Text.Regex.XMLSchema.String.Regex

W3C XML Schema Regular Expression Matcher

Grammar can be found under http://www.w3.org/TR/xmlschema11-2/#regexs

Documentation

type Regex = GenRegex String

data GenRegex l

Instances

Eq l => Eq (GenRegex l)

Ord l => Ord (GenRegex l)

Show l => Show (GenRegex l)

mkZero :: String -> GenRegex l

construct the r.e. for the empty set. An (error-) message may be attached

mkUnit :: GenRegex l

construct the r.e. for the set containing the empty word

mkSym :: CharSet -> GenRegex l

construct the r.e. for a set of chars

mkSym1 :: Char -> GenRegex l

construct an r.e. for a single char set

mkSymRng :: Char -> Char -> GenRegex l

construct an r.e. for an intervall of chars

mkWord :: [Char] -> GenRegex l

mkSym generaized for strings

mkDot :: GenRegex l

construct an r.e. for the set of all Unicode chars

mkStar :: Eq l => GenRegex l -> GenRegex l

construct r.e. for r*

mkAll :: Eq l => GenRegex l

construct an r.e. for the set of all Unicode words

mkAlt :: Eq l => GenRegex l -> GenRegex l -> GenRegex l

construct the r.e for r1|r2

mkElse :: Eq l => GenRegex l -> GenRegex l -> GenRegex l

construct the r.e. for r1{|}r2 (r1 orElse r2).

This represents the same r.e. as r1|r2, but when collecting the results of subexpressions in (...) and r1 succeeds, the subexpressions of r2 are discarded, so r1 matches are prioritized

example

 splitSubex "({1}x)|({2}.)"   "x" = ([("1","x"),("2","x")], "")

 splitSubex "({1}x){|}({2}.)" "x" = ([("1","x")], "")

mkSeq :: GenRegex l -> GenRegex l -> GenRegex l

Construct the sequence r.e. r1.r2

mkSeqs :: [GenRegex l] -> GenRegex l

mkSeq extened to lists

mkRep :: Eq l => Int -> GenRegex l -> GenRegex l

Construct repetition r{i,}

mkRng :: Int -> Int -> GenRegex l -> GenRegex l

Construct range r{i,j}

mkOpt :: GenRegex l -> GenRegex l

Construct option r?

mkDiff :: Eq l => GenRegex l -> GenRegex l -> GenRegex l

Construct difference r.e.: r1 {\} r2

example

 match "[a-z]+{\\}bush" "obama"     = True
 match "[a-z]+{\\}bush" "clinton"   = True
 match "[a-z]+{\\}bush" "bush"      = False     -- not important any more

mkIsect :: Eq l => GenRegex l -> GenRegex l -> GenRegex l

Construct r.e. for intersection: r1 {&} r2

example

 match ".*a.*{&}.*b.*" "-a-b-"  = True
 match ".*a.*{&}.*b.*" "-b-a-"  = True
 match ".*a.*{&}.*b.*" "-a-a-"  = False
 match ".*a.*{&}.*b.*" "---b-"  = False

mkExor :: Eq l => GenRegex l -> GenRegex l -> GenRegex l

Construct r.e. for exclusive or: r1 {^} r2

example

 match "[a-c]+{^}[c-d]+" "abc"  = True
 match "[a-c]+{^}[c-d]+" "acdc" = False
 match "[a-c]+{^}[c-d]+" "ccc"  = False
 match "[a-c]+{^}[c-d]+" "cdc"  = True

mkInterleave :: GenRegex l -> GenRegex l -> GenRegex l

mkCompl :: Eq l => GenRegex l -> GenRegex l

Construct the Complement of an r.e.: whole set of words - r

mkBr :: l -> GenRegex l -> GenRegex l

Construct a labeled subexpression: ({label}r)

isZero :: GenRegex l -> Bool

errRegex :: GenRegex l -> String

nullable :: GenRegex l -> Bool

nullable' :: GenRegex l -> Nullable l

delta1 :: Eq l => GenRegex l -> Char -> GenRegex l

delta :: Eq l => GenRegex l -> String -> GenRegex l

firstChars :: GenRegex l -> CharSet

FIRST for regular expressions

this is only an approximation, the real set of char may be smaller, when the expression contains intersection, set difference or exor operators

matchWithRegex :: Eq l => GenRegex l -> String -> Bool

matchWithRegex' :: Eq l => GenRegex l -> String -> Maybe [(Label l, String)]

splitWithRegex :: Eq l => GenRegex l -> String -> Maybe ([(Label l, String)], String)

This function wraps the whole regex in a subexpression before starting the parse. This is done for getting acces to the whole parsed string. Therfore we need one special label, this label is the Nothing value, all explicit labels are Just labels.

splitWithRegex' :: Eq l => GenRegex l -> String -> Maybe (GenRegex l, String)

The main scanner function

splitWithRegexCS :: Eq l => GenRegex l -> CharSet -> String -> Maybe ([(Label l, String)], String)

splitWithRegexCS' :: Eq l => GenRegex l -> CharSet -> String -> Maybe (GenRegex l, String)

speedup version for splitWithRegex'

This function checks whether the input starts with a char from FIRST re. If this is not the case, the split fails. The FIRST set can be computed once for a whole tokenizer and reused by every call of split