Safe Haskell	Safe-Inferred
Language	Haskell2010

Text.Regex.TDFA.Pattern

Contents

Internal use
Internal use, operations to support debugging under ghci

Description

This Text.Regex.TDFA.Pattern module provides the Pattern data type and its subtypes. This Pattern type is used to represent the parsed form of a regular expression.

Synopsis

data Pattern
- = PEmpty
- | PGroup (Maybe GroupIndex) Pattern
- | POr [Pattern]
- | PConcat [Pattern]
- | PQuest Pattern
- | PPlus Pattern
- | PStar Bool Pattern
- | PBound Int (Maybe Int) Pattern
- | PCarat {
  - getDoPa :: DoPa
  }
- | PDollar {
  - getDoPa :: DoPa
  }
- | PDot {
  - getDoPa :: DoPa
  }
- | PAny {
  - getDoPa :: DoPa
  - getPatternSet :: PatternSet
  }
- | PAnyNot {
  - getDoPa :: DoPa
  - getPatternSet :: PatternSet
  }
- | PEscape {
  - getDoPa :: DoPa
  - getPatternChar :: Char
  }
- | PChar {
  - getDoPa :: DoPa
  - getPatternChar :: Char
  }
- | PNonCapture Pattern
- | PNonEmpty Pattern
data PatternSet = PatternSet (Maybe (Set Char)) (Maybe (Set PatternSetCharacterClass)) (Maybe (Set PatternSetCollatingElement)) (Maybe (Set PatternSetEquivalenceClass))
newtype PatternSetCharacterClass = PatternSetCharacterClass {
- unSCC :: String
}
newtype PatternSetCollatingElement = PatternSetCollatingElement {
- unSCE :: String
}
newtype PatternSetEquivalenceClass = PatternSetEquivalenceClass {
- unSEC :: String
}
type GroupIndex = Int
newtype DoPa = DoPa {
- dopaIndex :: Int
}
decodeCharacterClass :: PatternSetCharacterClass -> String
decodePatternSet :: PatternSet -> Set Char
showPattern :: Pattern -> String
starTrans :: Pattern -> Pattern
starTrans' :: Pattern -> Pattern
simplify' :: Pattern -> Pattern
dfsPattern :: (Pattern -> Pattern) -> Pattern -> Pattern

Documentation

data Pattern Source #

Pattern is the type returned by the regular expression parser parseRegex. This is consumed by the Text.Regex.TDFA.CorePattern module and the tender leaves are nibbled by the Text.Regex.TDFA.TNFA module.

The DoPa field is the index of the component in the regex string r.

Constructors

PEmpty	`()`, matches the empty string.
PGroup (Maybe GroupIndex) Pattern	Group `(r)`. `Nothing` indicates non-matching `PGroup` (never produced by parser `parseRegex`).
POr [Pattern]	Alternative `r\|s` (flattened by `starTrans`).
PConcat [Pattern]	Sequence `rs` (flattened by `starTrans`).
PQuest Pattern	Zero or one repetitions `r?` (eliminated by `starTrans`).
PPlus Pattern	One or more repetitions `r+` (eliminated by `starTrans`).
PStar Bool Pattern	Zero or more repetitions `r*`. `True` (default) means may accept the empty string on its first iteration.
PBound Int (Maybe Int) Pattern	Given number or repetitions `r{n}` or `r{n,m}` (eliminated by `starTrans`).
PCarat	`^` matches beginning of input.
Fields getDoPa :: DoPa
PDollar	`$` matches end of input.
Fields getDoPa :: DoPa
PDot	`.` matches any character.
Fields getDoPa :: DoPa
PAny	Bracket expression `[...]`.
Fields getDoPa :: DoPa getPatternSet :: PatternSet
PAnyNot	Inverted bracket expression `[^...]`.
Fields getDoPa :: DoPa getPatternSet :: PatternSet
PEscape	Backslashed character `c`, may have special meaning.
Fields getDoPa :: DoPa getPatternChar :: Char
PChar	Single character, matches given character.
Fields getDoPa :: DoPa getPatternChar :: Char
PNonCapture Pattern	Tag for internal use, introduced by `starTrans`.
PNonEmpty Pattern	Tag for internal use, introduced by `starTrans`.

Instances

Instances details

Show Pattern Source #
Instance details Defined in Text.Regex.TDFA.Pattern Methods showsPrec :: Int -> Pattern -> ShowS # show :: Pattern -> String # showList :: [Pattern] -> ShowS #
Eq Pattern Source #
Instance details Defined in Text.Regex.TDFA.Pattern Methods (==) :: Pattern -> Pattern -> Bool # (/=) :: Pattern -> Pattern -> Bool #

data PatternSet Source #

Content of a bracket expression [...] organized into characters, POSIX character classes (e.g. [[:alnum:]]), collating elements (e.g. [.ch.], unused), and equivalence classes (e.g. [=a=], treated as characters).

Constructors

PatternSet (Maybe (Set Char)) (Maybe (Set PatternSetCharacterClass)) (Maybe (Set PatternSetCollatingElement)) (Maybe (Set PatternSetEquivalenceClass))

Instances

Instances details

Show PatternSet Source #	Hand-rolled implementation, giving textual rather than Haskell representation.
Instance details Defined in Text.Regex.TDFA.Pattern Methods showsPrec :: Int -> PatternSet -> ShowS # show :: PatternSet -> String # showList :: [PatternSet] -> ShowS #
Eq PatternSet Source #
Instance details Defined in Text.Regex.TDFA.Pattern Methods (==) :: PatternSet -> PatternSet -> Bool # (/=) :: PatternSet -> PatternSet -> Bool #

newtype PatternSetCharacterClass Source #

Content of [: :], e.g. "alnum" for [:alnum:].

Constructors

PatternSetCharacterClass
Fields unSCC :: String

Instances

Instances details

Show PatternSetCharacterClass Source #	Hand-rolled implementation, giving textual rather than Haskell representation.
Instance details Defined in Text.Regex.TDFA.Pattern Methods showsPrec :: Int -> PatternSetCharacterClass -> ShowS # show :: PatternSetCharacterClass -> String # showList :: [PatternSetCharacterClass] -> ShowS #
Eq PatternSetCharacterClass Source #
Instance details Defined in Text.Regex.TDFA.Pattern Methods (==) :: PatternSetCharacterClass -> PatternSetCharacterClass -> Bool # (/=) :: PatternSetCharacterClass -> PatternSetCharacterClass -> Bool #
Ord PatternSetCharacterClass Source #
Instance details Defined in Text.Regex.TDFA.Pattern Methods compare :: PatternSetCharacterClass -> PatternSetCharacterClass -> Ordering # (<) :: PatternSetCharacterClass -> PatternSetCharacterClass -> Bool # (<=) :: PatternSetCharacterClass -> PatternSetCharacterClass -> Bool # (>) :: PatternSetCharacterClass -> PatternSetCharacterClass -> Bool # (>=) :: PatternSetCharacterClass -> PatternSetCharacterClass -> Bool # max :: PatternSetCharacterClass -> PatternSetCharacterClass -> PatternSetCharacterClass # min :: PatternSetCharacterClass -> PatternSetCharacterClass -> PatternSetCharacterClass #

newtype PatternSetCollatingElement Source #

Content of [. .], e.g. "ch" for [.ch.].

Constructors

PatternSetCollatingElement
Fields unSCE :: String

Instances

Instances details

Show PatternSetCollatingElement Source #	Hand-rolled implementation, giving textual rather than Haskell representation.
Instance details Defined in Text.Regex.TDFA.Pattern Methods showsPrec :: Int -> PatternSetCollatingElement -> ShowS # show :: PatternSetCollatingElement -> String # showList :: [PatternSetCollatingElement] -> ShowS #
Eq PatternSetCollatingElement Source #
Instance details Defined in Text.Regex.TDFA.Pattern Methods (==) :: PatternSetCollatingElement -> PatternSetCollatingElement -> Bool # (/=) :: PatternSetCollatingElement -> PatternSetCollatingElement -> Bool #
Ord PatternSetCollatingElement Source #
Instance details Defined in Text.Regex.TDFA.Pattern Methods compare :: PatternSetCollatingElement -> PatternSetCollatingElement -> Ordering # (<) :: PatternSetCollatingElement -> PatternSetCollatingElement -> Bool # (<=) :: PatternSetCollatingElement -> PatternSetCollatingElement -> Bool # (>) :: PatternSetCollatingElement -> PatternSetCollatingElement -> Bool # (>=) :: PatternSetCollatingElement -> PatternSetCollatingElement -> Bool # max :: PatternSetCollatingElement -> PatternSetCollatingElement -> PatternSetCollatingElement # min :: PatternSetCollatingElement -> PatternSetCollatingElement -> PatternSetCollatingElement #

newtype PatternSetEquivalenceClass Source #

Content of [= =], e.g. "a" for [=a=].

Constructors

PatternSetEquivalenceClass
Fields unSEC :: String

Instances

Instances details

Show PatternSetEquivalenceClass Source #	Hand-rolled implementation, giving textual rather than Haskell representation.
Instance details Defined in Text.Regex.TDFA.Pattern Methods showsPrec :: Int -> PatternSetEquivalenceClass -> ShowS # show :: PatternSetEquivalenceClass -> String # showList :: [PatternSetEquivalenceClass] -> ShowS #
Eq PatternSetEquivalenceClass Source #
Instance details Defined in Text.Regex.TDFA.Pattern Methods (==) :: PatternSetEquivalenceClass -> PatternSetEquivalenceClass -> Bool # (/=) :: PatternSetEquivalenceClass -> PatternSetEquivalenceClass -> Bool #
Ord PatternSetEquivalenceClass Source #
Instance details Defined in Text.Regex.TDFA.Pattern Methods compare :: PatternSetEquivalenceClass -> PatternSetEquivalenceClass -> Ordering # (<) :: PatternSetEquivalenceClass -> PatternSetEquivalenceClass -> Bool # (<=) :: PatternSetEquivalenceClass -> PatternSetEquivalenceClass -> Bool # (>) :: PatternSetEquivalenceClass -> PatternSetEquivalenceClass -> Bool # (>=) :: PatternSetEquivalenceClass -> PatternSetEquivalenceClass -> Bool # max :: PatternSetEquivalenceClass -> PatternSetEquivalenceClass -> PatternSetEquivalenceClass # min :: PatternSetEquivalenceClass -> PatternSetEquivalenceClass -> PatternSetEquivalenceClass #

type GroupIndex = Int Source #

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

newtype DoPa Source #

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

Constructors

DoPa
Fields dopaIndex :: Int

Instances

Instances details

Enum DoPa Source #
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] #
Show DoPa Source #
Instance details Defined in Text.Regex.TDFA.Common Methods showsPrec :: Int -> DoPa -> ShowS # show :: DoPa -> String # showList :: [DoPa] -> ShowS #
Eq DoPa Source #
Instance details Defined in Text.Regex.TDFA.Common Methods (==) :: DoPa -> DoPa -> Bool # (/=) :: DoPa -> DoPa -> Bool #
Ord DoPa Source #
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 #

decodeCharacterClass :: PatternSetCharacterClass -> String Source #

This returns the strictly ascending list of characters represented by [: :] POSIX character classes. Unrecognized class names return an empty string.

Since: 1.3.2

decodePatternSet :: PatternSet -> Set Char Source #

decodePatternSet cannot handle collating element and treats equivalence classes as just their definition and nothing more.

Since: 1.3.2

showPattern :: Pattern -> String Source #

Internal use

starTrans :: Pattern -> Pattern Source #

Do the transformation and simplification in a single traversal. This removes the PPlus, PQuest, and PBound values, changing to POr and PEmpty and PStar. For some PBound values it adds PNonEmpty and PNonCapture semantic marker. It also simplifies to flatten out nested POr and PConcat instances and eliminate some unneeded PEmpty values.