Safe Haskell	Safe-Inferred
Language	Haskell2010

Text.Seonbi.Facade

Contents

HTML transformation
Configuration and presets
Content types
Dictionaries
Options

Description

Provides higher-level APIs. Read transformHtmlText function first, and then see also Configuration type.

Synopsis

transformHtmlText :: forall (m :: Type -> Type) a. (Monad m, MonadFail m) => Configuration m a -> Text -> m Text
transformHtmlLazyText :: forall (m :: Type -> Type) a. (Monad m, MonadFail m) => Configuration m a -> Text -> m Text
data Monad m => Configuration m a = Configuration {
- debugLogger :: Maybe (HtmlEntity -> m a)
- contentType :: ContentType
- quote :: Maybe QuoteOption
- cite :: Maybe CiteOption
- arrow :: Maybe ArrowOption
- ellipsis :: Bool
- emDash :: Bool
- stop :: Maybe StopOption
- hanja :: Maybe HanjaOption
}
ko_KP :: Monad m => Configuration m a
ko_KR :: Monad m => Configuration m a
presets :: (Ord k, IsString k, Monad m) => Map k (Configuration m a)
type ContentType = MediaType
contentTypeFromText :: Text -> Maybe ContentType
contentTypes :: Set ContentType
contentTypeText :: ContentType -> Text
type HanjaDictionary = Trie Text
readDictionaryFile :: FilePath -> IO HanjaDictionary
southKoreanDictionary :: IO HanjaDictionary
data ArrowOption = ArrowOption {
- bidirArrow :: Bool
- doubleArrow :: Bool
}
data CiteOption
- = AngleQuotes
- | CornerBrackets
- | AngleQuotesWithCite
- | CornerBracketsWithCite
data HanjaOption = HanjaOption {
- rendering :: HanjaRenderingOption
- reading :: HanjaReadingOption
}
data HanjaReadingOption = HanjaReadingOption {
- initialSoundLaw :: Bool
- dictionary :: HanjaDictionary
}
data HanjaRenderingOption
- = HangulOnly
- | HanjaInParentheses
- | DisambiguatingHanjaInParentheses
- | HanjaInRuby
data QuoteOption
- = CurvedQuotes
- | VerticalCornerBrackets
- | HorizontalCornerBrackets
- | Guillemets
- | CurvedSingleQuotesWithQ
- | VerticalCornerBracketsWithQ
- | HorizontalCornerBracketsWithQ
data StopOption
- = Horizontal
- | HorizontalWithSlashes
- | Vertical

HTML transformation

transformHtmlText :: forall (m :: Type -> Type) a. (Monad m, MonadFail m) => Configuration m a -> Text -> m Text Source #

Transforms a given text. Nothing if it fails to parse the given text.

transformHtmlLazyText :: forall (m :: Type -> Type) a. (Monad m, MonadFail m) => Configuration m a -> Text -> m Text Source #

A lazy version of transformHtmlText function.

Configuration and presets

data Monad m => Configuration m a Source #

Transformation settings. For the most cases, you could use one of presets:

ko_KR
ko_KP

Constructors

Configuration

Fields

debugLogger :: Maybe (HtmlEntity -> m a)
An optional debugging logger to print its internal AST.
contentType :: ContentType
A content type of the input and output. It has to be a member of contentTypes.
quote :: Maybe QuoteOption
An option to decide how quotation marks are rendered. If Nothing no quotes are transformed.
cite :: Maybe CiteOption
An option to transform folk-citing quotes (e.g., <<한겨레>>) into proper citing quotes (e.g., 《한겨레》).
arrow :: Maybe ArrowOption
Settings to transform arrow-looking punctuations into proper arrows. If Nothing no arrows are transformed.
ellipsis :: Bool
Whether to transform triple periods into a proper ellipsis.
emDash :: Bool
Whether to transform folk em dashes into proper em dashes.
stop :: Maybe StopOption
Settings to normalize stops (periods, commas, and interpuncts). If Nothing stops are never touched.
hanja :: Maybe HanjaOption
Settings to deal with Sino-Korean words.

Instances

Instances details

Monad m => Show (Configuration m a) Source #
Instance details Defined in Text.Seonbi.Facade Methods showsPrec :: Int -> Configuration m a -> ShowS # show :: Configuration m a -> String # showList :: [Configuration m a] -> ShowS #

ko_KP :: Monad m => Configuration m a Source #

Preset Configuration for North Korean orthography.

ko_KR :: Monad m => Configuration m a Source #

Preset Configuration for South Korean orthography.

presets :: (Ord k, IsString k, Monad m) => Map k (Configuration m a) Source #

A mapping of locale code strings (e.g., "ko-kr") to the corresponding Configuration presets (e.g., ko_KR).

Content types

type ContentType = MediaType Source #

Represents a case-insensitive content type.

contentTypeFromText :: Text -> Maybe ContentType Source #

Converts a Text to a ContentType.

contentTypes :: Set ContentType Source #

Supported content types.

contentTypeText :: ContentType -> Text Source #

Converts a ContentType to a Text.

Dictionaries

type HanjaDictionary = Trie Text Source #

Represents a dictionary that has hanja keys and values of their corresponding hangul readings, e.g., [("敗北", "패배")].

readDictionaryFile :: FilePath -> IO HanjaDictionary Source #

Loads a dictionary file. The file consists of two-column TSV (tab-separated values); the first column is hanja and the second column is hangul.

southKoreanDictionary :: IO HanjaDictionary Source #

Loads Standard Korean Language Dictionary (標準國語大辭典) data.

Options

data ArrowOption Source #

Settings to transform arrow-looking punctuations into proper arrows.

Constructors

ArrowOption
Fields bidirArrow :: Bool Whether to transform bi-directional arrows as well as left/rightwards arrows. doubleArrow :: Bool Whether to transform double arrows as well as single arrows.

Instances

Instances details

Generic ArrowOption Source #
Instance details Defined in Text.Seonbi.Facade Associated Types type Rep ArrowOption :: Type -> Type # Methods from :: ArrowOption -> Rep ArrowOption x # to :: Rep ArrowOption x -> ArrowOption #
Show ArrowOption Source #
Instance details Defined in Text.Seonbi.Facade Methods showsPrec :: Int -> ArrowOption -> ShowS # show :: ArrowOption -> String # showList :: [ArrowOption] -> ShowS #
Eq ArrowOption Source #
Instance details Defined in Text.Seonbi.Facade Methods (==) :: ArrowOption -> ArrowOption -> Bool # (/=) :: ArrowOption -> ArrowOption -> Bool #
type Rep ArrowOption Source #
Instance details Defined in Text.Seonbi.Facade type Rep ArrowOption = D1 ('MetaData "ArrowOption" "Text.Seonbi.Facade" "seonbi-0.4.0-FOhxpaKIZkM2yOPV4QhpsQ" 'False) (C1 ('MetaCons "ArrowOption" 'PrefixI 'True) (S1 ('MetaSel ('Just "bidirArrow") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 Bool) :*: S1 ('MetaSel ('Just "doubleArrow") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 Bool)))

data CiteOption Source #

An option to transform folk-citing quotes (e.g., <<한겨레>>) into proper citing quotes (e.g., 《한겨레》).

Constructors

AngleQuotes	Cite a title using angle quotes, used by South Korean orthography in horizontal writing (橫書), e.g., 《나비와 엉겅퀴》 or 〈枾崎의 바다〉.
CornerBrackets	Cite a title using corner brackets, used by South Korean orthography in vertical writing (縱書) and Japanese orthography, e.g., 『나비와 엉겅퀴』 or 「枾崎의 바다」.
AngleQuotesWithCite	Same as `AngleQuotes` except it wraps the title with a `<cite>` tag.
CornerBracketsWithCite	Same as `CornerBrackets` except it wraps the title with a `<cite>` tag.

Instances

Instances details

Enum CiteOption Source #
Instance details Defined in Text.Seonbi.Facade Methods succ :: CiteOption -> CiteOption # pred :: CiteOption -> CiteOption # toEnum :: Int -> CiteOption # fromEnum :: CiteOption -> Int # enumFrom :: CiteOption -> [CiteOption] # enumFromThen :: CiteOption -> CiteOption -> [CiteOption] # enumFromTo :: CiteOption -> CiteOption -> [CiteOption] # enumFromThenTo :: CiteOption -> CiteOption -> CiteOption -> [CiteOption] #
Generic CiteOption Source #
Instance details Defined in Text.Seonbi.Facade Associated Types type Rep CiteOption :: Type -> Type # Methods from :: CiteOption -> Rep CiteOption x # to :: Rep CiteOption x -> CiteOption #
Read CiteOption Source #
Instance details Defined in Text.Seonbi.Facade Methods readsPrec :: Int -> ReadS CiteOption # readList :: ReadS [CiteOption] # readPrec :: ReadPrec CiteOption # readListPrec :: ReadPrec [CiteOption] #
Show CiteOption Source #
Instance details Defined in Text.Seonbi.Facade Methods showsPrec :: Int -> CiteOption -> ShowS # show :: CiteOption -> String # showList :: [CiteOption] -> ShowS #
Eq CiteOption Source #
Instance details Defined in Text.Seonbi.Facade Methods (==) :: CiteOption -> CiteOption -> Bool # (/=) :: CiteOption -> CiteOption -> Bool #
type Rep CiteOption Source #
Instance details Defined in Text.Seonbi.Facade type Rep CiteOption = D1 ('MetaData "CiteOption" "Text.Seonbi.Facade" "seonbi-0.4.0-FOhxpaKIZkM2yOPV4QhpsQ" 'False) ((C1 ('MetaCons "AngleQuotes" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "CornerBrackets" 'PrefixI 'False) (U1 :: Type -> Type)) :+: (C1 ('MetaCons "AngleQuotesWithCite" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "CornerBracketsWithCite" 'PrefixI 'False) (U1 :: Type -> Type)))

data HanjaOption Source #

Settings to deal with Sino-Korean words.

Constructors

HanjaOption
Fields rendering :: HanjaRenderingOption How to render Sino-Korean words. reading :: HanjaReadingOption How to rewrite Sino-Korean words in hangul.

Instances

Instances details

Show HanjaOption Source #
Instance details Defined in Text.Seonbi.Facade Methods showsPrec :: Int -> HanjaOption -> ShowS # show :: HanjaOption -> String # showList :: [HanjaOption] -> ShowS #

data HanjaReadingOption Source #

Settings to read Sino-Korean words.

Constructors

HanjaReadingOption
Fields initialSoundLaw :: Bool Whether to apply Initial Sound Law (頭音法則) or not. dictionary :: HanjaDictionary A dictionary which has hanja readings. Keys are hanja words and values are their corresponding hangul readings, e.g.: [("敗北", "패배"), ("北極", "북극")] :: HanjaDictionary

Instances

Instances details

Show HanjaReadingOption Source #
Instance details Defined in Text.Seonbi.Facade Methods showsPrec :: Int -> HanjaReadingOption -> ShowS # show :: HanjaReadingOption -> String # showList :: [HanjaReadingOption] -> ShowS #

data HanjaRenderingOption Source #

Available options to render Sino-Korean words.

Constructors

HangulOnly	Renders a word in hangul-only, no hanja at all (e.g., `안녕히`).
HanjaInParentheses	Renders a word in hangul followed by hanja in parentheses (e.g., `안녕(安寧)히`).
DisambiguatingHanjaInParentheses	Renders words in hangul-only for the most part, and if there are homophones in a document put their hanja notation in parentheses (e.g., `안녕히` or `소수(小數)와 소수(素數)`).
HanjaInRuby	Renders a word in `ruby` tag (e.g., `<ruby>安寧<rp>(</rp><rt>안녕</rt><rp>)</rp></ruby>히`). Please read Use Cases & Exploratory Approaches for Ruby Markup as well for more information.

Instances

Instances details

Enum HanjaRenderingOption Source #
Instance details Defined in Text.Seonbi.Facade Methods succ :: HanjaRenderingOption -> HanjaRenderingOption # pred :: HanjaRenderingOption -> HanjaRenderingOption # toEnum :: Int -> HanjaRenderingOption # fromEnum :: HanjaRenderingOption -> Int # enumFrom :: HanjaRenderingOption -> [HanjaRenderingOption] # enumFromThen :: HanjaRenderingOption -> HanjaRenderingOption -> [HanjaRenderingOption] # enumFromTo :: HanjaRenderingOption -> HanjaRenderingOption -> [HanjaRenderingOption] # enumFromThenTo :: HanjaRenderingOption -> HanjaRenderingOption -> HanjaRenderingOption -> [HanjaRenderingOption] #
Generic HanjaRenderingOption Source #
Instance details Defined in Text.Seonbi.Facade Associated Types type Rep HanjaRenderingOption :: Type -> Type # Methods from :: HanjaRenderingOption -> Rep HanjaRenderingOption x # to :: Rep HanjaRenderingOption x -> HanjaRenderingOption #
Read HanjaRenderingOption Source #
Instance details Defined in Text.Seonbi.Facade Methods readsPrec :: Int -> ReadS HanjaRenderingOption # readList :: ReadS [HanjaRenderingOption] # readPrec :: ReadPrec HanjaRenderingOption # readListPrec :: ReadPrec [HanjaRenderingOption] #
Show HanjaRenderingOption Source #
Instance details Defined in Text.Seonbi.Facade Methods showsPrec :: Int -> HanjaRenderingOption -> ShowS # show :: HanjaRenderingOption -> String # showList :: [HanjaRenderingOption] -> ShowS #
Eq HanjaRenderingOption Source #
Instance details Defined in Text.Seonbi.Facade Methods (==) :: HanjaRenderingOption -> HanjaRenderingOption -> Bool # (/=) :: HanjaRenderingOption -> HanjaRenderingOption -> Bool #
type Rep HanjaRenderingOption Source #
Instance details Defined in Text.Seonbi.Facade type Rep HanjaRenderingOption = D1 ('MetaData "HanjaRenderingOption" "Text.Seonbi.Facade" "seonbi-0.4.0-FOhxpaKIZkM2yOPV4QhpsQ" 'False) ((C1 ('MetaCons "HangulOnly" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "HanjaInParentheses" 'PrefixI 'False) (U1 :: Type -> Type)) :+: (C1 ('MetaCons "DisambiguatingHanjaInParentheses" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "HanjaInRuby" 'PrefixI 'False) (U1 :: Type -> Type)))

data QuoteOption Source #

An option to decide how quotation marks are rendered.

Constructors

CurvedQuotes	English-style curved quotes (`‘`: U+2018, `’`: U+2019, `“`: U+201C, `”`: U+201D), which are used by South Korean orthography.
VerticalCornerBrackets	Vertical corner brackets (`﹁`: U+FE41, `﹂`: U+FE42, `﹃`: U+FE43, `﹄`: U+FE44), which are used by East Asian orthography.
HorizontalCornerBrackets	Traditional horizontal corner brackets (`「`: U+300C, `」`: U+300D, `『`: U+300E, `』`: U+300F), which are used by East Asian orthography.
Guillemets	East Asian guillemets (`〈`: U+3008, `〉`: U+3009, `《`: U+300A, `》`: U+300B), which are used by North Korean orthography.
CurvedSingleQuotesWithQ	Use English-style curved quotes (`‘`: U+2018, `’`: U+2019) for single quotes, and HTML `<q>` tags for double quotes.
VerticalCornerBracketsWithQ	Use vertical corner brackets (`﹁`: U+FE41, `﹂`: U+FE42) for single quotes, and HTML `<q>` tags for double quotes.
HorizontalCornerBracketsWithQ	Use horizontal corner brackets (`「`: U+300C, `」`: U+300D) for single quotes, and HTML `<q>` tags for double quotes.

Instances

Instances details

Enum QuoteOption Source #
Instance details Defined in Text.Seonbi.Facade Methods succ :: QuoteOption -> QuoteOption # pred :: QuoteOption -> QuoteOption # toEnum :: Int -> QuoteOption # fromEnum :: QuoteOption -> Int # enumFrom :: QuoteOption -> [QuoteOption] # enumFromThen :: QuoteOption -> QuoteOption -> [QuoteOption] # enumFromTo :: QuoteOption -> QuoteOption -> [QuoteOption] # enumFromThenTo :: QuoteOption -> QuoteOption -> QuoteOption -> [QuoteOption] #
Generic QuoteOption Source #
Instance details Defined in Text.Seonbi.Facade Associated Types type Rep QuoteOption :: Type -> Type # Methods from :: QuoteOption -> Rep QuoteOption x # to :: Rep QuoteOption x -> QuoteOption #
Read QuoteOption Source #
Instance details Defined in Text.Seonbi.Facade Methods readsPrec :: Int -> ReadS QuoteOption # readList :: ReadS [QuoteOption] # readPrec :: ReadPrec QuoteOption # readListPrec :: ReadPrec [QuoteOption] #
Show QuoteOption Source #
Instance details Defined in Text.Seonbi.Facade Methods showsPrec :: Int -> QuoteOption -> ShowS # show :: QuoteOption -> String # showList :: [QuoteOption] -> ShowS #
Eq QuoteOption Source #
Instance details Defined in Text.Seonbi.Facade Methods (==) :: QuoteOption -> QuoteOption -> Bool # (/=) :: QuoteOption -> QuoteOption -> Bool #
type Rep QuoteOption Source #
Instance details Defined in Text.Seonbi.Facade type Rep QuoteOption = D1 ('MetaData "QuoteOption" "Text.Seonbi.Facade" "seonbi-0.4.0-FOhxpaKIZkM2yOPV4QhpsQ" 'False) ((C1 ('MetaCons "CurvedQuotes" 'PrefixI 'False) (U1 :: Type -> Type) :+: (C1 ('MetaCons "VerticalCornerBrackets" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "HorizontalCornerBrackets" 'PrefixI 'False) (U1 :: Type -> Type))) :+: ((C1 ('MetaCons "Guillemets" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "CurvedSingleQuotesWithQ" 'PrefixI 'False) (U1 :: Type -> Type)) :+: (C1 ('MetaCons "VerticalCornerBracketsWithQ" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "HorizontalCornerBracketsWithQ" 'PrefixI 'False) (U1 :: Type -> Type))))

data StopOption Source #

Settings to normalize stops (periods, commas, and interpuncts) in docs.

Constructors

Horizontal

Stop sentences in the modern Korean style which follows Western stops. E.g.:

봄·여름·가을·겨울. 어제, 오늘.

HorizontalWithSlashes

Similar to horizontalStops except slashes are used instead of interpuncts. E.g.:

봄/여름/가을/겨울. 어제, 오늘.

Vertical

Stop sentences in the pre-modern Korean style which follows Chinese stops. E.g.:

봄·여름·가을·겨울。어제、오늘。

Instances

Instances details

Enum StopOption Source #
Instance details Defined in Text.Seonbi.Facade Methods succ :: StopOption -> StopOption # pred :: StopOption -> StopOption # toEnum :: Int -> StopOption # fromEnum :: StopOption -> Int # enumFrom :: StopOption -> [StopOption] # enumFromThen :: StopOption -> StopOption -> [StopOption] # enumFromTo :: StopOption -> StopOption -> [StopOption] # enumFromThenTo :: StopOption -> StopOption -> StopOption -> [StopOption] #
Generic StopOption Source #
Instance details Defined in Text.Seonbi.Facade Associated Types type Rep StopOption :: Type -> Type # Methods from :: StopOption -> Rep StopOption x # to :: Rep StopOption x -> StopOption #
Read StopOption Source #
Instance details Defined in Text.Seonbi.Facade Methods readsPrec :: Int -> ReadS StopOption # readList :: ReadS [StopOption] # readPrec :: ReadPrec StopOption # readListPrec :: ReadPrec [StopOption] #
Show StopOption Source #
Instance details Defined in Text.Seonbi.Facade Methods showsPrec :: Int -> StopOption -> ShowS # show :: StopOption -> String # showList :: [StopOption] -> ShowS #
Eq StopOption Source #
Instance details Defined in Text.Seonbi.Facade Methods (==) :: StopOption -> StopOption -> Bool # (/=) :: StopOption -> StopOption -> Bool #
type Rep StopOption Source #
Instance details Defined in Text.Seonbi.Facade type Rep StopOption = D1 ('MetaData "StopOption" "Text.Seonbi.Facade" "seonbi-0.4.0-FOhxpaKIZkM2yOPV4QhpsQ" 'False) (C1 ('MetaCons "Horizontal" 'PrefixI 'False) (U1 :: Type -> Type) :+: (C1 ('MetaCons "HorizontalWithSlashes" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "Vertical" 'PrefixI 'False) (U1 :: Type -> Type)))