[project @ 2005-03-14 15:57:57 by simonmar]

[ghc-base.git] / Text / Regex.hs

diff --git a/Text/Regex.hs b/Text/Regex.hs
index 62901a5..7a24043 100644 (file)
--- a/Text/Regex.hs
+++ b/Text/Regex.hs
@@ -6,29 +6,28 @@
 -- 
 -- Maintainer  :  libraries@haskell.org
 -- Stability   :  experimental
--- Portability :  non-portable (only on platforms that provide a regex lib)
+-- Portability :  portable
 --
 -- Regular expression matching.  Uses the POSIX regular expression
 -- interface in "Text.Regex.Posix".
 --
 -----------------------------------------------------------------------------
-
 module Text.Regex (
     -- * Regular expressions
     Regex,
     mkRegex,
     mkRegexWithOpts,
     matchRegex,
-    matchRegexAll
+    matchRegexAll,
+    subRegex,
+    splitRegex
   ) where
 
 import Prelude
 import qualified Text.Regex.Posix as RE
+import Text.Regex.Posix ( Regex )
 import System.IO.Unsafe
 
--- | A compiled regular expression
-type Regex = RE.Regex
-
 -- | Makes a regular expression with the default options (multi-line,
 -- case-sensitive).  The syntax of regular expressions is
 -- otherwise that of @egrep@ (i.e. POSIX \"extended\" regular
@@ -37,11 +36,11 @@ mkRegex :: String -> Regex
 mkRegex s = unsafePerformIO (RE.regcomp s RE.regExtended)
 
 -- | Makes a regular expression, where the multi-line and
--- case-sensitve options can be changed from the default settings.
+-- case-sensitive options can be changed from the default settings.
 mkRegexWithOpts
    :: String  -- ^ The regular expression to compile
-   -> Bool    -- ^ 'True' @\<=>@ '@^@' and '@$@' match the beginning and 
-             -- end of individual lines respectively, and '.' does /not/
+   -> Bool    -- ^ 'True' @\<=>@ @\'^\'@ and @\'$\'@ match the beginning and 
+             -- end of individual lines respectively, and @\'.\'@ does /not/
              -- match the newline character.
    -> Bool    -- ^ 'True' @\<=>@ matching is case-sensitive
    -> Regex   -- ^ Returns: the compiled regular expression
@@ -49,8 +48,8 @@ mkRegexWithOpts
 mkRegexWithOpts s single_line case_sensitive
    = unsafePerformIO (RE.regcomp s (RE.regExtended + newline + igcase))
    where
-       newline | single_line = 0
-               | otherwise   = RE.regNewline
+       newline | single_line = RE.regNewline
+               | otherwise   = 0
 
        igcase  | case_sensitive = 0 
                | otherwise      = RE.regIgnoreCase
@@ -82,3 +81,51 @@ matchRegexAll
 
 matchRegexAll p str = unsafePerformIO (RE.regexec p str)
 
+{- | Replaces every occurance of the given regexp with the replacement string.
+
+In the replacement string, @\"\\1\"@ refers to the first substring;
+@\"\\2\"@ to the second, etc; and @\"\\0\"@ to the entire match.
+@\"\\\\\\\\\"@ will insert a literal backslash.
+
+-}
+subRegex :: Regex                          -- ^ Search pattern
+      -> String                         -- ^ Input string
+      -> String                         -- ^ Replacement text
+      -> String                         -- ^ Output string
+subRegex _ "" _ = ""
+subRegex regexp inp repl =
+    let bre = mkRegex "\\\\(\\\\||[0-9]+)"
+        lookup _ [] _ = []
+        lookup [] _ _ = []
+        lookup match repl groups =
+            case matchRegexAll bre repl of
+                Nothing -> repl
+                Just (lead, _, trail, bgroups) ->
+                    let newval = if (head bgroups) == "\\"
+                                 then "\\"
+                                 else let index = (read (head bgroups)) - 1
+                                          in
+                                          if index == -1
+                                             then match
+                                             else groups !! index
+                        in
+                        lead ++ newval ++ lookup match trail groups
+        in
+        case matchRegexAll regexp inp of
+            Nothing -> inp
+            Just (lead, match, trail, groups) ->
+              lead ++ lookup match repl groups ++ (subRegex regexp trail repl)
+
+{- | Splits a string based on a regular expression.  The regular expression
+should identify one delimiter.
+-}
+
+splitRegex :: Regex -> String -> [String]
+splitRegex _ [] = []
+splitRegex delim str =
+    case matchRegexAll delim str of
+       Nothing -> [str]
+       Just (firstline, _, remainder, _) ->
+           if remainder == ""
+              then firstline : [] : []
+              else firstline : splitRegex delim remainder