diff --git a/examples/colorizeProgs/ColorizeSourceCode.hs b/examples/colorizeProgs/ColorizeSourceCode.hs --- a/examples/colorizeProgs/ColorizeSourceCode.hs +++ b/examples/colorizeProgs/ColorizeSourceCode.hs @@ -37,27 +37,27 @@ -- ------------------------------------------------------------ -data Process = P { inFilter :: String -> String - , tokenRE :: Regex - , markupRE :: Regex -> Regex - , formatToken :: (String, String) -> String - , formatDoc :: [String] -> String - , outFilter :: String -> String - , input :: Handle - , output :: Handle - , inputFile :: String - } +data Process = P { inFilter :: String -> String + , tokenRE :: Regex + , markupRE :: Regex -> Regex + , formatToken :: (String, String) -> String + , formatDoc :: [String] -> String + , outFilter :: String -> String + , input :: Handle + , output :: Handle + , inputFile :: String + } -defaultProcess = P { inFilter = id - , tokenRE = plainRE - , markupRE = id - , formatToken = uncurry (++) - , formatDoc = unlines - , outFilter = id - , input = stdin - , output = stdout - , inputFile = " " - } +defaultProcess = P { inFilter = id + , tokenRE = plainRE + , markupRE = id + , formatToken = uncurry (++) + , formatDoc = unlines + , outFilter = id + , input = stdin + , output = stdout + , inputFile = " " + } -- ------------------------------------------------------------ @@ -68,7 +68,7 @@ s <- hGetContents (input p) hPutStr (output p) (process p s) hFlush (output p) - hClose (output p) + hClose (output p) exitWith ExitSuccess options :: [OptDescr (String, String)] @@ -85,11 +85,11 @@ , Option "n" ["number"] (NoArg ("number", "1")) "with line numbers" , Option "t" ["tabs"] (NoArg ("tabs", "1")) "substitute tabs by blanks" , Option "m" ["markup"] (NoArg ("markup", "1")) "text contains embedded markup" - , Option "e" ["erefs"] (NoArg ("erefs", "1")) "resolve HTML entity refs before processing" + , Option "e" ["erefs"] (NoArg ("erefs", "1")) "resolve HTML entity refs before processing" , Option "o" ["output"] (ReqArg ((,) "output") "FILE") "output file, \"-\" stands for stdout" , Option "s" ["scan"] (NoArg ("scan", "1")) "just scan input, for testing" , Option "x" ["html"] (NoArg ("html", "1")) "html output" - , Option "f" ["full"] (NoArg ("full", "1")) "full HTML document with header and css" + , Option "f" ["full"] (NoArg ("full", "1")) "full HTML document with header and css" ] exitErr :: String -> IO a @@ -105,9 +105,9 @@ | otherwise = do inp <- openFile fn ReadMode evalOpts opts (defaultProcess { input = inp - , inputFile = fn - } - ) + , inputFile = fn + } + ) where (fn:fns) = files @@ -138,15 +138,15 @@ evalOpt ("pplass", "1") p = return $ p { tokenRE = pplassRE } evalOpt ("plain", "1") p = return $ p { tokenRE = plainRE } evalOpt ("scan", "1") p = return $ p { tokenRE = plainRE - , formatToken = uncurry formatTok + , formatToken = uncurry formatTok , formatDoc = formatHList } -evalOpt ("number", "1") p = return $ p { formatDoc = numberLines >>> formatDoc p } -evalOpt ("tabs", "1") p = return $ p { inFilter = inFilter p >>> substTabs } -evalOpt ("erefs", "1") p = return $ p { inFilter = resolveHtmlEntities >>> inFilter p } -evalOpt ("markup", "1") p = return $ p { markupRE = addMarkup } +evalOpt ("number", "1") p = return $ p { formatDoc = numberLines >>> formatDoc p } +evalOpt ("tabs", "1") p = return $ p { inFilter = inFilter p >>> substTabs } +evalOpt ("erefs", "1") p = return $ p { inFilter = resolveHtmlEntities >>> inFilter p } +evalOpt ("markup", "1") p = return $ p { markupRE = addMarkup } evalOpt ("html", "1") p = return $ p { formatToken = formatHtmlTok - , formatDoc = formatHtmlDoc } -evalOpt ("full", "1") p = return $ p { outFilter = outFilter p >>> fullHtml (inputFile p) } + , formatDoc = formatHtmlDoc } +evalOpt ("full", "1") p = return $ p { outFilter = outFilter p >>> fullHtml (inputFile p) } usage :: IO () usage = hPutStrLn stderr use @@ -158,18 +158,18 @@ process :: Process -> String -> String process p = inFilter p - >>> tokenizeSubexRE (markupRE p (tokenRE p)) + >>> tokenizeSubexRE (markupRE p (tokenRE p)) >>> map (formatToken p) >>> concat >>> lines >>> formatDoc p - >>> outFilter p + >>> outFilter p -addMarkup :: Regex -> Regex -addMarkup = mkElse (parseRegex . mkLE $ markupT) +addMarkup :: Regex -> Regex +addMarkup = mkElse (parseRegex . mkLE $ markupT) -tokenizeLines :: String -> [(String, String)] -tokenizeLines = map (\ l -> ("",l ++ "\n")) . lines +tokenizeLines :: String -> [(String, String)] +tokenizeLines = map (\ l -> ("",l ++ "\n")) . lines numberLines :: [String] -> [String] numberLines = zipWith addNum [1..] @@ -182,22 +182,22 @@ . (replicate l ' ' ++) . show -substTabs :: String -> String -substTabs = subs 0 +substTabs :: String -> String +substTabs = subs 0 -subs _ "" = "" +subs _ "" = "" subs i (x:xs) - | x == '\t' = replicate (8 - (i `mod` 8)) ' ' ++ subs 0 xs + | x == '\t' = replicate (8 - (i `mod` 8)) ' ' ++ subs 0 xs | x == '\n' = x : subs 0 xs - | otherwise = x : subs (i+1) xs + | otherwise = x : subs (i+1) xs -- ------------------------------------------------------------ -resolveHtmlEntities :: String -> String -resolveHtmlEntities = sed (replaceEntity . drop 1 . init) "&\\i\\c*;" - where - replaceEntity e = maybe ("&" ++ e ++ ";") ((:[]) . toEnum) - . lookup e $ xhtmlEntities +resolveHtmlEntities :: String -> String +resolveHtmlEntities = sed (replaceEntity . drop 1 . init) "&\\i\\c*;" + where + replaceEntity e = maybe ("&" ++ e ++ ";") ((:[]) . toEnum) + . lookup e $ xhtmlEntities -- ------------------------------------------------------------ @@ -211,35 +211,35 @@ >>> ("
" :) >>> (++ ["
"]) >>> unlines - where - preserveEmptyLines "" = " " - preserveEmptyLines l = l + where + preserveEmptyLines "" = " " + preserveEmptyLines l = l formatHtmlTok :: (String, String) -> String formatHtmlTok (m, t) - | m == "markup" = t - | otherwise = colorizeTokens m (escapeText >>> sed (const " ") " " $ t) + | m == "markup" = t + | otherwise = colorizeTokens m (escapeText >>> sed (const " ") " " $ t) escapeText :: String -> String escapeText = concat . runLA (xshow (mkText >>> escapeHtmlDoc)) -fullHtml :: String -> String -> String -fullHtml fn s = unlines - [ "" - , "" - , "" ++ fn ++ "" - , "" - , "" - , "" - , s - , "" - , "" - ] +fullHtml :: String -> String -> String +fullHtml fn s = unlines + [ "" + , "" + , "" ++ fn ++ "" + , "" + , "" + , "" + , s + , "" + , "" + ] -css :: String +css :: String css = unlines [ ".typename { color: #0000dd; }" , ".varname { color: #000000; }" @@ -263,10 +263,10 @@ , ".tclproc { color: #FF6000; }" , ".tclvar { color: #0000CD; }" , ".tclcomment { color: #c80000; }" - , "" - , ".linenr { color: #909090; padding-right: 2em; }" - , "div.codeline { font-family: monospace; width: 100%; white-space: pre; border-width: 1px; border-style: solid; border-color: transparent; padding-left: 0.3em; }" - , "div.codeline:hover { background-color:#ddddff; color:#c80000; border-width: 1px; border-style: solid; border-color: #c80000; }" + , "" + , ".linenr { color: #909090; padding-right: 2em; }" + , "div.codeline { font-family: monospace; width: 100%; white-space: pre; border-width: 1px; border-style: solid; border-color: transparent; padding-left: 0.3em; }" + , "div.codeline:hover { background-color:#ddddff; color:#c80000; border-width: 1px; border-style: solid; border-color: #c80000; }" ] @@ -276,24 +276,24 @@ colorizeTokens tok | tok `elem` [ "comment" , "keyword" - , "keyglyph" + , "keyglyph" , "typekeyword" , "varname", "typename", "labelname", "instancename", "globalname" , "opname" - , "par" + , "par" , "operator" , "strconst", "charconst" - , "bnfnt", "bnfmeta" - , "cppcommand" - , "specialword" + , "bnfnt", "bnfmeta" + , "cppcommand" + , "specialword" ] - = wrap + = wrap | tok == "longcomment" = wrap' "comment" . mlc - | tok == "bnfterminal" = wrap . drop 1 . init - -- | tok == "markupstart" = (("")) . drop 4 . init + | tok == "bnfterminal" = wrap . drop 1 . init + -- | tok == "markupstart" = (("")) . drop 4 . init -- | tok == "markupend" = const "" - | null tok = const "" - | otherwise = id + | null tok = const "" + | otherwise = id where wrap = wrap' tok wrap' tok' = (("") ++) . (++ "") @@ -303,9 +303,9 @@ buildRegex :: [(String, String)] -> Regex buildRegex = foldr1 mkElse . map (uncurry mkBr') . map (second parseRegex) - where - mkBr' "" = id - mkBr' l = mkBr l + where + mkBr' "" = id + mkBr' l = mkBr l buildKeywords :: [String] -> String @@ -314,10 +314,10 @@ untilRE :: String -> String untilRE re = "(\\A{" ++ "\\}\\A" ++ re ++ "\\A)" ++ re -mkLE :: (String, String) -> String -mkLE (l, re) = "({" ++ l ++ "}(" ++ re ++ "))" +mkLE :: (String, String) -> String +mkLE (l, re) = "({" ++ l ++ "}(" ++ re ++ "))" -ws1RE = "\\s+" +ws1RE = "\\s+" ws1RE' = "[ \t]+" ws0RE = "[ \t]*" @@ -325,38 +325,38 @@ charconst, number, par, xxx :: (String, String) --- markupS = ("markupstart", "<[a-zA-Z0-9]+>" ) --- markupE = ("markupend", "" ) +-- markupS = ("markupstart", "<[a-zA-Z0-9]+>" ) +-- markupE = ("markupend", "" ) markupT = ("markup", ( "" - ++ "|" ++ - "&" ++ xname ++ ";" - ) - ) - where - xname = "[A-Za-z][-_:A-Za-z0-9]*" - xattr = ws1RE ++ xname ++ eq ++ "(" ++ dq ++ "|" ++ sq ++ ")" - eq = "\\s*=\\s*" - dq = "\"[^\"]*\"" - sq = "\'[^\']*\'" + ++ "|" ++ + "&" ++ xname ++ ";" + ) + ) + where + xname = "[A-Za-z][-_:A-Za-z0-9]*" + xattr = ws1RE ++ xname ++ eq ++ "(" ++ dq ++ "|" ++ sq ++ ")" + eq = "\\s*=\\s*" + dq = "\"[^\"]*\"" + sq = "\'[^\']*\'" ws = ("ws", ws1RE ) ws' = ("ws", ws1RE' ) -javacmt1 = ("comment", "//.*" ) +javacmt1 = ("comment", "//.*" ) javacmt = ("longcomment", "/\\*" ++ untilRE "\\*/" ) -shcmt1 = ("comment", "#.*" ) -strconst = ("strconst", "\"([^\"\\\\\n\r]|\\\\.)*\"" ) -charconst = ("charconst", "\'([^\'\\\\\n\r]|\\\\.)*\'" ) +shcmt1 = ("comment", "#.*" ) +strconst = ("strconst", "\"([^\"\\\\\n\r]|\\\\.)*\"" ) +charconst = ("charconst", "\'([^\'\\\\\n\r]|\\\\.)*\'" ) number = ("number", "[0-9]+(\\.[0-9]*([eE][-+]?[0-9]+)?)?" ) par = ("par", "[\\(\\)\\[\\]\\{\\}]" ) xxx = ("xxx", "." ) -- ------------------------------------------------------------ -plainRE :: Regex -plainRE = buildRegex - [ ("xxx", "[^<&\n]+" ) - , ("xxx", "[<&\n]" ) - ] +plainRE :: Regex +plainRE = buildRegex + [ ("xxx", "[^<&\n]+" ) + , ("xxx", "[<&\n]" ) + ] -- ------------------------------------------------------------ @@ -367,26 +367,26 @@ , ("longcomment", "\\{" ++ untilRE "-\\}" ) , ("keyword", buildKeywords [ "case", "class" - , "data", "default", "deriving", "do" - , "else" - , "forall" - , "if", "import", "in" - , "infix", "infixl", "infixr" - , "instance" - , "let" - , "module" - , "newtype" - , "of" - , "qualified" - , "then", "type" - , "where" - , "_" - , "as", "ccall", "foreign", "hiding", "proc", "safe", "unsafe" + , "data", "default", "deriving", "do" + , "else" + , "forall" + , "if", "import", "in" + , "infix", "infixl", "infixr" + , "instance" + , "let" + , "module" + , "newtype" + , "of" + , "qualified" + , "then", "type" + , "where" + , "_" + , "as", "ccall", "foreign", "hiding", "proc", "safe", "unsafe" ] - ) - , ("keyglyph", buildKeywords - ["\\.\\.","::","=","\\\\","\\|","<-","->","-<","@","~","=>","!",",",";"] - ) + ) + , ("keyglyph", buildKeywords + ["\\.\\.","::","=","\\\\","\\|","<-","->","-<","@","~","=>","!",",",";"] + ) , ("varname" , varname ) , ("typename", "[A-Z_][a-zA-Z0-9_]*[']*" ) , ("opname", "`" ++ varname ++ "`" ) @@ -394,7 +394,7 @@ , charconst , number , par - , ("operator", "[-!#$%&\\*\\+./<=>\\?@\\\\^\\|~]+") + , ("operator", "[-!#$%&\\*\\+./<=>\\?@\\\\^\\|~]+") , xxx ] where @@ -436,13 +436,13 @@ , "true" , "void" ] ) - , ("labelname", "(" ++ varname ++ "{\\}default):" ) - , ("", ( mkLE ("keyword", "break|continue") - ++ mkLE ws ++ - mkLE ("labelname", varname) - ) - ) - , ("varname", varname ) + , ("labelname", "(" ++ varname ++ "{\\}default):" ) + , ("", ( mkLE ("keyword", "break|continue") + ++ mkLE ws ++ + mkLE ("labelname", varname) + ) + ) + , ("varname", varname ) , ("typename", "[A-Z][a-zA-Z0-9_]*" ) , strconst , charconst @@ -453,25 +453,25 @@ , xxx ] where - varname = "[a-z][a-zA-Z0-9_]*" + varname = "[a-z][a-zA-Z0-9_]*" -- ------------------------------------------------------------ -bnfRE = buildRegex - [ ws - , ("bnfnt" , "[A-Z][a-zA-Z0-9_]*" ) - , ("bnfterminal", "\"([^\"\\\\\n\r]|\\\\.)*\"" ) - , ("bnfmeta", buildKeywords - [ "\\[" - , "\\]" - , "::=" - , "\\|" - , "\\{" - , "\\}" - ] - ) - , xxx - ] +bnfRE = buildRegex + [ ws + , ("bnfnt" , "[A-Z][a-zA-Z0-9_]*" ) + , ("bnfterminal", "\"([^\"\\\\\n\r]|\\\\.)*\"" ) + , ("bnfmeta", buildKeywords + [ "\\[" + , "\\]" + , "::=" + , "\\|" + , "\\{" + , "\\}" + ] + ) + , xxx + ] -- ------------------------------------------------------------ @@ -482,63 +482,63 @@ , javacmt , ("keyword", buildKeywords [ "asm" , "auto" - , "break" - , "case" , "catch" , "class" , "const" , "continue" - , "default" , "delete" , "do" - , "else" , "extern" - , "for" , "friend" - , "goto" - , "if" , "inline" - , "new" - , "operator" , "overload" - , "private" , "protected" , "public" - , "register" , "return" - , "sizeof" , "static" , "switch" - , "template" , "this" , "typedef" , "throw" , "try" - , "virtual" , "volatile" - , "while" - ] - ) + , "break" + , "case" , "catch" , "class" , "const" , "continue" + , "default" , "delete" , "do" + , "else" , "extern" + , "for" , "friend" + , "goto" + , "if" , "inline" + , "new" + , "operator" , "overload" + , "private" , "protected" , "public" + , "register" , "return" + , "sizeof" , "static" , "switch" + , "template" , "this" , "typedef" , "throw" , "try" + , "virtual" , "volatile" + , "while" + ] + ) , ("typekeyword", buildKeywords [ "char" - , "double" - , "enum" - , "float" - , "int" - , "long" - , "short" - , "signed" - , "struct" - , "union" - , "unsigned" - , "void" - ] - ) - , ("cppcommand", ( "#" ++ ws0RE ++ "(" - ++ + , "double" + , "enum" + , "float" + , "int" + , "long" + , "short" + , "signed" + , "struct" + , "union" + , "unsigned" + , "void" + ] + ) + , ("cppcommand", ( "#" ++ ws0RE ++ "(" + ++ buildKeywords - [ "define" - , "else" - , "endif" - , "if" - , "ifdef" - , "ifndef" - , "(include[ \t].*)" - , "undef" - ] - ++ ")" - ) - ) - , ("specialword", buildKeywords + [ "define" + , "else" + , "endif" + , "if" + , "ifdef" + , "ifndef" + , "(include[ \t].*)" + , "undef" + ] + ++ ")" + ) + ) + , ("specialword", buildKeywords [ "assert" - , "exit" - , "free" - , "main" - , "malloc" - ] - ) - , ("varname", varname ) + , "exit" + , "free" + , "main" + , "malloc" + ] + ) + , ("varname", varname ) , ("typename", "[A-Z][a-zA-Z0-9_]*" ) , strconst , charconst @@ -549,114 +549,114 @@ , xxx ] where - varname = "[a-z][a-zA-Z0-9_]*" + varname = "[a-z][a-zA-Z0-9_]*" -- ------------------------------------------------------------ -shRE = buildRegex - [ ws - , shcmt1 - , ("keyword", buildKeywords - [ "alias" - , "break" , "bg" - , "case" , "cd" , "continue" - , "declare" , "do" , "done" - , "echo" , "elif" , "else" , "env" , "esac" , "eval" , "exec" , "exit" , "export" - , "false" , "fg" , "fi" , "for" , "function" - , "if" , "in" - , "jobs" - , "kill" - , "local" - , "pwd" - , "return" - , "set" , "shift" - , "test" , "then" , "trap" , "true" - , "unalias" , "unset" - , "while" , "wait" - ] - ) - , ("varname", "[A-Za-z_][a-zA-Z0-9_]*" ) - , ("operator", "[-+!%&=\\\\\\*\\?~|<>:@$]+" ) - , ("operator", "[\\(\\)\\[\\]\\{\\}]+" ) +shRE = buildRegex + [ ws + , shcmt1 + , ("keyword", buildKeywords + [ "alias" + , "break" , "bg" + , "case" , "cd" , "continue" + , "declare" , "do" , "done" + , "echo" , "elif" , "else" , "env" , "esac" , "eval" , "exec" , "exit" , "export" + , "false" , "fg" , "fi" , "for" , "function" + , "if" , "in" + , "jobs" + , "kill" + , "local" + , "pwd" + , "return" + , "set" , "shift" + , "test" , "then" , "trap" , "true" + , "unalias" , "unset" + , "while" , "wait" + ] + ) + , ("varname", "[A-Za-z_][a-zA-Z0-9_]*" ) + , ("operator", "[-+!%&=\\\\\\*\\?~|<>:@$]+" ) + , ("operator", "[\\(\\)\\[\\]\\{\\}]+" ) , strconst , charconst - , xxx - ] + , xxx + ] -- ------------------------------------------------------------ -rubyRE = buildRegex - [ ws - , rubycmt - , ("keyword", buildKeywords - [ "begin" , "break" - , "catch" , "case" , "class" - , "def" , "do" - , "else" , "elif" , "end" , "ensure" - , "false" , "for" - , "if" , "in" , "include" , "initialize" - , "loop" - , "module" - , "new" , "nil" - , "raise" , "require" , "rescue" - , "self" - , "then" , "true" , "type" - , "until" - , "when" , "while" - , "yield" - ] - ) - , ("typename", "[A-Z][A-Za-z0-9]*" ) - , ("varname", "[A-Za-z_][a-zA-Z0-9_]*(!|\\?)?" ) - , ("instancename", "(@{1,2}|$)[A-Za-z_][a-zA-Z0-9_]*" ) - , ("strconst", "%[qQx]\\{.*\\}" ) - , ("strconst", "#\\{.*\\}" ) - , ("strconst", ":[a-z][A-Za-z0-9]*" ) - , strconst - , charconst - , regex - , xxx - ] +rubyRE = buildRegex + [ ws + , rubycmt + , ("keyword", buildKeywords + [ "begin" , "break" + , "catch" , "case" , "class" + , "def" , "do" + , "else" , "elif" , "end" , "ensure" + , "false" , "for" + , "if" , "in" , "include" , "initialize" + , "loop" + , "module" + , "new" , "nil" + , "raise" , "require" , "rescue" + , "self" + , "then" , "true" , "type" + , "until" + , "when" , "while" + , "yield" + ] + ) + , ("typename", "[A-Z][A-Za-z0-9]*" ) + , ("varname", "[A-Za-z_][a-zA-Z0-9_]*(!|\\?)?" ) + , ("instancename", "(@{1,2}|$)[A-Za-z_][a-zA-Z0-9_]*" ) + , ("strconst", "%[qQx]\\{.*\\}" ) + , ("strconst", "#\\{.*\\}" ) + , ("strconst", ":[a-z][A-Za-z0-9]*" ) + , strconst + , charconst + , regex + , xxx + ] where - rubycmt = ("comment", "#(.{\\}\\{)*" ) - regex = ("strconst", "/([^/\\\\\n\r]|\\\\.)*/" ) + rubycmt = ("comment", "#(.{\\}\\{)*" ) + regex = ("strconst", "/([^/\\\\\n\r]|\\\\.)*/" ) -- ------------------------------------------------------------ pplRE :: Regex -pplRE = buildRegex +pplRE = buildRegex [ ws , ("comment", "(-)- .*" ) , ("keyword", buildKeywords [ "and" - , "begin" - , "div" , "do" - , "else" , "elseif" , "endif" , "endwhile" , "end" - , "function" - , "if" - , "max" , "min" , "mod" - , "not" - , "of" , "or" - , "procedure" - , "repeat" - , "return" - , "then" - , "until" - , "var" - , "while" - , "xor" - ] - ) - , ("typekeyword", buildKeywords + , "begin" + , "div" , "do" + , "else" , "elseif" , "endif" , "endwhile" , "end" + , "function" + , "if" + , "max" , "min" , "mod" + , "not" + , "of" , "or" + , "procedure" + , "repeat" + , "return" + , "then" + , "until" + , "var" + , "while" + , "xor" + ] + ) + , ("typekeyword", buildKeywords [ "boolean" - , "false" , "float" - , "int" - , "list" - , "picture" - , "string" - , "true" - ] - ) + , "false" , "float" + , "int" + , "list" + , "picture" + , "string" + , "true" + ] + ) , ("varname", "[A-Za-z_][a-zA-Z0-9_]*" ) , strconst , number @@ -666,30 +666,30 @@ -- ------------------------------------------------------------ pplassRE :: Regex -pplassRE = buildRegex +pplassRE = buildRegex [ ws , ("comment", "(-)- .*" ) , ("keyword", buildKeywords [ "loadi" , "loadf" - , "loads" , "emptyl" - , "undef" , "load" - ] - ) + , "loads" , "emptyl" + , "undef" , "load" + ] + ) , ("typename", buildKeywords [ "store" - , "pop" - ] - ) + , "pop" + ] + ) , ("typekeyword", buildKeywords [ "jmp" - , "brfalse" - , "brtrue" - , "pushj" - , "popj" - , "svc" - ] - ) - , ("labelname", "(l[0-9]+:?)|([se]?_[A-Za-z0-9]*:?)" ) + , "brfalse" + , "brtrue" + , "pushj" + , "popj" + , "svc" + ] + ) + , ("labelname", "(l[0-9]+:?)|([se]?_[A-Za-z0-9]*:?)" ) , ("varname", "[A-Za-z_][a-zA-Z0-9_]*" ) , strconst , xxx diff --git a/examples/performance/Makefile b/examples/performance/Makefile --- a/examples/performance/Makefile +++ b/examples/performance/Makefile @@ -1,10 +1,10 @@ -PKGFLAGS = +PKGFLAGS = GHCFLAGS = -Wall -O2 GHC = ghc $(GHCFLAGS) $(PKGFLAGS) CNT = 3 -ropts = +RTS -s -RTS +ropts = +RTS -s -RTS prog = ./REtest prog2 = ./Lines diff --git a/examples/performance/REtest.hs b/examples/performance/REtest.hs --- a/examples/performance/REtest.hs +++ b/examples/performance/REtest.hs @@ -6,43 +6,42 @@ where import Text.Regex.XMLSchema.String --- import Control.Monad.State.Strict hiding (when) + import Control.Arrow -import Data.List import Data.Maybe -import System.IO -- import the IO and commandline option stuff +import System.IO -- import the IO and commandline option stuff import System.Environment -- ---------------------------------------- -main :: IO () +main :: IO () main = do p <- getProgName al <- getArgs let i = if null al - then 4 - else (read . head $ al)::Int + then 4 + else (read . head $ al)::Int main' p i where main' p' = fromMaybe main1 . lookup (pn p') $ mpt - mpt = [ ("REtest", main1) - , ("Copy", main2 "copy" (:[])) - , ("Lines", main2 "lines" lines) - , ("RElines", main2 "relines" relines) - , ("SElines", main2 "selines'" relines') - , ("Words", main2 "words" words) - , ("REwords", main2 "rewords" rewords) - , ("SEwords", main2 "sewords" rewords') - ] + mpt = [ ("REtest", main1) + , ("Copy", main2 "copy" (:[])) + , ("Lines", main2 "lines" lines) + , ("RElines", main2 "relines" relines) + , ("SElines", main2 "selines'" relines') + , ("Words", main2 "words" words) + , ("REwords", main2 "rewords" rewords) + , ("SEwords", main2 "sewords" rewords') + ] -- ---------------------------------------- -- generate a document containing a binary tree of 2^i leafs (= 2^(i-1) XML elements) -main1 :: Int -> IO () +main1 :: Int -> IO () main1 i = do genDoc i "REtest.hs" (fn i) @@ -52,7 +51,7 @@ -- read a document containing a binary tree of 2^i leafs -main2 :: String -> (String -> [String]) -> Int -> IO () +main2 :: String -> (String -> [String]) -> Int -> IO () main2 ext lines' i = do hPutStrLn stderr "start processing" @@ -65,33 +64,33 @@ hClose h hPutStrLn stderr "end processing" -relines :: String -> [String] -relines = tokenize ".*" +relines :: String -> [String] +relines = tokenize ".*" -relines' :: String -> [String] -relines' = tokenizeSubex "({line}.*)" >>> map snd +relines' :: String -> [String] +relines' = tokenizeSubex "({line}.*)" >>> map snd -rewords :: String -> [String] -rewords = tokenize "\\S+" +rewords :: String -> [String] +rewords = tokenize "\\S+" -rewords' :: String -> [String] -rewords' = tokenizeSubex "({word}\\S+)" >>> map snd +rewords' :: String -> [String] +rewords' = tokenizeSubex "({word}\\S+)" >>> map snd -- ---------------------------------------- -pn :: String -> String -pn = reverse . takeWhile (/= '/') . reverse +pn :: String -> String +pn = reverse . takeWhile (/= '/') . reverse -fn :: Int -> String -fn = ("lines-" ++) . (++ ".txt") . reverse . take 4 . reverse . ((replicate 4 '0') ++ ) . show +fn :: Int -> String +fn = ("lines-" ++) . (++ ".txt") . reverse . take 4 . reverse . ((replicate 4 '0') ++ ) . show -- ---------------------------------------- -genDoc :: Int -> String -> String -> IO () +genDoc :: Int -> String -> String -> IO () genDoc d inp outp = do - s <- readFile inp - let s' = take (2^d) . concat . repeat $ s - writeFile outp s' + s <- readFile inp + let s' = take (2^d) . concat . repeat $ s + writeFile outp s' -- ---------------------------------------- diff --git a/examples/test/Main.hs b/examples/test/Main.hs --- a/examples/test/Main.hs +++ b/examples/test/Main.hs @@ -12,235 +12,235 @@ -- ------------------------------------------------------------ -parseTests :: Test +parseTests :: Test parseTests = TestLabel "parse tests" $ TestList $ map parseTest $ tests where parseTest (re, rep) - = TestCase $ - assertEqual (show re ++ " must be parsed as " ++ show rep) + = TestCase $ + assertEqual (show re ++ " must be parsed as " ++ show rep) rep - (show . parseRegex $ re) + (show . parseRegex $ re) - tests = [ ("", "()") - , (".", ".") - , (".*", "(.*)") - , ("\\a", "\\a") - , ("\\A", "\\A") - , ("(())", "()") - , ("(a*)*", "(a*)") - , ("(a*)+", "(a*)") - , ("(a+)*", "(a*)") - , ("(a+)+", "(a+)") - , ("(a?){2,}", "(a*)") - , ("((a?){2,}){0,}", "(a*)") - , ("((a?){2,}){3,}", "(a*)") - , ("(a{0,}){2,}", "(a*)") - , ("(a{2,}){3,}", "(a{6,})") - , ("[9-0]", "{empty char range}") - , ("[0-9]", "[0-9]") - , ("[0-99-0]", "[0-9]") - , ("[abc]", "[a-c]") - , ("[\0-\1114111]", "\\a") - , ("[\0-\1114111]|[0-9]", "\\a") - , ("[\0-\1114110]", "[�-􏿾]" ) + tests = [ ("", "()") + , (".", ".") + , (".*", "(.*)") + , ("\\a", "\\a") + , ("\\A", "\\A") + , ("(())", "()") + , ("(a*)*", "(a*)") + , ("(a*)+", "(a*)") + , ("(a+)*", "(a*)") + , ("(a+)+", "(a+)") + , ("(a?){2,}", "(a*)") + , ("((a?){2,}){0,}", "(a*)") + , ("((a?){2,}){3,}", "(a*)") + , ("(a{0,}){2,}", "(a*)") + , ("(a{2,}){3,}", "(a{6,})") + , ("[9-0]", "{empty char range}") + , ("[0-9]", "[0-9]") + , ("[0-99-0]", "[0-9]") + , ("[abc]", "[a-c]") + , ("[\0-\1114111]", "\\a") + , ("[\0-\1114111]|[0-9]", "\\a") + , ("[\0-\1114110]", "[�-􏿾]" ) , ("[abc-[b]]", "[ac]" ) - , ("a|b|c|d", "[a-d]" ) - , ("(a|b)|c", "[a-c]" ) - , ("a|(b|c)", "[a-c]" ) - , ("abc", "(a(bc))" ) -- seq is right ass - , ("a*{^}b*", "((a*){^}(b*))" ) -- extension: exor - , ("a*{^}b*{^}c*", "((a*){^}((b*){^}(c*)))") - , ("a*{&}b*", "((a*){&}(b*))" ) -- extension: intersection - , ("a*{&}b*{&}c*", "((a*){&}((b*){&}(c*)))") - , ("a*{\\}b*", "((a*){\\}(b*))" ) -- extension: set difference - , ("a*{\\}b*{\\}c*", "(((a*){\\}(b*)){\\}(c*))" ) - , ("(a|b)*{\\}(.*aa.*)", "(([ab]*){\\}((.*)(a(a(.*)))))" ) - , ("({1}a+)", "({1}(a+))" ) -- extension: labeled subexpressions - , ("({1}({2}({3}a)))", "({1}({2}({3}a)))" ) - , ("({1}do){|}({2}[a-z]+)", "(({1}(do)){|}({2}([a-z]+)))" ) -- deterministic choice of submatches - , ("a{:}b{:}c", "(a{:}(b{:}c))" ) -- interleave - ] + , ("a|b|c|d", "[a-d]" ) + , ("(a|b)|c", "[a-c]" ) + , ("a|(b|c)", "[a-c]" ) + , ("abc", "(a(bc))" ) -- seq is right ass + , ("a*{^}b*", "((a*){^}(b*))" ) -- extension: exor + , ("a*{^}b*{^}c*", "((a*){^}((b*){^}(c*)))") + , ("a*{&}b*", "((a*){&}(b*))" ) -- extension: intersection + , ("a*{&}b*{&}c*", "((a*){&}((b*){&}(c*)))") + , ("a*{\\}b*", "((a*){\\}(b*))" ) -- extension: set difference + , ("a*{\\}b*{\\}c*", "(((a*){\\}(b*)){\\}(c*))" ) + , ("(a|b)*{\\}(.*aa.*)", "(([ab]*){\\}((.*)(a(a(.*)))))" ) + , ("({1}a+)", "({1}(a+))" ) -- extension: labeled subexpressions + , ("({1}({2}({3}a)))", "({1}({2}({3}a)))" ) + , ("({1}do){|}({2}[a-z]+)", "(({1}(do)){|}({2}([a-z]+)))" ) -- deterministic choice of submatches + , ("a{:}b{:}c", "(a{:}(b{:}c))" ) -- interleave + ] -simpleMatchTests :: Test +simpleMatchTests :: Test simpleMatchTests = TestLabel "simple match tests" $ TestList $ concatMap matchTest $ tests where matchTest (re, ok, er) - = map (matchOK re) ok - ++ - map (matchErr re) er - matchOK re s = TestCase $ assertBool (show s ++ " must match " ++ show re) (match re s) - matchErr re s = TestCase $ assertBool (show s ++ " must not match " ++ show re) (not (match re s)) + = map (matchOK re) ok + ++ + map (matchErr re) er + matchOK re s = TestCase $ assertBool (show s ++ " must match " ++ show re) (match re s) + matchErr re s = TestCase $ assertBool (show s ++ " must not match " ++ show re) (not (match re s)) tests = [ ( "" - , [""] - , ["a"] - ) - , ( "a" - , ["a"] - , ["", "b", "ab"] - ) - , ( "()" - , [""] - , ["a"] - ) - , ( "ab" - , ["ab"] - , ["", "b", "abc"] - ) - , ( "." - , [".","a","\0","\1114111"] - , ["\n","\r","",".."] - ) - , ( "\\a" - , [".","a","\n","\r","\0","\1114111"] - , ["",".."] - ) - , ( "\\A" - , ["",".","a","\n","\r","\0","\1114111",".."] - , [] - ) - , ( "a*" - , ["", "a", "aa"] - , ["b", "ab", "aab"] - ) - , ( "a+" - , ["a", "aa", "aaa"] - , ["", "b", "ab"] - ) - , ( "a?" - , ["", "a"] - , ["b", "ab"] - ) - , ( "a{2}" - , ["aa"] - , ["", "a", "aaa"] - ) - , ( "a{2,}" - , ["aa","aaa"] - , ["", "a", "aaab"] - ) - , ( "a{2,4}" - , ["aa", "aaa", "aaaa"] - , ["", "a", "aaaaa", "ab"] - ) - , ( "a|b" - , ["a", "b"] - , ["", "c", "ab", "abc"] - ) - , ( "[0-9]" - , ["0", "5", "9"] - , ["", "a", "00"] - ) - , ( "[^0-9]" - , ["a"] - , ["", "0", "9", "00"]) - , ( "\32" - , [" "] - , [] - ) - , ( "[\0-\1114111]" - , ["\0","\1114111","a"] - , ["","aaa"] - ) - , ( "[^\0-\1114111]" - , [] - , ["","aaa","\0","\1114111","a"] - ) - , ( ".*a.*|.*b.*|.*c.*" - , ["a", "abc", "acdc"] - , ["", "dddd"] - ) - , ( ".*a.*{&}.*b.*{&}.*c.*" - , ["abc", "abcd", "abcabcd"] - , ["", "a", "bc", "acdc", "dddd"] - ) - , ( ".*a.*{&}.*b.*{&}.*c.*{&}.{3}" -- all permutations of "abc" - , ["abc", "acb", "bac", "bca", "cab", "cba"] - , ["", "a", "bc", "acd", "aaaa", "aba"] - ) - , ( ".*a.*{&}.*b.*{&}.*c.*" -- all words containing at least 1 a, 1 b and 1 c - , ["abc", "acb", "bac", "bca", "cab", "cba", "abcd", "abcabc"] - , ["", "a", "bc", "acd", "aaaa"] - ) - , ( ".*a.*{^}.*b.*" -- all words containing at least 1 a or 1 b but not both a's and b's - , ["a", "b", "ac", "bc", "aaaa", "bbb", "aacc", "ccbb", "acdc"] - , ["", "ab", "abc", "dddd"] - ) - , ( "/[*](.*{\\}(.*[*]/.*))[*]/" -- single line C comment of form /*...*/, but without any */ in the comment body - -- this is the way to specify none greedy expessions - -- if multy line comment are required, substitute .* by \A, so newlines are allowed - , ["/**/","/***/","/*x*/","/*///*/"] - , ["", "/", "/*", "/*/", "/**/*/", "/*xxx*/xxx*/"] - ) - , ( "a{:}b{:}c" - , ["abc", "acb", "bac", "bca", "cab", "cba"] - , ["", "a", "ab", "abcc", "abca", "aba"] - ) - ] + , [""] + , ["a"] + ) + , ( "a" + , ["a"] + , ["", "b", "ab"] + ) + , ( "()" + , [""] + , ["a"] + ) + , ( "ab" + , ["ab"] + , ["", "b", "abc"] + ) + , ( "." + , [".","a","\0","\1114111"] + , ["\n","\r","",".."] + ) + , ( "\\a" + , [".","a","\n","\r","\0","\1114111"] + , ["",".."] + ) + , ( "\\A" + , ["",".","a","\n","\r","\0","\1114111",".."] + , [] + ) + , ( "a*" + , ["", "a", "aa"] + , ["b", "ab", "aab"] + ) + , ( "a+" + , ["a", "aa", "aaa"] + , ["", "b", "ab"] + ) + , ( "a?" + , ["", "a"] + , ["b", "ab"] + ) + , ( "a{2}" + , ["aa"] + , ["", "a", "aaa"] + ) + , ( "a{2,}" + , ["aa","aaa"] + , ["", "a", "aaab"] + ) + , ( "a{2,4}" + , ["aa", "aaa", "aaaa"] + , ["", "a", "aaaaa", "ab"] + ) + , ( "a|b" + , ["a", "b"] + , ["", "c", "ab", "abc"] + ) + , ( "[0-9]" + , ["0", "5", "9"] + , ["", "a", "00"] + ) + , ( "[^0-9]" + , ["a"] + , ["", "0", "9", "00"]) + , ( "\32" + , [" "] + , [] + ) + , ( "[\0-\1114111]" + , ["\0","\1114111","a"] + , ["","aaa"] + ) + , ( "[^\0-\1114111]" + , [] + , ["","aaa","\0","\1114111","a"] + ) + , ( ".*a.*|.*b.*|.*c.*" + , ["a", "abc", "acdc"] + , ["", "dddd"] + ) + , ( ".*a.*{&}.*b.*{&}.*c.*" + , ["abc", "abcd", "abcabcd"] + , ["", "a", "bc", "acdc", "dddd"] + ) + , ( ".*a.*{&}.*b.*{&}.*c.*{&}.{3}" -- all permutations of "abc" + , ["abc", "acb", "bac", "bca", "cab", "cba"] + , ["", "a", "bc", "acd", "aaaa", "aba"] + ) + , ( ".*a.*{&}.*b.*{&}.*c.*" -- all words containing at least 1 a, 1 b and 1 c + , ["abc", "acb", "bac", "bca", "cab", "cba", "abcd", "abcabc"] + , ["", "a", "bc", "acd", "aaaa"] + ) + , ( ".*a.*{^}.*b.*" -- all words containing at least 1 a or 1 b but not both a's and b's + , ["a", "b", "ac", "bc", "aaaa", "bbb", "aacc", "ccbb", "acdc"] + , ["", "ab", "abc", "dddd"] + ) + , ( "/[*](.*{\\}(.*[*]/.*))[*]/" -- single line C comment of form /*...*/, but without any */ in the comment body + -- this is the way to specify none greedy expessions + -- if multy line comment are required, substitute .* by \A, so newlines are allowed + , ["/**/","/***/","/*x*/","/*///*/"] + , ["", "/", "/*", "/*/", "/**/*/", "/*xxx*/xxx*/"] + ) + , ( "a{:}b{:}c" + , ["abc", "acb", "bac", "bca", "cab", "cba"] + , ["", "a", "ab", "abcc", "abca", "aba"] + ) + ] -- ------------------------------------------------------------ -simpleSplitTests :: Test +simpleSplitTests :: Test simpleSplitTests = TestLabel "simple split tests" $ TestList $ map splitTest $ tests where splitTest (re, inp, tok) - = TestCase $ - assertEqual ("split " ++ show re ++ show inp ++ " = (" ++ show tok ++ ", ... )") - tok - (fst (split re inp)) - tests = [ ("", "a", "" ) - , ("a*b", "abc", "ab" ) - , ("a*", "bc", "" ) - , ("a+", "bc", "" ) - , ("a{2}", "aaa", "aa" ) - , ("a{2,}", "aaa", "aaa" ) - , ("a|b", "ab", "a" ) - , ("a|b*", "bbba", "bbb" ) - , ("abc", "abcd", "abc" ) - ] + = TestCase $ + assertEqual ("split " ++ show re ++ show inp ++ " = (" ++ show tok ++ ", ... )") + tok + (fst (split re inp)) + tests = [ ("", "a", "" ) + , ("a*b", "abc", "ab" ) + , ("a*", "bc", "" ) + , ("a+", "bc", "" ) + , ("a{2}", "aaa", "aa" ) + , ("a{2,}", "aaa", "aaa" ) + , ("a|b", "ab", "a" ) + , ("a|b*", "bbba", "bbb" ) + , ("abc", "abcd", "abc" ) + ] -- ------------------------------------------------------------ -simpleTokenTests :: Test +simpleTokenTests :: Test simpleTokenTests = TestLabel "simple token tests" $ TestList $ map tokenTest $ tests where tokenTest (re, inp, toks) - = TestCase $ - assertEqual ("tokenize " ++ show re ++ " " ++ show inp ++ " = " ++ show toks) - toks - (tokenize re inp) - tests = [ ("", "", [] ) - , ("a", "aba", ["a", "a"] ) - , ("a", "b", [] ) - , ("a", "ba", ["a"] ) - , ("a*", "a", ["a"] ) - , ("a*", "ba", ["","a"] ) - , ("a*", "aba", ["a", "a"] ) - , ("a*", "abba", ["a", "", "a"] ) - , ("a+", "abba", ["a", "a"] ) - , ("a*b", "abba", ["ab", "b"] ) - , (".*", "a\n\nb", ["a", "", "b"] ) - , (".*", "a\n\nb\n", ["a", "", "b"] ) - , ("\\w+", "a\n\nb\n", ["a", "b"] ) - , ("\\w|ab", "aaa\n\nabc\n", ["a", "a", "a", "ab", "c"] ) - , ("\\w|ab", "aaa abc", ["a", "a", "a", "ab", "c"] ) - ] + = TestCase $ + assertEqual ("tokenize " ++ show re ++ " " ++ show inp ++ " = " ++ show toks) + toks + (tokenize re inp) + tests = [ ("", "", [] ) + , ("a", "aba", ["a", "a"] ) + , ("a", "b", [] ) + , ("a", "ba", ["a"] ) + , ("a*", "a", ["a"] ) + , ("a*", "ba", ["","a"] ) + , ("a*", "aba", ["a", "a"] ) + , ("a*", "abba", ["a", "", "a"] ) + , ("a+", "abba", ["a", "a"] ) + , ("a*b", "abba", ["ab", "b"] ) + , (".*", "a\n\nb", ["a", "", "b"] ) + , (".*", "a\n\nb\n", ["a", "", "b"] ) + , ("\\w+", "a\n\nb\n", ["a", "b"] ) + , ("\\w|ab", "aaa\n\nabc\n", ["a", "a", "a", "ab", "c"] ) + , ("\\w|ab", "aaa abc", ["a", "a", "a", "ab", "c"] ) + ] -- ------------------------------------------------------------ -allTests :: Test +allTests :: Test allTests = TestList [ parseTests @@ -249,16 +249,16 @@ , simpleTokenTests ] -main :: IO () +main :: IO () main = do c <- runTestTT allTests putStrLn $ show c let errs = errors c - fails = failures c + fails = failures c System.exitWith (codeGet errs fails) -codeGet :: Int -> Int -> ExitCode +codeGet :: Int -> Int -> ExitCode codeGet errs fails | fails > 0 = ExitFailure 2 | errs > 0 = ExitFailure 1 @@ -266,35 +266,35 @@ -- ------------------------------------------------------------ -deltaTrc :: Regex -> String -> [(String, Regex)] -deltaTrc re "" = [("", re)] -deltaTrc re s@(c:cs) = (s, re) - : - ( if isZero re' - then [("",re')] - else deltaTrc re' cs - ) +deltaTrc :: Regex -> String -> [(String, Regex)] +deltaTrc re "" = [("", re)] +deltaTrc re s@(c:cs) = (s, re) + : + ( if isZero re' + then [("",re')] + else deltaTrc re' cs + ) where - re' = delta1 re c + re' = delta1 re c -matchTrc :: String -> String -> (Bool, [(String, Regex)]) -matchTrc re = ( parseRegex >>> deltaTrc$ re ) - >>> - ( (last >>> snd >>> nullable) &&& id ) - - -trcMatch :: String -> String -> IO() -trcMatch re = putStrLn . showTrc . matchTrc re +matchTrc :: String -> String -> (Bool, [(String, Regex)]) +matchTrc re = ( parseRegex >>> deltaTrc$ re ) + >>> + ( (last >>> snd >>> nullable) &&& id ) + + +trcMatch :: String -> String -> IO() +trcMatch re = putStrLn . showTrc . matchTrc re where - showTrc = - ( (show >>> (++ "\n")) - *** - (concatMap ( ((++ "\t") *** (show >>> (++"\n"))) - >>> uncurry (++) - ) - ) - ) - >>> - uncurry (flip (++)) + showTrc = + ( (show >>> (++ "\n")) + *** + (concatMap ( ((++ "\t") *** (show >>> (++"\n"))) + >>> uncurry (++) + ) + ) + ) + >>> + uncurry (flip (++)) -- ------------------------------------------------------------ diff --git a/regex-xmlschema.cabal b/regex-xmlschema.cabal --- a/regex-xmlschema.cabal +++ b/regex-xmlschema.cabal @@ -1,5 +1,5 @@ Name: regex-xmlschema -Version: 0.1.4 +Version: 0.1.5 Synopsis: A regular expression library for W3C XML Schema regular expressions Description: This library supports full W3C XML Schema regular expressions inclusive all Unicode character sets and blocks. diff --git a/src/Text/Regex/XMLSchema/String.hs b/src/Text/Regex/XMLSchema/String.hs --- a/src/Text/Regex/XMLSchema/String.hs +++ b/src/Text/Regex/XMLSchema/String.hs @@ -64,7 +64,7 @@ , isZero , errRegex - , parseRegex -- re-export of Text.Regex.XMLSchema.String.RegexParser + , parseRegex -- re-export of Text.Regex.XMLSchema.String.RegexParser ) where @@ -83,11 +83,11 @@ -- @Nothing@ is returned in case there is no matching prefix, -- else the pair of prefix and rest is returned -splitRE :: (Eq l, Show l) => GenRegex l -> String -> Maybe (String, String) +splitRE :: (Eq l, Show l) => GenRegex l -> String -> Maybe (String, String) splitRE re input - = do - (sms, rest) <- splitWithRegex re input - return (snd . head $ sms, rest) + = do + (sms, rest) <- splitWithRegex re input + return (snd . head $ sms, rest) -- | convenient function for 'splitRE' -- @@ -98,8 +98,8 @@ -- > split "a+" "bc" = ("", "bc") -- > split "[" "abc" = ("", "abc") -split :: String -> String -> (String, String) -split re input = fromMaybe ("", input) +split :: String -> String -> (String, String) +split re input = fromMaybe ("", input) . (splitRE . parseRegex $ re) $ input -- ------------------------------------------------------------ @@ -111,11 +111,11 @@ -- else the list of pairs of labels and submatches and the -- rest is returned -splitSubexRE :: (Eq l, Show l) => GenRegex l -> String -> Maybe ([(l, String)], String) +splitSubexRE :: (Eq l, Show l) => GenRegex l -> String -> Maybe ([(l, String)], String) splitSubexRE re input - = do - (sms, rest) <- splitWithRegex re input - return (map (first fromJust) . drop 1 $ sms, rest) + = do + (sms, rest) <- splitWithRegex re input + return (map (first fromJust) . drop 1 $ sms, rest) -- | convenient function for 'splitSubex' -- @@ -140,35 +140,35 @@ -- > splitSubex "[" "abc" = ([], "abc") -- syntax error -splitSubex :: String -> String -> ([(String,String)], String) +splitSubex :: String -> String -> ([(String,String)], String) splitSubex re inp - = fromMaybe ([], inp) . (splitSubexRE . parseRegex $ re) $ inp + = fromMaybe ([], inp) . (splitSubexRE . parseRegex $ re) $ inp -- ------------------------------------------------------------ -- | The function, that does the real work for 'tokenize' -tokenizeRE :: (Eq l, Show l) => GenRegex l -> String -> [String] +tokenizeRE :: (Eq l, Show l) => GenRegex l -> String -> [String] tokenizeRE re = token'' where - re1 = mkDiff re mkUnit + re1 = mkDiff re mkUnit token'' = token' re fcs - token1'' = token' re1 fcs + token1'' = token' re1 fcs fcs = firstChars re - -- token' :: (Eq l, Show l) => GenRegex l -> CharSet -> String -> [String] + -- token' :: (Eq l, Show l) => GenRegex l -> CharSet -> String -> [String] token' re' fcs' inp - | null inp = [] - | otherwise = evalRes . splitWithRegexCS re' fcs' $ inp - where - evalRes Nothing = token'' (tail inp) -- re does not match any prefix - evalRes (Just (toks, rest)) - | null tok = tok : token'' (tail rest) -- re is nullable and only the empty prefix matches - -- discard one char and try again - | otherwise = tok : token1'' rest -- real token found, next token must not be empty - where - tok = snd . head $ toks + | null inp = [] + | otherwise = evalRes . splitWithRegexCS re' fcs' $ inp + where + evalRes Nothing = token'' (tail inp) -- re does not match any prefix + evalRes (Just (toks, rest)) + | null tok = tok : token'' (tail rest) -- re is nullable and only the empty prefix matches + -- discard one char and try again + | otherwise = tok : token1'' rest -- real token found, next token must not be empty + where + tok = snd . head $ toks -- | split a string into tokens (words) by giving a regular expression -- which all tokens must match. @@ -208,8 +208,8 @@ -- > -- > tokenize "[^ \t\n\r]*" = words -tokenize :: String -> String -> [String] -tokenize = tokenizeRE . parseRegex +tokenize :: String -> String -> [String] +tokenize = tokenizeRE . parseRegex -- ------------------------------------------------------------ @@ -225,41 +225,41 @@ -- -- > concat . map (either id id) . tokenizeRE' re == id -tokenizeRE' :: (Eq l, Show l) => GenRegex l -> String -> [Either String String] +tokenizeRE' :: (Eq l, Show l) => GenRegex l -> String -> [Either String String] tokenizeRE' re = token'' "" where - re1 = mkDiff re mkUnit + re1 = mkDiff re mkUnit token'' = token' re fcs - token1'' = token' re1 fcs + token1'' = token' re1 fcs fcs = firstChars re - -- token' :: (Eq l, Show l) => GenRegex l -> CharSet -> String -> String -> [Either String String] + -- token' :: (Eq l, Show l) => GenRegex l -> CharSet -> String -> String -> [Either String String] token' re' fcs' unmatched inp - | null inp = addUnmatched [] - | otherwise = evalRes . splitWithRegexCS re' fcs' $ inp - where - addUnmatched - | null unmatched = id - | otherwise = ((Left . reverse $ unmatched) :) + | null inp = addUnmatched [] + | otherwise = evalRes . splitWithRegexCS re' fcs' $ inp + where + addUnmatched + | null unmatched = id + | otherwise = ((Left . reverse $ unmatched) :) - addMatched t = addUnmatched . ((Right t) :) + addMatched t = addUnmatched . ((Right t) :) - evalRes Nothing = token'' ((head inp) : unmatched) (tail inp) -- re does not match any prefix + evalRes Nothing = token'' ((head inp) : unmatched) (tail inp) -- re does not match any prefix - evalRes (Just (toks, rest)) - | null tok = addMatched tok $ token'' (take 1 rest) (tail rest) -- re is nullable and only the empty prefix matches - -- discard one char and try again - | otherwise = addMatched tok $ token1'' "" rest -- real token found, next token must not be empty - where - tok = snd . head $ toks + evalRes (Just (toks, rest)) + | null tok = addMatched tok $ token'' (take 1 rest) (tail rest) -- re is nullable and only the empty prefix matches + -- discard one char and try again + | otherwise = addMatched tok $ token1'' "" rest -- real token found, next token must not be empty + where + tok = snd . head $ toks -- | convenient function for 'tokenizeRE'' -- -- When the regular expression parses as Zero, @[Left input]@ is returned, that means no tokens are found -tokenize' :: String -> String -> [Either String String] -tokenize' = tokenizeRE' . parseRegex +tokenize' :: String -> String -> [Either String String] +tokenize' = tokenizeRE' . parseRegex -- ------------------------------------------------------------ @@ -277,27 +277,27 @@ -- All none matching chars are discarded. If the given regex contains syntax errors, -- @Nothing@ is returned -tokenizeSubexRE :: (Eq l, Show l) => GenRegex l -> String -> [(l, String)] +tokenizeSubexRE :: (Eq l, Show l) => GenRegex l -> String -> [(l, String)] tokenizeSubexRE re = token'' where - re1 = mkDiff re mkUnit + re1 = mkDiff re mkUnit token'' = token' re fcs - token1'' = token' re1 fcs + token1'' = token' re1 fcs fcs = firstChars re - -- token' :: (Eq l, Show l) => GenRegex l -> CharSet -> String -> [(l,String)] + -- token' :: (Eq l, Show l) => GenRegex l -> CharSet -> String -> [(l,String)] token' re' fcs' inp - | null inp = [] - | otherwise = evalRes . splitWithRegexCS re' fcs' $ inp - where - evalRes Nothing = token'' (tail inp) -- re does not match any prefix - evalRes (Just (toks, rest)) - | null tok = res ++ token'' (tail rest) -- re is nullable and only the empty prefix matches - | otherwise = res ++ token1'' rest -- token found, tokenize the rest - where - res = map (first fromJust) . tail $ toks - tok = snd . head $ toks + | null inp = [] + | otherwise = evalRes . splitWithRegexCS re' fcs' $ inp + where + evalRes Nothing = token'' (tail inp) -- re does not match any prefix + evalRes (Just (toks, rest)) + | null tok = res ++ token'' (tail rest) -- re is nullable and only the empty prefix matches + | otherwise = res ++ token1'' rest -- token found, tokenize the rest + where + res = map (first fromJust) . tail $ toks + tok = snd . head $ toks -- | convenient function for 'tokenizeSubexRE' a string -- @@ -323,8 +323,8 @@ -- > "12 34.56" = [("real","12"),("n","12"),("f","") -- > ,("real","34.56"),("n","34"),("f","56")] -tokenizeSubex :: String -> String -> [(String,String)] -tokenizeSubex = tokenizeSubexRE . parseRegex +tokenizeSubex :: String -> String -> [(String,String)] +tokenizeSubex = tokenizeSubexRE . parseRegex -- ------------------------------------------------------------ @@ -333,8 +333,8 @@ -- All matching tokens are edited by the 1. argument, the editing function, -- all other chars remain as they are -sedRE :: (Eq l, Show l) => (String -> String) -> GenRegex l -> String -> String -sedRE edit re = concatMap (either id edit) . tokenizeRE' re +sedRE :: (Eq l, Show l) => (String -> String) -> GenRegex l -> String -> String +sedRE edit re = concatMap (either id edit) . tokenizeRE' re -- | convenient function for 'sedRE' -- @@ -344,15 +344,15 @@ -- > sed (\ x -> x ++ x) "a" "xax" = "xaax" -- > sed undefined "[" "xxx" = "xxx" -sed :: (String -> String) -> String -> String -> String -sed edit = sedRE edit . parseRegex +sed :: (String -> String) -> String -> String -> String +sed edit = sedRE edit . parseRegex -- ------------------------------------------------------------ -- | match a string with a regular expression -matchRE :: (Eq l, Show l) => GenRegex l -> String -> Bool -matchRE = matchWithRegex +matchRE :: (Eq l, Show l) => GenRegex l -> String -> Bool +matchRE = matchWithRegex -- | convenient function for 'matchRE' -- @@ -362,16 +362,16 @@ -- > match "x" "xxx" = False -- > match "[" "xxx" = False -match :: String -> String -> Bool -match = matchWithRegex . parseRegex +match :: String -> String -> Bool +match = matchWithRegex . parseRegex -- ------------------------------------------------------------ -- | match a string with a regular expression -- and extract subexpression matches -matchSubexRE :: (Eq l, Show l) => GenRegex l -> String -> [(l, String)] -matchSubexRE re = map (first fromJust) . fromMaybe [] . matchWithRegex' re +matchSubexRE :: (Eq l, Show l) => GenRegex l -> String -> [(l, String)] +matchSubexRE re = map (first fromJust) . fromMaybe [] . matchWithRegex' re -- | convenient function for 'matchRE' -- @@ -382,8 +382,8 @@ -- > matchSubex "({w}[0-9]+)x({h}[0-9]+)" "800x600" = [("w","800"),("h","600")] -- > matchSubex "[" "xxx" = [] -matchSubex :: String -> String -> [(String, String)] -matchSubex = matchSubexRE . parseRegex +matchSubex :: String -> String -> [(String, String)] +matchSubex = matchSubexRE . parseRegex -- ------------------------------------------------------------ @@ -403,20 +403,20 @@ -- > grep "\\ ["x a b", " ax "] -- > grep "a\\>" ["x a b", " ax ", " xa ", "xab"] => ["x a b", " xa "] -grep :: String -> [String] -> [String] -grep re = filter (matchRE re') - where - re' = mkSeqs . concat $ [ startContext - , (:[]) . parseRegex $ re2 - , endContext - ] - (startContext, re1) - | "^" `isPrefixOf` re = ([], tail re) - | "\\<" `isPrefixOf` re = ([parseRegex "(\\A\\W)?"], drop 2 re) - | otherwise = ([mkStar mkDot], re) - (endContext, re2) - | "$" `isSuffixOf` re1 = ([], init re1) - | "\\>" `isSuffixOf` re1 = ([parseRegex "(\\W\\A)?"], init . init $ re1) - | otherwise = ([mkStar mkDot], re1) +grep :: String -> [String] -> [String] +grep re = filter (matchRE re') + where + re' = mkSeqs . concat $ [ startContext + , (:[]) . parseRegex $ re2 + , endContext + ] + (startContext, re1) + | "^" `isPrefixOf` re = ([], tail re) + | "\\<" `isPrefixOf` re = ([parseRegex "(\\A\\W)?"], drop 2 re) + | otherwise = ([mkStar mkDot], re) + (endContext, re2) + | "$" `isSuffixOf` re1 = ([], init re1) + | "\\>" `isSuffixOf` re1 = ([parseRegex "(\\W\\A)?"], init . init $ re1) + | otherwise = ([mkStar mkDot], re1) -- ------------------------------------------------------------ diff --git a/src/Text/Regex/XMLSchema/String/Regex.hs b/src/Text/Regex/XMLSchema/String/Regex.hs --- a/src/Text/Regex/XMLSchema/String/Regex.hs +++ b/src/Text/Regex/XMLSchema/String/Regex.hs @@ -64,7 +64,6 @@ ) where -import Data.Maybe import Data.List -- ( intercalate ) import Text.Regex.XMLSchema.String.CharSet diff --git a/src/Text/Regex/XMLSchema/String/RegexParser.hs b/src/Text/Regex/XMLSchema/String/RegexParser.hs --- a/src/Text/Regex/XMLSchema/String/RegexParser.hs +++ b/src/Text/Regex/XMLSchema/String/RegexParser.hs @@ -71,7 +71,7 @@ where branchList1 = do - char '|' + _ <- char '|' orElseList orElseList :: Parser Regex @@ -84,7 +84,7 @@ where orElseList1 = do - try (string "{|}") + _ <- try (string "{|}") interleaveList interleaveList :: Parser Regex @@ -97,7 +97,7 @@ where interleaveList1 = do - try (string "{:}") + _ <- try (string "{:}") exorList exorList :: Parser Regex @@ -109,7 +109,7 @@ where exorList1 = do - try (string "{^}") + _ <- try (string "{^}") diffList diffList :: Parser Regex @@ -121,7 +121,7 @@ where diffList1 = do - try (string "{\\}") + _ <- try (string "{\\}") intersectList intersectList :: Parser Regex @@ -133,7 +133,7 @@ where intersectList1 = do - try (string "{&}") + _ <- try (string "{&}") seqList seqList :: Parser Regex @@ -163,9 +163,9 @@ return $ mkRep 1 r ) <|> try ( do - char '{' + _ <- char '{' res <- quantity r - char '}' + _ <- char '}' return res ) <|> @@ -255,11 +255,11 @@ return $ mkSym . fromJust . lookup c $ pm ) <|> ( do -- extension: \a represents the whole alphabet inclusive newline chars: \a == .|\n|\r - char 'a' + _ <- char 'a' return mkDot ) <|> ( do -- extension: \A represents all words: \A == \a* or \A == (.|\n|\r)* - char 'A' + _ <- char 'A' return mkAll ) where es = map fst pm @@ -284,7 +284,7 @@ catEsc :: Parser Regex catEsc = do - char 'p' + _ <- char 'p' s <- between (char '{') (char '}') charProp return $ mkSym s @@ -432,7 +432,7 @@ xmlCharIncDash :: Parser Regex xmlCharIncDash - = try ( do -- dash is only allowed if not followed by a [, else charGroup differences do not parse correctly + = try ( do -- dash is only allowed if not followed by a [, else charGroup differences do not parse correctly _ <- char '-' notFollowedBy (char '[') return $ mkSym1 '-' @@ -453,7 +453,7 @@ wildCardEsc :: Parser Regex wildCardEsc = do - char '.' + _ <- char '.' return . mkSym . compCS $ stringCS "\n\r" diff --git a/src/Text/Regex/XMLSchema/String/Unicode/Blocks.hs b/src/Text/Regex/XMLSchema/String/Unicode/Blocks.hs --- a/src/Text/Regex/XMLSchema/String/Unicode/Blocks.hs +++ b/src/Text/Regex/XMLSchema/String/Unicode/Blocks.hs @@ -25,203 +25,203 @@ codeBlocks :: [(String, (Char, Char))] codeBlocks = - [ ( "BasicLatin", ( '\x0000', '\x007F') ) - , ( "Latin-1Supplement", ( '\x0080', '\x00FF') ) - , ( "LatinExtended-A", ( '\x0100', '\x017F') ) - , ( "LatinExtended-B", ( '\x0180', '\x024F') ) - , ( "IPAExtensions", ( '\x0250', '\x02AF') ) - , ( "SpacingModifierLetters", ( '\x02B0', '\x02FF') ) - , ( "CombiningDiacriticalMarks", ( '\x0300', '\x036F') ) - , ( "GreekandCoptic", ( '\x0370', '\x03FF') ) - , ( "Cyrillic", ( '\x0400', '\x04FF') ) - , ( "CyrillicSupplement", ( '\x0500', '\x052F') ) - , ( "Armenian", ( '\x0530', '\x058F') ) - , ( "Hebrew", ( '\x0590', '\x05FF') ) - , ( "Arabic", ( '\x0600', '\x06FF') ) - , ( "Syriac", ( '\x0700', '\x074F') ) - , ( "ArabicSupplement", ( '\x0750', '\x077F') ) - , ( "Thaana", ( '\x0780', '\x07BF') ) - , ( "NKo", ( '\x07C0', '\x07FF') ) - , ( "Samaritan", ( '\x0800', '\x083F') ) - , ( "Devanagari", ( '\x0900', '\x097F') ) - , ( "Bengali", ( '\x0980', '\x09FF') ) - , ( "Gurmukhi", ( '\x0A00', '\x0A7F') ) - , ( "Gujarati", ( '\x0A80', '\x0AFF') ) - , ( "Oriya", ( '\x0B00', '\x0B7F') ) - , ( "Tamil", ( '\x0B80', '\x0BFF') ) - , ( "Telugu", ( '\x0C00', '\x0C7F') ) - , ( "Kannada", ( '\x0C80', '\x0CFF') ) - , ( "Malayalam", ( '\x0D00', '\x0D7F') ) - , ( "Sinhala", ( '\x0D80', '\x0DFF') ) - , ( "Thai", ( '\x0E00', '\x0E7F') ) - , ( "Lao", ( '\x0E80', '\x0EFF') ) - , ( "Tibetan", ( '\x0F00', '\x0FFF') ) - , ( "Myanmar", ( '\x1000', '\x109F') ) - , ( "Georgian", ( '\x10A0', '\x10FF') ) - , ( "HangulJamo", ( '\x1100', '\x11FF') ) - , ( "Ethiopic", ( '\x1200', '\x137F') ) - , ( "EthiopicSupplement", ( '\x1380', '\x139F') ) - , ( "Cherokee", ( '\x13A0', '\x13FF') ) - , ( "UnifiedCanadianAboriginalSyllabics", ( '\x1400', '\x167F') ) - , ( "Ogham", ( '\x1680', '\x169F') ) - , ( "Runic", ( '\x16A0', '\x16FF') ) - , ( "Tagalog", ( '\x1700', '\x171F') ) - , ( "Hanunoo", ( '\x1720', '\x173F') ) - , ( "Buhid", ( '\x1740', '\x175F') ) - , ( "Tagbanwa", ( '\x1760', '\x177F') ) - , ( "Khmer", ( '\x1780', '\x17FF') ) - , ( "Mongolian", ( '\x1800', '\x18AF') ) - , ( "UnifiedCanadianAboriginalSyllabicsExtended", ( '\x18B0', '\x18FF') ) - , ( "Limbu", ( '\x1900', '\x194F') ) - , ( "TaiLe", ( '\x1950', '\x197F') ) - , ( "NewTaiLue", ( '\x1980', '\x19DF') ) - , ( "KhmerSymbols", ( '\x19E0', '\x19FF') ) - , ( "Buginese", ( '\x1A00', '\x1A1F') ) - , ( "TaiTham", ( '\x1A20', '\x1AAF') ) - , ( "Balinese", ( '\x1B00', '\x1B7F') ) - , ( "Sundanese", ( '\x1B80', '\x1BBF') ) - , ( "Lepcha", ( '\x1C00', '\x1C4F') ) - , ( "OlChiki", ( '\x1C50', '\x1C7F') ) - , ( "VedicExtensions", ( '\x1CD0', '\x1CFF') ) - , ( "PhoneticExtensions", ( '\x1D00', '\x1D7F') ) - , ( "PhoneticExtensionsSupplement", ( '\x1D80', '\x1DBF') ) - , ( "CombiningDiacriticalMarksSupplement", ( '\x1DC0', '\x1DFF') ) - , ( "LatinExtendedAdditional", ( '\x1E00', '\x1EFF') ) - , ( "GreekExtended", ( '\x1F00', '\x1FFF') ) - , ( "GeneralPunctuation", ( '\x2000', '\x206F') ) - , ( "SuperscriptsandSubscripts", ( '\x2070', '\x209F') ) - , ( "CurrencySymbols", ( '\x20A0', '\x20CF') ) - , ( "CombiningDiacriticalMarksforSymbols", ( '\x20D0', '\x20FF') ) - , ( "LetterlikeSymbols", ( '\x2100', '\x214F') ) - , ( "NumberForms", ( '\x2150', '\x218F') ) - , ( "Arrows", ( '\x2190', '\x21FF') ) - , ( "MathematicalOperators", ( '\x2200', '\x22FF') ) - , ( "MiscellaneousTechnical", ( '\x2300', '\x23FF') ) - , ( "ControlPictures", ( '\x2400', '\x243F') ) - , ( "OpticalCharacterRecognition", ( '\x2440', '\x245F') ) - , ( "EnclosedAlphanumerics", ( '\x2460', '\x24FF') ) - , ( "BoxDrawing", ( '\x2500', '\x257F') ) - , ( "BlockElements", ( '\x2580', '\x259F') ) - , ( "GeometricShapes", ( '\x25A0', '\x25FF') ) - , ( "MiscellaneousSymbols", ( '\x2600', '\x26FF') ) - , ( "Dingbats", ( '\x2700', '\x27BF') ) - , ( "MiscellaneousMathematicalSymbols-A", ( '\x27C0', '\x27EF') ) - , ( "SupplementalArrows-A", ( '\x27F0', '\x27FF') ) - , ( "BraillePatterns", ( '\x2800', '\x28FF') ) - , ( "SupplementalArrows-B", ( '\x2900', '\x297F') ) - , ( "MiscellaneousMathematicalSymbols-B", ( '\x2980', '\x29FF') ) - , ( "SupplementalMathematicalOperators", ( '\x2A00', '\x2AFF') ) - , ( "MiscellaneousSymbolsandArrows", ( '\x2B00', '\x2BFF') ) - , ( "Glagolitic", ( '\x2C00', '\x2C5F') ) - , ( "LatinExtended-C", ( '\x2C60', '\x2C7F') ) - , ( "Coptic", ( '\x2C80', '\x2CFF') ) - , ( "GeorgianSupplement", ( '\x2D00', '\x2D2F') ) - , ( "Tifinagh", ( '\x2D30', '\x2D7F') ) - , ( "EthiopicExtended", ( '\x2D80', '\x2DDF') ) - , ( "CyrillicExtended-A", ( '\x2DE0', '\x2DFF') ) - , ( "SupplementalPunctuation", ( '\x2E00', '\x2E7F') ) - , ( "CJKRadicalsSupplement", ( '\x2E80', '\x2EFF') ) - , ( "KangxiRadicals", ( '\x2F00', '\x2FDF') ) - , ( "IdeographicDescriptionCharacters", ( '\x2FF0', '\x2FFF') ) - , ( "CJKSymbolsandPunctuation", ( '\x3000', '\x303F') ) - , ( "Hiragana", ( '\x3040', '\x309F') ) - , ( "Katakana", ( '\x30A0', '\x30FF') ) - , ( "Bopomofo", ( '\x3100', '\x312F') ) - , ( "HangulCompatibilityJamo", ( '\x3130', '\x318F') ) - , ( "Kanbun", ( '\x3190', '\x319F') ) - , ( "BopomofoExtended", ( '\x31A0', '\x31BF') ) - , ( "CJKStrokes", ( '\x31C0', '\x31EF') ) - , ( "KatakanaPhoneticExtensions", ( '\x31F0', '\x31FF') ) - , ( "EnclosedCJKLettersandMonths", ( '\x3200', '\x32FF') ) - , ( "CJKCompatibility", ( '\x3300', '\x33FF') ) - , ( "CJKUnifiedIdeographsExtensionA", ( '\x3400', '\x4DBF') ) - , ( "YijingHexagramSymbols", ( '\x4DC0', '\x4DFF') ) - , ( "CJKUnifiedIdeographs", ( '\x4E00', '\x9FFF') ) - , ( "YiSyllables", ( '\xA000', '\xA48F') ) - , ( "YiRadicals", ( '\xA490', '\xA4CF') ) - , ( "Lisu", ( '\xA4D0', '\xA4FF') ) - , ( "Vai", ( '\xA500', '\xA63F') ) - , ( "CyrillicExtended-B", ( '\xA640', '\xA69F') ) - , ( "Bamum", ( '\xA6A0', '\xA6FF') ) - , ( "ModifierToneLetters", ( '\xA700', '\xA71F') ) - , ( "LatinExtended-D", ( '\xA720', '\xA7FF') ) - , ( "SylotiNagri", ( '\xA800', '\xA82F') ) - , ( "CommonIndicNumberForms", ( '\xA830', '\xA83F') ) - , ( "Phags-pa", ( '\xA840', '\xA87F') ) - , ( "Saurashtra", ( '\xA880', '\xA8DF') ) - , ( "DevanagariExtended", ( '\xA8E0', '\xA8FF') ) - , ( "KayahLi", ( '\xA900', '\xA92F') ) - , ( "Rejang", ( '\xA930', '\xA95F') ) - , ( "HangulJamoExtended-A", ( '\xA960', '\xA97F') ) - , ( "Javanese", ( '\xA980', '\xA9DF') ) - , ( "Cham", ( '\xAA00', '\xAA5F') ) - , ( "MyanmarExtended-A", ( '\xAA60', '\xAA7F') ) - , ( "TaiViet", ( '\xAA80', '\xAADF') ) - , ( "MeeteiMayek", ( '\xABC0', '\xABFF') ) - , ( "HangulSyllables", ( '\xAC00', '\xD7AF') ) - , ( "HangulJamoExtended-B", ( '\xD7B0', '\xD7FF') ) - , ( "HighSurrogates", ( '\xD800', '\xDB7F') ) - , ( "HighPrivateUseSurrogates", ( '\xDB80', '\xDBFF') ) - , ( "LowSurrogates", ( '\xDC00', '\xDFFF') ) - , ( "PrivateUseArea", ( '\xE000', '\xF8FF') ) - , ( "CJKCompatibilityIdeographs", ( '\xF900', '\xFAFF') ) - , ( "AlphabeticPresentationForms", ( '\xFB00', '\xFB4F') ) - , ( "ArabicPresentationForms-A", ( '\xFB50', '\xFDFF') ) - , ( "VariationSelectors", ( '\xFE00', '\xFE0F') ) - , ( "VerticalForms", ( '\xFE10', '\xFE1F') ) - , ( "CombiningHalfMarks", ( '\xFE20', '\xFE2F') ) - , ( "CJKCompatibilityForms", ( '\xFE30', '\xFE4F') ) - , ( "SmallFormVariants", ( '\xFE50', '\xFE6F') ) - , ( "ArabicPresentationForms-B", ( '\xFE70', '\xFEFF') ) - , ( "HalfwidthandFullwidthForms", ( '\xFF00', '\xFFEF') ) - , ( "Specials", ( '\xFFF0', '\xFFFF') ) - , ( "LinearBSyllabary", ( '\x10000', '\x1007F') ) - , ( "LinearBIdeograms", ( '\x10080', '\x100FF') ) - , ( "AegeanNumbers", ( '\x10100', '\x1013F') ) - , ( "AncientGreekNumbers", ( '\x10140', '\x1018F') ) - , ( "AncientSymbols", ( '\x10190', '\x101CF') ) - , ( "PhaistosDisc", ( '\x101D0', '\x101FF') ) - , ( "Lycian", ( '\x10280', '\x1029F') ) - , ( "Carian", ( '\x102A0', '\x102DF') ) - , ( "OldItalic", ( '\x10300', '\x1032F') ) - , ( "Gothic", ( '\x10330', '\x1034F') ) - , ( "Ugaritic", ( '\x10380', '\x1039F') ) - , ( "OldPersian", ( '\x103A0', '\x103DF') ) - , ( "Deseret", ( '\x10400', '\x1044F') ) - , ( "Shavian", ( '\x10450', '\x1047F') ) - , ( "Osmanya", ( '\x10480', '\x104AF') ) - , ( "CypriotSyllabary", ( '\x10800', '\x1083F') ) - , ( "ImperialAramaic", ( '\x10840', '\x1085F') ) - , ( "Phoenician", ( '\x10900', '\x1091F') ) - , ( "Lydian", ( '\x10920', '\x1093F') ) - , ( "Kharoshthi", ( '\x10A00', '\x10A5F') ) - , ( "OldSouthArabian", ( '\x10A60', '\x10A7F') ) - , ( "Avestan", ( '\x10B00', '\x10B3F') ) - , ( "InscriptionalParthian", ( '\x10B40', '\x10B5F') ) - , ( "InscriptionalPahlavi", ( '\x10B60', '\x10B7F') ) - , ( "OldTurkic", ( '\x10C00', '\x10C4F') ) - , ( "RumiNumeralSymbols", ( '\x10E60', '\x10E7F') ) - , ( "Kaithi", ( '\x11080', '\x110CF') ) - , ( "Cuneiform", ( '\x12000', '\x123FF') ) - , ( "CuneiformNumbersandPunctuation", ( '\x12400', '\x1247F') ) - , ( "EgyptianHieroglyphs", ( '\x13000', '\x1342F') ) - , ( "ByzantineMusicalSymbols", ( '\x1D000', '\x1D0FF') ) - , ( "MusicalSymbols", ( '\x1D100', '\x1D1FF') ) - , ( "AncientGreekMusicalNotation", ( '\x1D200', '\x1D24F') ) - , ( "TaiXuanJingSymbols", ( '\x1D300', '\x1D35F') ) - , ( "CountingRodNumerals", ( '\x1D360', '\x1D37F') ) - , ( "MathematicalAlphanumericSymbols", ( '\x1D400', '\x1D7FF') ) - , ( "MahjongTiles", ( '\x1F000', '\x1F02F') ) - , ( "DominoTiles", ( '\x1F030', '\x1F09F') ) - , ( "EnclosedAlphanumericSupplement", ( '\x1F100', '\x1F1FF') ) - , ( "EnclosedIdeographicSupplement", ( '\x1F200', '\x1F2FF') ) - , ( "CJKUnifiedIdeographsExtensionB", ( '\x20000', '\x2A6DF') ) - , ( "CJKUnifiedIdeographsExtensionC", ( '\x2A700', '\x2B73F') ) - , ( "CJKCompatibilityIdeographsSupplement", ( '\x2F800', '\x2FA1F') ) - , ( "Tags", ( '\xE0000', '\xE007F') ) - , ( "VariationSelectorsSupplement", ( '\xE0100', '\xE01EF') ) - , ( "SupplementaryPrivateUseArea-A", ( '\xF0000', '\xFFFFF') ) - , ( "SupplementaryPrivateUseArea-B", ( '\x100000', '\x10FFFF') ) + [ ( "BasicLatin", ( '\x0000', '\x007F') ) + , ( "Latin-1Supplement", ( '\x0080', '\x00FF') ) + , ( "LatinExtended-A", ( '\x0100', '\x017F') ) + , ( "LatinExtended-B", ( '\x0180', '\x024F') ) + , ( "IPAExtensions", ( '\x0250', '\x02AF') ) + , ( "SpacingModifierLetters", ( '\x02B0', '\x02FF') ) + , ( "CombiningDiacriticalMarks", ( '\x0300', '\x036F') ) + , ( "GreekandCoptic", ( '\x0370', '\x03FF') ) + , ( "Cyrillic", ( '\x0400', '\x04FF') ) + , ( "CyrillicSupplement", ( '\x0500', '\x052F') ) + , ( "Armenian", ( '\x0530', '\x058F') ) + , ( "Hebrew", ( '\x0590', '\x05FF') ) + , ( "Arabic", ( '\x0600', '\x06FF') ) + , ( "Syriac", ( '\x0700', '\x074F') ) + , ( "ArabicSupplement", ( '\x0750', '\x077F') ) + , ( "Thaana", ( '\x0780', '\x07BF') ) + , ( "NKo", ( '\x07C0', '\x07FF') ) + , ( "Samaritan", ( '\x0800', '\x083F') ) + , ( "Devanagari", ( '\x0900', '\x097F') ) + , ( "Bengali", ( '\x0980', '\x09FF') ) + , ( "Gurmukhi", ( '\x0A00', '\x0A7F') ) + , ( "Gujarati", ( '\x0A80', '\x0AFF') ) + , ( "Oriya", ( '\x0B00', '\x0B7F') ) + , ( "Tamil", ( '\x0B80', '\x0BFF') ) + , ( "Telugu", ( '\x0C00', '\x0C7F') ) + , ( "Kannada", ( '\x0C80', '\x0CFF') ) + , ( "Malayalam", ( '\x0D00', '\x0D7F') ) + , ( "Sinhala", ( '\x0D80', '\x0DFF') ) + , ( "Thai", ( '\x0E00', '\x0E7F') ) + , ( "Lao", ( '\x0E80', '\x0EFF') ) + , ( "Tibetan", ( '\x0F00', '\x0FFF') ) + , ( "Myanmar", ( '\x1000', '\x109F') ) + , ( "Georgian", ( '\x10A0', '\x10FF') ) + , ( "HangulJamo", ( '\x1100', '\x11FF') ) + , ( "Ethiopic", ( '\x1200', '\x137F') ) + , ( "EthiopicSupplement", ( '\x1380', '\x139F') ) + , ( "Cherokee", ( '\x13A0', '\x13FF') ) + , ( "UnifiedCanadianAboriginalSyllabics", ( '\x1400', '\x167F') ) + , ( "Ogham", ( '\x1680', '\x169F') ) + , ( "Runic", ( '\x16A0', '\x16FF') ) + , ( "Tagalog", ( '\x1700', '\x171F') ) + , ( "Hanunoo", ( '\x1720', '\x173F') ) + , ( "Buhid", ( '\x1740', '\x175F') ) + , ( "Tagbanwa", ( '\x1760', '\x177F') ) + , ( "Khmer", ( '\x1780', '\x17FF') ) + , ( "Mongolian", ( '\x1800', '\x18AF') ) + , ( "UnifiedCanadianAboriginalSyllabicsExtended", ( '\x18B0', '\x18FF') ) + , ( "Limbu", ( '\x1900', '\x194F') ) + , ( "TaiLe", ( '\x1950', '\x197F') ) + , ( "NewTaiLue", ( '\x1980', '\x19DF') ) + , ( "KhmerSymbols", ( '\x19E0', '\x19FF') ) + , ( "Buginese", ( '\x1A00', '\x1A1F') ) + , ( "TaiTham", ( '\x1A20', '\x1AAF') ) + , ( "Balinese", ( '\x1B00', '\x1B7F') ) + , ( "Sundanese", ( '\x1B80', '\x1BBF') ) + , ( "Lepcha", ( '\x1C00', '\x1C4F') ) + , ( "OlChiki", ( '\x1C50', '\x1C7F') ) + , ( "VedicExtensions", ( '\x1CD0', '\x1CFF') ) + , ( "PhoneticExtensions", ( '\x1D00', '\x1D7F') ) + , ( "PhoneticExtensionsSupplement", ( '\x1D80', '\x1DBF') ) + , ( "CombiningDiacriticalMarksSupplement", ( '\x1DC0', '\x1DFF') ) + , ( "LatinExtendedAdditional", ( '\x1E00', '\x1EFF') ) + , ( "GreekExtended", ( '\x1F00', '\x1FFF') ) + , ( "GeneralPunctuation", ( '\x2000', '\x206F') ) + , ( "SuperscriptsandSubscripts", ( '\x2070', '\x209F') ) + , ( "CurrencySymbols", ( '\x20A0', '\x20CF') ) + , ( "CombiningDiacriticalMarksforSymbols", ( '\x20D0', '\x20FF') ) + , ( "LetterlikeSymbols", ( '\x2100', '\x214F') ) + , ( "NumberForms", ( '\x2150', '\x218F') ) + , ( "Arrows", ( '\x2190', '\x21FF') ) + , ( "MathematicalOperators", ( '\x2200', '\x22FF') ) + , ( "MiscellaneousTechnical", ( '\x2300', '\x23FF') ) + , ( "ControlPictures", ( '\x2400', '\x243F') ) + , ( "OpticalCharacterRecognition", ( '\x2440', '\x245F') ) + , ( "EnclosedAlphanumerics", ( '\x2460', '\x24FF') ) + , ( "BoxDrawing", ( '\x2500', '\x257F') ) + , ( "BlockElements", ( '\x2580', '\x259F') ) + , ( "GeometricShapes", ( '\x25A0', '\x25FF') ) + , ( "MiscellaneousSymbols", ( '\x2600', '\x26FF') ) + , ( "Dingbats", ( '\x2700', '\x27BF') ) + , ( "MiscellaneousMathematicalSymbols-A", ( '\x27C0', '\x27EF') ) + , ( "SupplementalArrows-A", ( '\x27F0', '\x27FF') ) + , ( "BraillePatterns", ( '\x2800', '\x28FF') ) + , ( "SupplementalArrows-B", ( '\x2900', '\x297F') ) + , ( "MiscellaneousMathematicalSymbols-B", ( '\x2980', '\x29FF') ) + , ( "SupplementalMathematicalOperators", ( '\x2A00', '\x2AFF') ) + , ( "MiscellaneousSymbolsandArrows", ( '\x2B00', '\x2BFF') ) + , ( "Glagolitic", ( '\x2C00', '\x2C5F') ) + , ( "LatinExtended-C", ( '\x2C60', '\x2C7F') ) + , ( "Coptic", ( '\x2C80', '\x2CFF') ) + , ( "GeorgianSupplement", ( '\x2D00', '\x2D2F') ) + , ( "Tifinagh", ( '\x2D30', '\x2D7F') ) + , ( "EthiopicExtended", ( '\x2D80', '\x2DDF') ) + , ( "CyrillicExtended-A", ( '\x2DE0', '\x2DFF') ) + , ( "SupplementalPunctuation", ( '\x2E00', '\x2E7F') ) + , ( "CJKRadicalsSupplement", ( '\x2E80', '\x2EFF') ) + , ( "KangxiRadicals", ( '\x2F00', '\x2FDF') ) + , ( "IdeographicDescriptionCharacters", ( '\x2FF0', '\x2FFF') ) + , ( "CJKSymbolsandPunctuation", ( '\x3000', '\x303F') ) + , ( "Hiragana", ( '\x3040', '\x309F') ) + , ( "Katakana", ( '\x30A0', '\x30FF') ) + , ( "Bopomofo", ( '\x3100', '\x312F') ) + , ( "HangulCompatibilityJamo", ( '\x3130', '\x318F') ) + , ( "Kanbun", ( '\x3190', '\x319F') ) + , ( "BopomofoExtended", ( '\x31A0', '\x31BF') ) + , ( "CJKStrokes", ( '\x31C0', '\x31EF') ) + , ( "KatakanaPhoneticExtensions", ( '\x31F0', '\x31FF') ) + , ( "EnclosedCJKLettersandMonths", ( '\x3200', '\x32FF') ) + , ( "CJKCompatibility", ( '\x3300', '\x33FF') ) + , ( "CJKUnifiedIdeographsExtensionA", ( '\x3400', '\x4DBF') ) + , ( "YijingHexagramSymbols", ( '\x4DC0', '\x4DFF') ) + , ( "CJKUnifiedIdeographs", ( '\x4E00', '\x9FFF') ) + , ( "YiSyllables", ( '\xA000', '\xA48F') ) + , ( "YiRadicals", ( '\xA490', '\xA4CF') ) + , ( "Lisu", ( '\xA4D0', '\xA4FF') ) + , ( "Vai", ( '\xA500', '\xA63F') ) + , ( "CyrillicExtended-B", ( '\xA640', '\xA69F') ) + , ( "Bamum", ( '\xA6A0', '\xA6FF') ) + , ( "ModifierToneLetters", ( '\xA700', '\xA71F') ) + , ( "LatinExtended-D", ( '\xA720', '\xA7FF') ) + , ( "SylotiNagri", ( '\xA800', '\xA82F') ) + , ( "CommonIndicNumberForms", ( '\xA830', '\xA83F') ) + , ( "Phags-pa", ( '\xA840', '\xA87F') ) + , ( "Saurashtra", ( '\xA880', '\xA8DF') ) + , ( "DevanagariExtended", ( '\xA8E0', '\xA8FF') ) + , ( "KayahLi", ( '\xA900', '\xA92F') ) + , ( "Rejang", ( '\xA930', '\xA95F') ) + , ( "HangulJamoExtended-A", ( '\xA960', '\xA97F') ) + , ( "Javanese", ( '\xA980', '\xA9DF') ) + , ( "Cham", ( '\xAA00', '\xAA5F') ) + , ( "MyanmarExtended-A", ( '\xAA60', '\xAA7F') ) + , ( "TaiViet", ( '\xAA80', '\xAADF') ) + , ( "MeeteiMayek", ( '\xABC0', '\xABFF') ) + , ( "HangulSyllables", ( '\xAC00', '\xD7AF') ) + , ( "HangulJamoExtended-B", ( '\xD7B0', '\xD7FF') ) + , ( "HighSurrogates", ( '\xD800', '\xDB7F') ) + , ( "HighPrivateUseSurrogates", ( '\xDB80', '\xDBFF') ) + , ( "LowSurrogates", ( '\xDC00', '\xDFFF') ) + , ( "PrivateUseArea", ( '\xE000', '\xF8FF') ) + , ( "CJKCompatibilityIdeographs", ( '\xF900', '\xFAFF') ) + , ( "AlphabeticPresentationForms", ( '\xFB00', '\xFB4F') ) + , ( "ArabicPresentationForms-A", ( '\xFB50', '\xFDFF') ) + , ( "VariationSelectors", ( '\xFE00', '\xFE0F') ) + , ( "VerticalForms", ( '\xFE10', '\xFE1F') ) + , ( "CombiningHalfMarks", ( '\xFE20', '\xFE2F') ) + , ( "CJKCompatibilityForms", ( '\xFE30', '\xFE4F') ) + , ( "SmallFormVariants", ( '\xFE50', '\xFE6F') ) + , ( "ArabicPresentationForms-B", ( '\xFE70', '\xFEFF') ) + , ( "HalfwidthandFullwidthForms", ( '\xFF00', '\xFFEF') ) + , ( "Specials", ( '\xFFF0', '\xFFFF') ) + , ( "LinearBSyllabary", ( '\x10000', '\x1007F') ) + , ( "LinearBIdeograms", ( '\x10080', '\x100FF') ) + , ( "AegeanNumbers", ( '\x10100', '\x1013F') ) + , ( "AncientGreekNumbers", ( '\x10140', '\x1018F') ) + , ( "AncientSymbols", ( '\x10190', '\x101CF') ) + , ( "PhaistosDisc", ( '\x101D0', '\x101FF') ) + , ( "Lycian", ( '\x10280', '\x1029F') ) + , ( "Carian", ( '\x102A0', '\x102DF') ) + , ( "OldItalic", ( '\x10300', '\x1032F') ) + , ( "Gothic", ( '\x10330', '\x1034F') ) + , ( "Ugaritic", ( '\x10380', '\x1039F') ) + , ( "OldPersian", ( '\x103A0', '\x103DF') ) + , ( "Deseret", ( '\x10400', '\x1044F') ) + , ( "Shavian", ( '\x10450', '\x1047F') ) + , ( "Osmanya", ( '\x10480', '\x104AF') ) + , ( "CypriotSyllabary", ( '\x10800', '\x1083F') ) + , ( "ImperialAramaic", ( '\x10840', '\x1085F') ) + , ( "Phoenician", ( '\x10900', '\x1091F') ) + , ( "Lydian", ( '\x10920', '\x1093F') ) + , ( "Kharoshthi", ( '\x10A00', '\x10A5F') ) + , ( "OldSouthArabian", ( '\x10A60', '\x10A7F') ) + , ( "Avestan", ( '\x10B00', '\x10B3F') ) + , ( "InscriptionalParthian", ( '\x10B40', '\x10B5F') ) + , ( "InscriptionalPahlavi", ( '\x10B60', '\x10B7F') ) + , ( "OldTurkic", ( '\x10C00', '\x10C4F') ) + , ( "RumiNumeralSymbols", ( '\x10E60', '\x10E7F') ) + , ( "Kaithi", ( '\x11080', '\x110CF') ) + , ( "Cuneiform", ( '\x12000', '\x123FF') ) + , ( "CuneiformNumbersandPunctuation", ( '\x12400', '\x1247F') ) + , ( "EgyptianHieroglyphs", ( '\x13000', '\x1342F') ) + , ( "ByzantineMusicalSymbols", ( '\x1D000', '\x1D0FF') ) + , ( "MusicalSymbols", ( '\x1D100', '\x1D1FF') ) + , ( "AncientGreekMusicalNotation", ( '\x1D200', '\x1D24F') ) + , ( "TaiXuanJingSymbols", ( '\x1D300', '\x1D35F') ) + , ( "CountingRodNumerals", ( '\x1D360', '\x1D37F') ) + , ( "MathematicalAlphanumericSymbols", ( '\x1D400', '\x1D7FF') ) + , ( "MahjongTiles", ( '\x1F000', '\x1F02F') ) + , ( "DominoTiles", ( '\x1F030', '\x1F09F') ) + , ( "EnclosedAlphanumericSupplement", ( '\x1F100', '\x1F1FF') ) + , ( "EnclosedIdeographicSupplement", ( '\x1F200', '\x1F2FF') ) + , ( "CJKUnifiedIdeographsExtensionB", ( '\x20000', '\x2A6DF') ) + , ( "CJKUnifiedIdeographsExtensionC", ( '\x2A700', '\x2B73F') ) + , ( "CJKCompatibilityIdeographsSupplement", ( '\x2F800', '\x2FA1F') ) + , ( "Tags", ( '\xE0000', '\xE007F') ) + , ( "VariationSelectorsSupplement", ( '\xE0100', '\xE01EF') ) + , ( "SupplementaryPrivateUseArea-A", ( '\xF0000', '\xFFFFF') ) + , ( "SupplementaryPrivateUseArea-B", ( '\x100000', '\x10FFFF') ) ] -- ------------------------------------------------------------ diff --git a/src/Text/Regex/XMLSchema/String/Unicode/Blocks.txt b/src/Text/Regex/XMLSchema/String/Unicode/Blocks.txt --- a/src/Text/Regex/XMLSchema/String/Unicode/Blocks.txt +++ b/src/Text/Regex/XMLSchema/String/Unicode/Blocks.txt @@ -17,7 +17,7 @@ # Note: When comparing block names, casing, whitespace, hyphens, # and underbars are ignored. # For example, "Latin Extended-A" and "latin extended a" are equivalent. -# For more information on the comparison of property values, +# For more information on the comparison of property values, # see UAX #44: http://www.unicode.org/reports/tr44/ # # All code points not explicitly listed for Block diff --git a/src/Text/Regex/XMLSchema/String/Unicode/CharProps.hs b/src/Text/Regex/XMLSchema/String/Unicode/CharProps.hs --- a/src/Text/Regex/XMLSchema/String/Unicode/CharProps.hs +++ b/src/Text/Regex/XMLSchema/String/Unicode/CharProps.hs @@ -62,7 +62,7 @@ -- ------------------------------------------------------------ -isUnicodeC :: CharSet +isUnicodeC :: CharSet isUnicodeC = [ ('\NUL','\US') , ('\DEL','\159') @@ -94,7 +94,7 @@ -- ------------------------------------------------------------ -isUnicodeCc :: CharSet +isUnicodeCc :: CharSet isUnicodeCc = [ ('\NUL','\US') , ('\DEL','\159') @@ -102,7 +102,7 @@ -- ------------------------------------------------------------ -isUnicodeCf :: CharSet +isUnicodeCf :: CharSet isUnicodeCf = [ ('\173','\173') , ('\1536','\1539') @@ -123,7 +123,7 @@ -- ------------------------------------------------------------ -isUnicodeCo :: CharSet +isUnicodeCo :: CharSet isUnicodeCo = [ ('\57344','\57344') , ('\63743','\63743') @@ -135,7 +135,7 @@ -- ------------------------------------------------------------ -isUnicodeCs :: CharSet +isUnicodeCs :: CharSet isUnicodeCs = [ ('\55296','\55296') , ('\56191','\56192') @@ -145,7 +145,7 @@ -- ------------------------------------------------------------ -isUnicodeL :: CharSet +isUnicodeL :: CharSet isUnicodeL = [ ('A','Z') , ('a','z') @@ -578,7 +578,7 @@ -- ------------------------------------------------------------ -isUnicodeLl :: CharSet +isUnicodeLl :: CharSet isUnicodeLl = [ ('a','z') , ('\170','\170') @@ -1183,7 +1183,7 @@ -- ------------------------------------------------------------ -isUnicodeLm :: CharSet +isUnicodeLm :: CharSet isUnicodeLm = [ ('\688','\705') , ('\710','\721') @@ -1238,7 +1238,7 @@ -- ------------------------------------------------------------ -isUnicodeLo :: CharSet +isUnicodeLo :: CharSet isUnicodeLo = [ ('\443','\443') , ('\448','\451') @@ -1560,7 +1560,7 @@ -- ------------------------------------------------------------ -isUnicodeLt :: CharSet +isUnicodeLt :: CharSet isUnicodeLt = [ ('\453','\453') , ('\456','\456') @@ -1576,7 +1576,7 @@ -- ------------------------------------------------------------ -isUnicodeLu :: CharSet +isUnicodeLu :: CharSet isUnicodeLu = [ ('A','Z') , ('\192','\214') @@ -2176,7 +2176,7 @@ -- ------------------------------------------------------------ -isUnicodeM :: CharSet +isUnicodeM :: CharSet isUnicodeM = [ ('\768','\879') , ('\1155','\1161') @@ -2370,7 +2370,7 @@ -- ------------------------------------------------------------ -isUnicodeMc :: CharSet +isUnicodeMc :: CharSet isUnicodeMc = [ ('\2307','\2307') , ('\2366','\2368') @@ -2482,7 +2482,7 @@ -- ------------------------------------------------------------ -isUnicodeMe :: CharSet +isUnicodeMe :: CharSet isUnicodeMe = [ ('\1160','\1161') , ('\1758','\1758') @@ -2493,7 +2493,7 @@ -- ------------------------------------------------------------ -isUnicodeMn :: CharSet +isUnicodeMn :: CharSet isUnicodeMn = [ ('\768','\879') , ('\1155','\1159') @@ -2693,7 +2693,7 @@ -- ------------------------------------------------------------ -isUnicodeN :: CharSet +isUnicodeN :: CharSet isUnicodeN = [ ('0','9') , ('\178','\179') @@ -2780,7 +2780,7 @@ -- ------------------------------------------------------------ -isUnicodeNd :: CharSet +isUnicodeNd :: CharSet isUnicodeNd = [ ('0','9') , ('\1632','\1641') @@ -2823,7 +2823,7 @@ -- ------------------------------------------------------------ -isUnicodeNl :: CharSet +isUnicodeNl :: CharSet isUnicodeNl = [ ('\5870','\5872') , ('\8544','\8578') @@ -2841,7 +2841,7 @@ -- ------------------------------------------------------------ -isUnicodeNo :: CharSet +isUnicodeNo :: CharSet isUnicodeNo = [ ('\178','\179') , ('\185','\185') @@ -2885,7 +2885,7 @@ -- ------------------------------------------------------------ -isUnicodeP :: CharSet +isUnicodeP :: CharSet isUnicodeP = [ ('!','#') , ('%','*') @@ -3020,7 +3020,7 @@ -- ------------------------------------------------------------ -isUnicodePc :: CharSet +isUnicodePc :: CharSet isUnicodePc = [ ('_','_') , ('\8255','\8256') @@ -3032,7 +3032,7 @@ -- ------------------------------------------------------------ -isUnicodePd :: CharSet +isUnicodePd :: CharSet isUnicodePd = [ ('-','-') , ('\1418','\1418') @@ -3053,7 +3053,7 @@ -- ------------------------------------------------------------ -isUnicodePe :: CharSet +isUnicodePe :: CharSet isUnicodePe = [ (')',')') , (']',']') @@ -3129,7 +3129,7 @@ -- ------------------------------------------------------------ -isUnicodePf :: CharSet +isUnicodePf :: CharSet isUnicodePf = [ ('\187','\187') , ('\8217','\8217') @@ -3145,7 +3145,7 @@ -- ------------------------------------------------------------ -isUnicodePi :: CharSet +isUnicodePi :: CharSet isUnicodePi = [ ('\171','\171') , ('\8216','\8216') @@ -3162,7 +3162,7 @@ -- ------------------------------------------------------------ -isUnicodePo :: CharSet +isUnicodePo :: CharSet isUnicodePo = [ ('!','#') , ('%','\'') @@ -3292,7 +3292,7 @@ -- ------------------------------------------------------------ -isUnicodePs :: CharSet +isUnicodePs :: CharSet isUnicodePs = [ ('(','(') , ('[','[') @@ -3370,7 +3370,7 @@ -- ------------------------------------------------------------ -isUnicodeS :: CharSet +isUnicodeS :: CharSet isUnicodeS = [ ('$','$') , ('+','+') @@ -3574,7 +3574,7 @@ -- ------------------------------------------------------------ -isUnicodeSc :: CharSet +isUnicodeSc :: CharSet isUnicodeSc = [ ('$','$') , ('\162','\165') @@ -3596,7 +3596,7 @@ -- ------------------------------------------------------------ -isUnicodeSk :: CharSet +isUnicodeSk :: CharSet isUnicodeSk = [ ('^','^') , ('`','`') @@ -3628,7 +3628,7 @@ -- ------------------------------------------------------------ -isUnicodeSm :: CharSet +isUnicodeSm :: CharSet isUnicodeSm = [ ('+','+') , ('<','>') @@ -3699,7 +3699,7 @@ -- ------------------------------------------------------------ -isUnicodeSo :: CharSet +isUnicodeSo :: CharSet isUnicodeSo = [ ('\166','\167') , ('\169','\169') @@ -3859,7 +3859,7 @@ -- ------------------------------------------------------------ -isUnicodeZ :: CharSet +isUnicodeZ :: CharSet isUnicodeZ = [ (' ',' ') , ('\160','\160') @@ -3874,21 +3874,21 @@ -- ------------------------------------------------------------ -isUnicodeZl :: CharSet +isUnicodeZl :: CharSet isUnicodeZl = [ ('\8232','\8232') ] -- ------------------------------------------------------------ -isUnicodeZp :: CharSet +isUnicodeZp :: CharSet isUnicodeZp = [ ('\8233','\8233') ] -- ------------------------------------------------------------ -isUnicodeZs :: CharSet +isUnicodeZs :: CharSet isUnicodeZs = [ (' ',' ') , ('\160','\160') diff --git a/src/Text/Regex/XMLSchema/String/Unicode/GenBlocks.hs b/src/Text/Regex/XMLSchema/String/Unicode/GenBlocks.hs --- a/src/Text/Regex/XMLSchema/String/Unicode/GenBlocks.hs +++ b/src/Text/Regex/XMLSchema/String/Unicode/GenBlocks.hs @@ -89,6 +89,6 @@ 'a' <= c && c <= 'z' || '0' <= c && c <= '9' || '-' == c - + cmt :: String cmt = "-- " ++ replicate 60 '-' diff --git a/src/Text/Regex/XMLSchema/String/XML/CharProps.hs b/src/Text/Regex/XMLSchema/String/XML/CharProps.hs --- a/src/Text/Regex/XMLSchema/String/XML/CharProps.hs +++ b/src/Text/Regex/XMLSchema/String/XML/CharProps.hs @@ -41,7 +41,7 @@ -- | -- checking for valid XML characters -isXmlChar :: CharSet +isXmlChar :: CharSet isXmlChar = [ ('\x0009', '\x000A') , ('\x000D', '\x000D') @@ -53,7 +53,7 @@ -- | -- checking for XML space character: \\\n, \\\r, \\\t and \" \" -isXmlSpaceChar :: CharSet +isXmlSpaceChar :: CharSet isXmlSpaceChar = stringCS ['\x20', '\x09', '\x0D', '\x0A'] @@ -62,22 +62,22 @@ -- -- see also : 'isXmlSpaceChar' -isXml11SpaceChar :: CharSet +isXml11SpaceChar :: CharSet isXml11SpaceChar = stringCS ['\x20', '\x09', '\x0D', '\x0A', '\x85', '\x2028'] -- | -- checking for XML name character -isXmlNameChar :: CharSet +isXmlNameChar :: CharSet isXmlNameChar = isXmlLetter `unionCS` isXmlDigit `unionCS` - (singleCS '\x2D' `unionCS` singleCS '\x2E') -- '-' | '.' + (singleCS '\x2D' `unionCS` singleCS '\x2E') -- '-' | '.' `unionCS` - (singleCS '\x3A' `unionCS` singleCS '\x5F') -- Letter | ':' | '_' + (singleCS '\x3A' `unionCS` singleCS '\x5F') -- Letter | ':' | '_' `unionCS` isXmlCombiningChar `unionCS` @@ -88,20 +88,20 @@ -- -- see also : 'isXmlNameChar' -isXmlNameStartChar :: CharSet +isXmlNameStartChar :: CharSet isXmlNameStartChar = isXmlLetter `unionCS` singleCS '\x3A' `unionCS` - singleCS '\x5F' -- Letter | ':' | '_' + singleCS '\x5F' -- Letter | ':' | '_' -- | -- checking for XML NCName character: no \":\" allowed -- -- see also : 'isXmlNameChar' -isXmlNCNameChar :: CharSet +isXmlNCNameChar :: CharSet isXmlNCNameChar = isXmlNameChar `diffCS` @@ -112,7 +112,7 @@ -- -- see also : 'isXmlNameChar', 'isXmlNCNameChar' -isXmlNCNameStartChar :: CharSet +isXmlNCNameStartChar :: CharSet isXmlNCNameStartChar = isXmlNameStartChar `diffCS` @@ -121,7 +121,7 @@ -- | -- checking for XML public id character -isXmlPubidChar :: CharSet +isXmlPubidChar :: CharSet isXmlPubidChar = rangeCS '0' '9' `unionCS` @@ -134,7 +134,7 @@ -- | -- checking for XML letter -isXmlLetter :: CharSet +isXmlLetter :: CharSet isXmlLetter = isXmlBaseChar `unionCS` @@ -143,7 +143,7 @@ -- | -- checking for XML base charater -isXmlBaseChar :: CharSet +isXmlBaseChar :: CharSet isXmlBaseChar = [ ('\x0041', '\x005A') , ('\x0061', '\x007A') @@ -351,7 +351,7 @@ -- | -- checking for XML ideographic charater -isXmlIdeographicChar :: CharSet +isXmlIdeographicChar :: CharSet isXmlIdeographicChar = [ ('\x3007', '\x3007') , ('\x3021', '\x3029') @@ -361,7 +361,7 @@ -- | -- checking for XML combining charater -isXmlCombiningChar :: CharSet +isXmlCombiningChar :: CharSet isXmlCombiningChar = [ ('\x0300', '\x0345') , ('\x0360', '\x0361') @@ -463,7 +463,7 @@ -- | -- checking for XML digit -isXmlDigit :: CharSet +isXmlDigit :: CharSet isXmlDigit = [ ('\x0030', '\x0039') , ('\x0660', '\x0669') @@ -485,7 +485,7 @@ -- | -- checking for XML extender -isXmlExtender :: CharSet +isXmlExtender :: CharSet isXmlExtender = [ ('\x00B7', '\x00B7') , ('\x02D0', '\x02D0') @@ -511,7 +511,7 @@ -- They are either control characters or permanently undefined Unicode characters: -isXmlControlOrPermanentlyUndefined :: CharSet +isXmlControlOrPermanentlyUndefined :: CharSet isXmlControlOrPermanentlyUndefined = [ ('\x7F', '\x84') , ('\x86', '\x9F')