File: Sequence.hs

package info (click to toggle)
haskell-regex 1.1.0.2-4
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 424 kB
  • sloc: haskell: 4,533; makefile: 3
file content (219 lines) | stat: -rw-r--r-- 6,666 bytes parent folder | download | duplicates (2)
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
{-# LANGUAGE NoImplicitPrelude              #-}
{-# LANGUAGE MultiParamTypeClasses          #-}
{-# LANGUAGE FlexibleContexts               #-}
{-# LANGUAGE FlexibleInstances              #-}
{-# OPTIONS_GHC -fno-warn-orphans           #-}
{-# OPTIONS_GHC -fno-warn-duplicate-exports #-}
{-# LANGUAGE CPP                            #-}
#if __GLASGOW_HASKELL__ >= 800
{-# OPTIONS_GHC -fno-warn-redundant-constraints #-}
{-# OPTIONS_GHC -fno-warn-unused-imports        #-}
#endif

module Text.RE.TDFA.Sequence
  (
  -- * Tutorial
  -- $tutorial

  -- * 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
  , reSource
  -- * Options
  -- $options
  , SimpleREOptions(..)
  -- * Compiling and Escaping REs
  , SearchReplace(..)
  , compileRegex
  , compileRegexWith
  , compileSearchReplace
  , compileSearchReplaceWith
  , escape
  , escapeWith
  , 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
  , edMultilineSensitive
  , edMultilineInsensitive
  , edBlockSensitive
  , edBlockInsensitive
  , ed
  , edMS
  , edMI
  , edBS
  , edBI
  , ed_
  -- * The cp Quasi Quoters
  , cp
  -- * IsRegex
  -- $isregex
  , module Text.RE.Tools.IsRegex
  ) where

import           Control.Monad.Fail
import qualified Data.Sequence                 as S
import           Data.Typeable
import           Prelude.Compat
import           Text.RE.REOptions
import           Text.RE.Replace
import           Text.RE.TestBench.Parsers
import           Text.RE.Tools.IsRegex
import           Text.RE.ZeInternals
import           Text.RE.ZeInternals.SearchReplace.TDFA.Sequence
import           Text.RE.ZeInternals.TDFA
import           Text.Regex.Base
import qualified Text.Regex.TDFA               as TDFA
-- NB regex-base instance imports maybe be needed for for some API modules

-- | find all the matches in the argument text; e.g., to count the number
-- of naturals in s:
--
--   @countMatches $ s *=~ [re|[0-9]+|]@
--
(*=~) :: (S.Seq Char)
      -> RE
      -> Matches (S.Seq Char)
(*=~) bs rex = addCaptureNamesToMatches (reCaptureNames rex) $ match (reRegex 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]+|]@
--
(?=~) :: (S.Seq Char)
      -> RE
      -> Match (S.Seq Char)
(?=~) bs rex = addCaptureNamesToMatch (reCaptureNames rex) $ match (reRegex 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}|])@
--
(*=~/) :: (S.Seq Char) -> SearchReplace RE (S.Seq Char) -> (S.Seq Char)
(*=~/) = flip searchReplaceAll

-- | search and replace the first occurrence only (if any) in the input text
-- e.g., to prefix the first string of four hex digits in the input text,
-- if any, with @0x@:
--
--  @(?=~\/ [ed|[0-9A-Fa-f]{4}\/\/\/0x$0|])@
--
(?=~/) :: (S.Seq Char) -> SearchReplace RE (S.Seq Char) -> (S.Seq Char)
(?=~/) = flip searchReplaceFirst

-- | the `regex-base` polymorphic match operator
(=~) :: ( Typeable a
        , RegexContext TDFA.Regex (S.Seq Char) a
        )
     => (S.Seq Char)
     -> RE
     -> a
(=~) bs rex = addCaptureNames (reCaptureNames rex) $ match (reRegex rex) bs

-- | the `regex-base` monadic, polymorphic match operator
(=~~) :: ( Monad m, MonadFail m
         , Functor m
         , Typeable a
         , RegexContext TDFA.Regex (S.Seq Char) a
         )
      => (S.Seq Char)
      -> RE
      -> m a
(=~~) bs rex = addCaptureNames (reCaptureNames rex) <$> matchM (reRegex rex) bs

instance IsRegex RE (S.Seq Char) where
  matchOnce             = flip (?=~)
  matchMany             = flip (*=~)
  makeRegexWith         = \o -> compileRegexWith o . unpackR
  makeSearchReplaceWith = \o r t -> compileSearchReplaceWith o (unpackR r) (unpackR t)
  regexSource           = packR . reSource

-- $tutorial
-- We have a regex tutorial at <http://tutorial.regex.uk>.

-- $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 @[ed|.*\/\/\/foo|]@ quasi quoters, with variants for specifying different
-- options to the RE compiler (see "Text.RE.REOptions").

-- $ed
-- The -- | the @[ed| ... \/\/\/ ... |]@ quasi quoters; for example,
--
--  @[ed|${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.