | ||
| 266 | 39 | ||
| 267 | adverb_query adverbs() const | 40 | verb_query verbs() const; |
| 268 | { | 41 | adjective_query adjectives() const; |
| 269 | return adverb_query(*this); | 42 | adverb_query adverbs() const; |
| 270 | } | 43 | noun_query nouns() const; |
| 271 | 44 | ||
| 272 | }; | 45 | }; |
| 273 | 46 | ||
| diff --git a/verbly/noun.cpp b/verbly/noun.cpp new file mode 100644 index 0000000..9336a1c --- /dev/null +++ b/verbly/noun.cpp | |||
| @@ -0,0 +1,916 @@ | |||
| 1 | #include "verbly.h" | ||
| 2 | |||
| 3 | namespace verbly { | ||
| 4 | |||
| 5 | noun::noun(const data& _data, int _id) : word(_data, _id) | ||
| 6 | { | ||
| 7 | |||
| 8 | } | ||
| 9 | |||
| 10 | std::string noun::base_form() const | ||
| 11 | { | ||
| 12 | return _singular; | ||
| 13 | } | ||
| 14 | |||
| 15 | std::string noun::singular_form() const | ||
| 16 | { | ||
| 17 | return _singular; | ||
| 18 | } | ||
| 19 | |||
| 20 | std::string noun::plural_form() const | ||
| 21 | { | ||
| 22 | return _plural; | ||
| 23 | } | ||
| 24 | |||
| 25 | bool noun::has_plural_form() const | ||
| 26 | { | ||
| 27 | return !_plural.empty(); | ||
| 28 | } | ||
| 29 | |||
| 30 | noun_query noun::hypernyms() const | ||
| 31 | { | ||
| 32 | return _data.nouns().hypernym_of(*this); | ||
| 33 | } | ||
| 34 | |||
| 35 | noun_query noun::hyponyms() const | ||
| 36 | { | ||
| 37 | return _data.nouns().hyponym_of(*this); | ||
| 38 | } | ||
| 39 | |||
| 40 | noun_query noun::part_meronyms() const | ||
| 41 | { | ||
| 42 | return _data.nouns().part_meronym_of(*this); | ||
| 43 | } | ||
| 44 | |||
| 45 | noun_query noun::part_holonyms() const | ||
| 46 | { | ||
| 47 | return _data.nouns().part_holonym_of(*this); | ||
| 48 | } | ||
| 49 | |||
| 50 | noun_query noun::substance_meronyms() const | ||
| 51 | { | ||
| 52 | return _data.nouns().substance_meronym_of(*this); | ||
| 53 | } | ||
| 54 | |||
| 55 | noun_query noun::substance_holonyms() const | ||
| 56 | { | ||
| 57 | return _data.nouns().substance_holonym_of(*this); | ||
| 58 | } | ||
| 59 | |||
| 60 | noun_query noun::member_meronyms() const | ||
| 61 | { | ||
| 62 | return _data.nouns().member_meronym_of(*this); | ||
| 63 | } | ||
| 64 | |||
| 65 | noun_query noun::member_holonyms() const | ||
| 66 | { | ||
| 67 | return _data.nouns().member_holonym_of(*this); | ||
| 68 | } | ||
| 69 | |||
| 70 | noun_query noun::classes() const | ||
| 71 | { | ||
| 72 | return _data.nouns().class_of(*this); | ||
| 73 | } | ||
| 74 | |||
| 75 | noun_query noun::instances() const | ||
| 76 | { | ||
| 77 | return _data.nouns().instance_of(*this); | ||
| 78 | } | ||
| 79 | |||
| 80 | noun_query noun::synonyms() const | ||
| 81 | { | ||
| 82 | return _data.nouns().synonym_of(*this); | ||
| 83 | } | ||
| 84 | |||
| 85 | noun_query noun::antonyms() const | ||
| 86 | { | ||
| 87 | return _data.nouns().antonym_of(*this); | ||
| 88 | } | ||
| 89 | |||
| 90 | adjective_query noun::pertainyms() const | ||
| 91 | { | ||
| 92 | return _data.adjectives().pertainym_of(*this); | ||
| 93 | } | ||
| 94 | |||
| 95 | adjective_query noun::variations() const | ||
| 96 | { | ||
| 97 | return _data.adjectives().variant_of(*this); | ||
| 98 | } | ||
| 99 | |||
| 100 | noun_query::noun_query(const data& _data) : _data(_data) | ||
| 101 | { | ||
| 102 | |||
| 103 | } | ||
| 104 | |||
| 105 | noun_query& noun_query::limit(int _limit) | ||
| 106 | { | ||
| 107 | if ((_limit > 0) || (_limit == unlimited)) | ||
| 108 | { | ||
| 109 | this->_limit = _limit; | ||
| 110 | } | ||
| 111 | |||
| 112 | return *this; | ||
| 113 | } | ||
| 114 | |||
| 115 | noun_query& noun_query::random(bool _random) | ||
| 116 | { | ||
| 117 | this->_random = _random; | ||
| 118 | |||
| 119 | return *this; | ||
| 120 | } | ||
| 121 | |||
| 122 | noun_query& noun_query::except(const noun& _word) | ||
| 123 | { | ||
| 124 | _except.push_back(_word); | ||
| 125 | |||
| 126 | return *this; | ||
| 127 | } | ||
| 128 | |||
| 129 | noun_query& noun_query::rhymes_with(const word& _word) | ||
| 130 | { | ||
| 131 | for (auto rhyme : _word.rhyme_phonemes()) | ||
| 132 | { | ||
| 133 | _rhymes.push_back(rhyme); | ||
| 134 | } | ||
| 135 | |||
| 136 | if (dynamic_cast<const noun*>(&_word) != nullptr) | ||
| 137 | { | ||
| 138 | _except.push_back(dynamic_cast<const noun&>(_word)); | ||
| 139 | } | ||
| 140 | |||
| 141 | return *this; | ||
| 142 | } | ||
| 143 | |||
| 144 | noun_query& noun_query::has_pronunciation(bool _has_prn) | ||
| 145 | { | ||
| 146 | this->_has_prn = _has_prn; | ||
| 147 | |||
| 148 | return *this; | ||
| 149 | } | ||
| 150 | |||
| 151 | noun_query& noun_query::is_hypernym(bool _arg) | ||
| 152 | { | ||
| 153 | _is_hypernym = _arg; | ||
| 154 | |||
| 155 | return *this; | ||
| 156 | } | ||
| 157 | |||
| 158 | noun_query& noun_query::hypernym_of(const noun& _noun) | ||
| 159 | { | ||
| 160 | _hypernym_of.push_back(_noun); | ||
| 161 | |||
| 162 | return *this; | ||
| 163 | } | ||
| 164 | |||
| 165 | noun_query& noun_query::not_hypernym_of(const noun& _noun) | ||
| 166 | { | ||
| 167 | _not_hypernym_of.push_back(_noun); | ||
| 168 | |||
| 169 | return *this; | ||
| 170 | } | ||
| 171 | |||
| 172 | noun_query& noun_query::is_hyponym(bool _arg) | ||
| 173 | { | ||
| 174 | _is_hyponym = _arg; | ||
| 175 | |||
| 176 | return *this; | ||
| 177 | } | ||
| 178 | |||
| 179 | noun_query& noun_query::hyponym_of(const noun& _noun) | ||
| 180 | { | ||
| 181 | _hyponym_of.push_back(_noun); | ||
| 182 | |||
| 183 | return *this; | ||
| 184 | } | ||
| 185 | |||
| 186 | noun_query& noun_query::not_hyponym_of(const noun& _noun) | ||
| 187 | { | ||
| 188 | _not_hyponym_of.push_back(_noun); | ||
| 189 | |||
| 190 | return *this; | ||
| 191 | } | ||
| 192 | |||
| 193 | noun_query& noun_query::is_part_meronym(bool _arg) | ||
| 194 | { | ||
| 195 | _is_part_meronym = _arg; | ||
| 196 | |||
| 197 | return *this; | ||
| 198 | } | ||
| 199 | |||
| 200 | noun_query& noun_query::part_meronym_of(const noun& _noun) | ||
| 201 | { | ||
| 202 | _part_meronym_of.push_back(_noun); | ||
| 203 | |||
| 204 | return *this; | ||
| 205 | } | ||
| 206 | |||
| 207 | noun_query& noun_query::not_part_meronym_of(const noun& _noun) | ||
| 208 | { | ||
| 209 | _not_part_meronym_of.push_back(_noun); | ||
| 210 | |||
| 211 | return *this; | ||
| 212 | } | ||
| 213 | |||
| 214 | noun_query& noun_query::is_part_holonym(bool _arg) | ||
| 215 | { | ||
| 216 | _is_part_holonym = _arg; | ||
| 217 | |||
| 218 | return *this; | ||
| 219 | } | ||
| 220 | |||
| 221 | noun_query& noun_query::part_holonym_of(const noun& _noun) | ||
| 222 | { | ||
| 223 | _part_holonym_of.push_back(_noun); | ||
| 224 | |||
| 225 | return *this; | ||
| 226 | } | ||
| 227 | |||
| 228 | noun_query& noun_query::not_part_holonym_of(const noun& _noun) | ||
| 229 | { | ||
| 230 | _not_part_holonym_of.push_back(_noun); | ||
| 231 | |||
| 232 | return *this; | ||
| 233 | } | ||
| 234 | |||
| 235 | noun_query& noun_query::is_substance_meronym(bool _arg) | ||
| 236 | { | ||
| 237 | _is_substance_meronym = _arg; | ||
| 238 | |||
| 239 | return *this; | ||
| 240 | } | ||
| 241 | |||
| 242 | noun_query& noun_query::substance_meronym_of(const noun& _noun) | ||
| 243 | { | ||
| 244 | _substance_meronym_of.push_back(_noun); | ||
| 245 | |||
| 246 | return *this; | ||
| 247 | } | ||
| 248 | |||
| 249 | noun_query& noun_query::not_substance_meronym_of(const noun& _noun) | ||
| 250 | { | ||
| 251 | _not_substance_meronym_of.push_back(_noun); | ||
| 252 | |||
| 253 | return *this; | ||
| 254 | } | ||
| 255 | |||
| 256 | noun_query& noun_query::is_substance_holonym(bool _arg) | ||
| 257 | { | ||
| 258 | _is_substance_holonym = _arg; | ||
| 259 | |||
| 260 | return *this; | ||
| 261 | } | ||
| 262 | |||
| 263 | noun_query& noun_query::substance_holonym_of(const noun& _noun) | ||
| 264 | { | ||
| 265 | _substance_holonym_of.push_back(_noun); | ||
| 266 | |||
| 267 | return *this; | ||
| 268 | } | ||
| 269 | |||
| 270 | noun_query& noun_query::not_substance_holonym_of(const noun& _noun) | ||
| 271 | { | ||
| 272 | _not_substance_holonym_of.push_back(_noun); | ||
| 273 | |||
| 274 | return *this; | ||
| 275 | } | ||
| 276 | |||
| 277 | noun_query& noun_query::is_member_meronym(bool _arg) | ||
| 278 | { | ||
| 279 | _is_member_meronym = _arg; | ||
| 280 | |||
| 281 | return *this; | ||
| 282 | } | ||
| 283 | |||
| 284 | noun_query& noun_query::member_meronym_of(const noun& _noun) | ||
| 285 | { | ||
| 286 | _member_meronym_of.push_back(_noun); | ||
| 287 | |||
| 288 | return *this; | ||
| 289 | } | ||
| 290 | |||
| 291 | noun_query& noun_query::not_member_meronym_of(const noun& _noun) | ||
| 292 | { | ||
| 293 | _not_member_meronym_of.push_back(_noun); | ||
| 294 | |||
| 295 | return *this; | ||
| 296 | } | ||
| 297 | |||
| 298 | noun_query& noun_query::is_member_holonym(bool _arg) | ||
| 299 | { | ||
| 300 | _is_member_holonym = _arg; | ||
| 301 | |||
| 302 | return *this; | ||
| 303 | } | ||
| 304 | |||
| 305 | noun_query& noun_query::member_holonym_of(const noun& _noun) | ||
| 306 | { | ||
| 307 | _member_holonym_of.push_back(_noun); | ||
| 308 | |||
| 309 | return *this; | ||
| 310 | } | ||
| 311 | |||
| 312 | noun_query& noun_query::not_member_holonym_of(const noun& _noun) | ||
| 313 | { | ||
| 314 | _not_member_holonym_of.push_back(_noun); | ||
| 315 | |||
| 316 | return *this; | ||
| 317 | } | ||
| 318 | |||
| 319 | noun_query& noun_query::is_proper(bool _arg) | ||
| 320 | { | ||
| 321 | _is_proper = _arg; | ||
| 322 | |||
| 323 | return *this; | ||
| 324 | } | ||
| 325 | |||
| 326 | noun_query& noun_query::instance_of(const noun& _noun) | ||
| 327 | { | ||
| 328 | _instance_of.push_back(_noun); | ||
| 329 | |||
| 330 | return *this; | ||
| 331 | } | ||
| 332 | |||
| 333 | noun_query& noun_query::not_instance_of(const noun& _noun) | ||
| 334 | { | ||
| 335 | _not_instance_of.push_back(_noun); | ||
| 336 | |||
| 337 | return *this; | ||
| 338 | } | ||
| 339 | |||
| 340 | noun_query& noun_query::is_class(bool _arg) | ||
| 341 | { | ||
| 342 | _is_class = _arg; | ||
| 343 | |||
| 344 | return *this; | ||
| 345 | } | ||
| 346 | |||
| 347 | noun_query& noun_query::class_of(const noun& _noun) | ||
| 348 | { | ||
| 349 | _class_of.push_back(_noun); | ||
| 350 | |||
| 351 | return *this; | ||
| 352 | } | ||
| 353 | |||
| 354 | noun_query& noun_query::not_class_of(const noun& _noun) | ||
| 355 | { | ||
| 356 | _not_class_of.push_back(_noun); | ||
| 357 | |||
| 358 | return *this; | ||
| 359 | } | ||
| 360 | |||
| 361 | noun_query& noun_query::has_synonyms(bool _arg) | ||
| 362 | { | ||
| 363 | _has_synonyms = _arg; | ||
| 364 | |||
| 365 | return *this; | ||
| 366 | } | ||
| 367 | |||
| 368 | noun_query& noun_query::synonym_of(const noun& _noun) | ||
| 369 | { | ||
| 370 | _synonym_of.push_back(_noun); | ||
| 371 | |||
| 372 | return *this; | ||
| 373 | } | ||
| 374 | |||
| 375 | noun_query& noun_query::not_synonym_of(const noun& _noun) | ||
| 376 | { | ||
| 377 | _not_synonym_of.push_back(_noun); | ||
| 378 | |||
| 379 | return *this; | ||
| 380 | } | ||
| 381 | |||
| 382 | noun_query& noun_query::has_antonyms(bool _arg) | ||
| 383 | { | ||
| 384 | _has_antonyms = _arg; | ||
| 385 | |||
| 386 | return *this; | ||
| 387 | } | ||
| 388 | |||
| 389 | noun_query& noun_query::antonym_of(const noun& _noun) | ||
| 390 | { | ||
| 391 | _antonym_of.push_back(_noun); | ||
| 392 | |||
| 393 | return *this; | ||
| 394 | } | ||
| 395 | |||
| 396 | noun_query& noun_query::not_antonym_of(const noun& _noun) | ||
| 397 | { | ||
| 398 | _not_antonym_of.push_back(_noun); | ||
| 399 | |||
| 400 | return *this; | ||
| 401 | } | ||
| 402 | |||
| 403 | noun_query& noun_query::has_pertainym(bool _arg) | ||
| 404 | { | ||
| 405 | _has_pertainym = _arg; | ||
| 406 | |||
| 407 | return *this; | ||
| 408 | } | ||
| 409 | |||
| 410 | noun_query& noun_query::anti_pertainym_of(const adjective& _adj) | ||
| 411 | { | ||
| 412 | _anti_pertainym_of.push_back(_adj); | ||
| 413 | |||
| 414 | return *this; | ||
| 415 | } | ||
| 416 | |||
| 417 | noun_query& noun_query::is_attribute(bool _arg) | ||
| 418 | { | ||
| 419 | _is_attribute = _arg; | ||
| 420 | |||
| 421 | return *this; | ||
| 422 | } | ||
| 423 | |||
| 424 | noun_query& noun_query::attribute_of(const adjective& _adj) | ||
| 425 | { | ||
| 426 | _attribute_of.push_back(_adj); | ||
| 427 | |||
| 428 | return *this; | ||
| 429 | } | ||
| 430 | |||
| 431 | std::list<noun> noun_query::run() const | ||
| 432 | { | ||
| 433 | std::stringstream construct; | ||
| 434 | construct << "SELECT noun_id, singular, plural FROM nouns"; | ||
| 435 | std::list<std::string> conditions; | ||
| 436 | |||
| 437 | if (_has_prn) | ||
| 438 | { | ||
| 439 | conditions.push_back("noun_id IN (SELECT noun_id FROM noun_pronunciations)"); | ||
| 440 | } | ||
| 441 | |||
| 442 | if (!_rhymes.empty()) | ||
| 443 | { | ||
| 444 | std::list<std::string> clauses(_rhymes.size(), "pronunciation LIKE @RHMPRN"); | ||
| 445 | std::string cond = "noun_id IN (SELECT noun_id FROM noun_pronunciations WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 446 | conditions.push_back(cond); | ||
| 447 | } | ||
| 448 | |||
| 449 | for (auto except : _except) | ||
| 450 | { | ||
| 451 | conditions.push_back("noun_id != @EXCID"); | ||
| 452 | } | ||
| 453 | |||
| 454 | if (_is_hypernym) | ||
| 455 | { | ||
| 456 | conditions.push_back("noun_id IN (SELECT hypernym_id FROM hypernymy)"); | ||
| 457 | } | ||
| 458 | |||
| 459 | if (!_hypernym_of.empty()) | ||
| 460 | { | ||
| 461 | std::list<std::string> clauses(_hypernym_of.size(), "hyponym_id = @HYPO"); | ||
| 462 | std::string cond = "noun_id IN (SELECT hypernym_id FROM hypernymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 463 | conditions.push_back(cond); | ||
| 464 | } | ||
| 465 | |||
| 466 | if (!_not_hypernym_of.empty()) | ||
| 467 | { | ||
| 468 | std::list<std::string> clauses(_not_hypernym_of.size(), "hyponym_id = @NHYPO"); | ||
| 469 | std::string cond = "noun_id NOT IN (SELECT hypernym_id FROM hypernymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 470 | conditions.push_back(cond); | ||
| 471 | } | ||
| 472 | |||
| 473 | if (_is_hyponym) | ||
| 474 | { | ||
| 475 | conditions.push_back("noun_id IN (SELECT hyponym_id FROM hypernymy)"); | ||
| 476 | } | ||
| 477 | |||
| 478 | if (!_hyponym_of.empty()) | ||
| 479 | { | ||
| 480 | std::list<std::string> clauses(_hyponym_of.size(), "hypernym_id = @HYPER"); | ||
| 481 | std::string cond = "noun_id IN (SELECT hyponym_id FROM hypernymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 482 | conditions.push_back(cond); | ||
| 483 | } | ||
| 484 | |||
| 485 | if (!_not_hyponym_of.empty()) | ||
| 486 | { | ||
| 487 | std::list<std::string> clauses(_not_hyponym_of.size(), "hypernym_id = @NHYPER"); | ||
| 488 | std::string cond = "noun_id NOT IN (SELECT hyponym_id FROM hypernymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 489 | conditions.push_back(cond); | ||
| 490 | } | ||
| 491 | |||
| 492 | if (_is_part_meronym) | ||
| 493 | { | ||
| 494 | conditions.push_back("noun_id IN (SELECT meronym_id FROM part_meronymy)"); | ||
| 495 | } | ||
| 496 | |||
| 497 | if (!_part_meronym_of.empty()) | ||
| 498 | { | ||
| 499 | std::list<std::string> clauses(_part_meronym_of.size(), "holonym_id = @PHOLO"); | ||
| 500 | std::string cond = "noun_id IN (SELECT meronym_id FROM part_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 501 | conditions.push_back(cond); | ||
| 502 | } | ||
| 503 | |||
| 504 | if (!_not_part_meronym_of.empty()) | ||
| 505 | { | ||
| 506 | std::list<std::string> clauses(_not_part_meronym_of.size(), "holonym_id = @NPHOLO"); | ||
| 507 | std::string cond = "noun_id NOT IN (SELECT meronym_id FROM part_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 508 | conditions.push_back(cond); | ||
| 509 | } | ||
| 510 | |||
| 511 | if (_is_part_holonym) | ||
| 512 | { | ||
| 513 | conditions.push_back("noun_id IN (SELECT holonym_id FROM part_meronymy)"); | ||
| 514 | } | ||
| 515 | |||
| 516 | if (!_part_holonym_of.empty()) | ||
| 517 | { | ||
| 518 | std::list<std::string> clauses(_part_holonym_of.size(), "meronym_id = @PMERO"); | ||
| 519 | std::string cond = "noun_id IN (SELECT holonym_id FROM part_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 520 | conditions.push_back(cond); | ||
| 521 | } | ||
| 522 | |||
| 523 | if (!_not_part_holonym_of.empty()) | ||
| 524 | { | ||
| 525 | std::list<std::string> clauses(_not_part_holonym_of.size(), "meronym_id = @NPMERO"); | ||
| 526 | std::string cond = "noun_id NOT IN (SELECT holonym_id FROM part_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 527 | conditions.push_back(cond); | ||
| 528 | } | ||
| 529 | |||
| 530 | if (_is_substance_meronym) | ||
| 531 | { | ||
| 532 | conditions.push_back("noun_id IN (SELECT meronym_id FROM substance_meronymy)"); | ||
| 533 | } | ||
| 534 | |||
| 535 | if (!_substance_meronym_of.empty()) | ||
| 536 | { | ||
| 537 | std::list<std::string> clauses(_substance_meronym_of.size(), "holonym_id = @SHOLO"); | ||
| 538 | std::string cond = "noun_id IN (SELECT meronym_id FROM substance_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 539 | conditions.push_back(cond); | ||
| 540 | } | ||
| 541 | |||
| 542 | if (!_not_substance_meronym_of.empty()) | ||
| 543 | { | ||
| 544 | std::list<std::string> clauses(_not_substance_meronym_of.size(), "holonym_id = @NSHOLO"); | ||
| 545 | std::string cond = "noun_id NOT IN (SELECT meronym_id FROM substance_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 546 | conditions.push_back(cond); | ||
| 547 | } | ||
| 548 | |||
| 549 | if (_is_substance_holonym) | ||
| 550 | { | ||
| 551 | conditions.push_back("noun_id IN (SELECT holonym_id FROM substance_meronymy)"); | ||
| 552 | } | ||
| 553 | |||
| 554 | if (!_substance_holonym_of.empty()) | ||
| 555 | { | ||
| 556 | std::list<std::string> clauses(_substance_holonym_of.size(), "meronym_id = @SMERO"); | ||
| 557 | std::string cond = "noun_id IN (SELECT holonym_id FROM substance_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 558 | conditions.push_back(cond); | ||
| 559 | } | ||
| 560 | |||
| 561 | if (!_not_substance_holonym_of.empty()) | ||
| 562 | { | ||
| 563 | std::list<std::string> clauses(_not_substance_holonym_of.size(), "meronym_id = @NSMERO"); | ||
| 564 | std::string cond = "noun_id NOT IN (SELECT holonym_id FROM substance_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 565 | conditions.push_back(cond); | ||
| 566 | } | ||
| 567 | |||
| 568 | if (_is_member_meronym) | ||
| 569 | { | ||
| 570 | conditions.push_back("noun_id IN (SELECT meronym_id FROM member_meronymy)"); | ||
| 571 | } | ||
| 572 | |||
| 573 | if (!_member_meronym_of.empty()) | ||
| 574 | { | ||
| 575 | std::list<std::string> clauses(_member_meronym_of.size(), "holonym_id = @MHOLO"); | ||
| 576 | std::string cond = "noun_id IN (SELECT meronym_id FROM member_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 577 | conditions.push_back(cond); | ||
| 578 | } | ||
| 579 | |||
| 580 | if (!_not_member_meronym_of.empty()) | ||
| 581 | { | ||
| 582 | std::list<std::string> clauses(_not_member_meronym_of.size(), "holonym_id = @NMHOLO"); | ||
| 583 | std::string cond = "noun_id NOT IN (SELECT meronym_id FROM member_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 584 | conditions.push_back(cond); | ||
| 585 | } | ||
| 586 | |||
| 587 | if (_is_member_holonym) | ||
| 588 | { | ||
| 589 | conditions.push_back("noun_id IN (SELECT holonym_id FROM member_meronym)"); | ||
| 590 | } | ||
| 591 | |||
| 592 | if (!_member_holonym_of.empty()) | ||
| 593 | { | ||
| 594 | std::list<std::string> clauses(_member_holonym_of.size(), "meronym_id = @MMERO"); | ||
| 595 | std::string cond = "noun_id IN (SELECT holonym_id FROM member_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 596 | conditions.push_back(cond); | ||
| 597 | } | ||
| 598 | |||
| 599 | if (!_not_member_holonym_of.empty()) | ||
| 600 | { | ||
| 601 | std::list<std::string> clauses(_not_member_holonym_of.size(), "meronym_id = @NMMERO"); | ||
| 602 | std::string cond = "noun_id NOT IN (SELECT holonym_id FROM member_meronymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 603 | conditions.push_back(cond); | ||
| 604 | } | ||
| 605 | |||
| 606 | if (_is_proper) | ||
| 607 | { | ||
| 608 | conditions.push_back("noun_id IN (SELECT instance_id FROM instantiation)"); | ||
| 609 | } | ||
| 610 | |||
| 611 | if (!_instance_of.empty()) | ||
| 612 | { | ||
| 613 | std::list<std::string> clauses(_instance_of.size(), "class_id = @CLSID"); | ||
| 614 | std::string cond = "noun_id IN (SELECT instance_id FROM instantiation WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 615 | conditions.push_back(cond); | ||
| 616 | } | ||
| 617 | |||
| 618 | if (!_not_instance_of.empty()) | ||
| 619 | { | ||
| 620 | std::list<std::string> clauses(_not_instance_of.size(), "class_id = @NCLSID"); | ||
| 621 | std::string cond = "noun_id NOT IN (SELECT instance_id FROM instantiation WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 622 | conditions.push_back(cond); | ||
| 623 | } | ||
| 624 | |||
| 625 | if (_is_class) | ||
| 626 | { | ||
| 627 | conditions.push_back("noun_id IN (SELECT class_id FROM instantiation)"); | ||
| 628 | } | ||
| 629 | |||
| 630 | if (!_class_of.empty()) | ||
| 631 | { | ||
| 632 | std::list<std::string> clauses(_class_of.size(), "instance_id = @INSID"); | ||
| 633 | std::string cond = "noun_id IN (SELECT class_id FROM instantiation WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 634 | conditions.push_back(cond); | ||
| 635 | } | ||
| 636 | |||
| 637 | if (!_not_class_of.empty()) | ||
| 638 | { | ||
| 639 | std::list<std::string> clauses(_not_class_of.size(), "instance_id = @NINSID"); | ||
| 640 | std::string cond = "noun_id NOT IN (SELECT class_id FROM instantiation WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 641 | conditions.push_back(cond); | ||
| 642 | } | ||
| 643 | |||
| 644 | if (_has_synonyms) | ||
| 645 | { | ||
| 646 | conditions.push_back("noun_id IN (SELECT adjective_2_id FROM adjective_synonymy)"); | ||
| 647 | } | ||
| 648 | |||
| 649 | if (!_synonym_of.empty()) | ||
| 650 | { | ||
| 651 | std::list<std::string> clauses(_synonym_of.size(), "adjective_1_id = @SYNID"); | ||
| 652 | std::string cond = "noun_id IN (SELECT adjective_2_id FROM adjective_synonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 653 | conditions.push_back(cond); | ||
| 654 | } | ||
| 655 | |||
| 656 | if (!_not_synonym_of.empty()) | ||
| 657 | { | ||
| 658 | std::list<std::string> clauses(_not_synonym_of.size(), "adjective_1_id = @NSYNID"); | ||
| 659 | std::string cond = "noun_id NOT IN (SELECT adjective_2_id FROM adjective_synonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 660 | conditions.push_back(cond); | ||
| 661 | } | ||
| 662 | |||
| 663 | if (_has_antonyms) | ||
| 664 | { | ||
| 665 | conditions.push_back("noun_id IN (SELECT adjective_2_id FROM adjective_antonymy)"); | ||
| 666 | } | ||
| 667 | |||
| 668 | if (!_antonym_of.empty()) | ||
| 669 | { | ||
| 670 | std::list<std::string> clauses(_antonym_of.size(), "adjective_1_id = @ANTID"); | ||
| 671 | std::string cond = "noun_id IN (SELECT adjective_2_id FROM adjective_antonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 672 | conditions.push_back(cond); | ||
| 673 | } | ||
| 674 | |||
| 675 | if (!_not_antonym_of.empty()) | ||
| 676 | { | ||
| 677 | std::list<std::string> clauses(_not_antonym_of.size(), "adjective_1_id = @NANTID"); | ||
| 678 | std::string cond = "noun_id NOT IN (SELECT adjective_2_id FROM adjective_antonymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 679 | conditions.push_back(cond); | ||
| 680 | } | ||
| 681 | |||
| 682 | if (_has_pertainym) | ||
| 683 | { | ||
| 684 | conditions.push_back("noun_id IN (SELECT noun_id FROM pertainymy)"); | ||
| 685 | } | ||
| 686 | |||
| 687 | if (!_anti_pertainym_of.empty()) | ||
| 688 | { | ||
| 689 | std::list<std::string> clauses(_anti_pertainym_of.size(), "pertainym_id = @PERID"); | ||
| 690 | std::string cond = "noun_id IN (SELECT noun_id FROM pertainymy WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 691 | conditions.push_back(cond); | ||
| 692 | } | ||
| 693 | |||
| 694 | if (_is_attribute) | ||
| 695 | { | ||
| 696 | conditions.push_back("noun_id IN (SELECT noun_id FROM variation)"); | ||
| 697 | } | ||
| 698 | |||
| 699 | if (!_attribute_of.empty()) | ||
| 700 | { | ||
| 701 | std::list<std::string> clauses(_attribute_of.size(), "adjective_id = @VALID"); | ||
| 702 | std::string cond = "noun_id IN (SELECT noun_id FROM variation WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 703 | conditions.push_back(cond); | ||
| 704 | } | ||
| 705 | |||
| 706 | if (!conditions.empty()) | ||
| 707 | { | ||
| 708 | construct << " WHERE "; | ||
| 709 | construct << verbly::implode(std::begin(conditions), std::end(conditions), " AND "); | ||
| 710 | } | ||
| 711 | |||
| 712 | if (_random) | ||
| 713 | { | ||
| 714 | construct << " ORDER BY RANDOM()"; | ||
| 715 | } | ||
| 716 | |||
| 717 | if (_limit != unlimited) | ||
| 718 | { | ||
| 719 | construct << " LIMIT " << _limit; | ||
| 720 | } | ||
| 721 | |||
| 722 | sqlite3_stmt* ppstmt; | ||
| 723 | std::string query = construct.str(); | ||
| 724 | if (sqlite3_prepare_v2(_data.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 725 | { | ||
| 726 | throw std::runtime_error(sqlite3_errmsg(_data.ppdb)); | ||
| 727 | } | ||
| 728 | |||
| 729 | if (!_rhymes.empty()) | ||
| 730 | { | ||
| 731 | int i = 0; | ||
| 732 | for (auto rhyme : _rhymes) | ||
| 733 | { | ||
| 734 | std::string rhymer = "%" + rhyme; | ||
| 735 | sqlite3_bind_text(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@RHMPRN"), rhymer.c_str(), rhymer.length(), SQLITE_STATIC); | ||
| 736 | |||
| 737 | i++; | ||
| 738 | } | ||
| 739 | } | ||
| 740 | |||
| 741 | for (auto except : _except) | ||
| 742 | { | ||
| 743 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@EXCID"), except._id); | ||
| 744 | } | ||
| 745 | |||
| 746 | for (auto hyponym : _hypernym_of) | ||
| 747 | { | ||
| 748 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@HYPO"), hyponym._id); | ||
| 749 | } | ||
| 750 | |||
| 751 | for (auto hyponym : _not_hypernym_of) | ||
| 752 | { | ||
| 753 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NHYPO"), hyponym._id); | ||
| 754 | } | ||
| 755 | |||
| 756 | for (auto hypernym : _hyponym_of) | ||
| 757 | { | ||
| 758 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@HYPER"), hypernym._id); | ||
| 759 | } | ||
| 760 | |||
| 761 | for (auto hypernym : _not_hyponym_of) | ||
| 762 | { | ||
| 763 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NHYPER"), hypernym._id); | ||
| 764 | } | ||
| 765 | |||
| 766 | for (auto holonym : _part_meronym_of) | ||
| 767 | { | ||
| 768 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@PHOLO"), holonym._id); | ||
| 769 | } | ||
| 770 | |||
| 771 | for (auto holonym : _not_part_meronym_of) | ||
| 772 | { | ||
| 773 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NPHOLO"), holonym._id); | ||
| 774 | } | ||
| 775 | |||
| 776 | for (auto meronym : _part_holonym_of) | ||
| 777 | { | ||
| 778 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@PMERO"), meronym._id); | ||
| 779 | } | ||
| 780 | |||
| 781 | for (auto meronym : _not_part_holonym_of) | ||
| 782 | { | ||
| 783 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NPMERO"), meronym._id); | ||
| 784 | } | ||
| 785 | |||
| 786 | for (auto holonym : _substance_meronym_of) | ||
| 787 | { | ||
| 788 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@SHOLO"), holonym._id); | ||
| 789 | } | ||
| 790 | |||
| 791 | for (auto holonym : _not_substance_meronym_of) | ||
| 792 | { | ||
| 793 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NSHOLO"), holonym._id); | ||
| 794 | } | ||
| 795 | |||
| 796 | for (auto meronym : _substance_holonym_of) | ||
| 797 | { | ||
| 798 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@SMERO"), meronym._id); | ||
| 799 | } | ||
| 800 | |||
| 801 | for (auto meronym : _not_substance_holonym_of) | ||
| 802 | { | ||
| 803 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NSMERO"), meronym._id); | ||
| 804 | } | ||
| 805 | |||
| 806 | for (auto holonym : _member_meronym_of) | ||
| 807 | { | ||
| 808 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@MHOLO"), holonym._id); | ||
| 809 | } | ||
| 810 | |||
| 811 | for (auto holonym : _not_member_meronym_of) | ||
| 812 | { | ||
| 813 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NMHOLO"), holonym._id); | ||
| 814 | } | ||
| 815 | |||
| 816 | for (auto meronym : _member_holonym_of) | ||
| 817 | { | ||
| 818 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@MMERO"), meronym._id); | ||
| 819 | } | ||
| 820 | |||
| 821 | for (auto meronym : _not_member_holonym_of) | ||
| 822 | { | ||
| 823 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NMMERO"), meronym._id); | ||
| 824 | } | ||
| 825 | |||
| 826 | for (auto cls : _instance_of) | ||
| 827 | { | ||
| 828 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@CLSID"), cls._id); | ||
| 829 | } | ||
| 830 | |||
| 831 | for (auto cls : _not_instance_of) | ||
| 832 | { | ||
| 833 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NCLSID"), cls._id); | ||
| 834 | } | ||
| 835 | |||
| 836 | for (auto inst : _class_of) | ||
| 837 | { | ||
| 838 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@INSID"), inst._id); | ||
| 839 | } | ||
| 840 | |||
| 841 | for (auto inst : _not_class_of) | ||
| 842 | { | ||
| 843 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NINSID"), inst._id); | ||
| 844 | } | ||
| 845 | |||
| 846 | for (auto synonym : _synonym_of) | ||
| 847 | { | ||
| 848 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@SYNID"), synonym._id); | ||
| 849 | } | ||
| 850 | |||
| 851 | for (auto synonym : _not_synonym_of) | ||
| 852 | { | ||
| 853 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NSYNID"), synonym._id); | ||
| 854 | } | ||
| 855 | |||
| 856 | for (auto antonym : _antonym_of) | ||
| 857 | { | ||
| 858 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@ANTID"), antonym._id); | ||
| 859 | } | ||
| 860 | |||
| 861 | for (auto antonym : _not_antonym_of) | ||
| 862 | { | ||
| 863 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@NANTID"), antonym._id); | ||
| 864 | } | ||
| 865 | |||
| 866 | for (auto pertainym : _anti_pertainym_of) | ||
| 867 | { | ||
| 868 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@PERID"), pertainym._id); | ||
| 869 | } | ||
| 870 | |||
| 871 | for (auto value : _attribute_of) | ||
| 872 | { | ||
| 873 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@VALID"), value._id); | ||
| 874 | } | ||
| 875 | |||
| 876 | std::list<noun> output; | ||
| 877 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
| 878 | { | ||
| 879 | noun tnc {_data, sqlite3_column_int(ppstmt, 0)}; | ||
| 880 | tnc._singular = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 1))); | ||
| 881 | |||
| 882 | if (sqlite3_column_type(ppstmt, 2) != SQLITE_NULL) | ||
| 883 | { | ||
| 884 | tnc._plural = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 2))); | ||
| 885 | } | ||
| 886 | |||
| 887 | output.push_back(tnc); | ||
| 888 | } | ||
| 889 | |||
| 890 | sqlite3_finalize(ppstmt); | ||
| 891 | |||
| 892 | for (auto& noun : output) | ||
| 893 | { | ||
| 894 | query = "SELECT pronunciation FROM noun_pronunciations WHERE noun_id = ?"; | ||
| 895 | if (sqlite3_prepare_v2(_data.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 896 | { | ||
| 897 | throw std::runtime_error(sqlite3_errmsg(_data.ppdb)); | ||
| 898 | } | ||
| 899 | |||
| 900 | sqlite3_bind_int(ppstmt, 1, noun._id); | ||
| 901 | |||
| 902 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
| 903 | { | ||
| 904 | std::string pronunciation(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 0))); | ||
| 905 | auto phonemes = verbly::split<std::list<std::string>>(pronunciation, " "); | ||
| 906 | |||
| 907 | noun.pronunciations.push_back(phonemes); | ||
| 908 | } | ||
| 909 | |||
| 910 | sqlite3_finalize(ppstmt); | ||
| 911 | } | ||
| 912 | |||
| 913 | return output; | ||
| 914 | } | ||
| 915 | |||
| 916 | }; | ||
| diff --git a/verbly/noun.h b/verbly/noun.h new file mode 100644 index 0000000..f5ba256 --- /dev/null +++ b/verbly/noun.h | |||
| @@ -0,0 +1,171 @@ | |||
| 1 | #ifndef NOUN_H_24A03C83 | ||
| 2 | #define NOUN_H_24A03C83 | ||
| 3 | |||
| 4 | namespace verbly { | ||
| 5 | |||
| 6 | class noun : public word { | ||
| 7 | private: | ||
| 8 | std::string _singular; | ||
| 9 | std::string _plural; | ||
| 10 | |||
| 11 | friend class noun_query; | ||
| 12 | |||
| 13 | public: | ||
| 14 | noun(const data& _data, int _id); | ||
| 15 | |||
| 16 | std::string base_form() const; | ||
| 17 | std::string singular_form() const; | ||
| 18 | std::string plural_form() const; | ||
| 19 | |||
| 20 | bool has_plural_form() const; | ||
| 21 | |||
| 22 | noun_query hypernyms() const; | ||
| 23 | noun_query hyponyms() const; | ||
| 24 | noun_query part_meronyms() const; | ||
| 25 | noun_query part_holonyms() const; | ||
| 26 | noun_query substance_meronyms() const; | ||
| 27 | noun_query substance_holonyms() const; | ||
| 28 | noun_query member_meronyms() const; | ||
| 29 | noun_query member_holonyms() const; | ||
| 30 | noun_query classes() const; | ||
| 31 | noun_query instances() const; | ||
| 32 | noun_query synonyms() const; | ||
| 33 | noun_query antonyms() const; | ||
| 34 | adjective_query pertainyms() const; | ||
| 35 | adjective_query variations() const; | ||
| 36 | }; | ||
| 37 | |||
| 38 | class noun_query { | ||
| 39 | public: | ||
| 40 | noun_query(const data& _data); | ||
| 41 | |||
| 42 | noun_query& limit(int _limit); | ||
| 43 | noun_query& random(bool _random); | ||
| 44 | noun_query& except(const noun& _word); | ||
| 45 | noun_query& rhymes_with(const word& _word); | ||
| 46 | noun_query& has_pronunciation(bool _has_prn); | ||
| 47 | |||
| 48 | noun_query& is_hypernym(bool _arg); | ||
| 49 | noun_query& hypernym_of(const noun& _noun); | ||
| 50 | noun_query& not_hypernym_of(const noun& _noun); | ||
| 51 | |||
| 52 | noun_query& is_hyponym(bool _arg); | ||
| 53 | noun_query& hyponym_of(const noun& _noun); | ||
| 54 | noun_query& not_hyponym_of(const noun& _noun); | ||
| 55 | |||
| 56 | noun_query& is_part_meronym(bool _arg); | ||
| 57 | noun_query& part_meronym_of(const noun& _noun); | ||
| 58 | noun_query& not_part_meronym_of(const noun& _noun); | ||
| 59 | |||
| 60 | noun_query& is_part_holonym(bool _arg); | ||
| 61 | noun_query& part_holonym_of(const noun& _noun); | ||
| 62 | noun_query& not_part_holonym_of(const noun& _noun); | ||
| 63 | |||
| 64 | noun_query& is_substance_meronym(bool _arg); | ||
| 65 | noun_query& substance_meronym_of(const noun& _noun); | ||
| 66 | noun_query& not_substance_meronym_of(const noun& _noun); | ||
| 67 | |||
| 68 | noun_query& is_substance_holonym(bool _arg); | ||
| 69 | noun_query& substance_holonym_of(const noun& _noun); | ||
| 70 | noun_query& not_substance_holonym_of(const noun& _noun); | ||
| 71 | |||
| 72 | noun_query& is_member_meronym(bool _arg); | ||
| 73 | noun_query& member_meronym_of(const noun& _noun); | ||
| 74 | noun_query& not_member_meronym_of(const noun& _noun); | ||
| 75 | |||
| 76 | noun_query& is_member_holonym(bool _arg); | ||
| 77 | noun_query& member_holonym_of(const noun& _noun); | ||
| 78 | noun_query& not_member_holonym_of(const noun& _noun); | ||
| 79 | |||
| 80 | noun_query& is_proper(bool _arg); | ||
| 81 | noun_query& instance_of(const noun& _noun); | ||
| 82 | noun_query& not_instance_of(const noun& _noun); | ||
| 83 | |||
| 84 | noun_query& is_class(bool _arg); | ||
| 85 | noun_query& class_of(const noun& _noun); | ||
| 86 | noun_query& not_class_of(const noun& _noun); | ||
| 87 | |||
| 88 | noun_query& has_synonyms(bool _arg); | ||
| 89 | noun_query& synonym_of(const noun& _noun); | ||
| 90 | noun_query& not_synonym_of(const noun& _noun); | ||
| 91 | |||
| 92 | noun_query& has_antonyms(bool _arg); | ||
| 93 | noun_query& antonym_of(const noun& _noun); | ||
| 94 | noun_query& not_antonym_of(const noun& _noun); | ||
| 95 | |||
| 96 | noun_query& has_pertainym(bool _arg); | ||
| 97 | noun_query& anti_pertainym_of(const adjective& _adj); | ||
| 98 | |||
| 99 | noun_query& is_attribute(bool _arg); | ||
| 100 | noun_query& attribute_of(const adjective& _adj); | ||
| 101 | |||
| 102 | std::list<noun> run() const; | ||
| 103 | |||
| 104 | const static int unlimited = -1; | ||
| 105 | |||
| 106 | private: | ||
| 107 | const data& _data; | ||
| 108 | int _limit = unlimited; | ||
| 109 | bool _random = false; | ||
| 110 | std::list<std::string> _rhymes; | ||
| 111 | std::list<noun> _except; | ||
| 112 | bool _has_prn = false; | ||
| 113 | |||
| 114 | bool _is_hypernym = false; | ||
| 115 | std::list<noun> _hypernym_of; | ||
| 116 | std::list<noun> _not_hypernym_of; | ||
| 117 | |||
| 118 | bool _is_hyponym = false; | ||
| 119 | std::list<noun> _hyponym_of; | ||
| 120 | std::list<noun> _not_hyponym_of; | ||
| 121 | |||
| 122 | bool _is_part_meronym = false; | ||
| 123 | std::list<noun> _part_meronym_of; | ||
| 124 | std::list<noun> _not_part_meronym_of; | ||
| 125 | |||
| 126 | bool _is_substance_meronym = false; | ||
| 127 | std::list<noun> _substance_meronym_of; | ||
| 128 | std::list<noun> _not_substance_meronym_of; | ||
| 129 | |||
| 130 | bool _is_member_meronym = false; | ||
| 131 | std::list<noun> _member_meronym_of; | ||
| 132 | std::list<noun> _not_member_meronym_of; | ||
| 133 | |||
| 134 | bool _is_part_holonym = false; | ||
| 135 | std::list<noun> _part_holonym_of; | ||
| 136 | std::list<noun> _not_part_holonym_of; | ||
| 137 | |||
| 138 | bool _is_substance_holonym = false; | ||
| 139 | std::list<noun> _substance_holonym_of; | ||
| 140 | std::list<noun> _not_substance_holonym_of; | ||
| 141 | |||
| 142 | bool _is_member_holonym = false; | ||
| 143 | std::list<noun> _member_holonym_of; | ||
| 144 | std::list<noun> _not_member_holonym_of; | ||
| 145 | |||
| 146 | bool _is_proper = false; | ||
| 147 | std::list<noun> _instance_of; | ||
| 148 | std::list<noun> _not_instance_of; | ||
| 149 | |||
| 150 | bool _is_class = false; | ||
| 151 | std::list<noun> _class_of; | ||
| 152 | std::list<noun> _not_class_of; | ||
| 153 | |||
| 154 | bool _has_synonyms = false; | ||
| 155 | std::list<noun> _synonym_of; | ||
| 156 | std::list<noun> _not_synonym_of; | ||
| 157 | |||
| 158 | bool _has_antonyms = false; | ||
| 159 | std::list<noun> _antonym_of; | ||
| 160 | std::list<noun> _not_antonym_of; | ||
| 161 | |||
| 162 | bool _has_pertainym = false; | ||
| 163 | std::list<adjective> _anti_pertainym_of; | ||
| 164 | |||
| 165 | bool _is_attribute = false; | ||
| 166 | std::list<adjective> _attribute_of; | ||
| 167 | }; | ||
| 168 | |||
| 169 | }; | ||
| 170 | |||
| 171 | #endif /* end of include guard: NOUN_H_24A03C83 */ | ||
| diff --git a/verbly/token.cpp b/verbly/token.cpp new file mode 100644 index 0000000..aa8f50e --- /dev/null +++ b/verbly/token.cpp | |||
| @@ -0,0 +1,53 @@ | |||
| 1 | #include "verbly.h" | ||
| 2 | |||
| 3 | namespace verbly { | ||
| 4 | |||
| 5 | token::token(token::type _type) : _type(_type) | ||
| 6 | { | ||
| 7 | |||
| 8 | } | ||
| 9 | |||
| 10 | token::type token::token_type() const | ||
| 11 | { | ||
| 12 | return _type; | ||
| 13 | } | ||
| 14 | |||
| 15 | verb_token::verb_token(const class verb& _verb) : token(token::type::verb), _verb(&_verb) | ||
| 16 | { | ||
| 17 | |||
| 18 | } | ||
| 19 | |||
| 20 | const class verb& verb_token::verb() const | ||
| 21 | { | ||
| 22 | return *_verb; | ||
| 23 | } | ||
| 24 | |||
| 25 | verb_token& verb_token::inflect(verb_token::inflection infl) | ||
| 26 | { | ||
| 27 | _inflection = infl; | ||
| 28 | return *this; | ||
| 29 | } | ||
| 30 | |||
| 31 | bool verb_token::complete() const | ||
| 32 | { | ||
| 33 | return true; | ||
| 34 | } | ||
| 35 | |||
| 36 | std::string verb_token::compile() const | ||
| 37 | { | ||
| 38 | switch (_inflection) | ||
| 39 | { | ||
| 40 | case inflection::infinitive: return _verb->infinitive_form(); | ||
| 41 | case inflection::past_tense: return _verb->past_tense_form(); | ||
| 42 | case inflection::past_participle: return _verb->past_participle_form(); | ||
| 43 | case inflection::ing_form: return _verb->ing_form(); | ||
| 44 | case inflection::s_form: return _verb->s_form(); | ||
| 45 | } | ||
| 46 | } | ||
| 47 | |||
| 48 | token* verb_token::copy() const | ||
| 49 | { | ||
| 50 | return new verb_token(*this); | ||
| 51 | } | ||
| 52 | |||
| 53 | }; | ||
| diff --git a/verbly/token.h b/verbly/token.h index 2848fd0..44d99cb 100644 --- a/verbly/token.h +++ b/verbly/token.h | |||
| @@ -4,16 +4,10 @@ | |||
| 4 | #include <string> | 4 | #include <string> |
| 5 | #include <list> | 5 | #include <list> |
| 6 | #include <sstream> | 6 | #include <sstream> |
| 7 | #include "verb.h" | ||
| 8 | 7 | ||
| 9 | namespace verbly { | 8 | namespace verbly { |
| 10 | 9 | ||
| 11 | enum class type { | 10 | class verb; |
| 12 | verb, | ||
| 13 | fillin, | ||
| 14 | string, | ||
| 15 | utterance | ||
| 16 | }; | ||
| 17 | 11 | ||
| 18 | class selrestr { | 12 | class selrestr { |
| 19 | }; | 13 | }; |
| @@ -29,20 +23,22 @@ namespace verbly { | |||
| 29 | }; | 23 | }; |
| 30 | 24 | ||
| 31 | class token { | 25 | class token { |
| 26 | public: | ||
| 27 | enum class type { | ||
| 28 | verb, | ||
| 29 | fillin, | ||
| 30 | string, | ||
| 31 | utterance | ||
| 32 | }; | ||
| 33 | |||
| 32 | protected: | 34 | protected: |
| 33 | // General | 35 | // General |
| 34 | type type; | 36 | type _type; |
| 35 | 37 | ||
| 36 | token(enum type type) : type(type) | 38 | token(type _type); |
| 37 | { | ||
| 38 | |||
| 39 | } | ||
| 40 | 39 | ||
| 41 | public: | 40 | public: |
| 42 | enum type token_type() const | 41 | enum type token_type() const; |
| 43 | { | ||
| 44 | return type; | ||
| 45 | } | ||
| 46 | 42 | ||
| 47 | virtual bool complete() const = 0; | 43 | virtual bool complete() const = 0; |
| 48 | virtual std::string compile() const = 0; | 44 | virtual std::string compile() const = 0; |
| @@ -50,42 +46,32 @@ namespace verbly { | |||
| 50 | }; | 46 | }; |
| 51 | 47 | ||
| 52 | class verb_token : public token { | 48 | class verb_token : public token { |
| 49 | public: | ||
| 50 | enum class inflection { | ||
| 51 | infinitive, | ||
| 52 | past_tense, | ||
| 53 | past_participle, | ||
| 54 | ing_form, | ||
| 55 | s_form | ||
| 56 | }; | ||
| 57 | |||
| 53 | private: | 58 | private: |
| 54 | // Verb | 59 | // Verb |
| 55 | const verb* m_verb; | 60 | const verb* _verb; |
| 56 | conjugation verb_infl = conjugation::infinitive; | 61 | inflection _inflection = inflection::infinitive; |
| 57 | 62 | ||
| 58 | public: | 63 | public: |
| 59 | verb_token(const class verb& verb) : token(type::verb), m_verb(&verb) | 64 | verb_token(const class verb& _verb); |
| 60 | { | ||
| 61 | |||
| 62 | } | ||
| 63 | 65 | ||
| 64 | const class verb& verb() const | 66 | const class verb& verb() const; |
| 65 | { | ||
| 66 | return *m_verb; | ||
| 67 | } | ||
| 68 | 67 | ||
| 69 | verb_token& conjugate(conjugation infl) | 68 | verb_token& inflect(inflection infl); |
| 70 | { | ||
| 71 | verb_infl = infl; | ||
| 72 | return *this; | ||
| 73 | } | ||
| 74 | 69 | ||
| 75 | bool complete() const | 70 | bool complete() const; |
| 76 | { | ||
| 77 | return true; | ||
| 78 | } | ||
| 79 | 71 | ||
| 80 | std::string compile() const | 72 | std::string compile() const; |
| 81 | { | ||
| 82 | return m_verb->conjugate(verb_infl); | ||
| 83 | } | ||
| 84 | 73 | ||
| 85 | token* copy() const | 74 | token* copy() const; |
| 86 | { | ||
| 87 | return new verb_token(*this); | ||
| 88 | } | ||
| 89 | }; | 75 | }; |
| 90 | 76 | ||
| 91 | class utterance_token : public token { | 77 | class utterance_token : public token { |
| @@ -140,7 +126,7 @@ namespace verbly { | |||
| 140 | } | 126 | } |
| 141 | };*/ | 127 | };*/ |
| 142 | 128 | ||
| 143 | utterance_token(std::initializer_list<token*> tkns) : token(type::utterance) | 129 | utterance_token(std::initializer_list<token*> tkns) : token(token::type::utterance) |
| 144 | { | 130 | { |
| 145 | for (auto tkn : tkns) | 131 | for (auto tkn : tkns) |
| 146 | { | 132 | { |
| @@ -148,7 +134,7 @@ namespace verbly { | |||
| 148 | } | 134 | } |
| 149 | } | 135 | } |
| 150 | 136 | ||
| 151 | utterance_token(const utterance_token& other) : token(type::utterance) | 137 | utterance_token(const utterance_token& other) : token(token::type::utterance) |
| 152 | { | 138 | { |
| 153 | for (auto& tkn : other.utterance) | 139 | for (auto& tkn : other.utterance) |
| 154 | { | 140 | { |
| @@ -156,7 +142,7 @@ namespace verbly { | |||
| 156 | } | 142 | } |
| 157 | } | 143 | } |
| 158 | 144 | ||
| 159 | utterance_token(utterance_token&& other) : token(type::utterance), utterance(std::move(other.utterance)) | 145 | utterance_token(utterance_token&& other) : token(token::type::utterance), utterance(std::move(other.utterance)) |
| 160 | { | 146 | { |
| 161 | 147 | ||
| 162 | } | 148 | } |
| @@ -237,7 +223,7 @@ namespace verbly { | |||
| 237 | fillin_type m_fillin_type; | 223 | fillin_type m_fillin_type; |
| 238 | 224 | ||
| 239 | public: | 225 | public: |
| 240 | fillin_token(fillin_type ft) : token(type::fillin), m_fillin_type(ft) | 226 | fillin_token(fillin_type ft) : token(token::type::fillin), m_fillin_type(ft) |
| 241 | { | 227 | { |
| 242 | 228 | ||
| 243 | } | 229 | } |
| @@ -301,7 +287,7 @@ namespace verbly { | |||
| 301 | std::string str; | 287 | std::string str; |
| 302 | 288 | ||
| 303 | public: | 289 | public: |
| 304 | string_token(std::string str) : token(type::string), str(str) | 290 | string_token(std::string str) : token(token::type::string), str(str) |
| 305 | { | 291 | { |
| 306 | 292 | ||
| 307 | } | 293 | } |
| diff --git a/verbly/util.h b/verbly/util.h new file mode 100644 index 0000000..815b47c --- /dev/null +++ b/verbly/util.h | |||
| @@ -0,0 +1,53 @@ | |||
| 1 | #ifndef UTIL_H_15DDCA2D | ||
| 2 | #define UTIL_H_15DDCA2D | ||
| 3 | |||
| 4 | #include <string> | ||
| 5 | #include <iterator> | ||
| 6 | #include <sstream> | ||
| 7 | |||
| 8 | namespace verbly { | ||
| 9 | |||
| 10 | template <class InputIterator> | ||
| 11 | std::string implode(InputIterator first, InputIterator last, std::string delimiter) | ||
| 12 | { | ||
| 13 | std::stringstream result; | ||
| 14 | |||
| 15 | for (InputIterator it = first; it != last; it++) | ||
| 16 | { | ||
| 17 | if (it != first) | ||
| 18 | { | ||
| 19 | result << delimiter; | ||
| 20 | } | ||
| 21 | |||
| 22 | result << *it; | ||
| 23 | } | ||
| 24 | |||
| 25 | return result.str(); | ||
| 26 | } | ||
| 27 | |||
| 28 | template <class Container> | ||
| 29 | Container split(std::string input, std::string delimiter) | ||
| 30 | { | ||
| 31 | Container result; | ||
| 32 | |||
| 33 | while (!input.empty()) | ||
| 34 | { | ||
| 35 | int divider = input.find(" "); | ||
| 36 | if (divider == std::string::npos) | ||
| 37 | { | ||
| 38 | result.push_back(input); | ||
| 39 | |||
| 40 | input = ""; | ||
| 41 | } else { | ||
| 42 | result.push_back(input.substr(0, divider)); | ||
| 43 | |||
| 44 | input = input.substr(divider+1); | ||
| 45 | } | ||
| 46 | } | ||
| 47 | |||
| 48 | return result; | ||
| 49 | } | ||
| 50 | |||
| 51 | }; | ||
| 52 | |||
| 53 | #endif /* end of include guard: UTIL_H_15DDCA2D */ | ||
| diff --git a/verbly/verb.cpp b/verbly/verb.cpp new file mode 100644 index 0000000..23f7c92 --- /dev/null +++ b/verbly/verb.cpp | |||
| @@ -0,0 +1,193 @@ | |||
| 1 | #include "verbly.h" | ||
| 2 | |||
| 3 | namespace verbly { | ||
| 4 | |||
| 5 | verb::verb(const data& _data, int _id) : word(_data, _id) | ||
| 6 | { | ||
| 7 | |||
| 8 | } | ||
| 9 | |||
| 10 | std::string verb::base_form() const | ||
| 11 | { | ||
| 12 | return _infinitive; | ||
| 13 | } | ||
| 14 | |||
| 15 | std::string verb::infinitive_form() const | ||
| 16 | { | ||
| 17 | return _infinitive; | ||
| 18 | } | ||
| 19 | |||
| 20 | std::string verb::past_tense_form() const | ||
| 21 | { | ||
| 22 | return _past_tense; | ||
| 23 | } | ||
| 24 | |||
| 25 | std::string verb::past_participle_form() const | ||
| 26 | { | ||
| 27 | return _past_participle; | ||
| 28 | } | ||
| 29 | |||
| 30 | std::string verb::ing_form() const | ||
| 31 | { | ||
| 32 | return _ing_form; | ||
| 33 | } | ||
| 34 | |||
| 35 | std::string verb::s_form() const | ||
| 36 | { | ||
| 37 | return _s_form; | ||
| 38 | } | ||
| 39 | |||
| 40 | verb_query::verb_query(const data& _data) : _data(_data) | ||
| 41 | { | ||
| 42 | |||
| 43 | } | ||
| 44 | |||
| 45 | verb_query& verb_query::limit(int _limit) | ||
| 46 | { | ||
| 47 | if ((_limit > 0) || (_limit == unlimited)) | ||
| 48 | { | ||
| 49 | this->_limit = _limit; | ||
| 50 | } | ||
| 51 | |||
| 52 | return *this; | ||
| 53 | } | ||
| 54 | |||
| 55 | verb_query& verb_query::random(bool _random) | ||
| 56 | { | ||
| 57 | this->_random = _random; | ||
| 58 | |||
| 59 | return *this; | ||
| 60 | } | ||
| 61 | |||
| 62 | verb_query& verb_query::except(const verb& _word) | ||
| 63 | { | ||
| 64 | _except.push_back(_word); | ||
| 65 | |||
| 66 | return *this; | ||
| 67 | } | ||
| 68 | |||
| 69 | verb_query& verb_query::rhymes_with(const word& _word) | ||
| 70 | { | ||
| 71 | for (auto rhyme : _word.rhyme_phonemes()) | ||
| 72 | { | ||
| 73 | _rhymes.push_back(rhyme); | ||
| 74 | } | ||
| 75 | |||
| 76 | if (dynamic_cast<const verb*>(&_word) != nullptr) | ||
| 77 | { | ||
| 78 | _except.push_back(dynamic_cast<const verb&>(_word)); | ||
| 79 | } | ||
| 80 | |||
| 81 | return *this; | ||
| 82 | } | ||
| 83 | |||
| 84 | verb_query& verb_query::has_pronunciation(bool _has_prn) | ||
| 85 | { | ||
| 86 | this->_has_prn = _has_prn; | ||
| 87 | |||
| 88 | return *this; | ||
| 89 | } | ||
| 90 | |||
| 91 | std::list<verb> verb_query::run() const | ||
| 92 | { | ||
| 93 | std::stringstream construct; | ||
| 94 | construct << "SELECT verb_id, infinitive, past_tense, past_participle, ing_form, s_form FROM verbs"; | ||
| 95 | std::list<std::string> conditions; | ||
| 96 | |||
| 97 | if (_has_prn) | ||
| 98 | { | ||
| 99 | conditions.push_back("verb_id IN (SELECT verb_id FROM verb_pronunciations)"); | ||
| 100 | } | ||
| 101 | |||
| 102 | if (!_rhymes.empty()) | ||
| 103 | { | ||
| 104 | std::list<std::string> clauses(_rhymes.size(), "pronunciation LIKE @RHMPRN"); | ||
| 105 | std::string cond = "verb_id IN (SELECT verb_id FROM verb_pronunciations WHERE " + verbly::implode(std::begin(clauses), std::end(clauses), " OR ") + ")"; | ||
| 106 | conditions.push_back(cond); | ||
| 107 | } | ||
| 108 | |||
| 109 | for (auto except : _except) | ||
| 110 | { | ||
| 111 | conditions.push_back("verb_id != @EXCID"); | ||
| 112 | } | ||
| 113 | |||
| 114 | if (!conditions.empty()) | ||
| 115 | { | ||
| 116 | construct << " WHERE "; | ||
| 117 | construct << verbly::implode(std::begin(conditions), std::end(conditions), " AND "); | ||
| 118 | } | ||
| 119 | |||
| 120 | if (_random) | ||
| 121 | { | ||
| 122 | construct << " ORDER BY RANDOM()"; | ||
| 123 | } | ||
| 124 | |||
| 125 | if (_limit != unlimited) | ||
| 126 | { | ||
| 127 | construct << " LIMIT " << _limit; | ||
| 128 | } | ||
| 129 | |||
| 130 | sqlite3_stmt* ppstmt; | ||
| 131 | std::string query = construct.str(); | ||
| 132 | if (sqlite3_prepare_v2(_data.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 133 | { | ||
| 134 | throw std::runtime_error(sqlite3_errmsg(_data.ppdb)); | ||
| 135 | } | ||
| 136 | |||
| 137 | if (!_rhymes.empty()) | ||
| 138 | { | ||
| 139 | int i = 0; | ||
| 140 | for (auto rhyme : _rhymes) | ||
| 141 | { | ||
| 142 | std::string rhymer = "%" + rhyme; | ||
| 143 | sqlite3_bind_text(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@RHMPRN"), rhymer.c_str(), rhymer.length(), SQLITE_STATIC); | ||
| 144 | |||
| 145 | i++; | ||
| 146 | } | ||
| 147 | } | ||
| 148 | |||
| 149 | for (auto except : _except) | ||
| 150 | { | ||
| 151 | sqlite3_bind_int(ppstmt, sqlite3_bind_parameter_index(ppstmt, "@EXCID"), except._id); | ||
| 152 | } | ||
| 153 | |||
| 154 | std::list<verb> output; | ||
| 155 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
| 156 | { | ||
| 157 | verb tnc {_data, sqlite3_column_int(ppstmt, 0)}; | ||
| 158 | tnc._infinitive = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 1))); | ||
| 159 | tnc._past_tense = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 2))); | ||
| 160 | tnc._past_participle = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 3))); | ||
| 161 | tnc._ing_form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 4))); | ||
| 162 | tnc._s_form = std::string(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 5))); | ||
| 163 | |||
| 164 | output.push_back(tnc); | ||
| 165 | } | ||
| 166 | |||
| 167 | sqlite3_finalize(ppstmt); | ||
| 168 | |||
| 169 | for (auto& verb : output) | ||
| 170 | { | ||
| 171 | query = "SELECT pronunciation FROM verb_pronunciations WHERE verb_id = ?"; | ||
| 172 | if (sqlite3_prepare_v2(_data.ppdb, query.c_str(), query.length(), &ppstmt, NULL) != SQLITE_OK) | ||
| 173 | { | ||
| 174 | throw std::runtime_error(sqlite3_errmsg(_data.ppdb)); | ||
| 175 | } | ||
| 176 | |||
| 177 | sqlite3_bind_int(ppstmt, 1, verb._id); | ||
| 178 | |||
| 179 | while (sqlite3_step(ppstmt) == SQLITE_ROW) | ||
| 180 | { | ||
| 181 | std::string pronunciation(reinterpret_cast<const char*>(sqlite3_column_text(ppstmt, 0))); | ||
| 182 | auto phonemes = verbly::split<std::list<std::string>>(pronunciation, " "); | ||
| 183 | |||
| 184 | verb.pronunciations.push_back(phonemes); | ||
| 185 | } | ||
| 186 | |||
| 187 | sqlite3_finalize(ppstmt); | ||
| 188 | } | ||
| 189 | |||
| 190 | return output; | ||
| 191 | } | ||
| 192 | |||
| 193 | }; | ||
| diff --git a/verbly/verb.h b/verbly/verb.h index 42c8dc2..7cc87e2 100644 --- a/verbly/verb.h +++ b/verbly/verb.h | |||
| @@ -1,8 +1,6 @@ | |||
| 1 | #ifndef VERB_H_BCC929AD | 1 | #ifndef VERB_H_BCC929AD |
| 2 | #define VERB_H_BCC929AD | 2 | #define VERB_H_BCC929AD |
| 3 | 3 | ||
| 4 | #include <vector> | ||
| 5 | |||
| 6 | namespace verbly { | 4 | namespace verbly { |
| 7 | 5 | ||
| 8 | /*class frame_part { | 6 | /*class frame_part { |
| @@ -26,42 +24,50 @@ namespace verbly { | |||
| 26 | } | 24 | } |
| 27 | };*/ | 25 | };*/ |
| 28 | 26 | ||
| 29 | enum class conjugation { | 27 | class verb : public word { |
| 30 | present_participle, | ||
| 31 | past_participle, | ||
| 32 | infinitive | ||
| 33 | }; | ||
| 34 | |||
| 35 | class verb { | ||
| 36 | private: | 28 | private: |
| 37 | int id; | 29 | std::string _infinitive; |
| 30 | std::string _past_tense; | ||
| 31 | std::string _past_participle; | ||
| 32 | std::string _ing_form; | ||
| 33 | std::string _s_form; | ||
| 34 | |||
| 35 | friend class verb_query; | ||
| 38 | 36 | ||
| 39 | public: | 37 | public: |
| 40 | verb(int id) : id(id) | 38 | verb(const data& _data, int _id); |
| 41 | { | ||
| 42 | |||
| 43 | } | ||
| 44 | 39 | ||
| 45 | std::string infinitive; | 40 | std::string base_form() const; |
| 46 | std::string past_tense; | 41 | std::string infinitive_form() const; |
| 47 | std::string past_participle; | 42 | std::string past_tense_form() const; |
| 48 | std::string ing_form; | 43 | std::string past_participle_form() const; |
| 49 | std::string s_form; | 44 | std::string ing_form() const; |
| 50 | //std::vector<frame> frames; | 45 | std::string s_form() const; |
| 46 | }; | ||
| 47 | |||
| 48 | class verb_query { | ||
| 49 | public: | ||
| 50 | verb_query(const data& _data); | ||
| 51 | 51 | ||
| 52 | std::string conjugate(conjugation infl) const | 52 | verb_query& limit(int _limit); |
| 53 | { | 53 | verb_query& random(bool _random); |
| 54 | switch (infl) | 54 | verb_query& except(const verb& _word); |
| 55 | { | 55 | verb_query& rhymes_with(const word& _word); |
| 56 | case conjugation::infinitive: return infinitive; | 56 | verb_query& has_pronunciation(bool _has_prn); |
| 57 | case conjugation::past_participle: return past_participle; | 57 | |
| 58 | case conjugation::present_participle: return ing_form; | 58 | std::list<verb> run() const; |
| 59 | } | 59 | |
| 60 | } | 60 | const static int unlimited = -1; |
| 61 | |||
| 62 | private: | ||
| 63 | const data& _data; | ||
| 64 | int _limit = unlimited; | ||
| 65 | bool _random = false; | ||
| 66 | std::list<std::string> _rhymes; | ||
| 67 | std::list<verb> _except; | ||
| 68 | bool _has_prn = false; | ||
| 61 | }; | 69 | }; |
| 62 | 70 | ||
| 63 | }; | 71 | }; |
| 64 | 72 | ||
| 65 | #include "token.h" | ||
| 66 | |||
| 67 | #endif /* end of include guard: VERB_H_BCC929AD */ | 73 | #endif /* end of include guard: VERB_H_BCC929AD */ |
| diff --git a/verbly/verbly.h b/verbly/verbly.h index 44fd3a8..b9f5367 100644 --- a/verbly/verbly.h +++ b/verbly/verbly.h | |||
| @@ -2,10 +2,13 @@ | |||
| 2 | #define VERBLY_H_5B39CE50 | 2 | #define VERBLY_H_5B39CE50 |
| 3 | 3 | ||
| 4 | #include "c++14.h" | 4 | #include "c++14.h" |
| 5 | #include "util.h" | ||
| 5 | #include "token.h" | 6 | #include "token.h" |
| 7 | #include "data.h" | ||
| 8 | #include "word.h" | ||
| 6 | #include "verb.h" | 9 | #include "verb.h" |
| 7 | #include "adjective.h" | ||
| 8 | #include "adverb.h" | 10 | #include "adverb.h" |
| 9 | #include "data.h" | 11 | #include "adjective.h" |
| 12 | #include "noun.h" | ||
| 10 | 13 | ||
| 11 | #endif /* end of include guard: VERBLY_H_5B39CE50 */ | 14 | #endif /* end of include guard: VERBLY_H_5B39CE50 */ |
| diff --git a/verbly/word.cpp b/verbly/word.cpp new file mode 100644 index 0000000..c50e7d3 --- /dev/null +++ b/verbly/word.cpp | |||
| @@ -0,0 +1,32 @@ | |||
| 1 | #include "verbly.h" | ||
| 2 | |||
| 3 | namespace verbly { | ||
| 4 | |||
| 5 | word::word(const data& _data, int _id) : _data(_data), _id(_id) | ||
| 6 | { | ||
| 7 | |||
| 8 | } | ||
| 9 | |||
| 10 | std::list<std::string> word::rhyme_phonemes() const | ||
| 11 | { | ||
| 12 | std::list<std::string> result; | ||
| 13 | |||
| 14 | for (auto pronunciation : pronunciations) | ||
| 15 | { | ||
| 16 | auto phemstrt = std::find_if(std::begin(pronunciation), std::end(pronunciation), [] (std::string phoneme) { | ||
| 17 | return phoneme.find("1") != std::string::npos; | ||
| 18 | }); | ||
| 19 | |||
| 20 | std::stringstream rhymer; | ||
| 21 | for (auto it = phemstrt; it != std::end(pronunciation); it++) | ||
| 22 | { | ||
| 23 | rhymer << " " << *it; | ||
| 24 | } | ||
| 25 | |||
| 26 | result.push_back(rhymer.str()); | ||
| 27 | } | ||
| 28 | |||
| 29 | return result; | ||
| 30 | } | ||
| 31 | |||
| 32 | }; | ||
| diff --git a/verbly/word.h b/verbly/word.h new file mode 100644 index 0000000..23ddb2b --- /dev/null +++ b/verbly/word.h | |||
| @@ -0,0 +1,35 @@ | |||
| 1 | #ifndef WORD_H_8FC89498 | ||
| 2 | #define WORD_H_8FC89498 | ||
| 3 | |||
| 4 | namespace verbly { | ||
| 5 | |||
| 6 | class adjective_query; | ||
| 7 | class verb_query; | ||
| 8 | class adverb_query; | ||
| 9 | |||
| 10 | template <class T> | ||
| 11 | class query; | ||
| 12 | |||
| 13 | class word { | ||
| 14 | protected: | ||
| 15 | const data& _data; | ||
| 16 | int _id; | ||
| 17 | |||
| 18 | std::list<std::list<std::string>> pronunciations; | ||
| 19 | |||
| 20 | word(const data& _data, int _id); | ||
| 21 | |||
| 22 | friend class adjective_query; | ||
| 23 | friend class verb_query; | ||
| 24 | friend class noun_query; | ||
| 25 | friend class adverb_query; | ||
| 26 | |||
| 27 | public: | ||
| 28 | virtual std::string base_form() const = 0; | ||
| 29 | |||
| 30 | std::list<std::string> rhyme_phonemes() const; | ||
| 31 | }; | ||
| 32 | |||
| 33 | }; | ||
| 34 | |||
| 35 | #endif /* end of include guard: WORD_H_8FC89498 */ | ||
