summary refs log tree commit diff stats
path: root/lib/word.cpp
diff options
context:
space:
mode:
authorKelly Rauchenberger <fefferburbia@gmail.com>2017-02-06 20:58:37 -0500
committerKelly Rauchenberger <fefferburbia@gmail.com>2017-02-06 20:58:37 -0500
commitf1f67e62cebb4144f0599196263cd93b41fa972e (patch)
tree5d0f8fceeec63f47fb85846f5568bcb36f4a975f /lib/word.cpp
parent6cc23ba387d0813b801ba094709673a61bac889c (diff)
downloadverbly-f1f67e62cebb4144f0599196263cd93b41fa972e.tar.gz
verbly-f1f67e62cebb4144f0599196263cd93b41fa972e.tar.bz2
verbly-f1f67e62cebb4144f0599196263cd93b41fa972e.zip
Made pronunciation::rhymes join dynamic
This involved adding a new type of filter; one that compares (currently
only equality and inequality) a field with another field located in an
enclosing join context.

In the process, it was discovered that simplifying the lemma::forms join
field earlier actually made some queries return inaccurate results
because the inflection of the form was being ignored and anything in the
lemma would be used because of the inner join. Because the existing
condition join did not allow for the condition field to be on the from
side of the join, two things were done: a condition version of
joinThrough was made, and lemma was finally eliminated as a top-level
object, replaced instead with a condition join between word and form
through lemmas_forms.

Queries are also now grouped by the first select field (assumed to be
the primary ID) of the top table, in order to eliminate duplicates
created by inner joins, so that there is a uniform distribution between
results for random queries.

Created a database index on pronunciations(rhyme) which decreases query
time for rhyming filters. The new database version is
backwards-compatible because no data or structure changed.
Diffstat (limited to 'lib/word.cpp')
-rw-r--r--lib/word.cpp65
1 files changed, 39 insertions, 26 deletions
diff --git a/lib/word.cpp b/lib/word.cpp index d75159c..4dea569 100644 --- a/lib/word.cpp +++ b/lib/word.cpp
@@ -16,7 +16,6 @@ namespace verbly {
16 const field word::adjectivePosition = field::integerField(object::word, "position", true); 16 const field word::adjectivePosition = field::integerField(object::word, "position", true);
17 17
18 const field word::notions = field::joinField(object::word, "notion_id", object::notion); 18 const field word::notions = field::joinField(object::word, "notion_id", object::notion);
19 const field word::lemmas = field::joinField(object::word, "lemma_id", object::lemma);
20 const field word::frames = field::joinField(object::word, "group_id", object::frame, true); 19 const field word::frames = field::joinField(object::word, "group_id", object::frame, true);
21 20
22 const field word::antonyms = field::selfJoin(object::word, "word_id", "antonymy", "antonym_2_id", "antonym_1_id"); 21 const field word::antonyms = field::selfJoin(object::word, "word_id", "antonymy", "antonym_2_id", "antonym_1_id");
@@ -39,6 +38,11 @@ namespace verbly {
39 const field word::regionalTerms = field::selfJoin(object::word, "word_id", "regionality", "domain_id", "term_id"); 38 const field word::regionalTerms = field::selfJoin(object::word, "word_id", "regionality", "domain_id", "term_id");
40 const field word::regionalDomains = field::selfJoin(object::word, "word_id", "regionality", "term_id", "domain_id"); 39 const field word::regionalDomains = field::selfJoin(object::word, "word_id", "regionality", "term_id", "domain_id");
41 40
41 field word::forms(inflection category)
42 {
43 return field::joinThroughWhere(object::word, "lemma_id", object::form, "lemmas_forms", "form_id", "category", static_cast<int>(category));
44 }
45
42 word::word(const database& db, sqlite3_stmt* row) : db_(&db), valid_(true) 46 word::word(const database& db, sqlite3_stmt* row) : db_(&db), valid_(true)
43 { 47 {
44 id_ = sqlite3_column_int(row, 0); 48 id_ = sqlite3_column_int(row, 0);
@@ -78,21 +82,6 @@ namespace verbly {
78 return notion_; 82 return notion_;
79 } 83 }
80 84
81 const lemma& word::getLemma() const
82 {
83 if (!valid_)
84 {
85 throw std::domain_error("Bad access to uninitialized word");
86 }
87
88 if (!lemma_)
89 {
90 lemma_ = db_->lemmas(lemma::id == lemmaId_).first();
91 }
92
93 return lemma_;
94 }
95
96 bool word::hasFrames() const 85 bool word::hasFrames() const
97 { 86 {
98 if (!valid_) 87 if (!valid_)
@@ -133,26 +122,50 @@ namespace verbly {
133 return frames_; 122 return frames_;
134 } 123 }
135 124
136 std::string word::getBaseForm() const 125 void word::initializeFrames() const
137 { 126 {
138 return getLemma().getBaseForm().getText(); 127 initializedFrames_ = true;
128 frames_ = db_->frames(*this, {}, -1).all();
139 } 129 }
140 130
141 std::vector<std::string> word::getInflections(inflection category) const 131 const form& word::getBaseForm() const
142 { 132 {
143 std::vector<std::string> result; 133 if (!valid_)
144 for (const form& infl : getLemma().getInflections(category))
145 { 134 {
146 result.push_back(infl.getText()); 135 throw std::domain_error("Bad access to uninitialized word");
147 } 136 }
148 137
149 return result; 138 if (!forms_.count(inflection::base))
139 {
140 initializeForm(inflection::base);
141 }
142
143 return forms_.at(inflection::base).front();
150 } 144 }
151 145
152 void word::initializeFrames() const 146 bool word::hasInflection(inflection category) const
153 { 147 {
154 initializedFrames_ = true; 148 return !getInflections(category).empty();
155 frames_ = db_->frames(*this, {}, -1).all(); 149 }
150
151 const std::vector<form>& word::getInflections(inflection category) const
152 {
153 if (!valid_)
154 {
155 throw std::domain_error("Bad access to uninitialized word");
156 }
157
158 if (!forms_.count(category))
159 {
160 initializeForm(category);
161 }
162
163 return forms_.at(category);
164 }
165
166 void word::initializeForm(inflection infl) const
167 {
168 forms_[infl] = db_->forms(form::words(infl) %= *this, verbly::form::id, -1).all();
156 } 169 }
157 170
158}; 171};