Data.Kanji

A library for analysing the density of Kanji in given texts, according to their Level classification, as defined by the Japan Kanji Aptitude Testing Foundation (日本漢字能力検定協会).

Kanji

data Kanji

A single symbol of Kanji. Japanese Kanji were borrowed from China over several waves during the last 1,500 years. Japan names 2,136 of these as their standard set, with rarer characters being the domain of academia and esoteric writers.

Japanese has several Japan-only Kanji, including:

• 畑 (a type of rice field)
• 峠 (a narrow mountain pass)
• 働 (to do physical labour)

Instances

Eq Kanji

Methods

(==) :: Kanji -> Kanji -> Bool

(/=) :: Kanji -> Kanji -> Bool

Ord Kanji

Methods

compare :: Kanji -> Kanji -> Ordering

(<) :: Kanji -> Kanji -> Bool

(<=) :: Kanji -> Kanji -> Bool

(>) :: Kanji -> Kanji -> Bool

(>=) :: Kanji -> Kanji -> Bool

max :: Kanji -> Kanji -> Kanji

min :: Kanji -> Kanji -> Kanji

Show Kanji

Methods

showsPrec :: Int -> Kanji -> ShowS

show :: Kanji -> String

showList :: [Kanji] -> ShowS

Generic Kanji

Associated Types

type Rep Kanji :: * -> *

Methods

from :: Kanji -> Rep Kanji x

to :: Rep Kanji x -> Kanji

Hashable Kanji

Methods

hashWithSalt :: Int -> Kanji -> Int

hash :: Kanji -> Int

ToJSON Kanji

Methods

toJSON :: Kanji -> Value

toEncoding :: Kanji -> Encoding

toJSONList :: [Kanji] -> Value

toEncodingList :: [Kanji] -> Encoding

FromJSON Kanji

Methods

parseJSON :: Value -> Parser Kanji

parseJSONList :: Value -> Parser [Kanji]

NFData Kanji

Methods

rnf :: Kanji -> ()

type Rep Kanji

type Rep Kanji = D1 * (MetaData "Kanji" "Data.Kanji.Types" "kanji-3.1.0.1-G2K6XyiD6hiLlm25DD7LVV" True) (C1 * (MetaCons "Kanji" PrefixI True) (S1 * (MetaSel (Just Symbol "_kanji") NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 * Char)))

kanji :: Char -> Maybe Kanji

Construct a Kanji value from some Char if it falls in the correct UTF8 range.

_kanji :: Kanji -> Char

The original Char of a Kanji.

allKanji :: Map Level (Set Kanji)

All Japanese Kanji, grouped by their Level (級).

isKanji :: Char -> Bool

Legal Kanji appear between UTF8 characters 19968 and 40959.

Levels

data Level

A Level or Kyuu (級) of Japanese Kanji ranking. There are 12 of these, from 10 to 1, including intermediate levels between 3 and 2, and 2 and 1.

Japanese students will typically have Level-5 ability by the time they finish elementary school. Level-5 accounts for 1,006 characters.

By the end of middle school, they would have covered up to Level-3 (1607 Kanji) in their Japanese class curriculum.

While Level-2 (2,136 Kanji) is considered "standard adult" ability, many adults could not pass the Level-2, or even the Level-Pre2 (1940 Kanji) exam without considerable study.

Level data for Kanji above Level-2 is currently not provided by this library.

Constructors

Ten

Nine

Eight

Seven

Six

Five

Four

Three

PreTwo

Two

PreOne

One

Instances

Enum Level

Methods

succ :: Level -> Level

pred :: Level -> Level

toEnum :: Int -> Level

fromEnum :: Level -> Int

enumFrom :: Level -> [Level]

enumFromThen :: Level -> Level -> [Level]

enumFromTo :: Level -> Level -> [Level]

enumFromThenTo :: Level -> Level -> Level -> [Level]

Eq Level

Methods

(==) :: Level -> Level -> Bool

(/=) :: Level -> Level -> Bool

Ord Level

Methods

compare :: Level -> Level -> Ordering

(<) :: Level -> Level -> Bool

(<=) :: Level -> Level -> Bool

(>) :: Level -> Level -> Bool

(>=) :: Level -> Level -> Bool

max :: Level -> Level -> Level

min :: Level -> Level -> Level

Show Level

Methods

showsPrec :: Int -> Level -> ShowS

show :: Level -> String

showList :: [Level] -> ShowS

Generic Level

Associated Types

type Rep Level :: * -> *

Methods

from :: Level -> Rep Level x

to :: Rep Level x -> Level

Hashable Level

Methods

hashWithSalt :: Int -> Level -> Int

hash :: Level -> Int

ToJSON Level

Methods

toJSON :: Level -> Value

toEncoding :: Level -> Encoding

toJSONList :: [Level] -> Value

toEncodingList :: [Level] -> Encoding

ToJSONKey Level

Methods

toJSONKey :: ToJSONKeyFunction Level

toJSONKeyList :: ToJSONKeyFunction [Level]

FromJSON Level

Methods

parseJSON :: Value -> Parser Level

parseJSONList :: Value -> Parser [Level]

NFData Level

Methods

rnf :: Level -> ()

type Rep Level

type Rep Level = D1 * (MetaData "Level" "Data.Kanji.Types" "kanji-3.1.0.1-G2K6XyiD6hiLlm25DD7LVV" False) ((:+:) * ((:+:) * ((:+:) * (C1 * (MetaCons "Ten" PrefixI False) (U1 *)) ((:+:) * (C1 * (MetaCons "Nine" PrefixI False) (U1 *)) (C1 * (MetaCons "Eight" PrefixI False) (U1 *)))) ((:+:) * (C1 * (MetaCons "Seven" PrefixI False) (U1 *)) ((:+:) * (C1 * (MetaCons "Six" PrefixI False) (U1 *)) (C1 * (MetaCons "Five" PrefixI False) (U1 *))))) ((:+:) * ((:+:) * (C1 * (MetaCons "Four" PrefixI False) (U1 *)) ((:+:) * (C1 * (MetaCons "Three" PrefixI False) (U1 *)) (C1 * (MetaCons "PreTwo" PrefixI False) (U1 *)))) ((:+:) * (C1 * (MetaCons "Two" PrefixI False) (U1 *)) ((:+:) * (C1 * (MetaCons "PreOne" PrefixI False) (U1 *)) (C1 * (MetaCons "One" PrefixI False) (U1 *))))))

level :: Kanji -> Maybe Level

What Level does a Kanji belong to?

Analysis

percentSpread :: [Kanji] -> Map Kanji Float

The distribution of each Kanji in a set of them. The distribution values must sum to 1.

levelDist :: [Kanji] -> Map Level Float

How much of each Level is represented by a group of Kanji? The distribution values will sum to <= 1.

averageLevel :: [Kanji] -> Float

Find the average Level of a given set of Kanji.

uniques :: [Kanji] -> Map Level (Set Kanji)

Which Kanji appeared from each Level in the text?

Densities

kanjiDensity :: Int -> [Kanji] -> Float

Given the length of some String-like type and a list of Kanji found therein, what percentage of them were Kanji?

elementaryDen :: Map Level Float -> Float

How much of the Kanji found are learnt in elementary school in Japan?

elementaryDen . levelDist :: [Kanji] -> Float

middleDen :: Map Level Float -> Float

How much of the Kanji found are learnt by the end of middle school?

middleDen . levelDist :: [Kanji] -> Float

highDen :: Map Level Float -> Float

How much of the Kanji found are learnt by the end of high school?

highDen . levelDist :: [Kanji] -> Float

adultDen :: Map Level Float -> Float

How much of the Kanji found should be able to be read by the average person?

adultDen . levelDist :: [Kanji] -> Float