cargo fmt

jmdict/src/models/jmdict.rs

@@ -1,5 +1,5 @@
 use codes_iso_639::part_2::LanguageCode;
-use serde::{Serialize, Deserialize};
+use serde::{Deserialize, Serialize};
 
 use crate::serial::*;
 
@@ -13,8 +13,7 @@ pub struct Jmdict {
 #[serde(rename_all(deserialize = "PascalCase"), deny_unknown_fields)]
 pub struct JmdictEntry {
     pub sequence: i32,
-    #[serde(deserialize_with = "nullable_list")]
-    pub kanji: Vec<JmdictKanji>,
+    pub kanji: Option<Vec<JmdictKanji>>,
     pub readings: Vec<JmdictReading>,
     pub sense: Vec<JmdictSense>,
 }
@@ -48,10 +47,8 @@ pub enum JmdictGlossaryType {
 #[serde(rename_all(deserialize = "PascalCase"), deny_unknown_fields)]
 pub struct JmdictKanji {
     pub expression: String,
-    #[serde(deserialize_with = "nullable_list")]
-    pub information: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub priorities: Vec<String>,
+    pub information: Option<Vec<String>>,
+    pub priorities: Option<Vec<String>>,
 }
 
 #[derive(Serialize, Deserialize)]
@@ -61,44 +58,129 @@ pub struct JmdictReading {
     // Always empty with latest version of JMdict
     #[serde(default, skip_serializing, deserialize_with = "err_if_not_blank")]
     no_kanji: serde::de::IgnoredAny,
-    #[serde(deserialize_with = "nullable_list")]
-    pub restrictions: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub information: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub priorities: Vec<String>,
+    pub restrictions: Option<Vec<String>>,
+    pub information: Option<Vec<String>>,
+    pub priorities: Option<Vec<String>>,
 }
 
 #[derive(Serialize, Deserialize)]
 #[serde(rename_all(deserialize = "PascalCase"), deny_unknown_fields)]
 pub struct JmdictSense {
-    #[serde(deserialize_with = "nullable_list")]
-    pub restricted_kanji: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub restricted_readings: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub references: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub antonyms: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub parts_of_speech: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub fields: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub misc: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub source_languages: Vec<JmdictSource>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub dialects: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub information: Vec<String>,
-    #[serde(deserialize_with = "nullable_list")]
-    pub glossary: Vec<JmdictGlossary>,
+    pub restricted_kanji: Option<Vec<String>>,
+    pub restricted_readings: Option<Vec<String>>,
+    pub references: Option<Vec<String>>,
+    pub antonyms: Option<Vec<String>>,
+    pub parts_of_speech: Option<Vec<JmdictSensePartOfSpeech>>,
+    pub fields: Option<Vec<String>>,
+    pub misc: Option<Vec<String>>,
+    pub source_languages: Option<Vec<JmdictSource>>,
+    pub dialects: Option<Vec<String>>,
+    pub information: Option<Vec<String>>,
+    pub glossary: Option<Vec<JmdictGlossary>>,
     // Always empty with latest version of JMdict
     #[serde(default, skip_serializing, deserialize_with = "err_if_not_blank")]
     examples: serde::de::IgnoredAny,
 }
 
+macro_rules! JmdictSensePartOfSpeech {
+    { $( $variant:ident, $description:expr ),* } => {
+        #[derive(Serialize, Deserialize)]
+        pub enum JmdictSensePartOfSpeech {
+            $(
+                #[serde(rename = $description)]
+                #[doc = $description]
+                $variant
+            ),*
+        }
+    };
+}
+
+JmdictSensePartOfSpeech! {
+    Unclassified, "unclassified",
+    Noun,         "noun (common) (futsuumeishi)",
+    NounGenative, "nouns which may take the genitive case particle 'no'",
+    NounPrefix, "noun, used as a prefix",
+    NounSuffix, "noun, used as a suffix",
+    Expressions,  "expressions (phrases, clauses, etc.)",
+    AdjectiveI, "adjective (keiyoushi)",
+    AdjectiveIYoiIi, "adjective (keiyoushi) - yoi/ii class",
+    AdjectiveNa, "adjectival nouns or quasi-adjectives (keiyodoshi)",
+    AdjectiveNaArchaicFormal, "archaic/formal form of na-adjective",
+    AdjectiveTaru, "'taru' adjective",
+    AdjectiveShiku, "'shiku' adjective (archaic)",
+    AdjectivePreNoun, "pre-noun adjectival (rentaishi)",
+    AdjectiveAuxiliary, "auxiliary adjective",
+    VerbUnspecified, "verb unspecified", // e.g 得る
+    VerbIchidan, "Ichidan verb",
+    VerbIchidanKureru, "Ichidan verb - kureru special class",
+    VerbIchidanZuru, "Ichidan verb - zuru verb (alternative form of -jiru verbs)",
+    VerbSu, "su verb - precursor to the modern suru",
+    VerbNidanLowerMu, "Nidan verb (lower class) with 'mu' ending (archaic)",
+    VerbNidanLowerRu, "Nidan verb (lower class) with 'ru' ending (archaic)",
+    VerbNidanLowerFu, "Nidan verb (lower class) with 'hu/fu' ending (archaic)",
+    VerbNidanLowerGu, "Nidan verb (lower class) with 'gu' ending (archaic)",
+    VerbNidanLowerYu, "Nidan verb (lower class) with 'yu' ending (archaic)",
+    VerbNidanLowerDzu, "Nidan verb (lower class) with 'dzu' ending (archaic)",
+    VerbNidanLowerKu, "Nidan verb (lower class) with 'ku' ending (archaic)",
+    VerbNidanLowerSu, "Nidan verb (lower class) with 'su' ending (archaic)",
+    VerbNidanLowerZu, "Nidan verb (lower class) with 'zu' ending (archaic)",
+    VerbNidanLowerTsu, "Nidan verb (lower class) with 'tsu' ending (archaic)",
+    VerbNidanLowerNu, "Nidan verb (lower class) with 'nu' ending (archaic)",
+    VerbNidanLowerUWe, "Nidan verb (lower class) with 'u' ending and 'we' conjugation (archaic)",
+    VerbNidanUpperFu, "Nidan verb (upper class) with 'hu/fu' ending (archaic)",
+    VerbNidanUpperRu, "Nidan verb (upper class) with 'ru' ending (archaic)",
+    VerbNidanUpperTsu, "Nidan verb (upper class) with 'tsu' ending (archaic)",
+    VerbNidanUpperYu, "Nidan verb (upper class) with 'yu' ending (archaic)",
+    VerbNidanUpperKu, "Nidan verb (upper class) with 'ku' ending (archaic)",
+    VerbNidanUpperGu, "Nidan verb (upper class) with 'gu' ending (archaic)",
+    VerbNidanUpperBu, "Nidan verb (upper class) with 'bu' ending (archaic)",
+    VerbNidanU, "Nidan verb with 'u' ending (archaic)",
+    VerbGodanU, "Godan verb with 'u' ending",
+    VerbGodanUSpecial, "Godan verb with 'u' ending (special class)",
+    VerbGodanSu, "Godan verb with 'su' ending",
+    VerbGodanKu, "Godan verb with 'ku' ending",
+    VerbGodanRu, "Godan verb with 'ru' ending",
+    VerbGodanRuIrregular, "Godan verb with 'ru' ending (irregular verb)", // e.g. ある
+    VerbGodanMu, "Godan verb with 'mu' ending",
+    VerbGodanGu, "Godan verb with 'gu' ending",
+    VerbGodanTsu, "Godan verb with 'tsu' ending",
+    VerbGodanBu, "Godan verb with 'bu' ending",
+    VerbGodanNu, "Godan verb with 'nu' ending",
+    VerbGodanAru, "Godan verb - -aru special class", // e.g. いらっしゃる
+    VerbGodanIkuYuku, "Godan verb - Iku/Yuku special class",
+    VerbNuIrregular, "irregular nu verb", // e.g. 死ぬ
+    VerbKu, "'ku' adjective (archaic)",
+    VerbYodanRu, "Yodan verb with 'ru' ending (archaic)",
+    VerbYodanMu, "Yodan verb with 'mu' ending (archaic)",
+    VerbYodanSu, "Yodan verb with 'su' ending (archaic)",
+    VerbYodanKu, "Yodan verb with 'ku' ending (archaic)",
+    VerbYodanFu, "Yodan verb with 'hu/fu' ending (archaic)",
+    VerbYodanTsu, "Yodan verb with 'tsu' ending (archaic)",
+    VerbYodanGu, "Yodan verb with 'gu' ending (archaic)",
+    VerbYodanBu, "Yodan verb with 'bu' ending (archaic)",
+    VerbAuxiliary, "auxiliary verb",
+    VerbTransitive, "transitive verb",
+    VerbIntransitive, "intransitive verb",
+    VerbSuru, "suru verb - special class",
+    VerbSuruNoun, "noun or participle which takes the aux. verb suru",
+    VerbSuruIncluded, "suru verb - included",
+    VerbKuru, "Kuru verb - special class",
+    VerbRuIrregularRi, "irregular ru verb, plain form ends with -ri", // なり
+    Pronoun, "pronoun",
+    Adverb, "adverb (fukushi)",
+    AdverbTo, "adverb taking the 'to' particle",
+    Interjection, "interjection (kandoushi)",
+    Prenominal, "noun or verb acting prenominally", // e.g. ええ
+    Conjunction, "conjunction",
+    Particle, "particle",
+    Auxiliary, "auxiliary",
+    Copula, "copula", // である
+    Prefix, "prefix",
+    Suffix, "suffix",
+    Counter, "counter",
+    Numeric, "numeric"
+}
+
 #[derive(Serialize, Deserialize)]
 #[serde(rename_all(deserialize = "PascalCase"), deny_unknown_fields)]
 pub struct JmdictSource {

jmdict/src/serial.rs

@@ -3,27 +3,15 @@ use serde::{Deserialize, Deserializer};
 use serde_json::Value;
 use std::str::FromStr;
 
-pub fn nullable_list<'de, D, T>(deserializer: D) -> Result<Vec<T>, D::Error>
-where
-    D: Deserializer<'de>,
-    T: Deserialize<'de>,
-{
-    // Deserialize the JSON value using Serde's Value type
-    let value: Value = Deserialize::deserialize(deserializer)?;
-
-    // Check if the value is null and return an empty vector in that case
-    if value.is_null() {
-        Ok(Vec::new())
-    } else {
-        // Otherwise, try to deserialize the value as a Vec<String>
-        <Vec<T> as serde::Deserialize>::deserialize(value).map_err(serde::de::Error::custom)
-    }
-}
-
 pub fn wasei<'de, D>(deserializer: D) -> Result<bool, D::Error>
 where
     D: Deserializer<'de>,
 {
+    if !deserializer.is_human_readable() {
+        // bincode, will have already been serialized as bool
+        return Ok(Deserialize::deserialize(deserializer)?);
+    }
+
     // Deserialize the JSON value using Serde's Value type
     let value: Value = Deserialize::deserialize(deserializer)?;
 
@@ -58,6 +46,11 @@ pub fn lang_default_eng<'de, D>(deserializer: D) -> Result<LanguageCode, D::Erro
 where
     D: Deserializer<'de>,
 {
+    if !deserializer.is_human_readable() {
+        // bincode, will have already been serialized as LanguageCode
+        return Ok(Deserialize::deserialize(deserializer)?);
+    }
+
     lang_option(deserializer)
         .transpose()
         .unwrap_or(Ok(LanguageCode::Eng))
@@ -67,6 +60,11 @@ pub fn lang_option<'de, D>(deserializer: D) -> Result<Option<LanguageCode>, D::E
 where
     D: Deserializer<'de>,
 {
+    if !deserializer.is_human_readable() {
+        // bincode, will have already been serialized as Option<LanguageCode>
+        return Ok(Deserialize::deserialize(deserializer)?);
+    }
+
     Option::deserialize(deserializer)?
         .map(|str: String| parse_language_code(&str))
         .transpose()
@@ -77,6 +75,11 @@ pub fn err_if_not_blank<'de, D>(deserializer: D) -> Result<serde::de::IgnoredAny
 where
     D: Deserializer<'de>,
 {
+    if !deserializer.is_human_readable() {
+        // bincode, will have already been "serialized" as serde::de::IgnoredAny
+        return Ok(serde::de::IgnoredAny);
+    }
+
     let value = serde_json::Value::deserialize(deserializer)?;
     if value.is_null() || value == "" {
         Ok(serde::de::IgnoredAny)

jmdict/src/tests.rs

@@ -1,4 +1,7 @@
-use std::{fs::{self, File}, io::{Write, Read}};
+use std::{
+    fs::{self, File},
+    io::{Read, Write},
+};
 
 use crate::jmdict::Jmdict;