Merge pull request #12 from WeDontPanic/master

fix #11

Cargo.toml

@@ -13,16 +13,17 @@ version = "2.1.0"
 include = ["src/**/*", "LICENSE", "README.md"]
 
 [dependencies]
-fnv = "1.0.6"
-itertools = "0.8.1"
+fnv = "1.0.7"
+itertools = {version = "0.10.5", optional = true}
 lazy_static = "1.4.0"
-regex = { version = "1.3.1", optional = true }
+regex = { version = "1.7.0", optional = true }
 
 [dev-dependencies]
 speculate = "0.1.2"
 
 [features]
 enable_regex = ["regex"]
+tokenize = ["itertools"]
 default = []
 
 [[bin]]

src/is_mixed.rs

@@ -21,6 +21,7 @@ use crate::utils::is_char_kanji::is_char_kanji;
 use crate::utils::is_char_katakana::is_char_katakana;
 use crate::utils::is_char_romaji::is_char_romaji;
 
+#[inline]
 pub fn is_mixed(input: &str) -> bool {
     is_mixed_pass_kanji(input, true)
 }

src/lib.rs

@@ -1,6 +1,6 @@
 //! # ワナカナ <--> WanaKana <--> わなかな
 //!
-//! Utility library for checking and converting between Japanese characters - 
+//! Utility library for checking and converting between Japanese characters -
 //! Hiragana, Katakana - and Romaji (Ported from <https://github.com/WaniKani/WanaKana>)
 //!
 //! # Conversions
@@ -66,7 +66,9 @@ pub mod to_kana;
 pub mod to_katakana;
 pub mod to_romaji;
 
+#[cfg(feature = "tokenize")]
 pub mod tokenize;
+#[cfg(feature = "tokenize")]
 pub mod trim_okurigana;
 
 pub mod constants;

src/to_hiragana.rs

@@ -16,9 +16,11 @@ use crate::utils::is_char_english_punctuation::is_char_english_punctuation;
 use crate::utils::katakana_to_hiragana::*;
 use crate::utils::romaji_to_hiragana::romaji_to_hiragana;
 
+#[inline]
 pub fn to_hiragana(input: &str) -> String {
     to_hiragana_with_opt(input, Options::default())
 }
+
 pub fn to_hiragana_with_opt(input: &str, options: Options) -> String {
     let config = options;
     if config.pass_romaji {

src/to_kana.rs

@@ -18,6 +18,7 @@
 use crate::options::Options;
 use crate::utils::hiragana_to_katakana::*;
 
+#[inline]
 pub fn to_kana(input: &str) -> String {
     to_kana_with_opt(input, Options::default())
 }

src/to_romaji.rs

@@ -2469,6 +2469,13 @@ lazy_static! {
                     output: "ro",
                 },
             ),
+            (
+                'ゎ',
+                Node {
+                    transitions: None,
+                    output: "wa",
+                },
+            ),
             (
                 'わ',
                 Node {

src/traits.rs

@@ -66,21 +66,32 @@ pub trait ConvertJapanese {
 }
 
 impl ConvertJapanese for &str {
+    #[inline]
     fn to_kana(self) -> String {
         crate::to_kana::to_kana(self)
     }
+
+    #[inline]
     fn to_kana_with_opt(self, options: Options) -> String {
         crate::to_kana::to_kana_with_opt(self, options)
     }
+
+    #[inline]
     fn to_hiragana(self) -> String {
         crate::to_hiragana::to_hiragana(self)
     }
+
+    #[inline]
     fn to_katakana(self) -> String {
         crate::to_katakana::to_katakana(self)
     }
+
+    #[inline]
     fn to_romaji(self) -> String {
         crate::to_romaji::to_romaji(self)
     }
+
+    #[inline]
     fn to_romaji_with_opt(self, options: Options) -> String {
         crate::to_romaji::to_romaji_with_opt(self, options)
     }
@@ -187,24 +198,37 @@ pub trait IsJapaneseStr {
 }
 
 impl IsJapaneseStr for &str {
+    #[inline]
     fn is_hiragana(self) -> bool {
         crate::is_hiragana::is_hiragana(self)
     }
+
+    #[inline]
     fn is_katakana(self) -> bool {
         crate::is_katakana::is_katakana(self)
     }
+
+    #[inline]
     fn is_kana(self) -> bool {
         crate::is_kana::is_kana(self)
     }
+
+    #[inline]
     fn is_kanji(self) -> bool {
         crate::is_kanji::is_kanji(self)
     }
+
+    #[inline]
     fn is_japanese(self) -> bool {
         crate::is_japanese::is_japanese(self)
     }
+
+    #[inline]
     fn is_romaji(self) -> bool {
         crate::is_romaji::is_romaji(self)
     }
+
+    #[inline]
     fn is_mixed(self) -> bool {
         crate::is_mixed::is_mixed(self)
     }
@@ -230,24 +254,37 @@ pub trait IsJapaneseChar {
 }
 
 impl IsJapaneseChar for char {
+    #[inline]
     fn is_hiragana(self) -> bool {
         crate::utils::is_char_hiragana(self)
     }
+
+    #[inline]
     fn is_katakana(self) -> bool {
         crate::utils::is_char_katakana(self)
     }
+
+    #[inline]
     fn is_kana(self) -> bool {
         crate::utils::is_char_kana(self)
     }
+
+    #[inline]
     fn is_kanji(self) -> bool {
         crate::utils::is_char_kanji(self)
     }
+
+    #[inline]
     fn is_japanese(self) -> bool {
         crate::utils::is_char_japanese(self)
     }
+
+    #[inline]
     fn is_japanese_number(self) -> bool {
         crate::utils::is_char_japanese_number(self)
     }
+
+    #[inline]
     fn is_japanese_punctuation(self) -> bool {
         crate::utils::is_char_japanese_punctuation(self)
     }

src/trim_okurigana.rs

@@ -18,13 +18,16 @@ use crate::tokenize::*;
 use crate::utils::is_char_kana::*;
 use crate::utils::is_char_kanji::*;
 
+#[inline]
 pub fn trim_okurigana(input: &str) -> &str {
     trim_okurigana_with_opt(input, false, None)
 }
 
 pub fn is_leading_without_initial_kana(input: &str, from_start: bool) -> bool {
     from_start && !is_char_kana(input.chars().next().unwrap())
 }
+
+#[inline]
 pub fn is_trailing_without_final_kana(input: &str, from_start: bool) -> bool {
     !from_start && !is_char_kana(input.chars().last().unwrap())
 }

src/utils/is_char_consonant.rs

@@ -3,6 +3,7 @@
 /// * `include_Y` include y as a consonant in test
 ///
 
+#[inline]
 pub fn is_char_consonant(char: char, include_y: bool) -> bool {
     match char {
         'b' | 'c' | 'd' | 'f' | 'g' | 'h' | 'j' | 'k' | 'l' | 'm' | 'n' | 'p' | 'q' | 'r' | 's' | 't' | 'v' | 'w' | 'x' | 'z' => true,

src/utils/is_char_slash_dot.rs

@@ -1,6 +1,7 @@
 use crate::constants::KANA_SLASH_DOT;
 
 /// Tests if char is '・'
+#[inline]
 pub fn is_char_slash_dot(char: char) -> bool {
     char as u32 == KANA_SLASH_DOT
 }

src/utils/is_char_upper_case.rs

@@ -1,8 +1,10 @@
-use crate::utils::is_char_in_range::*;
-
-use crate::constants::{UPPERCASE_END, UPPERCASE_START};
+use crate::{
+    constants::{UPPERCASE_END, UPPERCASE_START},
+    utils::is_char_in_range::*,
+};
 
 /// Tests if char is in English unicode uppercase range
+#[inline]
 pub fn is_char_upper_case(char: char) -> bool {
     is_char_in_range(char, UPPERCASE_START, UPPERCASE_END)
 }

tests/tokenize.rs

@@ -6,8 +6,10 @@ extern crate speculate;
 #[cfg(test)]
 use speculate::speculate;
 
+#[cfg(feature = "tokenize")]
 use wana_kana::tokenize::*;
 
+#[cfg(feature = "tokenize")]
 speculate! {
 
     it "tokenize() with no input" {

tests/trim_okurigana.rs

@@ -6,8 +6,10 @@ extern crate speculate;
 #[cfg(test)]
 use speculate::speculate;
 
+#[cfg(feature = "tokenize")]
 use wana_kana::trim_okurigana::*;
 
+#[cfg(feature = "tokenize")]
 speculate! {
     it "trim_okurigana() with no input" {
         assert_eq!(trim_okurigana(""), "");