Safe Haskell | Safe-Inferred |
---|---|
Language | GHC2021 |
Synopsis
- data DevanagariToken
- data Vowel
- data Consonant
- data Digit
- type Tokenizer = Text -> Seq DevanagariToken
- tokenize :: Tokenizer
- selectTokenizerByContent :: Text -> Tokenizer
- fromDevanagari :: Tokenizer
- fromIso :: Tokenizer
- fromHarvard :: Tokenizer
- fromIast :: Tokenizer
- toDevanagari :: Generator
- toIso :: Generator
- toHarvard :: Generator
- toIast :: Generator
- tokenMap :: [(Text, Text, Text, Text)]
- tokenMapToMd :: Text
- tokenMapToHtml :: Text
Documentation
data DevanagariToken Source #
Vow Vowel | |
Cons Consonant | |
Dig Digit | |
Anusvara | |
Anunasika | |
Visarga | |
Avagraha | |
Virama | |
OM | |
PurnaViram | |
DeerghViram | |
ZWNJ | |
ZWJ | |
Unmapped Char |
Instances
Show DevanagariToken Source # | |
Defined in Data.Char.Devanagari.DevanagariTokens showsPrec :: Int -> DevanagariToken -> ShowS # show :: DevanagariToken -> String # showList :: [DevanagariToken] -> ShowS # | |
Eq DevanagariToken Source # | |
Defined in Data.Char.Devanagari.DevanagariTokens (==) :: DevanagariToken -> DevanagariToken -> Bool # (/=) :: DevanagariToken -> DevanagariToken -> Bool # | |
Ord DevanagariToken Source # | |
Defined in Data.Char.Devanagari.DevanagariTokens compare :: DevanagariToken -> DevanagariToken -> Ordering # (<) :: DevanagariToken -> DevanagariToken -> Bool # (<=) :: DevanagariToken -> DevanagariToken -> Bool # (>) :: DevanagariToken -> DevanagariToken -> Bool # (>=) :: DevanagariToken -> DevanagariToken -> Bool # max :: DevanagariToken -> DevanagariToken -> DevanagariToken # min :: DevanagariToken -> DevanagariToken -> DevanagariToken # |
K | |
C | |
Tdot | |
T | |
P | |
G | |
J | |
Ddot | |
D | |
B | |
Ntop | |
Ntild | |
Ndot | |
N | |
M | |
H | |
Y | |
R | |
L | |
V | |
Z | |
F | |
Stop | |
Sdot | |
S | |
KH | |
CH | |
TdotH | |
TH | |
PH | |
GH | |
JH | |
DdotH | |
DH | |
BH | |
Gtop |
Instances
Bounded Consonant Source # | |
Enum Consonant Source # | |
Defined in Data.Char.Devanagari.DevanagariTokens succ :: Consonant -> Consonant # pred :: Consonant -> Consonant # fromEnum :: Consonant -> Int # enumFrom :: Consonant -> [Consonant] # enumFromThen :: Consonant -> Consonant -> [Consonant] # enumFromTo :: Consonant -> Consonant -> [Consonant] # enumFromThenTo :: Consonant -> Consonant -> Consonant -> [Consonant] # | |
Show Consonant Source # | |
Eq Consonant Source # | |
Ord Consonant Source # | |
Defined in Data.Char.Devanagari.DevanagariTokens |
type Tokenizer = Text -> Seq DevanagariToken Source #
A Tokenizer is a function that takes a Text as input and produces a Sequence of DevanagariToken instances as output.
tokenize :: Tokenizer Source #
tokenize a string of Text into a sequence of DevanagariTokens. The actual tokenizer is selected based on the content of the input string. This tokenizer is then applied to the input string.
selectTokenizerByContent :: Text -> Tokenizer Source #
select the correct tokenizer based on the content of the input string.
fromDevanagari :: Tokenizer Source #
a tokenizer function that parses a Text containing Devanagari script into a Sequence of DevanagariToken instances.
a tokenizer function that parses a Text containing ISO15919 encoded Devanagari script into a Sequence of DevanagariToken instances.
fromHarvard :: Tokenizer Source #
a tokenizer function that parses a Text containing Harvard-Kyoto encoded Devanagari script into a Sequence of DevanagariToken instances.
fromIast :: Tokenizer Source #
a tokenizer function that parses a Text containing IAST encoded Devanagari script into a Sequence of DevanagariToken instances.
toDevanagari :: Generator Source #
tokenMap :: [(Text, Text, Text, Text)] Source #
returns a list of tuples containing all available characters in all four encodings.
tokenMapToMd :: Text Source #
this function creates a markdown table containing the complete character map in all four encodings.
tokenMapToHtml :: Text Source #
this function creates an html table containing the complete character map in all four encodings.