datamuse_api_rs/response.rs
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302
use crate::Result;
use serde::Deserialize;
/// This struct represents each word and its associated data in the response.
/// It is constructed when parsing a [Response](Response) with the method list().
/// Note that all optional values can still be None even if the proper flag
/// is set
#[derive(Debug, PartialEq)]
pub struct WordElement {
/// The word returned based on the search parameters
pub word: String,
/// A score which ranks the word based on how well it fit the provided parameters.
/// Note that by default the words are ranked by score from highest to lowest
pub score: usize,
/// The number of syllables the word has. This will only have a value if
/// the meta data flag [SyllableCount](crate::MetaDataFlag::SyllableCount) is set
pub num_syllables: Option<usize>,
/// The part(s) of speech a word can be. This will only have a value if
/// the meta data flag [PartsOfSpeech](crate::MetaDataFlag::PartsOfSpeech) is set
pub parts_of_speech: Option<Vec<PartOfSpeech>>,
/// The pronunciation of the word. This will only have a value if
/// the meta data flag [Pronunciation](crate::MetaDataFlag::Pronunciation) is set.
/// If an IPA pronuncation is available, it takes precedence as it is optional
pub pronunciation: Option<String>,
/// The frequency of a word based on how many times the word is used per 1,000,000
/// words of text. This will only have a value if the meta data flag
/// [WordFrequency](crate::MetaDataFlag::WordFrequency) is set
pub frequency: Option<f32>,
/// Definitions of a word and the associated part of speech with its use. This will only
/// have a value if the meta data flag [Definitions](crate::MetaDataFlag::Definitions) is set
pub definitions: Option<Vec<Definition>>,
}
/// A struct representing a word definition
#[derive(Debug, PartialEq)]
pub struct Definition {
/// The part of speech associated with the definition
pub part_of_speech: Option<PartOfSpeech>,
/// The definition itself
pub definition: String,
}
/// A struct representing a response from a request.
/// This can be parsed into a word list using the list() method
#[derive(Debug)]
pub struct Response {
json: String,
}
/// An enum representing all possible parts of speech returned from the api
#[derive(Clone, Copy, Debug, PartialEq)]
pub enum PartOfSpeech {
/// Noun
Noun, //n
/// Adjective
Adjective, //adj
/// Adverb
Adverb, //adv
/// Verb
Verb, //v
}
#[derive(Deserialize, Debug)]
#[serde(rename_all = "camelCase")]
struct DatamuseWordObject {
word: String,
score: usize,
num_syllables: Option<usize>,
tags: Option<Vec<String>>,
defs: Option<Vec<String>>,
}
impl Response {
/// Parses the response into a list of word elements
pub fn list(&self) -> Result<Vec<WordElement>> {
parse_response(&self.json)
}
pub(crate) fn new(json: String) -> Response {
Response { json }
}
}
impl PartOfSpeech {
fn from_str(pos: &str) -> Option<Self> {
match pos {
"n" => Some(Self::Noun),
"adj" => Some(Self::Adjective),
"adv" => Some(Self::Adverb),
"v" => Some(Self::Verb),
_ => None, //Also catches undefined option "u"
}
}
}
fn parse_response(response: &str) -> Result<Vec<WordElement>> {
let word_list: Vec<DatamuseWordObject> = serde_json::from_str(response)?;
let mut converted_word_list: Vec<WordElement> = Vec::new();
for word in word_list {
converted_word_list.push(word_obj_to_word_elem(word));
}
Ok(converted_word_list)
}
fn word_obj_to_word_elem(word_obj: DatamuseWordObject) -> WordElement {
let word = word_obj.word;
let score = word_obj.score;
let num_syllables = word_obj.num_syllables;
let mut parts_of_speech: Vec<PartOfSpeech> = Vec::new();
let mut pronunciation = None;
let mut frequency = None;
if let Some(tags) = word_obj.tags {
for tag in tags {
let parts: Vec<&str> = tag.split(':').collect();
match parts[0] {
"f" => {
if parts.len() == 2 {
frequency = match parts[1].parse() {
Ok(val) => Some(val),
Err(_) => None,
}
}
}
"pron" => {
if let None = pronunciation {
//If pronunciation already has a value ignore b/c of ipa
if parts.len() == 2 {
pronunciation = Some(parts[1].to_string());
}
}
}
"ipa_pron" => {
if parts.len() == 2 {
pronunciation = Some(parts[1].to_string());
}
}
val => match PartOfSpeech::from_str(&val) {
Some(val) => parts_of_speech.push(val),
None => continue,
},
}
}
}
let pos;
if parts_of_speech.len() > 0 {
pos = Some(parts_of_speech);
} else {
pos = None;
}
let parts_of_speech = pos;
let mut definitions = None;
if let Some(defs) = word_obj.defs {
if defs.len() > 0 {
let mut def_list: Vec<Definition> = Vec::new();
for def in defs {
let parts: Vec<&str> = def.split('\t').collect();
if parts.len() == 2 {
let pos = PartOfSpeech::from_str(&parts[0]);
def_list.push(Definition {
part_of_speech: pos,
definition: parts[1].to_string(),
});
}
}
definitions = Some(def_list);
}
}
WordElement {
word,
score,
num_syllables,
parts_of_speech,
pronunciation,
frequency,
definitions,
}
}
#[cfg(test)]
mod tests {
use super::DatamuseWordObject;
use crate::{Definition, PartOfSpeech, WordElement};
#[test]
fn word_obj_to_word_elem() {
let word_obj = DatamuseWordObject {
word: String::from("cow"),
score: 2168,
num_syllables: Some(1),
tags: Some(vec![
String::from("n"),
String::from("pron:K AW1 "),
String::from("f:16.567268"),
]),
defs: Some(vec![
String::from("n\tmature female of mammals of which the male is called `bull'"),
String::from("n\tfemale of domestic cattle"),
]),
};
let actual = super::word_obj_to_word_elem(word_obj);
let expected = WordElement {
word: String::from("cow"),
score: 2168,
num_syllables: Some(1),
parts_of_speech: Some(vec![PartOfSpeech::Noun]),
pronunciation: Some(String::from("K AW1 ")),
frequency: Some(16.567268),
definitions: Some(vec![
Definition {
part_of_speech: Some(PartOfSpeech::Noun),
definition: String::from(
"mature female of mammals of which the male is called `bull'",
),
},
Definition {
part_of_speech: Some(PartOfSpeech::Noun),
definition: String::from("female of domestic cattle"),
},
]),
};
assert_eq!(expected, actual);
}
#[test]
fn json_to_word_elem() {
let json = r#"
[
{
"word":"milk",
"score":2168,
"numSyllables":1,
"tags": [],
"defs": []
},
{
"word":"cow",
"score":2168,
"numSyllables":1,
"tags": [
"n",
"pron:K AW1 ",
"f:16.567268"
],
"defs": [
"n\tmature female of mammals of which the male is called `bull'",
"n\tfemale of domestic cattle"
]
}
]
"#;
let actual = super::parse_response(json).unwrap();
let expected1 = WordElement {
word: String::from("milk"),
score: 2168,
num_syllables: Some(1),
parts_of_speech: None,
pronunciation: None,
frequency: None,
definitions: None,
};
let expected2 = WordElement {
word: String::from("cow"),
score: 2168,
num_syllables: Some(1),
parts_of_speech: Some(vec![PartOfSpeech::Noun]),
pronunciation: Some(String::from("K AW1 ")),
frequency: Some(16.567268),
definitions: Some(vec![
Definition {
part_of_speech: Some(PartOfSpeech::Noun),
definition: String::from(
"mature female of mammals of which the male is called `bull'",
),
},
Definition {
part_of_speech: Some(PartOfSpeech::Noun),
definition: String::from("female of domestic cattle"),
},
]),
};
assert_eq!(expected1, actual[0]);
assert_eq!(expected2, actual[1]);
}
}