regex-tdfa-1.3.1.0: Pure Haskell Tagged DFA Backend for "Text.Regex" (regex-base)

Safe HaskellNone
LanguageHaskell2010

Text.Regex.TDFA.Common

Description

Common provides simple functions to the backend. It defines most of the data types. All modules should call error via the common_error function below.

Synopsis

Documentation

look :: Int -> IntMap a -> a #

on :: (t1 -> t1 -> t2) -> (t -> t1) -> t -> t -> t2 #

norep :: Eq a => [a] -> [a] #

after sort or sortBy the use of 'nub'\/'nubBy' can be replaced by 'norep'\/'norepBy'

norepBy :: (a -> a -> Bool) -> [a] -> [a] #

after sort or sortBy the use of 'nub'\/'nubBy' can be replaced by 'norep'\/'norepBy'

mapFst :: Functor f => (t -> t2) -> f (t, t1) -> f (t2, t1) #

mapSnd :: Functor f => (t1 -> t2) -> f (t, t1) -> f (t, t2) #

fst3 :: (a, b, c) -> a #

snd3 :: (a, b, c) -> b #

thd3 :: (a, b, c) -> c #

newtype DoPa #

Used to track elements of the pattern that accept characters or are anchors

Constructors

DoPa 

Fields

Instances
Enum DoPa # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

succ :: DoPa -> DoPa #

pred :: DoPa -> DoPa #

toEnum :: Int -> DoPa #

fromEnum :: DoPa -> Int #

enumFrom :: DoPa -> [DoPa] #

enumFromThen :: DoPa -> DoPa -> [DoPa] #

enumFromTo :: DoPa -> DoPa -> [DoPa] #

enumFromThenTo :: DoPa -> DoPa -> DoPa -> [DoPa] #

Eq DoPa # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

(==) :: DoPa -> DoPa -> Bool #

(/=) :: DoPa -> DoPa -> Bool #

Ord DoPa # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

compare :: DoPa -> DoPa -> Ordering #

(<) :: DoPa -> DoPa -> Bool #

(<=) :: DoPa -> DoPa -> Bool #

(>) :: DoPa -> DoPa -> Bool #

(>=) :: DoPa -> DoPa -> Bool #

max :: DoPa -> DoPa -> DoPa #

min :: DoPa -> DoPa -> DoPa #

Show DoPa # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

showsPrec :: Int -> DoPa -> ShowS #

show :: DoPa -> String #

showList :: [DoPa] -> ShowS #

data CompOption #

Control whether the pattern is multiline or case-sensitive like Text.Regex and whether to capture the subgroups (\1, \2, etc). Controls enabling extra anchor syntax.

Constructors

CompOption 

Fields

  • caseSensitive :: Bool

    True in blankCompOpt and defaultCompOpt

  • multiline :: Bool

    False in blankCompOpt, True in defaultCompOpt. Compile for newline-sensitive matching. "By default, newline is a completely ordinary character with no special meaning in either REs or strings. With this flag, inverted bracket expressions and . never match newline, a ^ anchor matches the null string after any newline in the string in addition to its normal function, and the $ anchor matches the null string before any newline in the string in addition to its normal function."

  • rightAssoc :: Bool

    True (and therefore Right associative) in blankCompOpt and defaultCompOpt

  • newSyntax :: Bool

    False in blankCompOpt, True in defaultCompOpt. Add the extended non-POSIX syntax described in Text.Regex.TDFA haddock documentation.

  • lastStarGreedy :: Bool

    False by default. This is POSIX correct but it takes space and is slower. Setting this to true will improve performance, and should be done if you plan to set the captureGroups execoption to False.

Instances
Read CompOption # 
Instance details

Defined in Text.Regex.TDFA.Common

Show CompOption # 
Instance details

Defined in Text.Regex.TDFA.Common

RegexOptions Regex CompOption ExecOption # 
Instance details

Defined in Text.Regex.TDFA.Common

RegexMaker Regex CompOption ExecOption String # 
Instance details

Defined in Text.Regex.TDFA.String

RegexMaker Regex CompOption ExecOption ByteString # 
Instance details

Defined in Text.Regex.TDFA.ByteString.Lazy

RegexMaker Regex CompOption ExecOption ByteString # 
Instance details

Defined in Text.Regex.TDFA.ByteString

RegexMaker Regex CompOption ExecOption Text #

Since: 1.3.1

Instance details

Defined in Text.Regex.TDFA.Text.Lazy

RegexMaker Regex CompOption ExecOption Text #

Since: 1.3.1

Instance details

Defined in Text.Regex.TDFA.Text

RegexMaker Regex CompOption ExecOption (Seq Char) # 
Instance details

Defined in Text.Regex.TDFA.Sequence

data ExecOption #

Constructors

ExecOption 

Fields

Instances
Read ExecOption # 
Instance details

Defined in Text.Regex.TDFA.Common

Show ExecOption # 
Instance details

Defined in Text.Regex.TDFA.Common

RegexOptions Regex CompOption ExecOption # 
Instance details

Defined in Text.Regex.TDFA.Common

RegexMaker Regex CompOption ExecOption String # 
Instance details

Defined in Text.Regex.TDFA.String

RegexMaker Regex CompOption ExecOption ByteString # 
Instance details

Defined in Text.Regex.TDFA.ByteString.Lazy

RegexMaker Regex CompOption ExecOption ByteString # 
Instance details

Defined in Text.Regex.TDFA.ByteString

RegexMaker Regex CompOption ExecOption Text #

Since: 1.3.1

Instance details

Defined in Text.Regex.TDFA.Text.Lazy

RegexMaker Regex CompOption ExecOption Text #

Since: 1.3.1

Instance details

Defined in Text.Regex.TDFA.Text

RegexMaker Regex CompOption ExecOption (Seq Char) # 
Instance details

Defined in Text.Regex.TDFA.Sequence

type Tag = Int #

Used by implementation to name certain Postions during matching. Identity of Position tag to set during a transition

data OP #

Internal use to indicate type of tag and preference for larger or smaller Positions

Constructors

Maximize 
Minimize 
Orbit 
Ignore 
Instances
Eq OP # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

(==) :: OP -> OP -> Bool #

(/=) :: OP -> OP -> Bool #

Show OP # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

showsPrec :: Int -> OP -> ShowS #

show :: OP -> String #

showList :: [OP] -> ShowS #

type Index = Int #

Internal NFA node identity number

type SetIndex = IntSet #

Internal DFA identity is this Set of NFA Index

type Position = Int #

Index into the text being searched

type GroupIndex = Int #

GroupIndex is for indexing submatches from capturing parenthesized groups (PGroup/Group)

data GroupInfo #

GroupInfo collects the parent and tag information for an instance of a group

Instances
Show GroupInfo # 
Instance details

Defined in Text.Regex.TDFA.Common

data Regex #

The TDFA backend specific Regex type, used by this module's RegexOptions and RegexMaker

Constructors

Regex 

Fields

Instances
RegexLike Regex String # 
Instance details

Defined in Text.Regex.TDFA.String

RegexLike Regex ByteString # 
Instance details

Defined in Text.Regex.TDFA.ByteString.Lazy

RegexLike Regex ByteString # 
Instance details

Defined in Text.Regex.TDFA.ByteString

RegexLike Regex Text #

Since: 1.3.1

Instance details

Defined in Text.Regex.TDFA.Text.Lazy

RegexLike Regex Text #

Since: 1.3.1

Instance details

Defined in Text.Regex.TDFA.Text

RegexOptions Regex CompOption ExecOption # 
Instance details

Defined in Text.Regex.TDFA.Common

RegexContext Regex String String # 
Instance details

Defined in Text.Regex.TDFA.String

Methods

match :: Regex -> String -> String #

matchM :: MonadFail m => Regex -> String -> m String #

RegexContext Regex ByteString ByteString # 
Instance details

Defined in Text.Regex.TDFA.ByteString.Lazy

RegexContext Regex ByteString ByteString # 
Instance details

Defined in Text.Regex.TDFA.ByteString

RegexContext Regex Text Text #

Since: 1.3.1

Instance details

Defined in Text.Regex.TDFA.Text.Lazy

Methods

match :: Regex -> Text -> Text #

matchM :: MonadFail m => Regex -> Text -> m Text #

RegexContext Regex Text Text #

Since: 1.3.1

Instance details

Defined in Text.Regex.TDFA.Text

Methods

match :: Regex -> Text -> Text #

matchM :: MonadFail m => Regex -> Text -> m Text #

RegexMaker Regex CompOption ExecOption String # 
Instance details

Defined in Text.Regex.TDFA.String

RegexMaker Regex CompOption ExecOption ByteString # 
Instance details

Defined in Text.Regex.TDFA.ByteString.Lazy

RegexMaker Regex CompOption ExecOption ByteString # 
Instance details

Defined in Text.Regex.TDFA.ByteString

RegexMaker Regex CompOption ExecOption Text #

Since: 1.3.1

Instance details

Defined in Text.Regex.TDFA.Text.Lazy

RegexMaker Regex CompOption ExecOption Text #

Since: 1.3.1

Instance details

Defined in Text.Regex.TDFA.Text

RegexMaker Regex CompOption ExecOption (Seq Char) # 
Instance details

Defined in Text.Regex.TDFA.Sequence

RegexLike Regex (Seq Char) # 
Instance details

Defined in Text.Regex.TDFA.Sequence

RegexContext Regex (Seq Char) (Seq Char) # 
Instance details

Defined in Text.Regex.TDFA.Sequence

Methods

match :: Regex -> Seq Char -> Seq Char #

matchM :: MonadFail m => Regex -> Seq Char -> m (Seq Char) #

data QNFA #

Internal NFA node type

Constructors

QNFA 

Fields

Instances
Show QNFA # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

showsPrec :: Int -> QNFA -> ShowS #

show :: QNFA -> String #

showList :: [QNFA] -> ShowS #

data QT #

Internal to QNFA type.

Constructors

Simple 

Fields

Testing 

Fields

Instances
Eq QT # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

(==) :: QT -> QT -> Bool #

(/=) :: QT -> QT -> Bool #

Show QT # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

showsPrec :: Int -> QT -> ShowS #

show :: QT -> String #

showList :: [QT] -> ShowS #

type QTrans = IntMap [TagCommand] #

Internal type to represent the tagged transition from one QNFA to another (or itself). The key is the Index of the destination QNFA.

data WhichTest #

Known predicates, just Beginning of Line (^) and End of Line ($). Also support for GNU extensions is being added: \` beginning of buffer, \' end of buffer, \< and \> for begin and end of words, \b and \B for word boundary and not word boundary.

data TagTask #

The things that can be done with a Tag. TagTask and ResetGroupStopTask are for tags with Maximize or Minimize OP values. ResetOrbitTask and EnterOrbitTask and LeaveOrbitTask are for tags with Orbit OP value.

Instances
Eq TagTask # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

(==) :: TagTask -> TagTask -> Bool #

(/=) :: TagTask -> TagTask -> Bool #

Show TagTask # 
Instance details

Defined in Text.Regex.TDFA.Common

type TagTasks = [(Tag, TagTask)] #

Ordered list of tags and their associated Task

data TagUpdate #

When attached to a QTrans the TagTask can be done before or after accepting the character.

Instances
Eq TagUpdate # 
Instance details

Defined in Text.Regex.TDFA.Common

Show TagUpdate # 
Instance details

Defined in Text.Regex.TDFA.Common

type TagList = [(Tag, TagUpdate)] #

Ordered list of tags and their associated update operation.

type TagCommand = (DoPa, TagList) #

A TagList and the location of the item in the original pattern that is being accepted.

type WinTags = TagList #

Ordered list of tags and their associated update operation to perform on an empty transition to the virtual winning state.

data DFA #

Internal DFA node, identified by the Set of indices of the QNFA nodes it represents.

Constructors

DFA 

Fields

Instances
Show DFA # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

showsPrec :: Int -> DFA -> ShowS #

show :: DFA -> String #

showList :: [DFA] -> ShowS #

data Transition #

Constructors

Transition 

Fields

data DT #

Internal to the DFA node

Constructors

Simple' 

Fields

Testing' 

Fields

Instances
Show DT # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

showsPrec :: Int -> DT -> ShowS #

show :: DT -> String #

showList :: [DT] -> ShowS #

type DTrans = IntMap (IntMap (DoPa, Instructions)) #

Internal type to repesent the commands for the tagged transition. The outer IntMap is for the destination Index and the inner IntMap is for the Source Index. This is convenient since all runtime data going to the same destination must be compared to find the best.

A Destination IntMap entry may have an empty Source IntMap if and only if the destination is the starting index and the NFA/DFA. This instructs the matching engine to spawn a new entry starting at the post-update position.

type DTrans' = [(Index, [(Index, (DoPa, ([(Tag, (Position, Bool))], [String])))])] #

Internal convenience type for the text display code

data Orbits #

Positions for which a * was re-started while looping. Need to append locations at back but compare starting with front, so use Seq as a Queue. The initial position is saved in basePos (and a Maximize Tag), the middle positions in the Seq, and the final position is NOT saved in the Orbits (only in a Maximize Tag).

The orderinal code is being written XXX TODO document it.

Constructors

Orbits 
Instances
Show Orbits # 
Instance details

Defined in Text.Regex.TDFA.Common

data Instructions #

The newPos and newFlags lists in Instructions are sorted by, and unique in, the Tag values

Constructors

Instructions 
Instances
Show Instructions # 
Instance details

Defined in Text.Regex.TDFA.Common

data Action #

Constructors

SetPre 
SetPost 
SetVal Int 
Instances
Eq Action # 
Instance details

Defined in Text.Regex.TDFA.Common

Methods

(==) :: Action -> Action -> Bool #

(/=) :: Action -> Action -> Bool #

Show Action # 
Instance details

Defined in Text.Regex.TDFA.Common