1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255
|
{-# LANGUAGE FlexibleContexts #-}
{-# LANGUAGE CPP #-}
{-# OPTIONS_GHC -fno-warn-duplicate-exports #-}
#if __GLASGOW_HASKELL__ >= 800
{-# OPTIONS_GHC -fno-warn-redundant-constraints #-}
#endif
{-# OPTIONS_GHC -fno-warn-dodgy-exports #-}
{-# OPTIONS_GHC -fno-warn-unused-imports #-}
module Text.RE.TDFA
(
-- * Tutorial
-- $tutorial
-- * About this Module
-- $about
-- * The 'Matches' and 'Match' Operators
(*=~)
, (?=~)
-- * The 'SearchReplace' Operators
, (*=~/)
, (?=~/)
-- * The 'Matches' Type
, Matches
, matchesSource
, allMatches
, anyMatches
, countMatches
, matches
-- * The 'Match' Type
, Match
, matchSource
, matched
, matchedText
-- * The Macros and Parsers
-- $macros
, module Text.RE.TestBench.Parsers
-- * The 'RE' Type
, RE
, regexType
, reOptions
, reSource
, reCaptureNames
, reRegex
-- * Options
-- $options
, SimpleREOptions(..)
, IsOption(..)
, REOptions
, defaultREOptions
, noPreludeREOptions
, unpackSimpleREOptions
-- * Compiling and Escaping REs
, SearchReplace(..)
, compileRegex
, compileRegexWith
, compileRegexWithOptions
, compileSearchReplace
, compileSearchReplaceWith
, compileSearchReplaceWithOptions
, escape
, escapeWith
, escapeWithOptions
, escapeREString
-- * The Classic regex-base Match Operators
, (=~)
, (=~~)
-- * The re Quasi Quoters
-- $re
, re
, reMultilineSensitive
, reMultilineInsensitive
, reBlockSensitive
, reBlockInsensitive
, reMS
, reMI
, reBS
, reBI
, re_
-- * The Ed Quasi Quoters
-- $ed
, ed
, edMultilineSensitive
, edMultilineInsensitive
, edBlockSensitive
, edBlockInsensitive
, edMS
, edMI
, edBS
, edBI
, ed_
-- * The cp Quasi Quoters
, cp
-- * RE Macros Standard Environment
-- $prelude
, prelude
, preludeEnv
, preludeTestsFailing
, preludeTable
, preludeSummary
, preludeSources
, preludeSource
-- * IsRegex
-- $isregex
, module Text.RE.Tools.IsRegex
-- * The IsRegex Instances
-- $instances
, module Text.RE.TDFA.ByteString
, module Text.RE.TDFA.ByteString.Lazy
, module Text.RE.TDFA.Sequence
, module Text.RE.TDFA.String
, module Text.RE.TDFA.Text
, module Text.RE.TDFA.Text.Lazy
) where
import Control.Monad.Fail
import Text.RE.REOptions
import Text.RE.Replace
import Text.RE.TDFA.ByteString()
import Text.RE.TDFA.ByteString.Lazy()
import Text.RE.TDFA.Sequence()
import Text.RE.TDFA.String()
import Text.RE.TDFA.Text()
import Text.RE.TDFA.Text.Lazy()
import Text.RE.TestBench.Parsers
import Text.RE.Tools.IsRegex
import Text.RE.ZeInternals
import Text.RE.ZeInternals.SearchReplace.TDFA
import Text.RE.ZeInternals.TDFA
import qualified Text.Regex.Base as B
import qualified Text.Regex.TDFA as TDFA
-- | find all the matches in the argument text; e.g., to count the number
-- of naturals in s:
--
-- @countMatches $ s *=~ [re|[0-9]+|]@
--
(*=~) :: IsRegex RE s
=> s
-> RE
-> Matches s
(*=~) bs rex = addCaptureNamesToMatches (reCaptureNames rex) $ matchMany rex bs
-- | find the first match in the argument text; e.g., to test if there
-- is a natural number in the input text:
--
-- @matched $ s ?=~ [re|[0-9]+|]@
--
(?=~) :: IsRegex RE s
=> s
-> RE
-> Match s
(?=~) bs rex = addCaptureNamesToMatch (reCaptureNames rex) $ matchOnce rex bs
-- | search and replace all matches in the argument text; e.g., this section
-- will convert every YYYY-MM-DD format date in its argument text into a
-- DD\/MM\/YYYY date:
--
-- @(*=~\/ [ed|${y}([0-9]{4})-0*${m}([0-9]{2})-0*${d}([0-9]{2})\/\/\/${d}\/${m}\/${y}|])@
--
(*=~/) :: IsRegex RE s => s -> SearchReplace RE s -> s
(*=~/) = flip searchReplaceAll
-- | search and replace the first occurrence only
(?=~/) :: IsRegex RE s => s -> SearchReplace RE s -> s
(?=~/) = flip searchReplaceFirst
-- | the regex-base polymorphic match operator
(=~) :: ( B.RegexContext TDFA.Regex s a
, B.RegexMaker TDFA.Regex TDFA.CompOption TDFA.ExecOption s
)
=> s
-> RE
-> a
(=~) bs rex = B.match (reRegex rex) bs
-- | the regex-base monadic, polymorphic match operator
(=~~) :: ( Monad m, MonadFail m
, B.RegexContext TDFA.Regex s a
, B.RegexMaker TDFA.Regex TDFA.CompOption TDFA.ExecOption s
)
=> s
-> RE
-> m a
(=~~) bs rex = B.matchM (reRegex rex) bs
-- $tutorial
-- We have a regex tutorial at <http://tutorial.regex.uk>.
-- $about
-- This module provides access to the back end through polymorphic functions
-- that operate over all of the String\/Text\/ByteString types supported by the
-- back end. The module also provides all of the specialised back-end functionality
-- that will not be needed by most regex clients. If you don't need this generality
-- then you might want to consider using one of the simpler modules that have been
-- specialised for each of these types:
--
-- * "Text.RE.TDFA.ByteString"
-- * "Text.RE.TDFA.ByteString.Lazy"
-- * "Text.RE.TDFA.Sequence"
-- * "Text.RE.TDFA.String"
-- * "Text.RE.TDFA.Text"
-- * "Text.RE.TDFA.Text.Lazy"
-- $macros
-- There are a number of RE macros and corresponding Haskell parsers
-- for parsing the matched text into appropriate Haskell types. See
-- the [Macros Tables](http://regex.uk/macros) for details.
-- $options
-- You can specify different compilation options by appending a
-- to the name of an [re| ... |] or [ed| ... \/\/\/ ... |] quasi quoter
-- to select the corresponding compilation option. For example, the
-- section,
--
-- @(?=~/ [edBlockInsensitive|foo$\/\/\/bar|])@
--
-- will replace a @foo@ suffix of the argument text, of any
-- capitalisation, with a (lower case) @bar@. If you need to specify the
-- options dynamically, use the @[re_| ... |]@ and @[ed_| ... \/\/\/ ... |]@
-- quasi quoters, which generate functions that take an 'IsOption' option
-- (e.g., a 'SimpleReOptions' value) and yields a 'RE' or 'SearchReplace'
-- as appropriate. For example if you have a 'SimpleReOptions' value in
-- @sro@ then
--
-- @(?=~/ [ed_|foo$\/\/\/bar|] sro)@
--
-- will compile the @foo$@ RE according to the value of @sro@. For more
-- on specifying RE options see "Text.RE.REOptions".
-- $re
-- The @[re|.*|]@ quasi quoters, with variants for specifying different
-- options to the RE compiler (see "Text.RE.REOptions"), and the
-- specialised back-end types and functions.
-- $ed
-- The -- | the @[ed| ... \/\/\/ ... |]@ quasi quoters; for example,
--
-- @[ed|${y}([0-9]{4})-0*${m}([0-9]{2})-0*${d}([0-9]{2})\/\/\/${d}\/${m}\/${y}|])@
--
-- represents a @SearchReplace@ that will convert a YYYY-MM-DD format date
-- into a DD\/MM\/YYYY format date.
--
-- The only difference between these quasi quoters is the RE options that are set,
-- using the same conventions as the @[re| ... |]@ quasi quoters.
-- $isregex
-- The 'IsRegex' class is used to abstract over the different regex back ends and
-- the text types they work with -- see "Text.RE.Tools.IsRegex" for details.
-- $instances
--
-- These module exports merely provide the 'IsRegex' instances.
|