diff --git a/CHANGES.txt b/CHANGES.txt --- a/CHANGES.txt +++ b/CHANGES.txt @@ -1,5 +1,7 @@ Changelog for TagSoup +0.14.2 + #66, make sure positions are correct for lone & characters 0.14.1 #63, add maybeAttrib 0.14 diff --git a/Main.hs b/Main.hs deleted file mode 100644 --- a/Main.hs +++ /dev/null @@ -1,59 +0,0 @@ - -module Main(main) where - -import System.Environment -import TagSoup.Sample -import TagSoup.Test -import TagSoup.Benchmark -import Data.Char(toLower) - - -helpMsg :: IO () -helpMsg = putStr $ unlines $ - ["TagSoup, (C) Neil Mitchell 2006-2009" - ,"" - ," tagsoup arguments" - ,"" - ," may either be a local file, or a http:// page" - ,"" - ] ++ map f res - where - width = maximum $ map (length . fst) res - res = map g actions - - g (nam,msg,Left _) = (nam,msg) - g (nam,msg,Right _) = (nam ++ " ",msg) - - f (lhs,rhs) = " " ++ lhs ++ replicate (4 + width - length lhs) ' ' ++ rhs - - -actions :: [(String, String, Either (IO ()) (String -> IO ()))] -actions = [("test","Run the test suite",Left test) - ,("grab","Grab a web page",Right grab) - ,("parse","Parse a web page",Right parse) - ,("bench","Benchmark the parsing",Left time) - ,("benchfile","Benchmark the parsing of a file",Right timefile) - ,("validate","Validate a page",Right validate) - ,("lastmodifieddate","Get the wiki.haskell.org last modified date",Left haskellLastModifiedDateTime) - ,("spj","Simon Peyton Jones' papers",Left spjPapers) - ,("ndm","Neil Mitchell's papers",Left ndmPapers) - ,("time","Current time",Left currentTime) - ,("google","Google Tech News",Left googleTechNews) - ,("sequence","Creators on sequence.complete.org",Left rssCreators) - ,("help","This help message",Left helpMsg) - ] - -main :: IO () -main = do - args <- getArgs - case (args, lookup (map toLower $ head args) $ map (\(a,_,c) -> (a,c)) actions) of - ([],_) -> helpMsg - (x:_,Nothing) -> putStrLn ("Error: unknown command " ++ x) >> helpMsg - ([_],Just (Left a)) -> a - (x:xs,Just (Left a)) -> do - putStrLn $ "Warning: expected no arguments to " ++ x ++ " but got: " ++ unwords xs - a - ([_,y],Just (Right a)) -> a y - (x:xs,Just (Right _)) -> do - putStrLn $ "Error: expected exactly one argument to " ++ x ++ " but got: " ++ unwords xs - helpMsg diff --git a/TagSoup/Benchmark.hs b/TagSoup/Benchmark.hs deleted file mode 100644 --- a/TagSoup/Benchmark.hs +++ /dev/null @@ -1,201 +0,0 @@ -{-# LANGUAGE CPP #-} - -module TagSoup.Benchmark where - -import Text.HTML.TagSoup - -import Control.DeepSeq -import Control.Monad -import Data.List -import Data.Maybe -import System.IO.Unsafe(unsafeInterleaveIO) -import qualified Data.ByteString.Char8 as BS -import qualified Data.ByteString.Lazy.Char8 as LBS -import Data.Time.Clock.POSIX(getPOSIXTime) - -conf = 0.95 - - -timefile :: FilePath -> IO () -timefile file = do - -- use LBS to be most representative of real life - lbs <- LBS.readFile file - let str = LBS.unpack lbs - bs = BS.concat $ LBS.toChunks lbs - () <- LBS.length lbs `seq` length str `seq` BS.length bs `seq` return () - benchWith (const str, const bs, const lbs) $ benchStatic (toInteger $ LBS.length lbs) - - -sample :: String -sample = " is " ++ - " and some just random & test ><" - -nsample = genericLength sample :: Integer - -time :: IO () -time = benchWith (str,bs,lbs) benchVariable - where - str = \i -> concat $ genericReplicate i sample - bs = let s = BS.pack sample in \i -> BS.concat (genericReplicate i s) - lbs = let s = LBS.pack sample in \i -> LBS.concat (genericReplicate i s) - - - -benchWith :: (Integer -> String, Integer -> BS.ByteString, Integer -> LBS.ByteString) - -> ((Integer -> ()) -> IO [String]) -> IO () -benchWith (str,bs,lbs) bench = do - putStrLn "Timing parseTags in characters/second" - let header = map (:[]) ["(" ++ show (round $ conf * 100) ++ "% confidence)","String","BS","LBS"] - rows <- mapM row $ replicateM 3 [False,True] - mapM_ (putStrLn . strict . grid) $ delay2 $ header : rows - where - row [a,b,c] = do - let header = intercalate "," [g a "pos", g b "warn", g c "merge"] - g b x = (if b then ' ' else '!') : x - f x = bench $ \i -> rnf $ parseTagsOptions parseOptions{optTagPosition=a,optTagWarning=b,optTagTextMerge=c} $ x i - c1 <- f str - c2 <- f bs - c3 <- f lbs - return [[header],c1,c2,c3] - - strict = reverse . reverse - - ---------------------------------------------------------------------- --- BENCHMARK ON THE SAMPLE INPUT - -disp xs = showUnit (floor xbar) ++ " (~" ++ rng ++ "%)" - where xbar = mean xs - rng = if length xs <= 1 then "?" else show (ceiling $ (range conf xs) * 100 / xbar) - -cons x = fmap (x:) - - -aimTime = 0.3 :: Double -- seconds to aim for -minTime = 0.2 :: Double -- below this a test is considered invalid - - --- given a number of times to repeat sample, return a list of what --- to display -benchVariable :: (Integer -> ()) -> IO [String] -benchVariable op = cons "?" $ f 10 [] - where - f i seen | length seen > 9 = cons (" " ++ disp seen) $ return [] - | otherwise = unsafeInterleaveIO $ do - now <- timer $ op i - let cps = if now == 0 then 0 else fromInteger (i * nsample) / now - if now < minTime || (null seen && now < aimTime) then do - let factor = min 7 $ max 2 $ floor $ aimTime / now - cons ("? " ++ disp [cps]) $ f (i * factor) [] - else - cons (show (9 - length seen) ++ " " ++ disp (cps:seen)) $ f i (cps:seen) - - - -benchStatic :: Integer -> (Integer -> ()) -> IO [String] -benchStatic nsample op = cons "?" $ f [] - where - f seen | length seen > 9 = cons (" " ++ disp seen) $ return [] - | otherwise = unsafeInterleaveIO $ do - now <- timer $ op $ genericLength seen - let cps = if now == 0 then 0 else fromInteger nsample / now - cons (show (9 - length seen) ++ " " ++ disp (cps:seen)) $ f (cps:seen) - - ---------------------------------------------------------------------- --- UTILITY FUNCTIONS - --- | Given a number, show it using a unit and decimal place -showUnit :: Integer -> String -showUnit x = num ++ unit - where - units = " KMGTPEZY" - (use,skip) = splitAt 3 $ show x - - unit = [units !! ((length skip + 2) `div` 3)] - - dot = ((length skip - 1) `mod` 3) + 1 - num = a ++ ['.' | b /= ""] ++ b - where (a,b) = splitAt dot use - - --- copied from the criterion package -getTime :: IO Double -getTime = (fromRational . toRational) `fmap` getPOSIXTime - -timer :: () -> IO Double -timer x = do - start <- getTime - () <- return x - end <- getTime - return $ end - start - - --- display a grid -grid :: [[String]] -> String -grid xs = unlines $ map (concat . zipWith f cols) xs - where cols = map (maximum . map length) $ transpose xs - f n x = x ++ replicate (n+1 - length x) ' ' - - --- display a series of grids over time --- when a grid gets to [] keep its value at that --- when all grids get to [] return [] -delay2 :: [[[String]]] -> [[[String]]] -delay2 xs = map (map head) xs : (if all (null . tail) (concat xs) then [] else delay2 $ map (map tl) xs) - where tl (x:xs) = if null xs then x:xs else xs - - ---------------------------------------------------------------------- --- INSTANCES - -instance NFData a => NFData (Tag a) where - rnf (TagOpen x y) = rnf x `seq` rnf y - rnf (TagClose x) = rnf x - rnf (TagText x) = rnf x - rnf (TagComment x) = rnf x - rnf (TagWarning x) = rnf x - rnf (TagPosition x y) = () -- both are already ! bound - - -#ifndef BYTESTRING_HAS_NFDATA -# ifdef MIN_VERSION_bytestring -# define BYTESTRING_HAS_NFDATA (MIN_VERSION_bytestring(0,10,0)) -# else -# define BYTESTRING_HAS_NFDATA (__GLASGOW_HASKELL__ >= 706) -# endif -#endif - -#if !BYTESTRING_HAS_NFDATA -instance NFData LBS.ByteString where - rnf x = LBS.length x `seq` () - -instance NFData BS.ByteString where - rnf x = BS.length x `seq` () -#endif - - ---------------------------------------------------------------------- --- STATISTICS --- Provided by Emily Mitchell - -confNs = let (*) = (,) in - [0.95 * 1.96 - ,0.90 * 1.644] - -size :: [Double] -> Double -size = genericLength - -mean :: [Double] -> Double -mean xs = sum xs / size xs - -stddev :: [Double] -> Double -stddev xs = sqrt $ sum [sqr (x - xbar) | x <- xs] / size xs - where xbar = mean xs - sqr x = x * x - --- given a sample, and a required confidence --- of the mean (i.e. 2.5% = 0.025) -range ::Double -> [Double] -> Double -range conf xs = conf2 * stddev xs / sqrt (size xs) - where conf2 = fromMaybe (error $ "Unknown confidence interval: " ++ show conf) $ lookup conf confNs diff --git a/TagSoup/Sample.hs b/TagSoup/Sample.hs deleted file mode 100644 --- a/TagSoup/Sample.hs +++ /dev/null @@ -1,154 +0,0 @@ - -module TagSoup.Sample where - -import Text.HTML.TagSoup - -import Control.Exception -import Control.Monad -import Data.List -import System.Cmd -import System.Directory -import System.Exit -import System.IO - - -openItem :: String -> IO String -openItem url | not $ "http://" `isPrefixOf` url = readFile url -openItem url = bracket - (openTempFile "." "tagsoup.tmp") - (\(file,hndl) -> removeFile file) - $ \(file,hndl) -> do - hClose hndl - putStrLn $ "Downloading: " ++ url - res <- system $ "wget " ++ url ++ " -O " ++ file - when (res /= ExitSuccess) $ error $ "Failed to download using wget: " ++ url - src <- readFile file - length src `seq` return src - - -grab :: String -> IO () -grab x = openItem x >>= putStr - -parse :: String -> IO () -parse x = openItem x >>= putStr . show2 . parseTags - where - show2 [] = "[]" - show2 xs = "[" ++ concat (intersperseNotBroken "\n," $ map show xs) ++ "\n]\n" - - --- the standard intersperse has a strictness bug which sucks! -intersperseNotBroken :: a -> [a] -> [a] -intersperseNotBroken _ [] = [] -intersperseNotBroken sep (x:xs) = x : is xs - where - is [] = [] - is (y:ys) = sep : y : is ys - - -{- -
  • This page was last modified on 9 September 2013, at 22:38.
    • --} -haskellLastModifiedDateTime :: IO () -haskellLastModifiedDateTime = do - src <- openItem "http://wiki.haskell.org/Haskell" - let lastModifiedDateTime = fromFooter $ parseTags src - putStrLn $ "wiki.haskell.org was last modified on " ++ lastModifiedDateTime - where fromFooter = unwords . drop 6 . words . innerText . take 2 . dropWhile (~/= "
  • ") - - -googleTechNews :: IO () -googleTechNews = do - tags <- fmap parseTags $ openItem "http://news.google.com/?ned=us&topic=t" - let links = [ ascii name ++ " <" ++ maybe "unknown" shortUrl (lookup "href" atts) ++ ">" - | TagOpen "h2" [("class","title")]:TagText spaces:TagOpen "a" atts:TagText name:_ <- tails tags] - putStr $ unlines links - where - shortUrl x | "http://" `isPrefixOf` x = shortUrl $ drop 7 x - | "www." `isPrefixOf` x = shortUrl $ drop 4 x - | otherwise = takeWhile (/= '/') x - - ascii ('\226':'\128':'\147':xs) = '-' : ascii xs - ascii ('\194':'\163':xs) = "#GBP " ++ ascii xs - ascii (x:xs) = x : ascii xs - ascii [] = [] - - -spjPapers :: IO () -spjPapers = do - tags <- parseTags <$> openItem "http://research.microsoft.com/en-us/people/simonpj/" - let links = map f $ sections (~== "") $ - takeWhile (~/= "") $ - drop 5 $ dropWhile (~/= "") tags - putStr $ unlines links - where - f :: [Tag String] -> String - f = dequote . unwords . words . fromTagText . head . filter isTagText - - dequote ('\"':xs) | last xs == '\"' = init xs - dequote x = x - - -ndmPapers :: IO () -ndmPapers = do - tags <- parseTags <$> openItem "http://community.haskell.org/~ndm/downloads/" - let papers = map f $ sections (~== "
  • ") tags - putStr $ unlines papers - where - f :: [Tag String] -> String - f xs = fromTagText (xs !! 2) - - -currentTime :: IO () -currentTime = do - tags <- parseTags <$> openItem "http://www.timeanddate.com/worldclock/uk/london" - let time = fromTagText (dropWhile (~/= "") tags !! 1) - putStrLn time - - - -type Section = String -data Package = Package {name :: String, desc :: String, href :: String} - deriving Show - -hackage :: IO [(Section,[Package])] -hackage = do - tags <- fmap parseTags $ openItem "http://hackage.haskell.org/packages/archive/pkg-list.html" - return $ map parseSect $ partitions (~== "

    ") tags - where - parseSect xs = (nam, packs) - where - nam = fromTagText $ xs !! 2 - packs = map parsePackage $ partitions (~== "
  • ") xs - - parsePackage xs = - Package - (fromTagText $ xs !! 2) - (drop 2 $ dropWhile (/= ':') $ fromTagText $ xs !! 4) - (fromAttrib "href" $ xs !! 1) - --- rssCreators Example: prints names of story contributors on --- sequence.complete.org. This content is RSS (not HTML), and the selected --- tag uses a different XML namespace "dc:creator". -rssCreators :: IO () -rssCreators = do - tags <- fmap parseTags $ openItem "http://sequence.complete.org/node/feed" - putStrLn $ unlines $ map names $ partitions (~== "") tags - where names xs = fromTagText $ xs !! 1 - - -validate :: String -> IO () -validate x = putStr . unlines . g . f . parseTagsOptions opts =<< openItem x - where - opts = parseOptions{optTagPosition=True, optTagWarning=True} - - f :: [Tag String] -> [String] - f (TagPosition row col:TagWarning warn:rest) = - ("Warning (" ++ show row ++ "," ++ show col ++ "): " ++ warn) : f rest - f (TagWarning warn:rest) = - ("Warning (?,?): " ++ warn) : f rest - f (_:rest) = f rest - f [] = [] - - g xs = xs ++ [if n == 0 then "Success, no warnings" - else "Failed, " ++ show n ++ " warning" ++ ['s'|n>1]] - where n = length xs diff --git a/TagSoup/Test.hs b/TagSoup/Test.hs deleted file mode 100644 --- a/TagSoup/Test.hs +++ /dev/null @@ -1,245 +0,0 @@ -{-# OPTIONS_GHC -fno-warn-deprecations #-} - -module TagSoup.Test(test) where - -import Text.HTML.TagSoup -import Text.HTML.TagSoup.Entity -import Text.HTML.TagSoup.Match - -import Control.Monad -import Data.List -import Test.QuickCheck(Arbitrary(..), Testable(..), quickCheckWithResult, stdArgs, - Args(..), listOf, elements, Result(..)) - --- * The Test Monad - -type Test a = IO a - -pass :: Test () -pass = return () - -runTest :: Test () -> IO () -runTest x = x >> putStrLn "All tests passed" - -(===) :: (Show a, Eq a) => a -> a -> IO () -a === b = if a == b then pass else fail $ "Does not equal: " ++ show a ++ " =/= " ++ show b - -check :: Testable prop => prop -> IO () -check prop = do - res <- quickCheckWithResult stdArgs{maxSuccess=1000} prop - case res of - Success{} -> pass - _ -> fail "Property failed" - -newtype HTML = HTML String deriving Show -instance Arbitrary HTML where - arbitrary = fmap (HTML . concat) $ listOf $ elements frags - where frags = map (:[]) " \n!-#&;xy01[]?'\"" ++ ["CDATA","amp","gt","lt"] - shrink (HTML x) = map HTML $ zipWith (++) (inits x) (tail $ tails x) - - --- * The Main section - -test :: IO () -test = runTest $ do - warnTests - parseTests - optionsTests - renderTests - combiTests - entityTests - lazyTags == lazyTags `seq` pass - matchCombinators - - -{- | -This routine tests the laziness of the TagSoup parser. -For each critical part of the parser we provide a test input -with a token of infinite size. -Then the output must be infinite too. -If the laziness is broken, then the output will stop early. -We collect the thousandth character of the output of each test case. -If computation of the list stops somewhere, -you have found a laziness stopper. --} - - -lazyTags :: [Char] -lazyTags = map ((!!1000) . show . parseTags) - [cycle "Rhabarber" - ,repeat '&' - ,"<"++cycle "html" - ,"" === [TagOpen "!DOCTYPE" [("TEST","")]] - parseTags "" === [TagOpen "test" [("\"foo",""),("bar\"","")]] - parseTags "" === [TagOpen "test" [("baz",""),("\"foo\"","")]] - parseTags "" === [TagOpen "test" [("'foo",""),("bar'","")]] - parseTags "" === [TagOpen "test" [("bar",""),("'","")], TagClose "test"] - parseTags "" === [TagOpen "test2" [("a",""),("b","")]] - parseTags "" === [TagOpen "test2" [("''","")]] - parseTags "" === [TagClose "test"] - parseTags "" === [TagOpen "test" [], TagClose "test"] - parseTags "" === [TagOpen "test1" [("a","b")]] - parseTags "hello & world" === [TagText "hello & world"] - parseTags "hello @ world" === [TagText "hello @ world"] - parseTags "hello @ world" === [TagText "hello @ world"] - parseTags "hello @ world" === [TagText "hello @ world"] - parseTags "hello &haskell; world" === [TagText "hello &haskell; world"] - parseTags "hello \n\t world" === [TagText "hello \n\t world"] - parseTags "" === [TagOpen "a" [("href","http://www.google.com")]] - parseTags "" === [TagOpen "foo" [("bar","bar6baz")]] - parseTags "" === [TagOpen "foo" [("bar","bar&baz")]] - parseTags "hey &how are you" === [TagText "hey &how are you"] - parseTags "hey &how; are you" === [TagText "hey &how; are you"] - parseTags "hey & are you" === [TagText "hey & are you"] - parseTags "hey & are you" === [TagText "hey & are you"] - - -- real cases reported by users - parseTags "↖x≧̸" === [TagText ['\x2196','x','\x2267','\x0338']] - parseTags "test � test" === [TagText "test ? test"] - - parseTags "" === [TagOpen "a" [("href","series.php?view=single&ID=72710")]] - - parseTags "" === - [TagOpen "!DOCTYPE" [("HTML",""),("PUBLIC",""),("","-//W3C//DTD HTML 4.01//EN"),("","http://www.w3.org/TR/html4/strict.dtd")]] - - parseTags "" === [TagOpen "script" [], TagText " if (x if (x if (x" === [TagOpen "SCRIPT" [("language","foo")], TagText " if (x" === [TagOpen "script" [], TagClose "script", TagOpen "test" []] - - -- some escapes require trailing semicolons, see #28 and #27. - parseTags "one ∣ two" === [TagText "one \8739 two"] - parseTags "one &mid two" === [TagText "one &mid two"] - parseTags "one µ two" === [TagText "one \181 two"] - parseTags "one µ two" === [TagText "one \181 two"] - -optionsTests :: Test () -optionsTests = check $ \(HTML x) -> all (f x) $ replicateM 3 [False,True] - where - f str [pos,warn,merge] = - bool "merge" (not merge || adjacentTagText tags) && - bool "warn" (warn || all (not . isTagWarning) tags) && - bool "pos" (if pos then alternatePos tags else all (not . isTagPosition) tags) - where tags = parseTagsOptions parseOptions{optTagPosition=pos,optTagWarning=warn,optTagTextMerge=merge} str - bool x b = b || error ("optionsTests failed with " ++ x ++ " on " ++ show (pos,warn,merge,str,tags)) - - -- optTagTextMerge implies no adjacent TagText cells - -- and none separated by only warnings or positions - adjacentTagText = g True -- can the next be a tag text - where g i (x:xs) | isTagText x = i && g False xs - | isTagPosition x || isTagWarning x = g i xs - | otherwise = g True xs - g i [] = True - - -- optTagPosition implies every element must be followed - -- by a position node, no two position nodes must be adjacent - -- and all positions must be increasing - alternatePos (TagPosition l1 c1 : x : TagPosition l2 c2 : xs) - | (l1,c1) <= (l2,c2) && not (isTagPosition x) = alternatePos $ TagPosition l2 c2 : xs - alternatePos [TagPosition l1 c1, x] | not $ isTagPosition x = True - alternatePos [] = True - alternatePos _ = False - - -renderTests :: Test () -renderTests = do - let rp = renderTags . parseTags - rp "" === "" - rp "

    " === "
    " - rp "" === "" - rp "hello & world" === "hello & world" - rp "    " === "" - rp "" === "" - rp "" === "" - rp "" === "" - rp "" === "" - rp "" === "" - rp "" === "" - escapeHTML "this is a &\" '" === "this is a &" <test> '" - check $ \(HTML x) -> let y = rp x in rp y == (y :: String) - - -entityTests :: Test () -entityTests = do - lookupNumericEntity "65" === Just "A" - lookupNumericEntity "x41" === Just "A" - lookupNumericEntity "x4E" === Just "N" - lookupNumericEntity "x4e" === Just "N" - lookupNumericEntity "X4e" === Just "N" - lookupNumericEntity "Haskell" === Nothing - lookupNumericEntity "" === Nothing - lookupNumericEntity "89439085908539082" === Nothing - lookupNamedEntity "amp" === Just "&" - lookupNamedEntity "haskell" === Nothing - escapeXML "hello world" === "hello world" - escapeXML "hello & world" === "hello & world" - - -combiTests :: Test () -combiTests = do - (TagText "test" ~== TagText "" ) === True - (TagText "test" ~== TagText "test") === True - (TagText "test" ~== TagText "soup") === False - (TagText "test" ~== "test") === True - (TagOpen "test" [] ~== "") === True - (TagOpen "test" [] ~== "") === False - (TagOpen "test" [] ~/= "") === True - (TagComment "foo" ~== "") === True - (TagComment "bar" ~== "") === True - - -warnTests :: Test () -warnTests = do - let p = parseTagsOptions parseOptions{optTagPosition=True,optTagWarning=True} - wt x = [(msg,c) | TagWarning msg:TagPosition _ c:_ <- tails $ p x] - wt "neil &foo bar" === [("Unknown entity: foo",10)] diff --git a/Text/HTML/TagSoup.hs b/Text/HTML/TagSoup.hs deleted file mode 100644 --- a/Text/HTML/TagSoup.hs +++ /dev/null @@ -1,117 +0,0 @@ -{-# LANGUAGE TypeSynonymInstances, FlexibleInstances, PatternGuards #-} - -{-| - This module is for working with HTML/XML. It deals with both well-formed XML and - malformed HTML from the web. It features: - - * A lazy parser, based on the HTML 5 specification - see 'parseTags'. - - * A renderer that can write out HTML/XML - see 'renderTags'. - - * Utilities for extracting information from a document - see '~==', 'sections' and 'partitions'. - - The standard practice is to parse a 'String' to @[@'Tag' 'String'@]@ using 'parseTags', - then operate upon it to extract the necessary information. --} - -module Text.HTML.TagSoup( - -- * Data structures and parsing - Tag(..), Row, Column, Attribute, - module Text.HTML.TagSoup.Parser, - module Text.HTML.TagSoup.Render, - canonicalizeTags, - - -- Note: the "#tag-identification#" creates an anchor that's linked to from Match.hs - -- * #tag-identification# Tag identification - isTagOpen, isTagClose, isTagText, isTagWarning, isTagPosition, - isTagOpenName, isTagCloseName, isTagComment, - - -- * Extraction - fromTagText, fromAttrib, - maybeTagText, maybeTagWarning, - innerText, - - -- * Utility - sections, partitions, - - -- * Combinators - TagRep(..), (~==),(~/=) - ) where - -import Text.HTML.TagSoup.Type -import Text.HTML.TagSoup.Parser -import Text.HTML.TagSoup.Render -import Data.Char -import Data.List (groupBy, tails) -import Text.StringLike - - --- | Turns all tag names and attributes to lower case and --- converts DOCTYPE to upper case. -canonicalizeTags :: StringLike str => [Tag str] -> [Tag str] -canonicalizeTags = map f - where - f (TagOpen tag attrs) | Just ('!',name) <- uncons tag = TagOpen ('!' `cons` ucase name) attrs - f (TagOpen name attrs) = TagOpen (lcase name) [(lcase k, v) | (k,v) <- attrs] - f (TagClose name) = TagClose (lcase name) - f a = a - - ucase = fromString . map toUpper . toString - lcase = fromString . map toLower . toString - - --- | Define a class to allow String's or Tag str's to be used as matches -class TagRep a where - -- | Convert a value into a 'Tag'. - toTagRep :: StringLike str => a -> Tag str - -instance StringLike str => TagRep (Tag str) where toTagRep = fmap castString - -instance TagRep String where - toTagRep x = case parseTags x of - [a] -> toTagRep a - _ -> error $ "When using a TagRep it must be exactly one tag, you gave: " ++ x - - - --- | Performs an inexact match, the first item should be the thing to match. --- If the second item is a blank string, that is considered to match anything. --- For example: --- --- > (TagText "test" ~== TagText "" ) == True --- > (TagText "test" ~== TagText "test") == True --- > (TagText "test" ~== TagText "soup") == False --- --- For 'TagOpen' missing attributes on the right are allowed. -(~==) :: (StringLike str, TagRep t) => Tag str -> t -> Bool -(~==) a b = f a (toTagRep b) - where - f (TagText y) (TagText x) = strNull x || x == y - f (TagClose y) (TagClose x) = strNull x || x == y - f (TagOpen y ys) (TagOpen x xs) = (strNull x || x == y) && all g xs - where - g (name,val) | strNull name = val `elem` map snd ys - | strNull val = name `elem` map fst ys - g nameval = nameval `elem` ys - f (TagComment x) (TagComment y) = strNull x || x == y - f (TagWarning x) (TagWarning y) = strNull x || x == y - f (TagPosition x1 x2) (TagPosition y1 y2) = x1 == y1 && x2 == y2 - f _ _ = False - --- | Negation of '~==' -(~/=) :: (StringLike str, TagRep t) => Tag str -> t -> Bool -(~/=) a b = not (a ~== b) - - - --- | This function takes a list, and returns all suffixes whose --- first item matches the predicate. -sections :: (a -> Bool) -> [a] -> [[a]] -sections p = filter (p . head) . init . tails - --- | This function is similar to 'sections', but splits the list --- so no element appears in any two partitions. -partitions :: (a -> Bool) -> [a] -> [[a]] -partitions p = - let notp = not . p - in groupBy (const notp) . dropWhile notp diff --git a/Text/HTML/TagSoup/Entity.hs b/Text/HTML/TagSoup/Entity.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Entity.hs +++ /dev/null @@ -1,2320 +0,0 @@ --- | This module converts between HTML/XML entities (i.e. @&@) and --- the characters they represent. -module Text.HTML.TagSoup.Entity( - lookupEntity, lookupNamedEntity, lookupNumericEntity, - escapeXML, - xmlEntities, htmlEntities - ) where - -import Data.Char (chr, ord) -import qualified Data.IntMap as IntMap -import Data.Ix -import qualified Data.Map as Map -import Numeric (readHex) - - --- | Lookup an entity, using 'lookupNumericEntity' if it starts with --- @#@ and 'lookupNamedEntity' otherwise -lookupEntity :: String -> Maybe String -lookupEntity ('#':xs) = lookupNumericEntity xs -lookupEntity xs = lookupNamedEntity xs - - --- | Lookup a numeric entity, the leading @\'#\'@ must have already been removed. --- --- > lookupNumericEntity "65" == Just "A" --- > lookupNumericEntity "x41" == Just "A" --- > lookupNumericEntity "x4E" === Just "N" --- > lookupNumericEntity "x4e" === Just "N" --- > lookupNumericEntity "X4e" === Just "N" --- > lookupNumericEntity "Haskell" == Nothing --- > lookupNumericEntity "" == Nothing --- > lookupNumericEntity "89439085908539082" == Nothing -lookupNumericEntity :: String -> Maybe String -lookupNumericEntity = f - -- entity = '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';' - where - f (x:xs) | x `elem` "xX" = g [('0','9'),('a','f'),('A','F')] readHex xs - f xs = g [('0','9')] reads xs - - g :: [(Char,Char)] -> ReadS Integer -> String -> Maybe String - g valid reader xs = do - let test b = if b then Just () else Nothing - test $ isValid valid xs - test $ not $ null xs - case reader xs of - [(a,"")] -> do - test $ inRange (toInteger $ ord minBound, toInteger $ ord maxBound) a - return [chr $ fromInteger a] - _ -> Nothing - - isValid :: [(Char,Char)] -> String -> Bool - isValid valid xs = all (\x -> any (`inRange` x) valid) xs - - --- | Lookup a named entity, using 'htmlEntities' --- --- > lookupNamedEntity "amp" == Just "&" --- > lookupNamedEntity "haskell" == Nothing -lookupNamedEntity :: String -> Maybe String -lookupNamedEntity = \x -> Map.lookup x mp - where mp = Map.fromList htmlEntities - - --- | Escape an XML string. --- --- > escapeXML "hello world" == "hello world" --- > escapeXML "hello & world" == "hello & world" -escapeXML :: String -> String -escapeXML = concatMap $ \x -> IntMap.findWithDefault [x] (ord x) mp - where mp = IntMap.fromList [(ord b, "&"++a++";") | (a,[b]) <- xmlEntities] - - --- | A table mapping XML entity names to resolved strings. All strings are a single character long. --- Does /not/ include @apos@ as Internet Explorer does not know about it. -xmlEntities :: [(String, String)] -xmlEntities = let a*b = (a,[b]) in - ["quot" * '"' - ,"amp" * '&' - -- ,"apos" * '\'' -- Internet Explorer does not know that - ,"lt" * '<' - ,"gt" * '>' - ] - --- | A table mapping HTML entity names to resolved strings. Most resolved strings are a single character long, --- but some (e.g. @"ngeqq"@) are two characters long. The list is taken from --- . -htmlEntities :: [(String, String)] -htmlEntities = let (*) = (,) in - ["Aacute" * "\x00C1" - ,"aacute" * "\x00E1" - ,"Aacute;" * "\x00C1" - ,"aacute;" * "\x00E1" - ,"Abreve;" * "\x0102" - ,"abreve;" * "\x0103" - ,"ac;" * "\x223E" - ,"acd;" * "\x223F" - ,"acE;" * "\x223E\x0333" - ,"Acirc" * "\x00C2" - ,"acirc" * "\x00E2" - ,"Acirc;" * "\x00C2" - ,"acirc;" * "\x00E2" - ,"acute" * "\x00B4" - ,"acute;" * "\x00B4" - ,"Acy;" * "\x0410" - ,"acy;" * "\x0430" - ,"AElig" * "\x00C6" - ,"aelig" * "\x00E6" - ,"AElig;" * "\x00C6" - ,"aelig;" * "\x00E6" - ,"af;" * "\x2061" - ,"Afr;" * "\x1D504" - ,"afr;" * "\x1D51E" - ,"Agrave" * "\x00C0" - ,"agrave" * "\x00E0" - ,"Agrave;" * "\x00C0" - ,"agrave;" * "\x00E0" - ,"alefsym;" * "\x2135" - ,"aleph;" * "\x2135" - ,"Alpha;" * "\x0391" - ,"alpha;" * "\x03B1" - ,"Amacr;" * "\x0100" - ,"amacr;" * "\x0101" - ,"amalg;" * "\x2A3F" - ,"AMP" * "\x0026" - ,"amp" * "\x0026" - ,"AMP;" * "\x0026" - ,"amp;" * "\x0026" - ,"and;" * "\x2227" - ,"And;" * "\x2A53" - ,"andand;" * "\x2A55" - ,"andd;" * "\x2A5C" - ,"andslope;" * "\x2A58" - ,"andv;" * "\x2A5A" - ,"ang;" * "\x2220" - ,"ange;" * "\x29A4" - ,"angle;" * "\x2220" - ,"angmsd;" * "\x2221" - ,"angmsdaa;" * "\x29A8" - ,"angmsdab;" * "\x29A9" - ,"angmsdac;" * "\x29AA" - ,"angmsdad;" * "\x29AB" - ,"angmsdae;" * "\x29AC" - ,"angmsdaf;" * "\x29AD" - ,"angmsdag;" * "\x29AE" - ,"angmsdah;" * "\x29AF" - ,"angrt;" * "\x221F" - ,"angrtvb;" * "\x22BE" - ,"angrtvbd;" * "\x299D" - ,"angsph;" * "\x2222" - ,"angst;" * "\x00C5" - ,"angzarr;" * "\x237C" - ,"Aogon;" * "\x0104" - ,"aogon;" * "\x0105" - ,"Aopf;" * "\x1D538" - ,"aopf;" * "\x1D552" - ,"ap;" * "\x2248" - ,"apacir;" * "\x2A6F" - ,"ape;" * "\x224A" - ,"apE;" * "\x2A70" - ,"apid;" * "\x224B" - ,"apos;" * "\x0027" - ,"ApplyFunction;" * "\x2061" - ,"approx;" * "\x2248" - ,"approxeq;" * "\x224A" - ,"Aring" * "\x00C5" - ,"aring" * "\x00E5" - ,"Aring;" * "\x00C5" - ,"aring;" * "\x00E5" - ,"Ascr;" * "\x1D49C" - ,"ascr;" * "\x1D4B6" - ,"Assign;" * "\x2254" - ,"ast;" * "\x002A" - ,"asymp;" * "\x2248" - ,"asympeq;" * "\x224D" - ,"Atilde" * "\x00C3" - ,"atilde" * "\x00E3" - ,"Atilde;" * "\x00C3" - ,"atilde;" * "\x00E3" - ,"Auml" * "\x00C4" - ,"auml" * "\x00E4" - ,"Auml;" * "\x00C4" - ,"auml;" * "\x00E4" - ,"awconint;" * "\x2233" - ,"awint;" * "\x2A11" - ,"backcong;" * "\x224C" - ,"backepsilon;" * "\x03F6" - ,"backprime;" * "\x2035" - ,"backsim;" * "\x223D" - ,"backsimeq;" * "\x22CD" - ,"Backslash;" * "\x2216" - ,"Barv;" * "\x2AE7" - ,"barvee;" * "\x22BD" - ,"barwed;" * "\x2305" - ,"Barwed;" * "\x2306" - ,"barwedge;" * "\x2305" - ,"bbrk;" * "\x23B5" - ,"bbrktbrk;" * "\x23B6" - ,"bcong;" * "\x224C" - ,"Bcy;" * "\x0411" - ,"bcy;" * "\x0431" - ,"bdquo;" * "\x201E" - ,"becaus;" * "\x2235" - ,"Because;" * "\x2235" - ,"because;" * "\x2235" - ,"bemptyv;" * "\x29B0" - ,"bepsi;" * "\x03F6" - ,"bernou;" * "\x212C" - ,"Bernoullis;" * "\x212C" - ,"Beta;" * "\x0392" - ,"beta;" * "\x03B2" - ,"beth;" * "\x2136" - ,"between;" * "\x226C" - ,"Bfr;" * "\x1D505" - ,"bfr;" * "\x1D51F" - ,"bigcap;" * "\x22C2" - ,"bigcirc;" * "\x25EF" - ,"bigcup;" * "\x22C3" - ,"bigodot;" * "\x2A00" - ,"bigoplus;" * "\x2A01" - ,"bigotimes;" * "\x2A02" - ,"bigsqcup;" * "\x2A06" - ,"bigstar;" * "\x2605" - ,"bigtriangledown;" * "\x25BD" - ,"bigtriangleup;" * "\x25B3" - ,"biguplus;" * "\x2A04" - ,"bigvee;" * "\x22C1" - ,"bigwedge;" * "\x22C0" - ,"bkarow;" * "\x290D" - ,"blacklozenge;" * "\x29EB" - ,"blacksquare;" * "\x25AA" - ,"blacktriangle;" * "\x25B4" - ,"blacktriangledown;" * "\x25BE" - ,"blacktriangleleft;" * "\x25C2" - ,"blacktriangleright;" * "\x25B8" - ,"blank;" * "\x2423" - ,"blk12;" * "\x2592" - ,"blk14;" * "\x2591" - ,"blk34;" * "\x2593" - ,"block;" * "\x2588" - ,"bne;" * "\x003D\x20E5" - ,"bnequiv;" * "\x2261\x20E5" - ,"bnot;" * "\x2310" - ,"bNot;" * "\x2AED" - ,"Bopf;" * "\x1D539" - ,"bopf;" * "\x1D553" - ,"bot;" * "\x22A5" - ,"bottom;" * "\x22A5" - ,"bowtie;" * "\x22C8" - ,"boxbox;" * "\x29C9" - ,"boxdl;" * "\x2510" - ,"boxdL;" * "\x2555" - ,"boxDl;" * "\x2556" - ,"boxDL;" * "\x2557" - ,"boxdr;" * "\x250C" - ,"boxdR;" * "\x2552" - ,"boxDr;" * "\x2553" - ,"boxDR;" * "\x2554" - ,"boxh;" * "\x2500" - ,"boxH;" * "\x2550" - ,"boxhd;" * "\x252C" - ,"boxHd;" * "\x2564" - ,"boxhD;" * "\x2565" - ,"boxHD;" * "\x2566" - ,"boxhu;" * "\x2534" - ,"boxHu;" * "\x2567" - ,"boxhU;" * "\x2568" - ,"boxHU;" * "\x2569" - ,"boxminus;" * "\x229F" - ,"boxplus;" * "\x229E" - ,"boxtimes;" * "\x22A0" - ,"boxul;" * "\x2518" - ,"boxuL;" * "\x255B" - ,"boxUl;" * "\x255C" - ,"boxUL;" * "\x255D" - ,"boxur;" * "\x2514" - ,"boxuR;" * "\x2558" - ,"boxUr;" * "\x2559" - ,"boxUR;" * "\x255A" - ,"boxv;" * "\x2502" - ,"boxV;" * "\x2551" - ,"boxvh;" * "\x253C" - ,"boxvH;" * "\x256A" - ,"boxVh;" * "\x256B" - ,"boxVH;" * "\x256C" - ,"boxvl;" * "\x2524" - ,"boxvL;" * "\x2561" - ,"boxVl;" * "\x2562" - ,"boxVL;" * "\x2563" - ,"boxvr;" * "\x251C" - ,"boxvR;" * "\x255E" - ,"boxVr;" * "\x255F" - ,"boxVR;" * "\x2560" - ,"bprime;" * "\x2035" - ,"Breve;" * "\x02D8" - ,"breve;" * "\x02D8" - ,"brvbar" * "\x00A6" - ,"brvbar;" * "\x00A6" - ,"Bscr;" * "\x212C" - ,"bscr;" * "\x1D4B7" - ,"bsemi;" * "\x204F" - ,"bsim;" * "\x223D" - ,"bsime;" * "\x22CD" - ,"bsol;" * "\x005C" - ,"bsolb;" * "\x29C5" - ,"bsolhsub;" * "\x27C8" - ,"bull;" * "\x2022" - ,"bullet;" * "\x2022" - ,"bump;" * "\x224E" - ,"bumpe;" * "\x224F" - ,"bumpE;" * "\x2AAE" - ,"Bumpeq;" * "\x224E" - ,"bumpeq;" * "\x224F" - ,"Cacute;" * "\x0106" - ,"cacute;" * "\x0107" - ,"cap;" * "\x2229" - ,"Cap;" * "\x22D2" - ,"capand;" * "\x2A44" - ,"capbrcup;" * "\x2A49" - ,"capcap;" * "\x2A4B" - ,"capcup;" * "\x2A47" - ,"capdot;" * "\x2A40" - ,"CapitalDifferentialD;" * "\x2145" - ,"caps;" * "\x2229\xFE00" - ,"caret;" * "\x2041" - ,"caron;" * "\x02C7" - ,"Cayleys;" * "\x212D" - ,"ccaps;" * "\x2A4D" - ,"Ccaron;" * "\x010C" - ,"ccaron;" * "\x010D" - ,"Ccedil" * "\x00C7" - ,"ccedil" * "\x00E7" - ,"Ccedil;" * "\x00C7" - ,"ccedil;" * "\x00E7" - ,"Ccirc;" * "\x0108" - ,"ccirc;" * "\x0109" - ,"Cconint;" * "\x2230" - ,"ccups;" * "\x2A4C" - ,"ccupssm;" * "\x2A50" - ,"Cdot;" * "\x010A" - ,"cdot;" * "\x010B" - ,"cedil" * "\x00B8" - ,"cedil;" * "\x00B8" - ,"Cedilla;" * "\x00B8" - ,"cemptyv;" * "\x29B2" - ,"cent" * "\x00A2" - ,"cent;" * "\x00A2" - ,"CenterDot;" * "\x00B7" - ,"centerdot;" * "\x00B7" - ,"Cfr;" * "\x212D" - ,"cfr;" * "\x1D520" - ,"CHcy;" * "\x0427" - ,"chcy;" * "\x0447" - ,"check;" * "\x2713" - ,"checkmark;" * "\x2713" - ,"Chi;" * "\x03A7" - ,"chi;" * "\x03C7" - ,"cir;" * "\x25CB" - ,"circ;" * "\x02C6" - ,"circeq;" * "\x2257" - ,"circlearrowleft;" * "\x21BA" - ,"circlearrowright;" * "\x21BB" - ,"circledast;" * "\x229B" - ,"circledcirc;" * "\x229A" - ,"circleddash;" * "\x229D" - ,"CircleDot;" * "\x2299" - ,"circledR;" * "\x00AE" - ,"circledS;" * "\x24C8" - ,"CircleMinus;" * "\x2296" - ,"CirclePlus;" * "\x2295" - ,"CircleTimes;" * "\x2297" - ,"cire;" * "\x2257" - ,"cirE;" * "\x29C3" - ,"cirfnint;" * "\x2A10" - ,"cirmid;" * "\x2AEF" - ,"cirscir;" * "\x29C2" - ,"ClockwiseContourIntegral;" * "\x2232" - ,"CloseCurlyDoubleQuote;" * "\x201D" - ,"CloseCurlyQuote;" * "\x2019" - ,"clubs;" * "\x2663" - ,"clubsuit;" * "\x2663" - ,"colon;" * "\x003A" - ,"Colon;" * "\x2237" - ,"colone;" * "\x2254" - ,"Colone;" * "\x2A74" - ,"coloneq;" * "\x2254" - ,"comma;" * "\x002C" - ,"commat;" * "\x0040" - ,"comp;" * "\x2201" - ,"compfn;" * "\x2218" - ,"complement;" * "\x2201" - ,"complexes;" * "\x2102" - ,"cong;" * "\x2245" - ,"congdot;" * "\x2A6D" - ,"Congruent;" * "\x2261" - ,"conint;" * "\x222E" - ,"Conint;" * "\x222F" - ,"ContourIntegral;" * "\x222E" - ,"Copf;" * "\x2102" - ,"copf;" * "\x1D554" - ,"coprod;" * "\x2210" - ,"Coproduct;" * "\x2210" - ,"COPY" * "\x00A9" - ,"copy" * "\x00A9" - ,"COPY;" * "\x00A9" - ,"copy;" * "\x00A9" - ,"copysr;" * "\x2117" - ,"CounterClockwiseContourIntegral;" * "\x2233" - ,"crarr;" * "\x21B5" - ,"cross;" * "\x2717" - ,"Cross;" * "\x2A2F" - ,"Cscr;" * "\x1D49E" - ,"cscr;" * "\x1D4B8" - ,"csub;" * "\x2ACF" - ,"csube;" * "\x2AD1" - ,"csup;" * "\x2AD0" - ,"csupe;" * "\x2AD2" - ,"ctdot;" * "\x22EF" - ,"cudarrl;" * "\x2938" - ,"cudarrr;" * "\x2935" - ,"cuepr;" * "\x22DE" - ,"cuesc;" * "\x22DF" - ,"cularr;" * "\x21B6" - ,"cularrp;" * "\x293D" - ,"cup;" * "\x222A" - ,"Cup;" * "\x22D3" - ,"cupbrcap;" * "\x2A48" - ,"CupCap;" * "\x224D" - ,"cupcap;" * "\x2A46" - ,"cupcup;" * "\x2A4A" - ,"cupdot;" * "\x228D" - ,"cupor;" * "\x2A45" - ,"cups;" * "\x222A\xFE00" - ,"curarr;" * "\x21B7" - ,"curarrm;" * "\x293C" - ,"curlyeqprec;" * "\x22DE" - ,"curlyeqsucc;" * "\x22DF" - ,"curlyvee;" * "\x22CE" - ,"curlywedge;" * "\x22CF" - ,"curren" * "\x00A4" - ,"curren;" * "\x00A4" - ,"curvearrowleft;" * "\x21B6" - ,"curvearrowright;" * "\x21B7" - ,"cuvee;" * "\x22CE" - ,"cuwed;" * "\x22CF" - ,"cwconint;" * "\x2232" - ,"cwint;" * "\x2231" - ,"cylcty;" * "\x232D" - ,"dagger;" * "\x2020" - ,"Dagger;" * "\x2021" - ,"daleth;" * "\x2138" - ,"darr;" * "\x2193" - ,"Darr;" * "\x21A1" - ,"dArr;" * "\x21D3" - ,"dash;" * "\x2010" - ,"dashv;" * "\x22A3" - ,"Dashv;" * "\x2AE4" - ,"dbkarow;" * "\x290F" - ,"dblac;" * "\x02DD" - ,"Dcaron;" * "\x010E" - ,"dcaron;" * "\x010F" - ,"Dcy;" * "\x0414" - ,"dcy;" * "\x0434" - ,"DD;" * "\x2145" - ,"dd;" * "\x2146" - ,"ddagger;" * "\x2021" - ,"ddarr;" * "\x21CA" - ,"DDotrahd;" * "\x2911" - ,"ddotseq;" * "\x2A77" - ,"deg" * "\x00B0" - ,"deg;" * "\x00B0" - ,"Del;" * "\x2207" - ,"Delta;" * "\x0394" - ,"delta;" * "\x03B4" - ,"demptyv;" * "\x29B1" - ,"dfisht;" * "\x297F" - ,"Dfr;" * "\x1D507" - ,"dfr;" * "\x1D521" - ,"dHar;" * "\x2965" - ,"dharl;" * "\x21C3" - ,"dharr;" * "\x21C2" - ,"DiacriticalAcute;" * "\x00B4" - ,"DiacriticalDot;" * "\x02D9" - ,"DiacriticalDoubleAcute;" * "\x02DD" - ,"DiacriticalGrave;" * "\x0060" - ,"DiacriticalTilde;" * "\x02DC" - ,"diam;" * "\x22C4" - ,"Diamond;" * "\x22C4" - ,"diamond;" * "\x22C4" - ,"diamondsuit;" * "\x2666" - ,"diams;" * "\x2666" - ,"die;" * "\x00A8" - ,"DifferentialD;" * "\x2146" - ,"digamma;" * "\x03DD" - ,"disin;" * "\x22F2" - ,"div;" * "\x00F7" - ,"divide" * "\x00F7" - ,"divide;" * "\x00F7" - ,"divideontimes;" * "\x22C7" - ,"divonx;" * "\x22C7" - ,"DJcy;" * "\x0402" - ,"djcy;" * "\x0452" - ,"dlcorn;" * "\x231E" - ,"dlcrop;" * "\x230D" - ,"dollar;" * "\x0024" - ,"Dopf;" * "\x1D53B" - ,"dopf;" * "\x1D555" - ,"Dot;" * "\x00A8" - ,"dot;" * "\x02D9" - ,"DotDot;" * "\x20DC" - ,"doteq;" * "\x2250" - ,"doteqdot;" * "\x2251" - ,"DotEqual;" * "\x2250" - ,"dotminus;" * "\x2238" - ,"dotplus;" * "\x2214" - ,"dotsquare;" * "\x22A1" - ,"doublebarwedge;" * "\x2306" - ,"DoubleContourIntegral;" * "\x222F" - ,"DoubleDot;" * "\x00A8" - ,"DoubleDownArrow;" * "\x21D3" - ,"DoubleLeftArrow;" * "\x21D0" - ,"DoubleLeftRightArrow;" * "\x21D4" - ,"DoubleLeftTee;" * "\x2AE4" - ,"DoubleLongLeftArrow;" * "\x27F8" - ,"DoubleLongLeftRightArrow;" * "\x27FA" - ,"DoubleLongRightArrow;" * "\x27F9" - ,"DoubleRightArrow;" * "\x21D2" - ,"DoubleRightTee;" * "\x22A8" - ,"DoubleUpArrow;" * "\x21D1" - ,"DoubleUpDownArrow;" * "\x21D5" - ,"DoubleVerticalBar;" * "\x2225" - ,"DownArrow;" * "\x2193" - ,"downarrow;" * "\x2193" - ,"Downarrow;" * "\x21D3" - ,"DownArrowBar;" * "\x2913" - ,"DownArrowUpArrow;" * "\x21F5" - ,"DownBreve;" * "\x0311" - ,"downdownarrows;" * "\x21CA" - ,"downharpoonleft;" * "\x21C3" - ,"downharpoonright;" * "\x21C2" - ,"DownLeftRightVector;" * "\x2950" - ,"DownLeftTeeVector;" * "\x295E" - ,"DownLeftVector;" * "\x21BD" - ,"DownLeftVectorBar;" * "\x2956" - ,"DownRightTeeVector;" * "\x295F" - ,"DownRightVector;" * "\x21C1" - ,"DownRightVectorBar;" * "\x2957" - ,"DownTee;" * "\x22A4" - ,"DownTeeArrow;" * "\x21A7" - ,"drbkarow;" * "\x2910" - ,"drcorn;" * "\x231F" - ,"drcrop;" * "\x230C" - ,"Dscr;" * "\x1D49F" - ,"dscr;" * "\x1D4B9" - ,"DScy;" * "\x0405" - ,"dscy;" * "\x0455" - ,"dsol;" * "\x29F6" - ,"Dstrok;" * "\x0110" - ,"dstrok;" * "\x0111" - ,"dtdot;" * "\x22F1" - ,"dtri;" * "\x25BF" - ,"dtrif;" * "\x25BE" - ,"duarr;" * "\x21F5" - ,"duhar;" * "\x296F" - ,"dwangle;" * "\x29A6" - ,"DZcy;" * "\x040F" - ,"dzcy;" * "\x045F" - ,"dzigrarr;" * "\x27FF" - ,"Eacute" * "\x00C9" - ,"eacute" * "\x00E9" - ,"Eacute;" * "\x00C9" - ,"eacute;" * "\x00E9" - ,"easter;" * "\x2A6E" - ,"Ecaron;" * "\x011A" - ,"ecaron;" * "\x011B" - ,"ecir;" * "\x2256" - ,"Ecirc" * "\x00CA" - ,"ecirc" * "\x00EA" - ,"Ecirc;" * "\x00CA" - ,"ecirc;" * "\x00EA" - ,"ecolon;" * "\x2255" - ,"Ecy;" * "\x042D" - ,"ecy;" * "\x044D" - ,"eDDot;" * "\x2A77" - ,"Edot;" * "\x0116" - ,"edot;" * "\x0117" - ,"eDot;" * "\x2251" - ,"ee;" * "\x2147" - ,"efDot;" * "\x2252" - ,"Efr;" * "\x1D508" - ,"efr;" * "\x1D522" - ,"eg;" * "\x2A9A" - ,"Egrave" * "\x00C8" - ,"egrave" * "\x00E8" - ,"Egrave;" * "\x00C8" - ,"egrave;" * "\x00E8" - ,"egs;" * "\x2A96" - ,"egsdot;" * "\x2A98" - ,"el;" * "\x2A99" - ,"Element;" * "\x2208" - ,"elinters;" * "\x23E7" - ,"ell;" * "\x2113" - ,"els;" * "\x2A95" - ,"elsdot;" * "\x2A97" - ,"Emacr;" * "\x0112" - ,"emacr;" * "\x0113" - ,"empty;" * "\x2205" - ,"emptyset;" * "\x2205" - ,"EmptySmallSquare;" * "\x25FB" - ,"emptyv;" * "\x2205" - ,"EmptyVerySmallSquare;" * "\x25AB" - ,"emsp13;" * "\x2004" - ,"emsp14;" * "\x2005" - ,"emsp;" * "\x2003" - ,"ENG;" * "\x014A" - ,"eng;" * "\x014B" - ,"ensp;" * "\x2002" - ,"Eogon;" * "\x0118" - ,"eogon;" * "\x0119" - ,"Eopf;" * "\x1D53C" - ,"eopf;" * "\x1D556" - ,"epar;" * "\x22D5" - ,"eparsl;" * "\x29E3" - ,"eplus;" * "\x2A71" - ,"epsi;" * "\x03B5" - ,"Epsilon;" * "\x0395" - ,"epsilon;" * "\x03B5" - ,"epsiv;" * "\x03F5" - ,"eqcirc;" * "\x2256" - ,"eqcolon;" * "\x2255" - ,"eqsim;" * "\x2242" - ,"eqslantgtr;" * "\x2A96" - ,"eqslantless;" * "\x2A95" - ,"Equal;" * "\x2A75" - ,"equals;" * "\x003D" - ,"EqualTilde;" * "\x2242" - ,"equest;" * "\x225F" - ,"Equilibrium;" * "\x21CC" - ,"equiv;" * "\x2261" - ,"equivDD;" * "\x2A78" - ,"eqvparsl;" * "\x29E5" - ,"erarr;" * "\x2971" - ,"erDot;" * "\x2253" - ,"escr;" * "\x212F" - ,"Escr;" * "\x2130" - ,"esdot;" * "\x2250" - ,"esim;" * "\x2242" - ,"Esim;" * "\x2A73" - ,"Eta;" * "\x0397" - ,"eta;" * "\x03B7" - ,"ETH" * "\x00D0" - ,"eth" * "\x00F0" - ,"ETH;" * "\x00D0" - ,"eth;" * "\x00F0" - ,"Euml" * "\x00CB" - ,"euml" * "\x00EB" - ,"Euml;" * "\x00CB" - ,"euml;" * "\x00EB" - ,"euro;" * "\x20AC" - ,"excl;" * "\x0021" - ,"exist;" * "\x2203" - ,"Exists;" * "\x2203" - ,"expectation;" * "\x2130" - ,"ExponentialE;" * "\x2147" - ,"exponentiale;" * "\x2147" - ,"fallingdotseq;" * "\x2252" - ,"Fcy;" * "\x0424" - ,"fcy;" * "\x0444" - ,"female;" * "\x2640" - ,"ffilig;" * "\xFB03" - ,"fflig;" * "\xFB00" - ,"ffllig;" * "\xFB04" - ,"Ffr;" * "\x1D509" - ,"ffr;" * "\x1D523" - ,"filig;" * "\xFB01" - ,"FilledSmallSquare;" * "\x25FC" - ,"FilledVerySmallSquare;" * "\x25AA" - ,"fjlig;" * "\x0066\x006A" - ,"flat;" * "\x266D" - ,"fllig;" * "\xFB02" - ,"fltns;" * "\x25B1" - ,"fnof;" * "\x0192" - ,"Fopf;" * "\x1D53D" - ,"fopf;" * "\x1D557" - ,"ForAll;" * "\x2200" - ,"forall;" * "\x2200" - ,"fork;" * "\x22D4" - ,"forkv;" * "\x2AD9" - ,"Fouriertrf;" * "\x2131" - ,"fpartint;" * "\x2A0D" - ,"frac12" * "\x00BD" - ,"frac12;" * "\x00BD" - ,"frac13;" * "\x2153" - ,"frac14" * "\x00BC" - ,"frac14;" * "\x00BC" - ,"frac15;" * "\x2155" - ,"frac16;" * "\x2159" - ,"frac18;" * "\x215B" - ,"frac23;" * "\x2154" - ,"frac25;" * "\x2156" - ,"frac34" * "\x00BE" - ,"frac34;" * "\x00BE" - ,"frac35;" * "\x2157" - ,"frac38;" * "\x215C" - ,"frac45;" * "\x2158" - ,"frac56;" * "\x215A" - ,"frac58;" * "\x215D" - ,"frac78;" * "\x215E" - ,"frasl;" * "\x2044" - ,"frown;" * "\x2322" - ,"Fscr;" * "\x2131" - ,"fscr;" * "\x1D4BB" - ,"gacute;" * "\x01F5" - ,"Gamma;" * "\x0393" - ,"gamma;" * "\x03B3" - ,"Gammad;" * "\x03DC" - ,"gammad;" * "\x03DD" - ,"gap;" * "\x2A86" - ,"Gbreve;" * "\x011E" - ,"gbreve;" * "\x011F" - ,"Gcedil;" * "\x0122" - ,"Gcirc;" * "\x011C" - ,"gcirc;" * "\x011D" - ,"Gcy;" * "\x0413" - ,"gcy;" * "\x0433" - ,"Gdot;" * "\x0120" - ,"gdot;" * "\x0121" - ,"ge;" * "\x2265" - ,"gE;" * "\x2267" - ,"gel;" * "\x22DB" - ,"gEl;" * "\x2A8C" - ,"geq;" * "\x2265" - ,"geqq;" * "\x2267" - ,"geqslant;" * "\x2A7E" - ,"ges;" * "\x2A7E" - ,"gescc;" * "\x2AA9" - ,"gesdot;" * "\x2A80" - ,"gesdoto;" * "\x2A82" - ,"gesdotol;" * "\x2A84" - ,"gesl;" * "\x22DB\xFE00" - ,"gesles;" * "\x2A94" - ,"Gfr;" * "\x1D50A" - ,"gfr;" * "\x1D524" - ,"gg;" * "\x226B" - ,"Gg;" * "\x22D9" - ,"ggg;" * "\x22D9" - ,"gimel;" * "\x2137" - ,"GJcy;" * "\x0403" - ,"gjcy;" * "\x0453" - ,"gl;" * "\x2277" - ,"gla;" * "\x2AA5" - ,"glE;" * "\x2A92" - ,"glj;" * "\x2AA4" - ,"gnap;" * "\x2A8A" - ,"gnapprox;" * "\x2A8A" - ,"gnE;" * "\x2269" - ,"gne;" * "\x2A88" - ,"gneq;" * "\x2A88" - ,"gneqq;" * "\x2269" - ,"gnsim;" * "\x22E7" - ,"Gopf;" * "\x1D53E" - ,"gopf;" * "\x1D558" - ,"grave;" * "\x0060" - ,"GreaterEqual;" * "\x2265" - ,"GreaterEqualLess;" * "\x22DB" - ,"GreaterFullEqual;" * "\x2267" - ,"GreaterGreater;" * "\x2AA2" - ,"GreaterLess;" * "\x2277" - ,"GreaterSlantEqual;" * "\x2A7E" - ,"GreaterTilde;" * "\x2273" - ,"gscr;" * "\x210A" - ,"Gscr;" * "\x1D4A2" - ,"gsim;" * "\x2273" - ,"gsime;" * "\x2A8E" - ,"gsiml;" * "\x2A90" - ,"GT" * "\x003E" - ,"gt" * "\x003E" - ,"GT;" * "\x003E" - ,"gt;" * "\x003E" - ,"Gt;" * "\x226B" - ,"gtcc;" * "\x2AA7" - ,"gtcir;" * "\x2A7A" - ,"gtdot;" * "\x22D7" - ,"gtlPar;" * "\x2995" - ,"gtquest;" * "\x2A7C" - ,"gtrapprox;" * "\x2A86" - ,"gtrarr;" * "\x2978" - ,"gtrdot;" * "\x22D7" - ,"gtreqless;" * "\x22DB" - ,"gtreqqless;" * "\x2A8C" - ,"gtrless;" * "\x2277" - ,"gtrsim;" * "\x2273" - ,"gvertneqq;" * "\x2269\xFE00" - ,"gvnE;" * "\x2269\xFE00" - ,"Hacek;" * "\x02C7" - ,"hairsp;" * "\x200A" - ,"half;" * "\x00BD" - ,"hamilt;" * "\x210B" - ,"HARDcy;" * "\x042A" - ,"hardcy;" * "\x044A" - ,"harr;" * "\x2194" - ,"hArr;" * "\x21D4" - ,"harrcir;" * "\x2948" - ,"harrw;" * "\x21AD" - ,"Hat;" * "\x005E" - ,"hbar;" * "\x210F" - ,"Hcirc;" * "\x0124" - ,"hcirc;" * "\x0125" - ,"hearts;" * "\x2665" - ,"heartsuit;" * "\x2665" - ,"hellip;" * "\x2026" - ,"hercon;" * "\x22B9" - ,"Hfr;" * "\x210C" - ,"hfr;" * "\x1D525" - ,"HilbertSpace;" * "\x210B" - ,"hksearow;" * "\x2925" - ,"hkswarow;" * "\x2926" - ,"hoarr;" * "\x21FF" - ,"homtht;" * "\x223B" - ,"hookleftarrow;" * "\x21A9" - ,"hookrightarrow;" * "\x21AA" - ,"Hopf;" * "\x210D" - ,"hopf;" * "\x1D559" - ,"horbar;" * "\x2015" - ,"HorizontalLine;" * "\x2500" - ,"Hscr;" * "\x210B" - ,"hscr;" * "\x1D4BD" - ,"hslash;" * "\x210F" - ,"Hstrok;" * "\x0126" - ,"hstrok;" * "\x0127" - ,"HumpDownHump;" * "\x224E" - ,"HumpEqual;" * "\x224F" - ,"hybull;" * "\x2043" - ,"hyphen;" * "\x2010" - ,"Iacute" * "\x00CD" - ,"iacute" * "\x00ED" - ,"Iacute;" * "\x00CD" - ,"iacute;" * "\x00ED" - ,"ic;" * "\x2063" - ,"Icirc" * "\x00CE" - ,"icirc" * "\x00EE" - ,"Icirc;" * "\x00CE" - ,"icirc;" * "\x00EE" - ,"Icy;" * "\x0418" - ,"icy;" * "\x0438" - ,"Idot;" * "\x0130" - ,"IEcy;" * "\x0415" - ,"iecy;" * "\x0435" - ,"iexcl" * "\x00A1" - ,"iexcl;" * "\x00A1" - ,"iff;" * "\x21D4" - ,"Ifr;" * "\x2111" - ,"ifr;" * "\x1D526" - ,"Igrave" * "\x00CC" - ,"igrave" * "\x00EC" - ,"Igrave;" * "\x00CC" - ,"igrave;" * "\x00EC" - ,"ii;" * "\x2148" - ,"iiiint;" * "\x2A0C" - ,"iiint;" * "\x222D" - ,"iinfin;" * "\x29DC" - ,"iiota;" * "\x2129" - ,"IJlig;" * "\x0132" - ,"ijlig;" * "\x0133" - ,"Im;" * "\x2111" - ,"Imacr;" * "\x012A" - ,"imacr;" * "\x012B" - ,"image;" * "\x2111" - ,"ImaginaryI;" * "\x2148" - ,"imagline;" * "\x2110" - ,"imagpart;" * "\x2111" - ,"imath;" * "\x0131" - ,"imof;" * "\x22B7" - ,"imped;" * "\x01B5" - ,"Implies;" * "\x21D2" - ,"in;" * "\x2208" - ,"incare;" * "\x2105" - ,"infin;" * "\x221E" - ,"infintie;" * "\x29DD" - ,"inodot;" * "\x0131" - ,"int;" * "\x222B" - ,"Int;" * "\x222C" - ,"intcal;" * "\x22BA" - ,"integers;" * "\x2124" - ,"Integral;" * "\x222B" - ,"intercal;" * "\x22BA" - ,"Intersection;" * "\x22C2" - ,"intlarhk;" * "\x2A17" - ,"intprod;" * "\x2A3C" - ,"InvisibleComma;" * "\x2063" - ,"InvisibleTimes;" * "\x2062" - ,"IOcy;" * "\x0401" - ,"iocy;" * "\x0451" - ,"Iogon;" * "\x012E" - ,"iogon;" * "\x012F" - ,"Iopf;" * "\x1D540" - ,"iopf;" * "\x1D55A" - ,"Iota;" * "\x0399" - ,"iota;" * "\x03B9" - ,"iprod;" * "\x2A3C" - ,"iquest" * "\x00BF" - ,"iquest;" * "\x00BF" - ,"Iscr;" * "\x2110" - ,"iscr;" * "\x1D4BE" - ,"isin;" * "\x2208" - ,"isindot;" * "\x22F5" - ,"isinE;" * "\x22F9" - ,"isins;" * "\x22F4" - ,"isinsv;" * "\x22F3" - ,"isinv;" * "\x2208" - ,"it;" * "\x2062" - ,"Itilde;" * "\x0128" - ,"itilde;" * "\x0129" - ,"Iukcy;" * "\x0406" - ,"iukcy;" * "\x0456" - ,"Iuml" * "\x00CF" - ,"iuml" * "\x00EF" - ,"Iuml;" * "\x00CF" - ,"iuml;" * "\x00EF" - ,"Jcirc;" * "\x0134" - ,"jcirc;" * "\x0135" - ,"Jcy;" * "\x0419" - ,"jcy;" * "\x0439" - ,"Jfr;" * "\x1D50D" - ,"jfr;" * "\x1D527" - ,"jmath;" * "\x0237" - ,"Jopf;" * "\x1D541" - ,"jopf;" * "\x1D55B" - ,"Jscr;" * "\x1D4A5" - ,"jscr;" * "\x1D4BF" - ,"Jsercy;" * "\x0408" - ,"jsercy;" * "\x0458" - ,"Jukcy;" * "\x0404" - ,"jukcy;" * "\x0454" - ,"Kappa;" * "\x039A" - ,"kappa;" * "\x03BA" - ,"kappav;" * "\x03F0" - ,"Kcedil;" * "\x0136" - ,"kcedil;" * "\x0137" - ,"Kcy;" * "\x041A" - ,"kcy;" * "\x043A" - ,"Kfr;" * "\x1D50E" - ,"kfr;" * "\x1D528" - ,"kgreen;" * "\x0138" - ,"KHcy;" * "\x0425" - ,"khcy;" * "\x0445" - ,"KJcy;" * "\x040C" - ,"kjcy;" * "\x045C" - ,"Kopf;" * "\x1D542" - ,"kopf;" * "\x1D55C" - ,"Kscr;" * "\x1D4A6" - ,"kscr;" * "\x1D4C0" - ,"lAarr;" * "\x21DA" - ,"Lacute;" * "\x0139" - ,"lacute;" * "\x013A" - ,"laemptyv;" * "\x29B4" - ,"lagran;" * "\x2112" - ,"Lambda;" * "\x039B" - ,"lambda;" * "\x03BB" - ,"lang;" * "\x27E8" - ,"Lang;" * "\x27EA" - ,"langd;" * "\x2991" - ,"langle;" * "\x27E8" - ,"lap;" * "\x2A85" - ,"Laplacetrf;" * "\x2112" - ,"laquo" * "\x00AB" - ,"laquo;" * "\x00AB" - ,"larr;" * "\x2190" - ,"Larr;" * "\x219E" - ,"lArr;" * "\x21D0" - ,"larrb;" * "\x21E4" - ,"larrbfs;" * "\x291F" - ,"larrfs;" * "\x291D" - ,"larrhk;" * "\x21A9" - ,"larrlp;" * "\x21AB" - ,"larrpl;" * "\x2939" - ,"larrsim;" * "\x2973" - ,"larrtl;" * "\x21A2" - ,"lat;" * "\x2AAB" - ,"latail;" * "\x2919" - ,"lAtail;" * "\x291B" - ,"late;" * "\x2AAD" - ,"lates;" * "\x2AAD\xFE00" - ,"lbarr;" * "\x290C" - ,"lBarr;" * "\x290E" - ,"lbbrk;" * "\x2772" - ,"lbrace;" * "\x007B" - ,"lbrack;" * "\x005B" - ,"lbrke;" * "\x298B" - ,"lbrksld;" * "\x298F" - ,"lbrkslu;" * "\x298D" - ,"Lcaron;" * "\x013D" - ,"lcaron;" * "\x013E" - ,"Lcedil;" * "\x013B" - ,"lcedil;" * "\x013C" - ,"lceil;" * "\x2308" - ,"lcub;" * "\x007B" - ,"Lcy;" * "\x041B" - ,"lcy;" * "\x043B" - ,"ldca;" * "\x2936" - ,"ldquo;" * "\x201C" - ,"ldquor;" * "\x201E" - ,"ldrdhar;" * "\x2967" - ,"ldrushar;" * "\x294B" - ,"ldsh;" * "\x21B2" - ,"le;" * "\x2264" - ,"lE;" * "\x2266" - ,"LeftAngleBracket;" * "\x27E8" - ,"LeftArrow;" * "\x2190" - ,"leftarrow;" * "\x2190" - ,"Leftarrow;" * "\x21D0" - ,"LeftArrowBar;" * "\x21E4" - ,"LeftArrowRightArrow;" * "\x21C6" - ,"leftarrowtail;" * "\x21A2" - ,"LeftCeiling;" * "\x2308" - ,"LeftDoubleBracket;" * "\x27E6" - ,"LeftDownTeeVector;" * "\x2961" - ,"LeftDownVector;" * "\x21C3" - ,"LeftDownVectorBar;" * "\x2959" - ,"LeftFloor;" * "\x230A" - ,"leftharpoondown;" * "\x21BD" - ,"leftharpoonup;" * "\x21BC" - ,"leftleftarrows;" * "\x21C7" - ,"LeftRightArrow;" * "\x2194" - ,"leftrightarrow;" * "\x2194" - ,"Leftrightarrow;" * "\x21D4" - ,"leftrightarrows;" * "\x21C6" - ,"leftrightharpoons;" * "\x21CB" - ,"leftrightsquigarrow;" * "\x21AD" - ,"LeftRightVector;" * "\x294E" - ,"LeftTee;" * "\x22A3" - ,"LeftTeeArrow;" * "\x21A4" - ,"LeftTeeVector;" * "\x295A" - ,"leftthreetimes;" * "\x22CB" - ,"LeftTriangle;" * "\x22B2" - ,"LeftTriangleBar;" * "\x29CF" - ,"LeftTriangleEqual;" * "\x22B4" - ,"LeftUpDownVector;" * "\x2951" - ,"LeftUpTeeVector;" * "\x2960" - ,"LeftUpVector;" * "\x21BF" - ,"LeftUpVectorBar;" * "\x2958" - ,"LeftVector;" * "\x21BC" - ,"LeftVectorBar;" * "\x2952" - ,"leg;" * "\x22DA" - ,"lEg;" * "\x2A8B" - ,"leq;" * "\x2264" - ,"leqq;" * "\x2266" - ,"leqslant;" * "\x2A7D" - ,"les;" * "\x2A7D" - ,"lescc;" * "\x2AA8" - ,"lesdot;" * "\x2A7F" - ,"lesdoto;" * "\x2A81" - ,"lesdotor;" * "\x2A83" - ,"lesg;" * "\x22DA\xFE00" - ,"lesges;" * "\x2A93" - ,"lessapprox;" * "\x2A85" - ,"lessdot;" * "\x22D6" - ,"lesseqgtr;" * "\x22DA" - ,"lesseqqgtr;" * "\x2A8B" - ,"LessEqualGreater;" * "\x22DA" - ,"LessFullEqual;" * "\x2266" - ,"LessGreater;" * "\x2276" - ,"lessgtr;" * "\x2276" - ,"LessLess;" * "\x2AA1" - ,"lesssim;" * "\x2272" - ,"LessSlantEqual;" * "\x2A7D" - ,"LessTilde;" * "\x2272" - ,"lfisht;" * "\x297C" - ,"lfloor;" * "\x230A" - ,"Lfr;" * "\x1D50F" - ,"lfr;" * "\x1D529" - ,"lg;" * "\x2276" - ,"lgE;" * "\x2A91" - ,"lHar;" * "\x2962" - ,"lhard;" * "\x21BD" - ,"lharu;" * "\x21BC" - ,"lharul;" * "\x296A" - ,"lhblk;" * "\x2584" - ,"LJcy;" * "\x0409" - ,"ljcy;" * "\x0459" - ,"ll;" * "\x226A" - ,"Ll;" * "\x22D8" - ,"llarr;" * "\x21C7" - ,"llcorner;" * "\x231E" - ,"Lleftarrow;" * "\x21DA" - ,"llhard;" * "\x296B" - ,"lltri;" * "\x25FA" - ,"Lmidot;" * "\x013F" - ,"lmidot;" * "\x0140" - ,"lmoust;" * "\x23B0" - ,"lmoustache;" * "\x23B0" - ,"lnap;" * "\x2A89" - ,"lnapprox;" * "\x2A89" - ,"lnE;" * "\x2268" - ,"lne;" * "\x2A87" - ,"lneq;" * "\x2A87" - ,"lneqq;" * "\x2268" - ,"lnsim;" * "\x22E6" - ,"loang;" * "\x27EC" - ,"loarr;" * "\x21FD" - ,"lobrk;" * "\x27E6" - ,"LongLeftArrow;" * "\x27F5" - ,"longleftarrow;" * "\x27F5" - ,"Longleftarrow;" * "\x27F8" - ,"LongLeftRightArrow;" * "\x27F7" - ,"longleftrightarrow;" * "\x27F7" - ,"Longleftrightarrow;" * "\x27FA" - ,"longmapsto;" * "\x27FC" - ,"LongRightArrow;" * "\x27F6" - ,"longrightarrow;" * "\x27F6" - ,"Longrightarrow;" * "\x27F9" - ,"looparrowleft;" * "\x21AB" - ,"looparrowright;" * "\x21AC" - ,"lopar;" * "\x2985" - ,"Lopf;" * "\x1D543" - ,"lopf;" * "\x1D55D" - ,"loplus;" * "\x2A2D" - ,"lotimes;" * "\x2A34" - ,"lowast;" * "\x2217" - ,"lowbar;" * "\x005F" - ,"LowerLeftArrow;" * "\x2199" - ,"LowerRightArrow;" * "\x2198" - ,"loz;" * "\x25CA" - ,"lozenge;" * "\x25CA" - ,"lozf;" * "\x29EB" - ,"lpar;" * "\x0028" - ,"lparlt;" * "\x2993" - ,"lrarr;" * "\x21C6" - ,"lrcorner;" * "\x231F" - ,"lrhar;" * "\x21CB" - ,"lrhard;" * "\x296D" - ,"lrm;" * "\x200E" - ,"lrtri;" * "\x22BF" - ,"lsaquo;" * "\x2039" - ,"Lscr;" * "\x2112" - ,"lscr;" * "\x1D4C1" - ,"Lsh;" * "\x21B0" - ,"lsh;" * "\x21B0" - ,"lsim;" * "\x2272" - ,"lsime;" * "\x2A8D" - ,"lsimg;" * "\x2A8F" - ,"lsqb;" * "\x005B" - ,"lsquo;" * "\x2018" - ,"lsquor;" * "\x201A" - ,"Lstrok;" * "\x0141" - ,"lstrok;" * "\x0142" - ,"LT" * "\x003C" - ,"lt" * "\x003C" - ,"LT;" * "\x003C" - ,"lt;" * "\x003C" - ,"Lt;" * "\x226A" - ,"ltcc;" * "\x2AA6" - ,"ltcir;" * "\x2A79" - ,"ltdot;" * "\x22D6" - ,"lthree;" * "\x22CB" - ,"ltimes;" * "\x22C9" - ,"ltlarr;" * "\x2976" - ,"ltquest;" * "\x2A7B" - ,"ltri;" * "\x25C3" - ,"ltrie;" * "\x22B4" - ,"ltrif;" * "\x25C2" - ,"ltrPar;" * "\x2996" - ,"lurdshar;" * "\x294A" - ,"luruhar;" * "\x2966" - ,"lvertneqq;" * "\x2268\xFE00" - ,"lvnE;" * "\x2268\xFE00" - ,"macr" * "\x00AF" - ,"macr;" * "\x00AF" - ,"male;" * "\x2642" - ,"malt;" * "\x2720" - ,"maltese;" * "\x2720" - ,"map;" * "\x21A6" - ,"Map;" * "\x2905" - ,"mapsto;" * "\x21A6" - ,"mapstodown;" * "\x21A7" - ,"mapstoleft;" * "\x21A4" - ,"mapstoup;" * "\x21A5" - ,"marker;" * "\x25AE" - ,"mcomma;" * "\x2A29" - ,"Mcy;" * "\x041C" - ,"mcy;" * "\x043C" - ,"mdash;" * "\x2014" - ,"mDDot;" * "\x223A" - ,"measuredangle;" * "\x2221" - ,"MediumSpace;" * "\x205F" - ,"Mellintrf;" * "\x2133" - ,"Mfr;" * "\x1D510" - ,"mfr;" * "\x1D52A" - ,"mho;" * "\x2127" - ,"micro" * "\x00B5" - ,"micro;" * "\x00B5" - ,"mid;" * "\x2223" - ,"midast;" * "\x002A" - ,"midcir;" * "\x2AF0" - ,"middot" * "\x00B7" - ,"middot;" * "\x00B7" - ,"minus;" * "\x2212" - ,"minusb;" * "\x229F" - ,"minusd;" * "\x2238" - ,"minusdu;" * "\x2A2A" - ,"MinusPlus;" * "\x2213" - ,"mlcp;" * "\x2ADB" - ,"mldr;" * "\x2026" - ,"mnplus;" * "\x2213" - ,"models;" * "\x22A7" - ,"Mopf;" * "\x1D544" - ,"mopf;" * "\x1D55E" - ,"mp;" * "\x2213" - ,"Mscr;" * "\x2133" - ,"mscr;" * "\x1D4C2" - ,"mstpos;" * "\x223E" - ,"Mu;" * "\x039C" - ,"mu;" * "\x03BC" - ,"multimap;" * "\x22B8" - ,"mumap;" * "\x22B8" - ,"nabla;" * "\x2207" - ,"Nacute;" * "\x0143" - ,"nacute;" * "\x0144" - ,"nang;" * "\x2220\x20D2" - ,"nap;" * "\x2249" - ,"napE;" * "\x2A70\x0338" - ,"napid;" * "\x224B\x0338" - ,"napos;" * "\x0149" - ,"napprox;" * "\x2249" - ,"natur;" * "\x266E" - ,"natural;" * "\x266E" - ,"naturals;" * "\x2115" - ,"nbsp" * "\x00A0" - ,"nbsp;" * "\x00A0" - ,"nbump;" * "\x224E\x0338" - ,"nbumpe;" * "\x224F\x0338" - ,"ncap;" * "\x2A43" - ,"Ncaron;" * "\x0147" - ,"ncaron;" * "\x0148" - ,"Ncedil;" * "\x0145" - ,"ncedil;" * "\x0146" - ,"ncong;" * "\x2247" - ,"ncongdot;" * "\x2A6D\x0338" - ,"ncup;" * "\x2A42" - ,"Ncy;" * "\x041D" - ,"ncy;" * "\x043D" - ,"ndash;" * "\x2013" - ,"ne;" * "\x2260" - ,"nearhk;" * "\x2924" - ,"nearr;" * "\x2197" - ,"neArr;" * "\x21D7" - ,"nearrow;" * "\x2197" - ,"nedot;" * "\x2250\x0338" - ,"NegativeMediumSpace;" * "\x200B" - ,"NegativeThickSpace;" * "\x200B" - ,"NegativeThinSpace;" * "\x200B" - ,"NegativeVeryThinSpace;" * "\x200B" - ,"nequiv;" * "\x2262" - ,"nesear;" * "\x2928" - ,"nesim;" * "\x2242\x0338" - ,"NestedGreaterGreater;" * "\x226B" - ,"NestedLessLess;" * "\x226A" - ,"NewLine;" * "\x000A" - ,"nexist;" * "\x2204" - ,"nexists;" * "\x2204" - ,"Nfr;" * "\x1D511" - ,"nfr;" * "\x1D52B" - ,"ngE;" * "\x2267\x0338" - ,"nge;" * "\x2271" - ,"ngeq;" * "\x2271" - ,"ngeqq;" * "\x2267\x0338" - ,"ngeqslant;" * "\x2A7E\x0338" - ,"nges;" * "\x2A7E\x0338" - ,"nGg;" * "\x22D9\x0338" - ,"ngsim;" * "\x2275" - ,"nGt;" * "\x226B\x20D2" - ,"ngt;" * "\x226F" - ,"ngtr;" * "\x226F" - ,"nGtv;" * "\x226B\x0338" - ,"nharr;" * "\x21AE" - ,"nhArr;" * "\x21CE" - ,"nhpar;" * "\x2AF2" - ,"ni;" * "\x220B" - ,"nis;" * "\x22FC" - ,"nisd;" * "\x22FA" - ,"niv;" * "\x220B" - ,"NJcy;" * "\x040A" - ,"njcy;" * "\x045A" - ,"nlarr;" * "\x219A" - ,"nlArr;" * "\x21CD" - ,"nldr;" * "\x2025" - ,"nlE;" * "\x2266\x0338" - ,"nle;" * "\x2270" - ,"nleftarrow;" * "\x219A" - ,"nLeftarrow;" * "\x21CD" - ,"nleftrightarrow;" * "\x21AE" - ,"nLeftrightarrow;" * "\x21CE" - ,"nleq;" * "\x2270" - ,"nleqq;" * "\x2266\x0338" - ,"nleqslant;" * "\x2A7D\x0338" - ,"nles;" * "\x2A7D\x0338" - ,"nless;" * "\x226E" - ,"nLl;" * "\x22D8\x0338" - ,"nlsim;" * "\x2274" - ,"nLt;" * "\x226A\x20D2" - ,"nlt;" * "\x226E" - ,"nltri;" * "\x22EA" - ,"nltrie;" * "\x22EC" - ,"nLtv;" * "\x226A\x0338" - ,"nmid;" * "\x2224" - ,"NoBreak;" * "\x2060" - ,"NonBreakingSpace;" * "\x00A0" - ,"Nopf;" * "\x2115" - ,"nopf;" * "\x1D55F" - ,"not" * "\x00AC" - ,"not;" * "\x00AC" - ,"Not;" * "\x2AEC" - ,"NotCongruent;" * "\x2262" - ,"NotCupCap;" * "\x226D" - ,"NotDoubleVerticalBar;" * "\x2226" - ,"NotElement;" * "\x2209" - ,"NotEqual;" * "\x2260" - ,"NotEqualTilde;" * "\x2242\x0338" - ,"NotExists;" * "\x2204" - ,"NotGreater;" * "\x226F" - ,"NotGreaterEqual;" * "\x2271" - ,"NotGreaterFullEqual;" * "\x2267\x0338" - ,"NotGreaterGreater;" * "\x226B\x0338" - ,"NotGreaterLess;" * "\x2279" - ,"NotGreaterSlantEqual;" * "\x2A7E\x0338" - ,"NotGreaterTilde;" * "\x2275" - ,"NotHumpDownHump;" * "\x224E\x0338" - ,"NotHumpEqual;" * "\x224F\x0338" - ,"notin;" * "\x2209" - ,"notindot;" * "\x22F5\x0338" - ,"notinE;" * "\x22F9\x0338" - ,"notinva;" * "\x2209" - ,"notinvb;" * "\x22F7" - ,"notinvc;" * "\x22F6" - ,"NotLeftTriangle;" * "\x22EA" - ,"NotLeftTriangleBar;" * "\x29CF\x0338" - ,"NotLeftTriangleEqual;" * "\x22EC" - ,"NotLess;" * "\x226E" - ,"NotLessEqual;" * "\x2270" - ,"NotLessGreater;" * "\x2278" - ,"NotLessLess;" * "\x226A\x0338" - ,"NotLessSlantEqual;" * "\x2A7D\x0338" - ,"NotLessTilde;" * "\x2274" - ,"NotNestedGreaterGreater;" * "\x2AA2\x0338" - ,"NotNestedLessLess;" * "\x2AA1\x0338" - ,"notni;" * "\x220C" - ,"notniva;" * "\x220C" - ,"notnivb;" * "\x22FE" - ,"notnivc;" * "\x22FD" - ,"NotPrecedes;" * "\x2280" - ,"NotPrecedesEqual;" * "\x2AAF\x0338" - ,"NotPrecedesSlantEqual;" * "\x22E0" - ,"NotReverseElement;" * "\x220C" - ,"NotRightTriangle;" * "\x22EB" - ,"NotRightTriangleBar;" * "\x29D0\x0338" - ,"NotRightTriangleEqual;" * "\x22ED" - ,"NotSquareSubset;" * "\x228F\x0338" - ,"NotSquareSubsetEqual;" * "\x22E2" - ,"NotSquareSuperset;" * "\x2290\x0338" - ,"NotSquareSupersetEqual;" * "\x22E3" - ,"NotSubset;" * "\x2282\x20D2" - ,"NotSubsetEqual;" * "\x2288" - ,"NotSucceeds;" * "\x2281" - ,"NotSucceedsEqual;" * "\x2AB0\x0338" - ,"NotSucceedsSlantEqual;" * "\x22E1" - ,"NotSucceedsTilde;" * "\x227F\x0338" - ,"NotSuperset;" * "\x2283\x20D2" - ,"NotSupersetEqual;" * "\x2289" - ,"NotTilde;" * "\x2241" - ,"NotTildeEqual;" * "\x2244" - ,"NotTildeFullEqual;" * "\x2247" - ,"NotTildeTilde;" * "\x2249" - ,"NotVerticalBar;" * "\x2224" - ,"npar;" * "\x2226" - ,"nparallel;" * "\x2226" - ,"nparsl;" * "\x2AFD\x20E5" - ,"npart;" * "\x2202\x0338" - ,"npolint;" * "\x2A14" - ,"npr;" * "\x2280" - ,"nprcue;" * "\x22E0" - ,"npre;" * "\x2AAF\x0338" - ,"nprec;" * "\x2280" - ,"npreceq;" * "\x2AAF\x0338" - ,"nrarr;" * "\x219B" - ,"nrArr;" * "\x21CF" - ,"nrarrc;" * "\x2933\x0338" - ,"nrarrw;" * "\x219D\x0338" - ,"nrightarrow;" * "\x219B" - ,"nRightarrow;" * "\x21CF" - ,"nrtri;" * "\x22EB" - ,"nrtrie;" * "\x22ED" - ,"nsc;" * "\x2281" - ,"nsccue;" * "\x22E1" - ,"nsce;" * "\x2AB0\x0338" - ,"Nscr;" * "\x1D4A9" - ,"nscr;" * "\x1D4C3" - ,"nshortmid;" * "\x2224" - ,"nshortparallel;" * "\x2226" - ,"nsim;" * "\x2241" - ,"nsime;" * "\x2244" - ,"nsimeq;" * "\x2244" - ,"nsmid;" * "\x2224" - ,"nspar;" * "\x2226" - ,"nsqsube;" * "\x22E2" - ,"nsqsupe;" * "\x22E3" - ,"nsub;" * "\x2284" - ,"nsube;" * "\x2288" - ,"nsubE;" * "\x2AC5\x0338" - ,"nsubset;" * "\x2282\x20D2" - ,"nsubseteq;" * "\x2288" - ,"nsubseteqq;" * "\x2AC5\x0338" - ,"nsucc;" * "\x2281" - ,"nsucceq;" * "\x2AB0\x0338" - ,"nsup;" * "\x2285" - ,"nsupe;" * "\x2289" - ,"nsupE;" * "\x2AC6\x0338" - ,"nsupset;" * "\x2283\x20D2" - ,"nsupseteq;" * "\x2289" - ,"nsupseteqq;" * "\x2AC6\x0338" - ,"ntgl;" * "\x2279" - ,"Ntilde" * "\x00D1" - ,"ntilde" * "\x00F1" - ,"Ntilde;" * "\x00D1" - ,"ntilde;" * "\x00F1" - ,"ntlg;" * "\x2278" - ,"ntriangleleft;" * "\x22EA" - ,"ntrianglelefteq;" * "\x22EC" - ,"ntriangleright;" * "\x22EB" - ,"ntrianglerighteq;" * "\x22ED" - ,"Nu;" * "\x039D" - ,"nu;" * "\x03BD" - ,"num;" * "\x0023" - ,"numero;" * "\x2116" - ,"numsp;" * "\x2007" - ,"nvap;" * "\x224D\x20D2" - ,"nvdash;" * "\x22AC" - ,"nvDash;" * "\x22AD" - ,"nVdash;" * "\x22AE" - ,"nVDash;" * "\x22AF" - ,"nvge;" * "\x2265\x20D2" - ,"nvgt;" * "\x003E\x20D2" - ,"nvHarr;" * "\x2904" - ,"nvinfin;" * "\x29DE" - ,"nvlArr;" * "\x2902" - ,"nvle;" * "\x2264\x20D2" - ,"nvlt;" * "\x003C\x20D2" - ,"nvltrie;" * "\x22B4\x20D2" - ,"nvrArr;" * "\x2903" - ,"nvrtrie;" * "\x22B5\x20D2" - ,"nvsim;" * "\x223C\x20D2" - ,"nwarhk;" * "\x2923" - ,"nwarr;" * "\x2196" - ,"nwArr;" * "\x21D6" - ,"nwarrow;" * "\x2196" - ,"nwnear;" * "\x2927" - ,"Oacute" * "\x00D3" - ,"oacute" * "\x00F3" - ,"Oacute;" * "\x00D3" - ,"oacute;" * "\x00F3" - ,"oast;" * "\x229B" - ,"ocir;" * "\x229A" - ,"Ocirc" * "\x00D4" - ,"ocirc" * "\x00F4" - ,"Ocirc;" * "\x00D4" - ,"ocirc;" * "\x00F4" - ,"Ocy;" * "\x041E" - ,"ocy;" * "\x043E" - ,"odash;" * "\x229D" - ,"Odblac;" * "\x0150" - ,"odblac;" * "\x0151" - ,"odiv;" * "\x2A38" - ,"odot;" * "\x2299" - ,"odsold;" * "\x29BC" - ,"OElig;" * "\x0152" - ,"oelig;" * "\x0153" - ,"ofcir;" * "\x29BF" - ,"Ofr;" * "\x1D512" - ,"ofr;" * "\x1D52C" - ,"ogon;" * "\x02DB" - ,"Ograve" * "\x00D2" - ,"ograve" * "\x00F2" - ,"Ograve;" * "\x00D2" - ,"ograve;" * "\x00F2" - ,"ogt;" * "\x29C1" - ,"ohbar;" * "\x29B5" - ,"ohm;" * "\x03A9" - ,"oint;" * "\x222E" - ,"olarr;" * "\x21BA" - ,"olcir;" * "\x29BE" - ,"olcross;" * "\x29BB" - ,"oline;" * "\x203E" - ,"olt;" * "\x29C0" - ,"Omacr;" * "\x014C" - ,"omacr;" * "\x014D" - ,"Omega;" * "\x03A9" - ,"omega;" * "\x03C9" - ,"Omicron;" * "\x039F" - ,"omicron;" * "\x03BF" - ,"omid;" * "\x29B6" - ,"ominus;" * "\x2296" - ,"Oopf;" * "\x1D546" - ,"oopf;" * "\x1D560" - ,"opar;" * "\x29B7" - ,"OpenCurlyDoubleQuote;" * "\x201C" - ,"OpenCurlyQuote;" * "\x2018" - ,"operp;" * "\x29B9" - ,"oplus;" * "\x2295" - ,"or;" * "\x2228" - ,"Or;" * "\x2A54" - ,"orarr;" * "\x21BB" - ,"ord;" * "\x2A5D" - ,"order;" * "\x2134" - ,"orderof;" * "\x2134" - ,"ordf" * "\x00AA" - ,"ordf;" * "\x00AA" - ,"ordm" * "\x00BA" - ,"ordm;" * "\x00BA" - ,"origof;" * "\x22B6" - ,"oror;" * "\x2A56" - ,"orslope;" * "\x2A57" - ,"orv;" * "\x2A5B" - ,"oS;" * "\x24C8" - ,"oscr;" * "\x2134" - ,"Oscr;" * "\x1D4AA" - ,"Oslash" * "\x00D8" - ,"oslash" * "\x00F8" - ,"Oslash;" * "\x00D8" - ,"oslash;" * "\x00F8" - ,"osol;" * "\x2298" - ,"Otilde" * "\x00D5" - ,"otilde" * "\x00F5" - ,"Otilde;" * "\x00D5" - ,"otilde;" * "\x00F5" - ,"otimes;" * "\x2297" - ,"Otimes;" * "\x2A37" - ,"otimesas;" * "\x2A36" - ,"Ouml" * "\x00D6" - ,"ouml" * "\x00F6" - ,"Ouml;" * "\x00D6" - ,"ouml;" * "\x00F6" - ,"ovbar;" * "\x233D" - ,"OverBar;" * "\x203E" - ,"OverBrace;" * "\x23DE" - ,"OverBracket;" * "\x23B4" - ,"OverParenthesis;" * "\x23DC" - ,"par;" * "\x2225" - ,"para" * "\x00B6" - ,"para;" * "\x00B6" - ,"parallel;" * "\x2225" - ,"parsim;" * "\x2AF3" - ,"parsl;" * "\x2AFD" - ,"part;" * "\x2202" - ,"PartialD;" * "\x2202" - ,"Pcy;" * "\x041F" - ,"pcy;" * "\x043F" - ,"percnt;" * "\x0025" - ,"period;" * "\x002E" - ,"permil;" * "\x2030" - ,"perp;" * "\x22A5" - ,"pertenk;" * "\x2031" - ,"Pfr;" * "\x1D513" - ,"pfr;" * "\x1D52D" - ,"Phi;" * "\x03A6" - ,"phi;" * "\x03C6" - ,"phiv;" * "\x03D5" - ,"phmmat;" * "\x2133" - ,"phone;" * "\x260E" - ,"Pi;" * "\x03A0" - ,"pi;" * "\x03C0" - ,"pitchfork;" * "\x22D4" - ,"piv;" * "\x03D6" - ,"planck;" * "\x210F" - ,"planckh;" * "\x210E" - ,"plankv;" * "\x210F" - ,"plus;" * "\x002B" - ,"plusacir;" * "\x2A23" - ,"plusb;" * "\x229E" - ,"pluscir;" * "\x2A22" - ,"plusdo;" * "\x2214" - ,"plusdu;" * "\x2A25" - ,"pluse;" * "\x2A72" - ,"PlusMinus;" * "\x00B1" - ,"plusmn" * "\x00B1" - ,"plusmn;" * "\x00B1" - ,"plussim;" * "\x2A26" - ,"plustwo;" * "\x2A27" - ,"pm;" * "\x00B1" - ,"Poincareplane;" * "\x210C" - ,"pointint;" * "\x2A15" - ,"Popf;" * "\x2119" - ,"popf;" * "\x1D561" - ,"pound" * "\x00A3" - ,"pound;" * "\x00A3" - ,"pr;" * "\x227A" - ,"Pr;" * "\x2ABB" - ,"prap;" * "\x2AB7" - ,"prcue;" * "\x227C" - ,"pre;" * "\x2AAF" - ,"prE;" * "\x2AB3" - ,"prec;" * "\x227A" - ,"precapprox;" * "\x2AB7" - ,"preccurlyeq;" * "\x227C" - ,"Precedes;" * "\x227A" - ,"PrecedesEqual;" * "\x2AAF" - ,"PrecedesSlantEqual;" * "\x227C" - ,"PrecedesTilde;" * "\x227E" - ,"preceq;" * "\x2AAF" - ,"precnapprox;" * "\x2AB9" - ,"precneqq;" * "\x2AB5" - ,"precnsim;" * "\x22E8" - ,"precsim;" * "\x227E" - ,"prime;" * "\x2032" - ,"Prime;" * "\x2033" - ,"primes;" * "\x2119" - ,"prnap;" * "\x2AB9" - ,"prnE;" * "\x2AB5" - ,"prnsim;" * "\x22E8" - ,"prod;" * "\x220F" - ,"Product;" * "\x220F" - ,"profalar;" * "\x232E" - ,"profline;" * "\x2312" - ,"profsurf;" * "\x2313" - ,"prop;" * "\x221D" - ,"Proportion;" * "\x2237" - ,"Proportional;" * "\x221D" - ,"propto;" * "\x221D" - ,"prsim;" * "\x227E" - ,"prurel;" * "\x22B0" - ,"Pscr;" * "\x1D4AB" - ,"pscr;" * "\x1D4C5" - ,"Psi;" * "\x03A8" - ,"psi;" * "\x03C8" - ,"puncsp;" * "\x2008" - ,"Qfr;" * "\x1D514" - ,"qfr;" * "\x1D52E" - ,"qint;" * "\x2A0C" - ,"Qopf;" * "\x211A" - ,"qopf;" * "\x1D562" - ,"qprime;" * "\x2057" - ,"Qscr;" * "\x1D4AC" - ,"qscr;" * "\x1D4C6" - ,"quaternions;" * "\x210D" - ,"quatint;" * "\x2A16" - ,"quest;" * "\x003F" - ,"questeq;" * "\x225F" - ,"QUOT" * "\x0022" - ,"quot" * "\x0022" - ,"QUOT;" * "\x0022" - ,"quot;" * "\x0022" - ,"rAarr;" * "\x21DB" - ,"race;" * "\x223D\x0331" - ,"Racute;" * "\x0154" - ,"racute;" * "\x0155" - ,"radic;" * "\x221A" - ,"raemptyv;" * "\x29B3" - ,"rang;" * "\x27E9" - ,"Rang;" * "\x27EB" - ,"rangd;" * "\x2992" - ,"range;" * "\x29A5" - ,"rangle;" * "\x27E9" - ,"raquo" * "\x00BB" - ,"raquo;" * "\x00BB" - ,"rarr;" * "\x2192" - ,"Rarr;" * "\x21A0" - ,"rArr;" * "\x21D2" - ,"rarrap;" * "\x2975" - ,"rarrb;" * "\x21E5" - ,"rarrbfs;" * "\x2920" - ,"rarrc;" * "\x2933" - ,"rarrfs;" * "\x291E" - ,"rarrhk;" * "\x21AA" - ,"rarrlp;" * "\x21AC" - ,"rarrpl;" * "\x2945" - ,"rarrsim;" * "\x2974" - ,"rarrtl;" * "\x21A3" - ,"Rarrtl;" * "\x2916" - ,"rarrw;" * "\x219D" - ,"ratail;" * "\x291A" - ,"rAtail;" * "\x291C" - ,"ratio;" * "\x2236" - ,"rationals;" * "\x211A" - ,"rbarr;" * "\x290D" - ,"rBarr;" * "\x290F" - ,"RBarr;" * "\x2910" - ,"rbbrk;" * "\x2773" - ,"rbrace;" * "\x007D" - ,"rbrack;" * "\x005D" - ,"rbrke;" * "\x298C" - ,"rbrksld;" * "\x298E" - ,"rbrkslu;" * "\x2990" - ,"Rcaron;" * "\x0158" - ,"rcaron;" * "\x0159" - ,"Rcedil;" * "\x0156" - ,"rcedil;" * "\x0157" - ,"rceil;" * "\x2309" - ,"rcub;" * "\x007D" - ,"Rcy;" * "\x0420" - ,"rcy;" * "\x0440" - ,"rdca;" * "\x2937" - ,"rdldhar;" * "\x2969" - ,"rdquo;" * "\x201D" - ,"rdquor;" * "\x201D" - ,"rdsh;" * "\x21B3" - ,"Re;" * "\x211C" - ,"real;" * "\x211C" - ,"realine;" * "\x211B" - ,"realpart;" * "\x211C" - ,"reals;" * "\x211D" - ,"rect;" * "\x25AD" - ,"REG" * "\x00AE" - ,"reg" * "\x00AE" - ,"REG;" * "\x00AE" - ,"reg;" * "\x00AE" - ,"ReverseElement;" * "\x220B" - ,"ReverseEquilibrium;" * "\x21CB" - ,"ReverseUpEquilibrium;" * "\x296F" - ,"rfisht;" * "\x297D" - ,"rfloor;" * "\x230B" - ,"Rfr;" * "\x211C" - ,"rfr;" * "\x1D52F" - ,"rHar;" * "\x2964" - ,"rhard;" * "\x21C1" - ,"rharu;" * "\x21C0" - ,"rharul;" * "\x296C" - ,"Rho;" * "\x03A1" - ,"rho;" * "\x03C1" - ,"rhov;" * "\x03F1" - ,"RightAngleBracket;" * "\x27E9" - ,"RightArrow;" * "\x2192" - ,"rightarrow;" * "\x2192" - ,"Rightarrow;" * "\x21D2" - ,"RightArrowBar;" * "\x21E5" - ,"RightArrowLeftArrow;" * "\x21C4" - ,"rightarrowtail;" * "\x21A3" - ,"RightCeiling;" * "\x2309" - ,"RightDoubleBracket;" * "\x27E7" - ,"RightDownTeeVector;" * "\x295D" - ,"RightDownVector;" * "\x21C2" - ,"RightDownVectorBar;" * "\x2955" - ,"RightFloor;" * "\x230B" - ,"rightharpoondown;" * "\x21C1" - ,"rightharpoonup;" * "\x21C0" - ,"rightleftarrows;" * "\x21C4" - ,"rightleftharpoons;" * "\x21CC" - ,"rightrightarrows;" * "\x21C9" - ,"rightsquigarrow;" * "\x219D" - ,"RightTee;" * "\x22A2" - ,"RightTeeArrow;" * "\x21A6" - ,"RightTeeVector;" * "\x295B" - ,"rightthreetimes;" * "\x22CC" - ,"RightTriangle;" * "\x22B3" - ,"RightTriangleBar;" * "\x29D0" - ,"RightTriangleEqual;" * "\x22B5" - ,"RightUpDownVector;" * "\x294F" - ,"RightUpTeeVector;" * "\x295C" - ,"RightUpVector;" * "\x21BE" - ,"RightUpVectorBar;" * "\x2954" - ,"RightVector;" * "\x21C0" - ,"RightVectorBar;" * "\x2953" - ,"ring;" * "\x02DA" - ,"risingdotseq;" * "\x2253" - ,"rlarr;" * "\x21C4" - ,"rlhar;" * "\x21CC" - ,"rlm;" * "\x200F" - ,"rmoust;" * "\x23B1" - ,"rmoustache;" * "\x23B1" - ,"rnmid;" * "\x2AEE" - ,"roang;" * "\x27ED" - ,"roarr;" * "\x21FE" - ,"robrk;" * "\x27E7" - ,"ropar;" * "\x2986" - ,"Ropf;" * "\x211D" - ,"ropf;" * "\x1D563" - ,"roplus;" * "\x2A2E" - ,"rotimes;" * "\x2A35" - ,"RoundImplies;" * "\x2970" - ,"rpar;" * "\x0029" - ,"rpargt;" * "\x2994" - ,"rppolint;" * "\x2A12" - ,"rrarr;" * "\x21C9" - ,"Rrightarrow;" * "\x21DB" - ,"rsaquo;" * "\x203A" - ,"Rscr;" * "\x211B" - ,"rscr;" * "\x1D4C7" - ,"Rsh;" * "\x21B1" - ,"rsh;" * "\x21B1" - ,"rsqb;" * "\x005D" - ,"rsquo;" * "\x2019" - ,"rsquor;" * "\x2019" - ,"rthree;" * "\x22CC" - ,"rtimes;" * "\x22CA" - ,"rtri;" * "\x25B9" - ,"rtrie;" * "\x22B5" - ,"rtrif;" * "\x25B8" - ,"rtriltri;" * "\x29CE" - ,"RuleDelayed;" * "\x29F4" - ,"ruluhar;" * "\x2968" - ,"rx;" * "\x211E" - ,"Sacute;" * "\x015A" - ,"sacute;" * "\x015B" - ,"sbquo;" * "\x201A" - ,"sc;" * "\x227B" - ,"Sc;" * "\x2ABC" - ,"scap;" * "\x2AB8" - ,"Scaron;" * "\x0160" - ,"scaron;" * "\x0161" - ,"sccue;" * "\x227D" - ,"sce;" * "\x2AB0" - ,"scE;" * "\x2AB4" - ,"Scedil;" * "\x015E" - ,"scedil;" * "\x015F" - ,"Scirc;" * "\x015C" - ,"scirc;" * "\x015D" - ,"scnap;" * "\x2ABA" - ,"scnE;" * "\x2AB6" - ,"scnsim;" * "\x22E9" - ,"scpolint;" * "\x2A13" - ,"scsim;" * "\x227F" - ,"Scy;" * "\x0421" - ,"scy;" * "\x0441" - ,"sdot;" * "\x22C5" - ,"sdotb;" * "\x22A1" - ,"sdote;" * "\x2A66" - ,"searhk;" * "\x2925" - ,"searr;" * "\x2198" - ,"seArr;" * "\x21D8" - ,"searrow;" * "\x2198" - ,"sect" * "\x00A7" - ,"sect;" * "\x00A7" - ,"semi;" * "\x003B" - ,"seswar;" * "\x2929" - ,"setminus;" * "\x2216" - ,"setmn;" * "\x2216" - ,"sext;" * "\x2736" - ,"Sfr;" * "\x1D516" - ,"sfr;" * "\x1D530" - ,"sfrown;" * "\x2322" - ,"sharp;" * "\x266F" - ,"SHCHcy;" * "\x0429" - ,"shchcy;" * "\x0449" - ,"SHcy;" * "\x0428" - ,"shcy;" * "\x0448" - ,"ShortDownArrow;" * "\x2193" - ,"ShortLeftArrow;" * "\x2190" - ,"shortmid;" * "\x2223" - ,"shortparallel;" * "\x2225" - ,"ShortRightArrow;" * "\x2192" - ,"ShortUpArrow;" * "\x2191" - ,"shy" * "\x00AD" - ,"shy;" * "\x00AD" - ,"Sigma;" * "\x03A3" - ,"sigma;" * "\x03C3" - ,"sigmaf;" * "\x03C2" - ,"sigmav;" * "\x03C2" - ,"sim;" * "\x223C" - ,"simdot;" * "\x2A6A" - ,"sime;" * "\x2243" - ,"simeq;" * "\x2243" - ,"simg;" * "\x2A9E" - ,"simgE;" * "\x2AA0" - ,"siml;" * "\x2A9D" - ,"simlE;" * "\x2A9F" - ,"simne;" * "\x2246" - ,"simplus;" * "\x2A24" - ,"simrarr;" * "\x2972" - ,"slarr;" * "\x2190" - ,"SmallCircle;" * "\x2218" - ,"smallsetminus;" * "\x2216" - ,"smashp;" * "\x2A33" - ,"smeparsl;" * "\x29E4" - ,"smid;" * "\x2223" - ,"smile;" * "\x2323" - ,"smt;" * "\x2AAA" - ,"smte;" * "\x2AAC" - ,"smtes;" * "\x2AAC\xFE00" - ,"SOFTcy;" * "\x042C" - ,"softcy;" * "\x044C" - ,"sol;" * "\x002F" - ,"solb;" * "\x29C4" - ,"solbar;" * "\x233F" - ,"Sopf;" * "\x1D54A" - ,"sopf;" * "\x1D564" - ,"spades;" * "\x2660" - ,"spadesuit;" * "\x2660" - ,"spar;" * "\x2225" - ,"sqcap;" * "\x2293" - ,"sqcaps;" * "\x2293\xFE00" - ,"sqcup;" * "\x2294" - ,"sqcups;" * "\x2294\xFE00" - ,"Sqrt;" * "\x221A" - ,"sqsub;" * "\x228F" - ,"sqsube;" * "\x2291" - ,"sqsubset;" * "\x228F" - ,"sqsubseteq;" * "\x2291" - ,"sqsup;" * "\x2290" - ,"sqsupe;" * "\x2292" - ,"sqsupset;" * "\x2290" - ,"sqsupseteq;" * "\x2292" - ,"squ;" * "\x25A1" - ,"Square;" * "\x25A1" - ,"square;" * "\x25A1" - ,"SquareIntersection;" * "\x2293" - ,"SquareSubset;" * "\x228F" - ,"SquareSubsetEqual;" * "\x2291" - ,"SquareSuperset;" * "\x2290" - ,"SquareSupersetEqual;" * "\x2292" - ,"SquareUnion;" * "\x2294" - ,"squarf;" * "\x25AA" - ,"squf;" * "\x25AA" - ,"srarr;" * "\x2192" - ,"Sscr;" * "\x1D4AE" - ,"sscr;" * "\x1D4C8" - ,"ssetmn;" * "\x2216" - ,"ssmile;" * "\x2323" - ,"sstarf;" * "\x22C6" - ,"Star;" * "\x22C6" - ,"star;" * "\x2606" - ,"starf;" * "\x2605" - ,"straightepsilon;" * "\x03F5" - ,"straightphi;" * "\x03D5" - ,"strns;" * "\x00AF" - ,"sub;" * "\x2282" - ,"Sub;" * "\x22D0" - ,"subdot;" * "\x2ABD" - ,"sube;" * "\x2286" - ,"subE;" * "\x2AC5" - ,"subedot;" * "\x2AC3" - ,"submult;" * "\x2AC1" - ,"subne;" * "\x228A" - ,"subnE;" * "\x2ACB" - ,"subplus;" * "\x2ABF" - ,"subrarr;" * "\x2979" - ,"subset;" * "\x2282" - ,"Subset;" * "\x22D0" - ,"subseteq;" * "\x2286" - ,"subseteqq;" * "\x2AC5" - ,"SubsetEqual;" * "\x2286" - ,"subsetneq;" * "\x228A" - ,"subsetneqq;" * "\x2ACB" - ,"subsim;" * "\x2AC7" - ,"subsub;" * "\x2AD5" - ,"subsup;" * "\x2AD3" - ,"succ;" * "\x227B" - ,"succapprox;" * "\x2AB8" - ,"succcurlyeq;" * "\x227D" - ,"Succeeds;" * "\x227B" - ,"SucceedsEqual;" * "\x2AB0" - ,"SucceedsSlantEqual;" * "\x227D" - ,"SucceedsTilde;" * "\x227F" - ,"succeq;" * "\x2AB0" - ,"succnapprox;" * "\x2ABA" - ,"succneqq;" * "\x2AB6" - ,"succnsim;" * "\x22E9" - ,"succsim;" * "\x227F" - ,"SuchThat;" * "\x220B" - ,"Sum;" * "\x2211" - ,"sum;" * "\x2211" - ,"sung;" * "\x266A" - ,"sup1" * "\x00B9" - ,"sup1;" * "\x00B9" - ,"sup2" * "\x00B2" - ,"sup2;" * "\x00B2" - ,"sup3" * "\x00B3" - ,"sup3;" * "\x00B3" - ,"sup;" * "\x2283" - ,"Sup;" * "\x22D1" - ,"supdot;" * "\x2ABE" - ,"supdsub;" * "\x2AD8" - ,"supe;" * "\x2287" - ,"supE;" * "\x2AC6" - ,"supedot;" * "\x2AC4" - ,"Superset;" * "\x2283" - ,"SupersetEqual;" * "\x2287" - ,"suphsol;" * "\x27C9" - ,"suphsub;" * "\x2AD7" - ,"suplarr;" * "\x297B" - ,"supmult;" * "\x2AC2" - ,"supne;" * "\x228B" - ,"supnE;" * "\x2ACC" - ,"supplus;" * "\x2AC0" - ,"supset;" * "\x2283" - ,"Supset;" * "\x22D1" - ,"supseteq;" * "\x2287" - ,"supseteqq;" * "\x2AC6" - ,"supsetneq;" * "\x228B" - ,"supsetneqq;" * "\x2ACC" - ,"supsim;" * "\x2AC8" - ,"supsub;" * "\x2AD4" - ,"supsup;" * "\x2AD6" - ,"swarhk;" * "\x2926" - ,"swarr;" * "\x2199" - ,"swArr;" * "\x21D9" - ,"swarrow;" * "\x2199" - ,"swnwar;" * "\x292A" - ,"szlig" * "\x00DF" - ,"szlig;" * "\x00DF" - ,"Tab;" * "\x0009" - ,"target;" * "\x2316" - ,"Tau;" * "\x03A4" - ,"tau;" * "\x03C4" - ,"tbrk;" * "\x23B4" - ,"Tcaron;" * "\x0164" - ,"tcaron;" * "\x0165" - ,"Tcedil;" * "\x0162" - ,"tcedil;" * "\x0163" - ,"Tcy;" * "\x0422" - ,"tcy;" * "\x0442" - ,"tdot;" * "\x20DB" - ,"telrec;" * "\x2315" - ,"Tfr;" * "\x1D517" - ,"tfr;" * "\x1D531" - ,"there4;" * "\x2234" - ,"Therefore;" * "\x2234" - ,"therefore;" * "\x2234" - ,"Theta;" * "\x0398" - ,"theta;" * "\x03B8" - ,"thetasym;" * "\x03D1" - ,"thetav;" * "\x03D1" - ,"thickapprox;" * "\x2248" - ,"thicksim;" * "\x223C" - ,"ThickSpace;" * "\x205F\x200A" - ,"thinsp;" * "\x2009" - ,"ThinSpace;" * "\x2009" - ,"thkap;" * "\x2248" - ,"thksim;" * "\x223C" - ,"THORN" * "\x00DE" - ,"thorn" * "\x00FE" - ,"THORN;" * "\x00DE" - ,"thorn;" * "\x00FE" - ,"tilde;" * "\x02DC" - ,"Tilde;" * "\x223C" - ,"TildeEqual;" * "\x2243" - ,"TildeFullEqual;" * "\x2245" - ,"TildeTilde;" * "\x2248" - ,"times" * "\x00D7" - ,"times;" * "\x00D7" - ,"timesb;" * "\x22A0" - ,"timesbar;" * "\x2A31" - ,"timesd;" * "\x2A30" - ,"tint;" * "\x222D" - ,"toea;" * "\x2928" - ,"top;" * "\x22A4" - ,"topbot;" * "\x2336" - ,"topcir;" * "\x2AF1" - ,"Topf;" * "\x1D54B" - ,"topf;" * "\x1D565" - ,"topfork;" * "\x2ADA" - ,"tosa;" * "\x2929" - ,"tprime;" * "\x2034" - ,"TRADE;" * "\x2122" - ,"trade;" * "\x2122" - ,"triangle;" * "\x25B5" - ,"triangledown;" * "\x25BF" - ,"triangleleft;" * "\x25C3" - ,"trianglelefteq;" * "\x22B4" - ,"triangleq;" * "\x225C" - ,"triangleright;" * "\x25B9" - ,"trianglerighteq;" * "\x22B5" - ,"tridot;" * "\x25EC" - ,"trie;" * "\x225C" - ,"triminus;" * "\x2A3A" - ,"TripleDot;" * "\x20DB" - ,"triplus;" * "\x2A39" - ,"trisb;" * "\x29CD" - ,"tritime;" * "\x2A3B" - ,"trpezium;" * "\x23E2" - ,"Tscr;" * "\x1D4AF" - ,"tscr;" * "\x1D4C9" - ,"TScy;" * "\x0426" - ,"tscy;" * "\x0446" - ,"TSHcy;" * "\x040B" - ,"tshcy;" * "\x045B" - ,"Tstrok;" * "\x0166" - ,"tstrok;" * "\x0167" - ,"twixt;" * "\x226C" - ,"twoheadleftarrow;" * "\x219E" - ,"twoheadrightarrow;" * "\x21A0" - ,"Uacute" * "\x00DA" - ,"uacute" * "\x00FA" - ,"Uacute;" * "\x00DA" - ,"uacute;" * "\x00FA" - ,"uarr;" * "\x2191" - ,"Uarr;" * "\x219F" - ,"uArr;" * "\x21D1" - ,"Uarrocir;" * "\x2949" - ,"Ubrcy;" * "\x040E" - ,"ubrcy;" * "\x045E" - ,"Ubreve;" * "\x016C" - ,"ubreve;" * "\x016D" - ,"Ucirc" * "\x00DB" - ,"ucirc" * "\x00FB" - ,"Ucirc;" * "\x00DB" - ,"ucirc;" * "\x00FB" - ,"Ucy;" * "\x0423" - ,"ucy;" * "\x0443" - ,"udarr;" * "\x21C5" - ,"Udblac;" * "\x0170" - ,"udblac;" * "\x0171" - ,"udhar;" * "\x296E" - ,"ufisht;" * "\x297E" - ,"Ufr;" * "\x1D518" - ,"ufr;" * "\x1D532" - ,"Ugrave" * "\x00D9" - ,"ugrave" * "\x00F9" - ,"Ugrave;" * "\x00D9" - ,"ugrave;" * "\x00F9" - ,"uHar;" * "\x2963" - ,"uharl;" * "\x21BF" - ,"uharr;" * "\x21BE" - ,"uhblk;" * "\x2580" - ,"ulcorn;" * "\x231C" - ,"ulcorner;" * "\x231C" - ,"ulcrop;" * "\x230F" - ,"ultri;" * "\x25F8" - ,"Umacr;" * "\x016A" - ,"umacr;" * "\x016B" - ,"uml" * "\x00A8" - ,"uml;" * "\x00A8" - ,"UnderBar;" * "\x005F" - ,"UnderBrace;" * "\x23DF" - ,"UnderBracket;" * "\x23B5" - ,"UnderParenthesis;" * "\x23DD" - ,"Union;" * "\x22C3" - ,"UnionPlus;" * "\x228E" - ,"Uogon;" * "\x0172" - ,"uogon;" * "\x0173" - ,"Uopf;" * "\x1D54C" - ,"uopf;" * "\x1D566" - ,"UpArrow;" * "\x2191" - ,"uparrow;" * "\x2191" - ,"Uparrow;" * "\x21D1" - ,"UpArrowBar;" * "\x2912" - ,"UpArrowDownArrow;" * "\x21C5" - ,"UpDownArrow;" * "\x2195" - ,"updownarrow;" * "\x2195" - ,"Updownarrow;" * "\x21D5" - ,"UpEquilibrium;" * "\x296E" - ,"upharpoonleft;" * "\x21BF" - ,"upharpoonright;" * "\x21BE" - ,"uplus;" * "\x228E" - ,"UpperLeftArrow;" * "\x2196" - ,"UpperRightArrow;" * "\x2197" - ,"upsi;" * "\x03C5" - ,"Upsi;" * "\x03D2" - ,"upsih;" * "\x03D2" - ,"Upsilon;" * "\x03A5" - ,"upsilon;" * "\x03C5" - ,"UpTee;" * "\x22A5" - ,"UpTeeArrow;" * "\x21A5" - ,"upuparrows;" * "\x21C8" - ,"urcorn;" * "\x231D" - ,"urcorner;" * "\x231D" - ,"urcrop;" * "\x230E" - ,"Uring;" * "\x016E" - ,"uring;" * "\x016F" - ,"urtri;" * "\x25F9" - ,"Uscr;" * "\x1D4B0" - ,"uscr;" * "\x1D4CA" - ,"utdot;" * "\x22F0" - ,"Utilde;" * "\x0168" - ,"utilde;" * "\x0169" - ,"utri;" * "\x25B5" - ,"utrif;" * "\x25B4" - ,"uuarr;" * "\x21C8" - ,"Uuml" * "\x00DC" - ,"uuml" * "\x00FC" - ,"Uuml;" * "\x00DC" - ,"uuml;" * "\x00FC" - ,"uwangle;" * "\x29A7" - ,"vangrt;" * "\x299C" - ,"varepsilon;" * "\x03F5" - ,"varkappa;" * "\x03F0" - ,"varnothing;" * "\x2205" - ,"varphi;" * "\x03D5" - ,"varpi;" * "\x03D6" - ,"varpropto;" * "\x221D" - ,"varr;" * "\x2195" - ,"vArr;" * "\x21D5" - ,"varrho;" * "\x03F1" - ,"varsigma;" * "\x03C2" - ,"varsubsetneq;" * "\x228A\xFE00" - ,"varsubsetneqq;" * "\x2ACB\xFE00" - ,"varsupsetneq;" * "\x228B\xFE00" - ,"varsupsetneqq;" * "\x2ACC\xFE00" - ,"vartheta;" * "\x03D1" - ,"vartriangleleft;" * "\x22B2" - ,"vartriangleright;" * "\x22B3" - ,"vBar;" * "\x2AE8" - ,"Vbar;" * "\x2AEB" - ,"vBarv;" * "\x2AE9" - ,"Vcy;" * "\x0412" - ,"vcy;" * "\x0432" - ,"vdash;" * "\x22A2" - ,"vDash;" * "\x22A8" - ,"Vdash;" * "\x22A9" - ,"VDash;" * "\x22AB" - ,"Vdashl;" * "\x2AE6" - ,"vee;" * "\x2228" - ,"Vee;" * "\x22C1" - ,"veebar;" * "\x22BB" - ,"veeeq;" * "\x225A" - ,"vellip;" * "\x22EE" - ,"verbar;" * "\x007C" - ,"Verbar;" * "\x2016" - ,"vert;" * "\x007C" - ,"Vert;" * "\x2016" - ,"VerticalBar;" * "\x2223" - ,"VerticalLine;" * "\x007C" - ,"VerticalSeparator;" * "\x2758" - ,"VerticalTilde;" * "\x2240" - ,"VeryThinSpace;" * "\x200A" - ,"Vfr;" * "\x1D519" - ,"vfr;" * "\x1D533" - ,"vltri;" * "\x22B2" - ,"vnsub;" * "\x2282\x20D2" - ,"vnsup;" * "\x2283\x20D2" - ,"Vopf;" * "\x1D54D" - ,"vopf;" * "\x1D567" - ,"vprop;" * "\x221D" - ,"vrtri;" * "\x22B3" - ,"Vscr;" * "\x1D4B1" - ,"vscr;" * "\x1D4CB" - ,"vsubne;" * "\x228A\xFE00" - ,"vsubnE;" * "\x2ACB\xFE00" - ,"vsupne;" * "\x228B\xFE00" - ,"vsupnE;" * "\x2ACC\xFE00" - ,"Vvdash;" * "\x22AA" - ,"vzigzag;" * "\x299A" - ,"Wcirc;" * "\x0174" - ,"wcirc;" * "\x0175" - ,"wedbar;" * "\x2A5F" - ,"wedge;" * "\x2227" - ,"Wedge;" * "\x22C0" - ,"wedgeq;" * "\x2259" - ,"weierp;" * "\x2118" - ,"Wfr;" * "\x1D51A" - ,"wfr;" * "\x1D534" - ,"Wopf;" * "\x1D54E" - ,"wopf;" * "\x1D568" - ,"wp;" * "\x2118" - ,"wr;" * "\x2240" - ,"wreath;" * "\x2240" - ,"Wscr;" * "\x1D4B2" - ,"wscr;" * "\x1D4CC" - ,"xcap;" * "\x22C2" - ,"xcirc;" * "\x25EF" - ,"xcup;" * "\x22C3" - ,"xdtri;" * "\x25BD" - ,"Xfr;" * "\x1D51B" - ,"xfr;" * "\x1D535" - ,"xharr;" * "\x27F7" - ,"xhArr;" * "\x27FA" - ,"Xi;" * "\x039E" - ,"xi;" * "\x03BE" - ,"xlarr;" * "\x27F5" - ,"xlArr;" * "\x27F8" - ,"xmap;" * "\x27FC" - ,"xnis;" * "\x22FB" - ,"xodot;" * "\x2A00" - ,"Xopf;" * "\x1D54F" - ,"xopf;" * "\x1D569" - ,"xoplus;" * "\x2A01" - ,"xotime;" * "\x2A02" - ,"xrarr;" * "\x27F6" - ,"xrArr;" * "\x27F9" - ,"Xscr;" * "\x1D4B3" - ,"xscr;" * "\x1D4CD" - ,"xsqcup;" * "\x2A06" - ,"xuplus;" * "\x2A04" - ,"xutri;" * "\x25B3" - ,"xvee;" * "\x22C1" - ,"xwedge;" * "\x22C0" - ,"Yacute" * "\x00DD" - ,"yacute" * "\x00FD" - ,"Yacute;" * "\x00DD" - ,"yacute;" * "\x00FD" - ,"YAcy;" * "\x042F" - ,"yacy;" * "\x044F" - ,"Ycirc;" * "\x0176" - ,"ycirc;" * "\x0177" - ,"Ycy;" * "\x042B" - ,"ycy;" * "\x044B" - ,"yen" * "\x00A5" - ,"yen;" * "\x00A5" - ,"Yfr;" * "\x1D51C" - ,"yfr;" * "\x1D536" - ,"YIcy;" * "\x0407" - ,"yicy;" * "\x0457" - ,"Yopf;" * "\x1D550" - ,"yopf;" * "\x1D56A" - ,"Yscr;" * "\x1D4B4" - ,"yscr;" * "\x1D4CE" - ,"YUcy;" * "\x042E" - ,"yucy;" * "\x044E" - ,"yuml" * "\x00FF" - ,"yuml;" * "\x00FF" - ,"Yuml;" * "\x0178" - ,"Zacute;" * "\x0179" - ,"zacute;" * "\x017A" - ,"Zcaron;" * "\x017D" - ,"zcaron;" * "\x017E" - ,"Zcy;" * "\x0417" - ,"zcy;" * "\x0437" - ,"Zdot;" * "\x017B" - ,"zdot;" * "\x017C" - ,"zeetrf;" * "\x2128" - ,"ZeroWidthSpace;" * "\x200B" - ,"Zeta;" * "\x0396" - ,"zeta;" * "\x03B6" - ,"Zfr;" * "\x2128" - ,"zfr;" * "\x1D537" - ,"ZHcy;" * "\x0416" - ,"zhcy;" * "\x0436" - ,"zigrarr;" * "\x21DD" - ,"Zopf;" * "\x2124" - ,"zopf;" * "\x1D56B" - ,"Zscr;" * "\x1D4B5" - ,"zscr;" * "\x1D4CF" - ,"zwj;" * "\x200D" - ,"zwnj;" * "\x200C" - ] diff --git a/Text/HTML/TagSoup/Generated.hs b/Text/HTML/TagSoup/Generated.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Generated.hs +++ /dev/null @@ -1,2 +0,0 @@ -module Text.HTML.TagSoup.Generated(parseTagsOptions) where -import Text.HTML.TagSoup.Manual diff --git a/Text/HTML/TagSoup/Implementation.hs b/Text/HTML/TagSoup/Implementation.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Implementation.hs +++ /dev/null @@ -1,193 +0,0 @@ -{-# LANGUAGE RecordWildCards, PatternGuards, ScopedTypeVariables #-} - -module Text.HTML.TagSoup.Implementation where - -import Text.HTML.TagSoup.Type -import Text.HTML.TagSoup.Options -import Text.StringLike as Str -import Numeric (readHex) -import Data.Char (chr, ord) -import Data.Ix -import Control.Exception(assert) -import Control.Arrow - ---------------------------------------------------------------------- --- BOTTOM LAYER - -data Out - = Char Char - | Tag -- < - | TagShut -- - | TagEndClose -- /> - | Comment -- - | EntityName -- & - | EntityNum -- &# - | EntityHex -- &#x - | EntityEnd Bool -- Attributed followed by ; for True, missing ; for False - | Warn String - | Pos Position - deriving (Show,Eq) - -errSeen x = Warn $ "Unexpected " ++ show x -errWant x = Warn $ "Expected " ++ show x - -data S = S - {s :: S - ,tl :: S - ,hd :: Char - ,eof :: Bool - ,next :: String -> Maybe S - ,pos :: [Out] -> [Out] - } - - -expand :: Position -> String -> S -expand p text = p `seq` res - where res = S{s = res - ,tl = expand (positionChar p (head text)) (tail text) - ,hd = if null text then '\0' else head text - ,eof = null text - ,next = next p text - ,pos = (Pos p:) - } - - next p (t:ext) (s:tr) | t == s = next (positionChar p t) ext tr - next p text [] = Just $ expand p text - next _ _ _ = Nothing - - -infixr & - -class Outable a where (&) :: a -> [Out] -> [Out] -instance Outable Char where (&) = ampChar -instance Outable Out where (&) = ampOut -ampChar x y = Char x : y -ampOut x y = x : y - - -state :: String -> S -state s = expand nullPosition s - ---------------------------------------------------------------------- --- TOP LAYER - - -output :: forall str . StringLike str => ParseOptions str -> [Out] -> [Tag str] -output ParseOptions{..} x = (if optTagTextMerge then tagTextMerge else id) $ go ((nullPosition,[]),x) - where - -- main choice loop - go :: ((Position,[Tag str]),[Out]) -> [Tag str] - go ((p,ws),xs) | p `seq` False = [] -- otherwise p is a space leak when optTagPosition == False - go ((p,ws),xs) | not $ null ws = (if optTagWarning then (reverse ws++) else id) $ go ((p,[]),xs) - go ((p,ws),Pos p2:xs) = go ((p2,ws),xs) - - go x | isChar x = pos x $ TagText a : go y - where (y,a) = charsStr x - go x | isTag x = pos x $ TagOpen a b : (if isTagEndClose z then pos x $ TagClose a : go (next z) else go (skip isTagEnd z)) - where (y,a) = charsStr $ next x - (z,b) = atts y - go x | isTagShut x = pos x $ (TagClose a:) $ - (if not (null b) then warn x "Unexpected attributes in close tag" else id) $ - if isTagEndClose z then warn x "Unexpected self-closing in close tag" $ go (next z) else go (skip isTagEnd z) - where (y,a) = charsStr $ next x - (z,b) = atts y - go x | isComment x = pos x $ TagComment a : go (skip isCommentEnd y) - where (y,a) = charsStr $ next x - go x | isEntityName x = poss x ((if optTagWarning then id else filter (not . isTagWarning)) $ optEntityData (a, getEntityEnd y)) ++ go (skip isEntityEnd y) - where (y,a) = charsStr $ next x - go x | isEntityNumHex x = pos x $ TagText (fromChar $ entityChr x a) : go (skip isEntityEnd y) - where (y,a) = chars $ next x - go x | Just a <- fromWarn x = if optTagWarning then pos x $ TagWarning (fromString a) : go (next x) else go (next x) - go x | isEof x = [] - - atts :: ((Position,[Tag str]),[Out]) -> ( ((Position,[Tag str]),[Out]) , [(str,str)] ) - atts x | isAttName x = second ((a,b):) $ atts z - where (y,a) = charsStr (next x) - (z,b) = if isAttVal y then charsEntsStr (next y) else (y, empty) - atts x | isAttVal x = second ((empty,a):) $ atts y - where (y,a) = charsEntsStr (next x) - atts x = (x, []) - - -- chars - chars x = charss False x - charsStr x = (id *** fromString) $ chars x - charsEntsStr x = (id *** fromString) $ charss True x - - -- loop round collecting characters, if the b is set including entity - charss :: Bool -> ((Position,[Tag str]),[Out]) -> ( ((Position,[Tag str]),[Out]) , String) - charss t x | Just a <- fromChr x = (y, a:b) - where (y,b) = charss t (next x) - charss t x | t, isEntityName x = second (toString n ++) $ charss t $ addWarns m z - where (y,a) = charsStr $ next x - b = getEntityEnd y - z = skip isEntityEnd y - (n,m) = optEntityAttrib (a,b) - charss t x | t, isEntityNumHex x = second (entityChr x a:) $ charss t z - where (y,a) = chars $ next x - z = skip isEntityEnd y - charss t ((_,w),Pos p:xs) = charss t ((p,w),xs) - charss t x | Just a <- fromWarn x = charss t $ (if optTagWarning then addWarns [TagWarning $ fromString a] else id) $ next x - charss t x = (x, []) - - -- utility functions - next x = second (drop 1) x - skip f x = assert (isEof x || f x) (next x) - addWarns ws x@((p,w),y) = ((p, reverse (poss x ws) ++ w), y) - pos ((p,_),_) rest = if optTagPosition then tagPosition p : rest else rest - warn x s rest = if optTagWarning then pos x $ TagWarning (fromString s) : rest else rest - poss x = concatMap (\w -> pos x [w]) - - -entityChr x s | isEntityNum x = chr_ $ read s - | isEntityHex x = chr_ $ fst $ head $ readHex s - where chr_ x | inRange (toInteger $ ord minBound, toInteger $ ord maxBound) x = chr $ fromInteger x - | otherwise = '?' - - -isEof (_,[]) = True; isEof _ = False -isChar (_,Char{}:_) = True; isChar _ = False -isTag (_,Tag{}:_) = True; isTag _ = False -isTagShut (_,TagShut{}:_) = True; isTagShut _ = False -isAttName (_,AttName{}:_) = True; isAttName _ = False -isAttVal (_,AttVal{}:_) = True; isAttVal _ = False -isTagEnd (_,TagEnd{}:_) = True; isTagEnd _ = False -isTagEndClose (_,TagEndClose{}:_) = True; isTagEndClose _ = False -isComment (_,Comment{}:_) = True; isComment _ = False -isCommentEnd (_,CommentEnd{}:_) = True; isCommentEnd _ = False -isEntityName (_,EntityName{}:_) = True; isEntityName _ = False -isEntityNumHex (_,EntityNum{}:_) = True; isEntityNumHex (_,EntityHex{}:_) = True; isEntityNumHex _ = False -isEntityNum (_,EntityNum{}:_) = True; isEntityNum _ = False -isEntityHex (_,EntityHex{}:_) = True; isEntityHex _ = False -isEntityEnd (_,EntityEnd{}:_) = True; isEntityEnd _ = False -isWarn (_,Warn{}:_) = True; isWarn _ = False - -fromChr (_,Char x:_) = Just x ; fromChr _ = Nothing -fromWarn (_,Warn x:_) = Just x ; fromWarn _ = Nothing - -getEntityEnd (_,EntityEnd b:_) = b - - --- Merge all adjacent TagText bits -tagTextMerge :: StringLike str => [Tag str] -> [Tag str] -tagTextMerge (TagText x:xs) = TagText (strConcat (x:a)) : tagTextMerge b - where - (a,b) = f xs - - -- additional brackets on 3 lines to work around HSE 1.3.2 bugs with pattern fixities - f (TagText x:xs) = (x:a,b) - where (a,b) = f xs - f (TagPosition{}:(x@TagText{}:xs)) = f $ x : xs - f x = g x id x - - g o op (p@TagPosition{}:(w@TagWarning{}:xs)) = g o (op . (p:) . (w:)) xs - g o op (w@TagWarning{}:xs) = g o (op . (w:)) xs - g o op (p@TagPosition{}:(x@TagText{}:xs)) = f $ p : x : op xs - g o op (x@TagText{}:xs) = f $ x : op xs - g o op _ = ([], o) - -tagTextMerge (x:xs) = x : tagTextMerge xs -tagTextMerge [] = [] diff --git a/Text/HTML/TagSoup/Manual.hs b/Text/HTML/TagSoup/Manual.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Manual.hs +++ /dev/null @@ -1,13 +0,0 @@ - -module Text.HTML.TagSoup.Manual(parseTagsOptions) where - -import Text.HTML.TagSoup.Specification -import Text.HTML.TagSoup.Implementation -import Text.HTML.TagSoup.Type -import Text.HTML.TagSoup.Options -import Text.StringLike - - -parseTagsOptions :: StringLike str => ParseOptions str -> str -> [Tag str] -parseTagsOptions opts = output opts . parse . toString - diff --git a/Text/HTML/TagSoup/Match.hs b/Text/HTML/TagSoup/Match.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Match.hs +++ /dev/null @@ -1,198 +0,0 @@ --- | Combinators to match tags. Some people prefer to use @(~==)@ from --- "Text.HTML.TagSoup", others prefer these more structured combinators. --- Which you use is personal preference. --- --- The functions below offer maximum flexibility for matching tags. --- Using 'tagOpen', for example, you can match all links or buttons that have the "btn" class. --- --- For simple uses cases—like matching all comment tags, or matching opening @\@ tags, --- use the tag identification functions in "Text.HTML.TagSoup#tag-identification". -module Text.HTML.TagSoup.Match where - -import Text.HTML.TagSoup.Type (Tag(..), Attribute) -import Data.List (tails) - --- * Matching Tags - --- | Match an opening tag --- --- ==== __Examples__ --- --- /Matching an opening @\@ tag with a @"btn"@ class:/ --- --- >>> let tag = TagOpen "a" [("class", "btn")] --- >>> tagOpen (== "a") (\attrs -> any (== ("class", "btn")) attrs) tag --- True -tagOpen :: (str -> Bool) -> ([Attribute str] -> Bool) -> Tag str -> Bool -tagOpen pName pAttrs (TagOpen name attrs) = - pName name && pAttrs attrs -tagOpen _ _ _ = False - --- | Match a closing tag --- --- ==== __Examples__ --- --- /Matching a closing @\<\/a>@ tag:/ --- --- >>> tagClose (== "a") (TagClose "a") --- True --- --- >>> tagClose (== "a") (TagOpen "a" []) --- False -tagClose :: (str -> Bool) -> Tag str -> Bool -tagClose pName (TagClose name) = pName name -tagClose _ _ = False - --- | Match text tags --- --- ==== __Examples__ --- --- /Match all text tags:/ --- --- >>> let tags = parseTags "

    This is a paragraph

    " --- [TagOpen "p" [],TagText "This is a paragraph",TagClose "p"] --- >>> filter (tagText (const True)) tags --- [TagText "This is a paragraph"] -tagText :: (str -> Bool) -> Tag str -> Bool -tagText p (TagText text) = p text -tagText _ _ = False - --- | Match comment tags --- --- ==== __Examples__ --- --- /Matching comment tags that include an exclamation mark:/ --- --- >>> let tags = parseTags "" --- [TagComment "This is a comment!"] --- >>> all (tagComment (\s -> '!' `elem` s)) tags --- True -tagComment :: (str -> Bool) -> Tag str -> Bool -tagComment p (TagComment text) = p text -tagComment _ _ = False - - --- | Match an opening tag's name literally --- --- ==== __Examples__ --- --- /Matching @\    @ tags with the @id@ "foo":/ --- --- >>> let tag = TagOpen "a" [("id", "foo")] --- TagOpen "a" [("id","foo")] --- >>> tagOpenLit "a" (\attrs -> any (== ("id", "foo")) attrs) tag --- True --- -tagOpenLit :: Eq str => str -> ([Attribute str] -> Bool) -> Tag str -> Bool -tagOpenLit name = tagOpen (name==) - --- | Match a closing tag's name literally --- --- ==== __Examples__ --- --- /Match a closing @\@ tag:/ --- --- >>> tagCloseLit "a" (TagClose "a") --- True --- --- >>> tagCloseLit "a" (TagClose "em") --- False -tagCloseLit :: Eq str => str -> Tag str -> Bool -tagCloseLit name = tagClose (name==) - --- | Match an opening tag's name literally, and at least one of its attributes --- --- ==== __Examples__ --- --- /Matching a @\
    @ tag with the @id@ "foo":/ --- --- >>> tagOpenAttrLit "div" ("id", "foo") (TagOpen "div" [("id", "foo")]) --- True -tagOpenAttrLit :: Eq str => str -> Attribute str -> Tag str -> Bool -tagOpenAttrLit name attr = - tagOpenLit name (anyAttrLit attr) - -{- | -Match a tag with given name, that contains an attribute -with given name, that satisfies a predicate. -If an attribute occurs multiple times, -all occurrences are checked. - -==== __Examples__ - -/Matching an @\@ tag with an ID that starts with "comment-":/ - ->>> let commentTag = TagOpen "a" [("id", "comment-45678")] ->>> tagOpenAttrNameLit "a" "id" (\idValue -> "comment-" `Data.List.isPrefixOf` idValue) commentTag -True --} -tagOpenAttrNameLit :: Eq str => str -> str -> (str -> Bool) -> Tag str -> Bool -tagOpenAttrNameLit tagName attrName pAttrValue = - tagOpenLit tagName - (anyAttr (\(name,value) -> name==attrName && pAttrValue value)) - - --- | Check if the 'Tag str' is 'TagOpen' and matches the given name --- --- ==== __Examples__ --- --- /Matching an @\@ tag:/ --- --- >>> tagOpenNameLit "a" (TagOpen "a" []) --- True --- --- >>> tagOpenNameLit "a" (TagOpen "div" []) --- False -tagOpenNameLit :: Eq str => str -> Tag str -> Bool -tagOpenNameLit name = tagOpenLit name (const True) - --- | Check if the 'Tag str' is 'TagClose' and matches the given name --- --- ==== __Examples__ --- --- /Matching a closing @\<\/a>@ tag:/ --- --- >>> tagCloseNameLit "a" (TagClose "a") --- True --- --- >>> tagCloseNameLit "a" (TagClose "div") --- False -tagCloseNameLit :: Eq str => str -> Tag str -> Bool -tagCloseNameLit name = tagCloseLit name - - --- * Matching attributes - --- | Does any attribute name/value match the predicate. -anyAttr :: ((str,str) -> Bool) -> [Attribute str] -> Bool -anyAttr = any - --- | Does any attribute name match the predicate. -anyAttrName :: (str -> Bool) -> [Attribute str] -> Bool -anyAttrName p = any (p . fst) - --- | Does any attribute value match the predicate. -anyAttrValue :: (str -> Bool) -> [Attribute str] -> Bool -anyAttrValue p = any (p . snd) - - --- | Does any attribute name/value match. -anyAttrLit :: Eq str => (str,str) -> [Attribute str] -> Bool -anyAttrLit attr = anyAttr (attr==) - --- | Does any attribute name match. -anyAttrNameLit :: Eq str => str -> [Attribute str] -> Bool -anyAttrNameLit name = anyAttrName (name==) - --- | Does any attribute value match. -anyAttrValueLit :: Eq str => str -> [Attribute str] -> Bool -anyAttrValueLit value = anyAttrValue (value==) - - - --- | Get the tags under tags with a given name where the attributes match some predicate. -getTagContent :: Eq str => str -> ([Attribute str] -> Bool) -> [Tag str] -> [Tag str] -getTagContent name pAttrs = - takeWhile (not . tagCloseLit name) . drop 1 . - head . sections (tagOpenLit name pAttrs) - where sections p = filter (p . head) . init . tails diff --git a/Text/HTML/TagSoup/Options.hs b/Text/HTML/TagSoup/Options.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Options.hs +++ /dev/null @@ -1,80 +0,0 @@ -{-# LANGUAGE DeriveDataTypeable #-} - -module Text.HTML.TagSoup.Options where - -import Data.Typeable -import Text.HTML.TagSoup.Type -import Text.HTML.TagSoup.Entity -import Text.StringLike - - --- | These options control how 'parseTags' works. The 'ParseOptions' type is usually generated by one of --- 'parseOptions', 'parseOptionsFast' or 'parseOptionsEntities', then selected fields may be overriden. --- --- The options 'optTagPosition' and 'optTagWarning' specify whether to generate --- 'TagPosition' or 'TagWarning' elements respectively. Usually these options should be set to @False@ --- to simplify future stages, unless you rely on position information or want to give malformed HTML --- messages to the end user. --- --- The options 'optEntityData' and 'optEntityAttrib' control how entities, for example @ @ are handled. --- Both take a string, and a boolean, where @True@ indicates that the entity ended with a semi-colon @;@. --- Inside normal text 'optEntityData' will be called, and the results will be inserted in the tag stream. --- Inside a tag attribute 'optEntityAttrib' will be called, and the first component of the result will be used --- in the attribute, and the second component will be appended after the 'TagOpen' value (usually the second --- component is @[]@). As an example, to not decode any entities, pass: --- --- > parseOptions --- > {optEntityData=\(str,b) -> [TagText $ "&" ++ str ++ [';' | b]] --- > ,optEntityAttrib\(str,b) -> ("&" ++ str ++ [';' | b], []) - --- The 'optTagTextMerge' value specifies if you always want adjacent 'TagText' values to be merged. --- Merging adjacent pieces of text has a small performance penalty, but will usually make subsequent analysis --- simpler. Contiguous runs of characters without entities or tags will also be generated as single 'TagText' --- values. -data ParseOptions str = ParseOptions - {optTagPosition :: Bool -- ^ Should 'TagPosition' values be given before some items (default=False,fast=False). - ,optTagWarning :: Bool -- ^ Should 'TagWarning' values be given (default=False,fast=False) - ,optEntityData :: (str,Bool) -> [Tag str] -- ^ How to lookup an entity (Bool = has ending @';'@) - ,optEntityAttrib :: (str,Bool) -> (str,[Tag str]) -- ^ How to lookup an entity in an attribute (Bool = has ending @';'@?) - ,optTagTextMerge :: Bool -- ^ Require no adjacent 'TagText' values (default=True,fast=False) - } - deriving Typeable - - --- | A 'ParseOptions' structure using a custom function to lookup attributes. Any attribute --- that is not found will be left intact, and a 'TagWarning' given (if 'optTagWarning' is set). --- --- If you do not want to resolve any entities, simpliy pass @const Nothing@ for the lookup function. -parseOptionsEntities :: StringLike str => (str -> Maybe str) -> ParseOptions str -parseOptionsEntities lookupEntity = ParseOptions False False entityData entityAttrib True - where - entityData x = TagText a : b - where (a,b) = entityAttrib x - - entityAttrib ~(x,b) = - let x' = x `append` fromString [';'|b] - in case lookupEntity x' of - Just y -> (y, []) - Nothing -> (fromChar '&' `append` x' - ,[TagWarning $ fromString "Unknown entity: " `append` x]) - - --- | The default parse options value, described in 'ParseOptions'. Equivalent to --- @'parseOptionsEntities' 'lookupEntity'@. -parseOptions :: StringLike str => ParseOptions str -parseOptions = parseOptionsEntities $ fmap fromString . lookupEntity . toString - - --- | A 'ParseOptions' structure optimised for speed, following the fast options. -parseOptionsFast :: StringLike str => ParseOptions str -parseOptionsFast = parseOptions{optTagTextMerge=False} - - --- | Change the underlying string type of a 'ParseOptions' value. -fmapParseOptions :: (StringLike from, StringLike to) => ParseOptions from -> ParseOptions to -fmapParseOptions (ParseOptions a b c d e) = ParseOptions a b c2 d2 e - where - c2 ~(x,y) = map (fmap castString) $ c (castString x, y) - d2 ~(x,y) = (castString r, map (fmap castString) s) - where (r,s) = d (castString x, y) - diff --git a/Text/HTML/TagSoup/Parser.hs b/Text/HTML/TagSoup/Parser.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Parser.hs +++ /dev/null @@ -1,25 +0,0 @@ - -module Text.HTML.TagSoup.Parser( - parseTags, parseTagsOptions, - ParseOptions(..), parseOptions, parseOptionsFast, parseOptionsEntities - ) where - -import Text.HTML.TagSoup.Type -import Text.HTML.TagSoup.Options -import qualified Text.HTML.TagSoup.Generated as Gen - - --- | Parse a string to a list of tags, using an HTML 5 compliant parser. --- --- > parseTags "my&" == [TagOpen "hello" [],TagText "my&",TagClose "world"] -parseTags :: StringLike str => str -> [Tag str] -parseTags = parseTagsOptions parseOptions - - --- | Parse a string to a list of tags, using settings supplied by the 'ParseOptions' parameter, --- eg. to output position information: --- --- > parseTagsOptions parseOptions{optTagPosition = True} "my&" == --- > [TagPosition 1 1,TagOpen "hello" [],TagPosition 1 8,TagText "my&",TagPosition 1 15,TagClose "world"] -parseTagsOptions :: StringLike str => ParseOptions str -> str -> [Tag str] -parseTagsOptions = Gen.parseTagsOptions diff --git a/Text/HTML/TagSoup/Render.hs b/Text/HTML/TagSoup/Render.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Render.hs +++ /dev/null @@ -1,80 +0,0 @@ -{-# LANGUAGE PatternGuards, OverloadedStrings #-} -{-| - This module converts a list of 'Tag' back into a string. --} - -module Text.HTML.TagSoup.Render - ( - renderTags, renderTagsOptions, escapeHTML, - RenderOptions(..), renderOptions - ) where - -import Text.HTML.TagSoup.Entity -import Text.HTML.TagSoup.Type -import Text.StringLike - - --- | These options control how 'renderTags' works. --- --- The strange quirk of only minimizing @\@ tags is due to Internet Explorer treating --- @\\<\/br\>@ as @\\@. -data RenderOptions str = RenderOptions - {optEscape :: str -> str -- ^ Escape a piece of text (default = escape the four characters @&\"\<\>@) - ,optMinimize :: str -> Bool -- ^ Minimise \\<\/b\> -> \ (default = minimise only @\@ tags) - ,optRawTag :: str -> Bool -- ^ Should a tag be output with no escaping (default = true only for @script@) - } - - --- | Replace the four characters @&\"\<\>@ with their HTML entities ('escapeXML' lifted to 'StringLike'). -escapeHTML :: StringLike str => str -> str -escapeHTML = fromString . escapeXML . toString - --- | The default render options value, described in 'RenderOptions'. -renderOptions :: StringLike str => RenderOptions str -renderOptions = RenderOptions escapeHTML (\x -> toString x == "br") (\x -> toString x == "script") - - --- | Show a list of tags, as they might have been parsed, using the default settings given in --- 'RenderOptions'. --- --- > renderTags [TagOpen "hello" [],TagText "my&",TagClose "world"] == "my&" -renderTags :: StringLike str => [Tag str] -> str -renderTags = renderTagsOptions renderOptions - - --- | Show a list of tags using settings supplied by the 'RenderOptions' parameter, --- eg. to avoid escaping any characters one could do: --- --- > renderTagsOptions renderOptions{optEscape = id} [TagText "my&"] == "my&" -renderTagsOptions :: StringLike str => RenderOptions str -> [Tag str] -> str -renderTagsOptions opts = strConcat . tags - where - ss x = [x] - - tags (TagOpen name atts:TagClose name2:xs) - | name == name2 && optMinimize opts name = open name atts " /" ++ tags xs - tags (TagOpen name atts:xs) - | Just ('?',_) <- uncons name = open name atts " ?" ++ tags xs - | optRawTag opts name = - let (a,b) = break (== TagClose name) (TagOpen name atts:xs) - in concatMap (\x -> case x of TagText s -> [s]; _ -> tag x) a ++ tags b - tags (x:xs) = tag x ++ tags xs - tags [] = [] - - tag (TagOpen name atts) = open name atts "" - tag (TagClose name) = [""] - tag (TagText text) = [txt text] - tag (TagComment text) = ss "" - tag _ = ss "" - - txt = optEscape opts - open name atts shut = ["<",name] ++ concatMap att atts ++ [shut,">"] - att ("","") = [" \"\""] - att (x ,"") = [" ", x] - att ("", y) = [" \"",txt y,"\""] - att (x , y) = [" ",x,"=\"",txt y,"\""] - - com xs | Just ('-',xs) <- uncons xs, Just ('-',xs) <- uncons xs, Just ('>',xs) <- uncons xs = "-- >" : com xs - com xs = case uncons xs of - Nothing -> [] - Just (x,xs) -> fromChar x : com xs diff --git a/Text/HTML/TagSoup/Specification.hs b/Text/HTML/TagSoup/Specification.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Specification.hs +++ /dev/null @@ -1,332 +0,0 @@ -{-# LANGUAGE RecordWildCards, PatternGuards #-} - -module Text.HTML.TagSoup.Specification(parse) where - -import Text.HTML.TagSoup.Implementation -import Data.Char (isAlpha, isAlphaNum, isDigit, toLower) - --- We make some generalisations: --- --- --- is a valid closing tag --- is a valid closing tag --- is a valid tag attibute in ! and ?, i.e missing an attribute name --- We also don't do lowercase conversion --- Entities are handled without a list of known entity names --- We don't have RCData, CData or Escape modes (only effects dat and tagOpen) - - -data TypeTag = TypeNormal -- [Out] - -parse :: String -> [Out] -parse = dat . state - --- 8.2.4.1 Data state -dat :: Parser -dat S{..} = pos $ case hd of - '&' -> charReference tl - '<' -> tagOpen tl - _ | eof -> [] - _ -> hd & dat tl - - --- 8.2.4.2 Character reference data state -charReference s = charRef dat False Nothing s - - --- 8.2.4.3 Tag open state -tagOpen S{..} = case hd of - '!' -> markupDeclOpen tl - '/' -> closeTagOpen tl - _ | isAlpha hd -> Tag & hd & tagName (if isScript s then TypeScript else TypeNormal) tl - '>' -> errSeen "<>" & '<' & '>' & dat tl - '?' -> neilXmlTagOpen tl -- NEIL - _ -> errSeen "<" & '<' & dat s - -isScript = f "script" - where - f (c:cs) S{..} = toLower hd == c && f cs tl - f [] S{..} = white hd || hd == '/' || hd == '>' || hd == '?' || eof - - --- seen " Tag & '?' & hd & tagName TypeXml tl - _ -> errSeen "" -neilXmlTagClose S{..} = pos $ case hd of - '>' -> TagEnd & dat tl - _ -> errSeen "?" & beforeAttName TypeXml s - - --- just seen ">" at the end, am given tl -neilTagEnd typ S{..} - | typ == TypeXml = pos $ errWant "?>" & TagEnd & dat s - | typ == TypeScript = pos $ TagEnd & neilScriptBody s - | otherwise = pos $ TagEnd & dat s - --- Inside a we output to the text --- Deviation: is a closing tag, not a bogus comment -closeTagOpen S{..} = case hd of - _ | isAlpha hd || hd `elem` "?!" -> TagShut & hd & tagName TypeNormal tl - '>' -> errSeen "" & '<' & '/' & '>' & dat tl - _ | eof -> '<' & '/' & dat s - _ -> errWant "tag name" & bogusComment s - - --- 8.2.4.5 Tag name state -tagName typ S{..} = pos $ case hd of - _ | white hd -> beforeAttName typ tl - '/' -> selfClosingStartTag typ tl - '>' -> neilTagEnd typ tl - '?' | typ == TypeXml -> neilXmlTagClose tl - _ | isAlpha hd -> hd & tagName typ tl - _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s - _ -> hd & tagName typ tl - - --- 8.2.4.6 Before attribute name state -beforeAttName typ S{..} = pos $ case hd of - _ | white hd -> beforeAttName typ tl - '/' -> selfClosingStartTag typ tl - '>' -> neilTagEnd typ tl - '?' | typ == TypeXml -> neilXmlTagClose tl - _ | typ /= TypeNormal && hd `elem` "\'\"" -> beforeAttValue typ s -- NEIL - _ | hd `elem` "\"'<=" -> errSeen [hd] & AttName & hd & attName typ tl - _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s - _ -> AttName & hd & attName typ tl - - --- 8.2.4.7 Attribute name state -attName typ S{..} = pos $ case hd of - _ | white hd -> afterAttName typ tl - '/' -> selfClosingStartTag typ tl - '=' -> beforeAttValue typ tl - '>' -> neilTagEnd typ tl - '?' | typ == TypeXml -> neilXmlTagClose tl - _ | hd `elem` "\"'<" -> errSeen [hd] & def - _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s - _ -> def - where def = hd & attName typ tl - - --- 8.2.4.8 After attribute name state -afterAttName typ S{..} = pos $ case hd of - _ | white hd -> afterAttName typ tl - '/' -> selfClosingStartTag typ tl - '=' -> beforeAttValue typ tl - '>' -> neilTagEnd typ tl - '?' | typ == TypeXml -> neilXmlTagClose tl - _ | typ /= TypeNormal && hd `elem` "\"'" -> AttVal & beforeAttValue typ s -- NEIL - _ | hd `elem` "\"'<" -> errSeen [hd] & def - _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s - _ -> def - where def = AttName & hd & attName typ tl - --- 8.2.4.9 Before attribute value state -beforeAttValue typ S{..} = pos $ case hd of - _ | white hd -> beforeAttValue typ tl - '\"' -> AttVal & attValueDQuoted typ tl - '&' -> AttVal & attValueUnquoted typ s - '\'' -> AttVal & attValueSQuoted typ tl - '>' -> errSeen "=" & neilTagEnd typ tl - '?' | typ == TypeXml -> neilXmlTagClose tl - _ | hd `elem` "<=" -> errSeen [hd] & def - _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s - _ -> def - where def = AttVal & hd & attValueUnquoted typ tl - - --- 8.2.4.10 Attribute value (double-quoted) state -attValueDQuoted typ S{..} = pos $ case hd of - '\"' -> afterAttValueQuoted typ tl - '&' -> charRefAttValue (attValueDQuoted typ) (Just '\"') tl - _ | eof -> errWant "\"" & dat s - _ -> hd & attValueDQuoted typ tl - - --- 8.2.4.11 Attribute value (single-quoted) state -attValueSQuoted typ S{..} = pos $ case hd of - '\'' -> afterAttValueQuoted typ tl - '&' -> charRefAttValue (attValueSQuoted typ) (Just '\'') tl - _ | eof -> errWant "\'" & dat s - _ -> hd & attValueSQuoted typ tl - - --- 8.2.4.12 Attribute value (unquoted) state -attValueUnquoted typ S{..} = pos $ case hd of - _ | white hd -> beforeAttName typ tl - '&' -> charRefAttValue (attValueUnquoted typ) Nothing tl - '>' -> neilTagEnd typ tl - '?' | typ == TypeXml -> neilXmlTagClose tl - _ | hd `elem` "\"'<=" -> errSeen [hd] & def - _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s - _ -> def - where def = hd & attValueUnquoted typ tl - - --- 8.2.4.13 Character reference in attribute value state -charRefAttValue :: Parser -> Maybe Char -> Parser -charRefAttValue resume c s = charRef resume True c s - - --- 8.2.4.14 After attribute value (quoted) state -afterAttValueQuoted typ S{..} = pos $ case hd of - _ | white hd -> beforeAttName typ tl - '/' -> selfClosingStartTag typ tl - '>' -> neilTagEnd typ tl - '?' | typ == TypeXml -> neilXmlTagClose tl - _ | eof -> dat s - _ -> errSeen [hd] & beforeAttName typ s - - --- 8.2.4.15 Self-closing start tag state -selfClosingStartTag typ S{..} = pos $ case hd of - _ | typ == TypeXml -> errSeen "/" & beforeAttName typ s - '>' -> TagEndClose & dat tl - _ | eof -> errWant ">" & dat s - _ -> errSeen "/" & beforeAttName typ s - - --- 8.2.4.16 Bogus comment state -bogusComment S{..} = Comment & bogusComment1 s -bogusComment1 S{..} = pos $ case hd of - '>' -> CommentEnd & dat tl - _ | eof -> CommentEnd & dat s - _ -> hd & bogusComment1 tl - - --- 8.2.4.17 Markup declaration open state -markupDeclOpen S{..} = pos $ case hd of - _ | Just s <- next "--" -> Comment & commentStart s - _ | isAlpha hd -> Tag & '!' & hd & tagName TypeDecl tl -- NEIL - _ | Just s <- next "[CDATA[" -> cdataSection s - _ -> errWant "tag name" & bogusComment s - - --- 8.2.4.18 Comment start state -commentStart S{..} = pos $ case hd of - '-' -> commentStartDash tl - '>' -> errSeen "" & CommentEnd & dat tl - _ | eof -> errWant "-->" & CommentEnd & dat s - _ -> hd & comment tl - - --- 8.2.4.19 Comment start dash state -commentStartDash S{..} = pos $ case hd of - '-' -> commentEnd tl - '>' -> errSeen "" & CommentEnd & dat tl - _ | eof -> errWant "-->" & CommentEnd & dat s - _ -> '-' & hd & comment tl - - --- 8.2.4.20 Comment state -comment S{..} = pos $ case hd of - '-' -> commentEndDash tl - _ | eof -> errWant "-->" & CommentEnd & dat s - _ -> hd & comment tl - - --- 8.2.4.21 Comment end dash state -commentEndDash S{..} = pos $ case hd of - '-' -> commentEnd tl - _ | eof -> errWant "-->" & CommentEnd & dat s - _ -> '-' & hd & comment tl - - --- 8.2.4.22 Comment end state -commentEnd S{..} = pos $ case hd of - '>' -> CommentEnd & dat tl - '-' -> errWant "-->" & '-' & commentEnd tl - _ | white hd -> errSeen "--" & '-' & '-' & hd & commentEndSpace tl - '!' -> errSeen "!" & commentEndBang tl - _ | eof -> errWant "-->" & CommentEnd & dat s - _ -> errSeen "--" & '-' & '-' & hd & comment tl - - --- 8.2.4.23 Comment end bang state -commentEndBang S{..} = pos $ case hd of - '>' -> CommentEnd & dat tl - '-' -> '-' & '-' & '!' & commentEndDash tl - _ | eof -> errWant "-->" & CommentEnd & dat s - _ -> '-' & '-' & '!' & hd & comment tl - - --- 8.2.4.24 Comment end space state -commentEndSpace S{..} = pos $ case hd of - '>' -> CommentEnd & dat tl - '-' -> commentEndDash tl - _ | white hd -> hd & commentEndSpace tl - _ | eof -> errWant "-->" & CommentEnd & dat s - _ -> hd & comment tl - - --- 8.2.4.38 CDATA section state -cdataSection S{..} = pos $ case hd of - _ | Just s <- next "]]>" -> dat s - _ | eof -> dat s - _ | otherwise -> hd & cdataSection tl - - --- 8.2.4.39 Tokenizing character references --- Change from spec: this is reponsible for writing '&' if nothing is to be written -charRef :: Parser -> Bool -> Maybe Char -> S -> [Out] -charRef resume att end S{..} = pos $ case hd of - _ | eof || hd `elem` "\t\n\f <&" || maybe False (== hd) end -> '&' & resume s - '#' -> charRefNum resume s tl - _ -> charRefAlpha resume att s - -charRefNum resume o S{..} = pos $ case hd of - _ | hd `elem` "xX" -> charRefNum2 resume o True tl - _ -> charRefNum2 resume o False s - -charRefNum2 resume o hex S{..} = pos $ case hd of - _ | hexChar hex hd -> (if hex then EntityHex else EntityNum) & hd & charRefNum3 resume hex tl - _ -> errSeen "&" & '&' & resume o - -charRefNum3 resume hex S{..} = pos $ case hd of - _ | hexChar hex hd -> hd & charRefNum3 resume hex tl - ';' -> EntityEnd True & resume tl - _ -> EntityEnd False & errWant ";" & resume s - -charRefAlpha resume att S{..} = pos $ case hd of - _ | isAlpha hd -> EntityName & hd & charRefAlpha2 resume att tl - _ -> errSeen "&" & '&' & resume s - -charRefAlpha2 resume att S{..} = pos $ case hd of - _ | alphaChar hd -> hd & charRefAlpha2 resume att tl - ';' -> EntityEnd True & resume tl - _ | att -> EntityEnd False & resume s - _ -> EntityEnd False & errWant ";" & resume s - - -alphaChar x = isAlphaNum x || x `elem` ":-_" - -hexChar False x = isDigit x -hexChar True x = isDigit x || (x >= 'a' && x <= 'f') || (x >= 'A' && x <= 'F') diff --git a/Text/HTML/TagSoup/Tree.hs b/Text/HTML/TagSoup/Tree.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Tree.hs +++ /dev/null @@ -1,118 +0,0 @@ -{-| - /NOTE/: This module is preliminary and may change at a future date. - - This module is intended to help converting a list of tags into a - tree of tags. --} - -module Text.HTML.TagSoup.Tree - ( - TagTree(..), tagTree, parseTree, parseTreeOptions, ParseOptions(..), - flattenTree, renderTree, renderTreeOptions, RenderOptions(..), transformTree, universeTree - ) where - -import Text.HTML.TagSoup (parseTags, parseTagsOptions, renderTags, renderTagsOptions, ParseOptions(..), RenderOptions(..)) -import Text.HTML.TagSoup.Type -import Control.Arrow -import GHC.Exts (build) - - --- | A tree of 'Tag' values. -data TagTree str - = -- | A 'TagOpen'/'TagClose' pair with the 'Tag' values in between. - TagBranch str [Attribute str] [TagTree str] - | -- | Any leaf node - TagLeaf (Tag str) - deriving (Eq,Ord,Show) - -instance Functor TagTree where - fmap f (TagBranch x y z) = TagBranch (f x) (map (f***f) y) (map (fmap f) z) - fmap f (TagLeaf x) = TagLeaf (fmap f x) - - --- | Convert a list of tags into a tree. This version is not lazy at --- all, that is saved for version 2. -tagTree :: Eq str => [Tag str] -> [TagTree str] -tagTree = g - where - g :: Eq str => [Tag str] -> [TagTree str] - g [] = [] - g xs = a ++ map TagLeaf (take 1 b) ++ g (drop 1 b) - where (a,b) = f xs - - -- the second tuple is either null or starts with a close - f :: Eq str => [Tag str] -> ([TagTree str],[Tag str]) - f (TagOpen name atts:rest) = - case f rest of - (inner,[]) -> (TagLeaf (TagOpen name atts):inner, []) - (inner,TagClose x:xs) - | x == name -> let (a,b) = f xs in (TagBranch name atts inner:a, b) - | otherwise -> (TagLeaf (TagOpen name atts):inner, TagClose x:xs) - _ -> error "TagSoup.Tree.tagTree: safe as - forall x . isTagClose (snd (f x))" - - f (TagClose x:xs) = ([], TagClose x:xs) - f (x:xs) = (TagLeaf x:a,b) - where (a,b) = f xs - f [] = ([], []) - --- | Build a 'TagTree' from a string. -parseTree :: StringLike str => str -> [TagTree str] -parseTree = tagTree . parseTags - --- | Build a 'TagTree' from a string, specifying the 'ParseOptions'. -parseTreeOptions :: StringLike str => ParseOptions str -> str -> [TagTree str] -parseTreeOptions opts str = tagTree $ parseTagsOptions opts str - --- | Flatten a 'TagTree' back to a list of 'Tag'. -flattenTree :: [TagTree str] -> [Tag str] -flattenTree xs = build $ flattenTreeFB xs - -flattenTreeFB :: [TagTree str] -> (Tag str -> lst -> lst) -> lst -> lst -flattenTreeFB xs cons nil = flattenTreeOnto xs nil - where - flattenTreeOnto [] tags = tags - flattenTreeOnto (TagBranch name atts inner:trs) tags = - TagOpen name atts `cons` flattenTreeOnto inner (TagClose name `cons` flattenTreeOnto trs tags) - flattenTreeOnto (TagLeaf x:trs) tags = x `cons` flattenTreeOnto trs tags - --- | Render a 'TagTree'. -renderTree :: StringLike str => [TagTree str] -> str -renderTree = renderTags . flattenTree - --- | Render a 'TagTree' with some 'RenderOptions'. -renderTreeOptions :: StringLike str => RenderOptions str -> [TagTree str] -> str -renderTreeOptions opts trees = renderTagsOptions opts $ flattenTree trees - --- | This operation is based on the Uniplate @universe@ function. Given a --- list of trees, it returns those trees, and all the children trees at --- any level. For example: --- --- > universeTree --- > [TagBranch "a" [("href","url")] [TagBranch "b" [] [TagLeaf (TagText "text")]]] --- > == [TagBranch "a" [("href","url")] [TagBranch "b" [] [TagLeaf (TagText "text")]]] --- > ,TagBranch "b" [] [TagLeaf (TagText "text")]] --- --- This operation is particularly useful for queries. To collect all @\"a\"@ --- tags in a tree, simply do: --- --- > [x | x@(TagBranch "a" _ _) <- universeTree tree] -universeTree :: [TagTree str] -> [TagTree str] -universeTree = concatMap f - where - f t@(TagBranch _ _ inner) = t : universeTree inner - f x = [x] - - --- | This operation is based on the Uniplate @transform@ function. Given a --- list of trees, it applies the function to every tree in a bottom-up --- manner. This operation is useful for manipulating a tree - for example --- to make all tag names upper case: --- --- > upperCase = transformTree f --- > where f (TagBranch name atts inner) = [TagBranch (map toUpper name) atts inner] --- > f x = [x] -transformTree :: (TagTree str -> [TagTree str]) -> [TagTree str] -> [TagTree str] -transformTree act = concatMap f - where - f (TagBranch a b inner) = act $ TagBranch a b (transformTree act inner) - f x = act x diff --git a/Text/HTML/TagSoup/Type.hs b/Text/HTML/TagSoup/Type.hs deleted file mode 100644 --- a/Text/HTML/TagSoup/Type.hs +++ /dev/null @@ -1,142 +0,0 @@ -{-# LANGUAGE DeriveDataTypeable #-} --- | The central type in TagSoup - -module Text.HTML.TagSoup.Type( - -- * Data structures and parsing - StringLike, Tag(..), Attribute, Row, Column, - - -- * Position manipulation - Position(..), tagPosition, nullPosition, positionChar, positionString, - - -- * Tag identification - isTagOpen, isTagClose, isTagText, isTagWarning, isTagPosition, - isTagOpenName, isTagCloseName, isTagComment, - - -- * Extraction - fromTagText, fromAttrib, - maybeTagText, maybeTagWarning, - innerText, - ) where - - -import Data.List (foldl') -import Data.Maybe (fromMaybe, mapMaybe) -import Text.StringLike -import Data.Data(Data, Typeable) - --- | An HTML attribute @id=\"name\"@ generates @(\"id\",\"name\")@ -type Attribute str = (str,str) - --- | The row/line of a position, starting at 1 -type Row = Int - --- | The column of a position, starting at 1 -type Column = Int - - ---- All positions are stored as a row and a column, with (1,1) being the ---- top-left position -data Position = Position !Row !Column deriving (Show,Eq,Ord) - -nullPosition :: Position -nullPosition = Position 1 1 - -positionString :: Position -> String -> Position -positionString = foldl' positionChar - -positionChar :: Position -> Char -> Position -positionChar (Position r c) x = case x of - '\n' -> Position (r+1) 1 - '\t' -> Position r (c + 8 - mod (c-1) 8) - _ -> Position r (c+1) - -tagPosition :: Position -> Tag str -tagPosition (Position r c) = TagPosition r c - - --- | A single HTML element. A whole document is represented by a list of @Tag@. --- There is no requirement for 'TagOpen' and 'TagClose' to match. -data Tag str = - TagOpen str [Attribute str] -- ^ An open tag with 'Attribute's in their original order - | TagClose str -- ^ A closing tag - | TagText str -- ^ A text node, guaranteed not to be the empty string - | TagComment str -- ^ A comment - | TagWarning str -- ^ Meta: A syntax error in the input file - | TagPosition !Row !Column -- ^ Meta: The position of a parsed element - deriving (Show, Eq, Ord, Data, Typeable) - -instance Functor Tag where - fmap f (TagOpen x y) = TagOpen (f x) [(f a, f b) | (a,b) <- y] - fmap f (TagClose x) = TagClose (f x) - fmap f (TagText x) = TagText (f x) - fmap f (TagComment x) = TagComment (f x) - fmap f (TagWarning x) = TagWarning (f x) - fmap f (TagPosition x y) = TagPosition x y - - --- | Test if a 'Tag' is a 'TagOpen' -isTagOpen :: Tag str -> Bool -isTagOpen (TagOpen {}) = True; isTagOpen _ = False - --- | Test if a 'Tag' is a 'TagClose' -isTagClose :: Tag str -> Bool -isTagClose (TagClose {}) = True; isTagClose _ = False - --- | Test if a 'Tag' is a 'TagText' -isTagText :: Tag str -> Bool -isTagText (TagText {}) = True; isTagText _ = False - --- | Extract the string from within 'TagText', otherwise 'Nothing' -maybeTagText :: Tag str -> Maybe str -maybeTagText (TagText x) = Just x -maybeTagText _ = Nothing - --- | Extract the string from within 'TagText', crashes if not a 'TagText' -fromTagText :: Show str => Tag str -> str -fromTagText (TagText x) = x -fromTagText x = error $ "(" ++ show x ++ ") is not a TagText" - --- | Extract all text content from tags (similar to Verbatim found in HaXml) -innerText :: StringLike str => [Tag str] -> str -innerText = strConcat . mapMaybe maybeTagText - --- | Test if a 'Tag' is a 'TagWarning' -isTagWarning :: Tag str -> Bool -isTagWarning (TagWarning {}) = True; isTagWarning _ = False - --- | Extract the string from within 'TagWarning', otherwise 'Nothing' -maybeTagWarning :: Tag str -> Maybe str -maybeTagWarning (TagWarning x) = Just x -maybeTagWarning _ = Nothing - --- | Test if a 'Tag' is a 'TagPosition' -isTagPosition :: Tag str -> Bool -isTagPosition TagPosition{} = True; isTagPosition _ = False - --- | Extract an attribute, crashes if not a 'TagOpen'. --- Returns @\"\"@ if no attribute present. --- --- Warning: does not distinquish between missing attribute --- and present attribute with value @\"\"@. -fromAttrib :: (Show str, Eq str, StringLike str) => str -> Tag str -> str -fromAttrib att tag = fromMaybe empty $ maybeAttrib att tag - --- | Extract an attribute, crashes if not a 'TagOpen'. --- Returns @Nothing@ if no attribute present. -maybeAttrib :: (Show str, Eq str) => str -> Tag str -> Maybe str -maybeAttrib att (TagOpen _ atts) = lookup att atts -maybeAttrib _ x = error ("(" ++ show x ++ ") is not a TagOpen") - --- | Returns True if the 'Tag' is 'TagOpen' and matches the given name -isTagOpenName :: Eq str => str -> Tag str -> Bool -isTagOpenName name (TagOpen n _) = n == name -isTagOpenName _ _ = False - --- | Returns True if the 'Tag' is 'TagClose' and matches the given name -isTagCloseName :: Eq str => str -> Tag str -> Bool -isTagCloseName name (TagClose n) = n == name -isTagCloseName _ _ = False - --- | Test if a 'Tag' is a 'TagComment' -isTagComment :: Tag str -> Bool -isTagComment TagComment {} = True; isTagComment _ = False diff --git a/Text/StringLike.hs b/Text/StringLike.hs deleted file mode 100644 --- a/Text/StringLike.hs +++ /dev/null @@ -1,96 +0,0 @@ -{-# LANGUAGE TypeSynonymInstances, FlexibleInstances #-} - --- | /WARNING/: This module is /not/ intended for use outside the TagSoup library. --- --- This module provides an abstraction for String's as used inside TagSoup. It allows --- TagSoup to work with String (list of Char), ByteString.Char8, ByteString.Lazy.Char8, --- Data.Text and Data.Text.Lazy. -module Text.StringLike (StringLike(..), fromString, castString) where - -import Data.String -import Data.Typeable - -import qualified Data.ByteString.Char8 as BS -import qualified Data.ByteString.Lazy.Char8 as LBS -import qualified Data.Text as T -import qualified Data.Text.Lazy as LT - - --- | A class to generalise TagSoup parsing over many types of string-like types. --- Examples are given for the String type. -class (Typeable a, Eq a, IsString a) => StringLike a where - -- | > empty = "" - empty :: a - -- | > cons = (:) - cons :: Char -> a -> a - -- | > uncons [] = Nothing - -- > uncons (x:xs) = Just (x, xs) - uncons :: a -> Maybe (Char, a) - - -- | > toString = id - toString :: a -> String - -- | > fromChar = return - fromChar :: Char -> a - -- | > strConcat = concat - strConcat :: [a] -> a - -- | > strNull = null - strNull :: a -> Bool - -- | > append = (++) - append :: a -> a -> a - - --- | Convert a String from one type to another. -castString :: (StringLike a, StringLike b) => a -> b -castString = fromString . toString - - -instance StringLike String where - uncons [] = Nothing - uncons (x:xs) = Just (x, xs) - toString = id - fromChar = (:[]) - strConcat = concat - empty = [] - strNull = null - cons c = (c:) - append = (++) - -instance StringLike BS.ByteString where - uncons = BS.uncons - toString = BS.unpack - fromChar = BS.singleton - strConcat = BS.concat - empty = BS.empty - strNull = BS.null - cons = BS.cons - append = BS.append - -instance StringLike LBS.ByteString where - uncons = LBS.uncons - toString = LBS.unpack - fromChar = LBS.singleton - strConcat = LBS.concat - empty = LBS.empty - strNull = LBS.null - cons = LBS.cons - append = LBS.append - -instance StringLike T.Text where - uncons = T.uncons - toString = T.unpack - fromChar = T.singleton - strConcat = T.concat - empty = T.empty - strNull = T.null - cons = T.cons - append = T.append - -instance StringLike LT.Text where - uncons = LT.uncons - toString = LT.unpack - fromChar = LT.singleton - strConcat = LT.concat - empty = LT.empty - strNull = LT.null - cons = LT.cons - append = LT.append diff --git a/src/Text/HTML/TagSoup.hs b/src/Text/HTML/TagSoup.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup.hs @@ -0,0 +1,117 @@ +{-# LANGUAGE TypeSynonymInstances, FlexibleInstances, PatternGuards #-} + +{-| + This module is for working with HTML/XML. It deals with both well-formed XML and + malformed HTML from the web. It features: + + * A lazy parser, based on the HTML 5 specification - see 'parseTags'. + + * A renderer that can write out HTML/XML - see 'renderTags'. + + * Utilities for extracting information from a document - see '~==', 'sections' and 'partitions'. + + The standard practice is to parse a 'String' to @[@'Tag' 'String'@]@ using 'parseTags', + then operate upon it to extract the necessary information. +-} + +module Text.HTML.TagSoup( + -- * Data structures and parsing + Tag(..), Row, Column, Attribute, + module Text.HTML.TagSoup.Parser, + module Text.HTML.TagSoup.Render, + canonicalizeTags, + + -- Note: the "#tag-identification#" creates an anchor that's linked to from Match.hs + -- * #tag-identification# Tag identification + isTagOpen, isTagClose, isTagText, isTagWarning, isTagPosition, + isTagOpenName, isTagCloseName, isTagComment, + + -- * Extraction + fromTagText, fromAttrib, + maybeTagText, maybeTagWarning, + innerText, + + -- * Utility + sections, partitions, + + -- * Combinators + TagRep(..), (~==),(~/=) + ) where + +import Text.HTML.TagSoup.Type +import Text.HTML.TagSoup.Parser +import Text.HTML.TagSoup.Render +import Data.Char +import Data.List (groupBy, tails) +import Text.StringLike + + +-- | Turns all tag names and attributes to lower case and +-- converts DOCTYPE to upper case. +canonicalizeTags :: StringLike str => [Tag str] -> [Tag str] +canonicalizeTags = map f + where + f (TagOpen tag attrs) | Just ('!',name) <- uncons tag = TagOpen ('!' `cons` ucase name) attrs + f (TagOpen name attrs) = TagOpen (lcase name) [(lcase k, v) | (k,v) <- attrs] + f (TagClose name) = TagClose (lcase name) + f a = a + + ucase = fromString . map toUpper . toString + lcase = fromString . map toLower . toString + + +-- | Define a class to allow String's or Tag str's to be used as matches +class TagRep a where + -- | Convert a value into a 'Tag'. + toTagRep :: StringLike str => a -> Tag str + +instance StringLike str => TagRep (Tag str) where toTagRep = fmap castString + +instance TagRep String where + toTagRep x = case parseTags x of + [a] -> toTagRep a + _ -> error $ "When using a TagRep it must be exactly one tag, you gave: " ++ x + + + +-- | Performs an inexact match, the first item should be the thing to match. +-- If the second item is a blank string, that is considered to match anything. +-- For example: +-- +-- > (TagText "test" ~== TagText "" ) == True +-- > (TagText "test" ~== TagText "test") == True +-- > (TagText "test" ~== TagText "soup") == False +-- +-- For 'TagOpen' missing attributes on the right are allowed. +(~==) :: (StringLike str, TagRep t) => Tag str -> t -> Bool +(~==) a b = f a (toTagRep b) + where + f (TagText y) (TagText x) = strNull x || x == y + f (TagClose y) (TagClose x) = strNull x || x == y + f (TagOpen y ys) (TagOpen x xs) = (strNull x || x == y) && all g xs + where + g (name,val) | strNull name = val `elem` map snd ys + | strNull val = name `elem` map fst ys + g nameval = nameval `elem` ys + f (TagComment x) (TagComment y) = strNull x || x == y + f (TagWarning x) (TagWarning y) = strNull x || x == y + f (TagPosition x1 x2) (TagPosition y1 y2) = x1 == y1 && x2 == y2 + f _ _ = False + +-- | Negation of '~==' +(~/=) :: (StringLike str, TagRep t) => Tag str -> t -> Bool +(~/=) a b = not (a ~== b) + + + +-- | This function takes a list, and returns all suffixes whose +-- first item matches the predicate. +sections :: (a -> Bool) -> [a] -> [[a]] +sections p = filter (p . head) . init . tails + +-- | This function is similar to 'sections', but splits the list +-- so no element appears in any two partitions. +partitions :: (a -> Bool) -> [a] -> [[a]] +partitions p = + let notp = not . p + in groupBy (const notp) . dropWhile notp diff --git a/src/Text/HTML/TagSoup/Entity.hs b/src/Text/HTML/TagSoup/Entity.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Entity.hs @@ -0,0 +1,2320 @@ +-- | This module converts between HTML/XML entities (i.e. @&@) and +-- the characters they represent. +module Text.HTML.TagSoup.Entity( + lookupEntity, lookupNamedEntity, lookupNumericEntity, + escapeXML, + xmlEntities, htmlEntities + ) where + +import Data.Char (chr, ord) +import qualified Data.IntMap as IntMap +import Data.Ix +import qualified Data.Map as Map +import Numeric (readHex) + + +-- | Lookup an entity, using 'lookupNumericEntity' if it starts with +-- @#@ and 'lookupNamedEntity' otherwise +lookupEntity :: String -> Maybe String +lookupEntity ('#':xs) = lookupNumericEntity xs +lookupEntity xs = lookupNamedEntity xs + + +-- | Lookup a numeric entity, the leading @\'#\'@ must have already been removed. +-- +-- > lookupNumericEntity "65" == Just "A" +-- > lookupNumericEntity "x41" == Just "A" +-- > lookupNumericEntity "x4E" === Just "N" +-- > lookupNumericEntity "x4e" === Just "N" +-- > lookupNumericEntity "X4e" === Just "N" +-- > lookupNumericEntity "Haskell" == Nothing +-- > lookupNumericEntity "" == Nothing +-- > lookupNumericEntity "89439085908539082" == Nothing +lookupNumericEntity :: String -> Maybe String +lookupNumericEntity = f + -- entity = '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';' + where + f (x:xs) | x `elem` "xX" = g [('0','9'),('a','f'),('A','F')] readHex xs + f xs = g [('0','9')] reads xs + + g :: [(Char,Char)] -> ReadS Integer -> String -> Maybe String + g valid reader xs = do + let test b = if b then Just () else Nothing + test $ isValid valid xs + test $ not $ null xs + case reader xs of + [(a,"")] -> do + test $ inRange (toInteger $ ord minBound, toInteger $ ord maxBound) a + return [chr $ fromInteger a] + _ -> Nothing + + isValid :: [(Char,Char)] -> String -> Bool + isValid valid xs = all (\x -> any (`inRange` x) valid) xs + + +-- | Lookup a named entity, using 'htmlEntities' +-- +-- > lookupNamedEntity "amp" == Just "&" +-- > lookupNamedEntity "haskell" == Nothing +lookupNamedEntity :: String -> Maybe String +lookupNamedEntity = \x -> Map.lookup x mp + where mp = Map.fromList htmlEntities + + +-- | Escape an XML string. +-- +-- > escapeXML "hello world" == "hello world" +-- > escapeXML "hello & world" == "hello & world" +escapeXML :: String -> String +escapeXML = concatMap $ \x -> IntMap.findWithDefault [x] (ord x) mp + where mp = IntMap.fromList [(ord b, "&"++a++";") | (a,[b]) <- xmlEntities] + + +-- | A table mapping XML entity names to resolved strings. All strings are a single character long. +-- Does /not/ include @apos@ as Internet Explorer does not know about it. +xmlEntities :: [(String, String)] +xmlEntities = let a*b = (a,[b]) in + ["quot" * '"' + ,"amp" * '&' + -- ,"apos" * '\'' -- Internet Explorer does not know that + ,"lt" * '<' + ,"gt" * '>' + ] + +-- | A table mapping HTML entity names to resolved strings. Most resolved strings are a single character long, +-- but some (e.g. @"ngeqq"@) are two characters long. The list is taken from +-- . +htmlEntities :: [(String, String)] +htmlEntities = let (*) = (,) in + ["Aacute" * "\x00C1" + ,"aacute" * "\x00E1" + ,"Aacute;" * "\x00C1" + ,"aacute;" * "\x00E1" + ,"Abreve;" * "\x0102" + ,"abreve;" * "\x0103" + ,"ac;" * "\x223E" + ,"acd;" * "\x223F" + ,"acE;" * "\x223E\x0333" + ,"Acirc" * "\x00C2" + ,"acirc" * "\x00E2" + ,"Acirc;" * "\x00C2" + ,"acirc;" * "\x00E2" + ,"acute" * "\x00B4" + ,"acute;" * "\x00B4" + ,"Acy;" * "\x0410" + ,"acy;" * "\x0430" + ,"AElig" * "\x00C6" + ,"aelig" * "\x00E6" + ,"AElig;" * "\x00C6" + ,"aelig;" * "\x00E6" + ,"af;" * "\x2061" + ,"Afr;" * "\x1D504" + ,"afr;" * "\x1D51E" + ,"Agrave" * "\x00C0" + ,"agrave" * "\x00E0" + ,"Agrave;" * "\x00C0" + ,"agrave;" * "\x00E0" + ,"alefsym;" * "\x2135" + ,"aleph;" * "\x2135" + ,"Alpha;" * "\x0391" + ,"alpha;" * "\x03B1" + ,"Amacr;" * "\x0100" + ,"amacr;" * "\x0101" + ,"amalg;" * "\x2A3F" + ,"AMP" * "\x0026" + ,"amp" * "\x0026" + ,"AMP;" * "\x0026" + ,"amp;" * "\x0026" + ,"and;" * "\x2227" + ,"And;" * "\x2A53" + ,"andand;" * "\x2A55" + ,"andd;" * "\x2A5C" + ,"andslope;" * "\x2A58" + ,"andv;" * "\x2A5A" + ,"ang;" * "\x2220" + ,"ange;" * "\x29A4" + ,"angle;" * "\x2220" + ,"angmsd;" * "\x2221" + ,"angmsdaa;" * "\x29A8" + ,"angmsdab;" * "\x29A9" + ,"angmsdac;" * "\x29AA" + ,"angmsdad;" * "\x29AB" + ,"angmsdae;" * "\x29AC" + ,"angmsdaf;" * "\x29AD" + ,"angmsdag;" * "\x29AE" + ,"angmsdah;" * "\x29AF" + ,"angrt;" * "\x221F" + ,"angrtvb;" * "\x22BE" + ,"angrtvbd;" * "\x299D" + ,"angsph;" * "\x2222" + ,"angst;" * "\x00C5" + ,"angzarr;" * "\x237C" + ,"Aogon;" * "\x0104" + ,"aogon;" * "\x0105" + ,"Aopf;" * "\x1D538" + ,"aopf;" * "\x1D552" + ,"ap;" * "\x2248" + ,"apacir;" * "\x2A6F" + ,"ape;" * "\x224A" + ,"apE;" * "\x2A70" + ,"apid;" * "\x224B" + ,"apos;" * "\x0027" + ,"ApplyFunction;" * "\x2061" + ,"approx;" * "\x2248" + ,"approxeq;" * "\x224A" + ,"Aring" * "\x00C5" + ,"aring" * "\x00E5" + ,"Aring;" * "\x00C5" + ,"aring;" * "\x00E5" + ,"Ascr;" * "\x1D49C" + ,"ascr;" * "\x1D4B6" + ,"Assign;" * "\x2254" + ,"ast;" * "\x002A" + ,"asymp;" * "\x2248" + ,"asympeq;" * "\x224D" + ,"Atilde" * "\x00C3" + ,"atilde" * "\x00E3" + ,"Atilde;" * "\x00C3" + ,"atilde;" * "\x00E3" + ,"Auml" * "\x00C4" + ,"auml" * "\x00E4" + ,"Auml;" * "\x00C4" + ,"auml;" * "\x00E4" + ,"awconint;" * "\x2233" + ,"awint;" * "\x2A11" + ,"backcong;" * "\x224C" + ,"backepsilon;" * "\x03F6" + ,"backprime;" * "\x2035" + ,"backsim;" * "\x223D" + ,"backsimeq;" * "\x22CD" + ,"Backslash;" * "\x2216" + ,"Barv;" * "\x2AE7" + ,"barvee;" * "\x22BD" + ,"barwed;" * "\x2305" + ,"Barwed;" * "\x2306" + ,"barwedge;" * "\x2305" + ,"bbrk;" * "\x23B5" + ,"bbrktbrk;" * "\x23B6" + ,"bcong;" * "\x224C" + ,"Bcy;" * "\x0411" + ,"bcy;" * "\x0431" + ,"bdquo;" * "\x201E" + ,"becaus;" * "\x2235" + ,"Because;" * "\x2235" + ,"because;" * "\x2235" + ,"bemptyv;" * "\x29B0" + ,"bepsi;" * "\x03F6" + ,"bernou;" * "\x212C" + ,"Bernoullis;" * "\x212C" + ,"Beta;" * "\x0392" + ,"beta;" * "\x03B2" + ,"beth;" * "\x2136" + ,"between;" * "\x226C" + ,"Bfr;" * "\x1D505" + ,"bfr;" * "\x1D51F" + ,"bigcap;" * "\x22C2" + ,"bigcirc;" * "\x25EF" + ,"bigcup;" * "\x22C3" + ,"bigodot;" * "\x2A00" + ,"bigoplus;" * "\x2A01" + ,"bigotimes;" * "\x2A02" + ,"bigsqcup;" * "\x2A06" + ,"bigstar;" * "\x2605" + ,"bigtriangledown;" * "\x25BD" + ,"bigtriangleup;" * "\x25B3" + ,"biguplus;" * "\x2A04" + ,"bigvee;" * "\x22C1" + ,"bigwedge;" * "\x22C0" + ,"bkarow;" * "\x290D" + ,"blacklozenge;" * "\x29EB" + ,"blacksquare;" * "\x25AA" + ,"blacktriangle;" * "\x25B4" + ,"blacktriangledown;" * "\x25BE" + ,"blacktriangleleft;" * "\x25C2" + ,"blacktriangleright;" * "\x25B8" + ,"blank;" * "\x2423" + ,"blk12;" * "\x2592" + ,"blk14;" * "\x2591" + ,"blk34;" * "\x2593" + ,"block;" * "\x2588" + ,"bne;" * "\x003D\x20E5" + ,"bnequiv;" * "\x2261\x20E5" + ,"bnot;" * "\x2310" + ,"bNot;" * "\x2AED" + ,"Bopf;" * "\x1D539" + ,"bopf;" * "\x1D553" + ,"bot;" * "\x22A5" + ,"bottom;" * "\x22A5" + ,"bowtie;" * "\x22C8" + ,"boxbox;" * "\x29C9" + ,"boxdl;" * "\x2510" + ,"boxdL;" * "\x2555" + ,"boxDl;" * "\x2556" + ,"boxDL;" * "\x2557" + ,"boxdr;" * "\x250C" + ,"boxdR;" * "\x2552" + ,"boxDr;" * "\x2553" + ,"boxDR;" * "\x2554" + ,"boxh;" * "\x2500" + ,"boxH;" * "\x2550" + ,"boxhd;" * "\x252C" + ,"boxHd;" * "\x2564" + ,"boxhD;" * "\x2565" + ,"boxHD;" * "\x2566" + ,"boxhu;" * "\x2534" + ,"boxHu;" * "\x2567" + ,"boxhU;" * "\x2568" + ,"boxHU;" * "\x2569" + ,"boxminus;" * "\x229F" + ,"boxplus;" * "\x229E" + ,"boxtimes;" * "\x22A0" + ,"boxul;" * "\x2518" + ,"boxuL;" * "\x255B" + ,"boxUl;" * "\x255C" + ,"boxUL;" * "\x255D" + ,"boxur;" * "\x2514" + ,"boxuR;" * "\x2558" + ,"boxUr;" * "\x2559" + ,"boxUR;" * "\x255A" + ,"boxv;" * "\x2502" + ,"boxV;" * "\x2551" + ,"boxvh;" * "\x253C" + ,"boxvH;" * "\x256A" + ,"boxVh;" * "\x256B" + ,"boxVH;" * "\x256C" + ,"boxvl;" * "\x2524" + ,"boxvL;" * "\x2561" + ,"boxVl;" * "\x2562" + ,"boxVL;" * "\x2563" + ,"boxvr;" * "\x251C" + ,"boxvR;" * "\x255E" + ,"boxVr;" * "\x255F" + ,"boxVR;" * "\x2560" + ,"bprime;" * "\x2035" + ,"Breve;" * "\x02D8" + ,"breve;" * "\x02D8" + ,"brvbar" * "\x00A6" + ,"brvbar;" * "\x00A6" + ,"Bscr;" * "\x212C" + ,"bscr;" * "\x1D4B7" + ,"bsemi;" * "\x204F" + ,"bsim;" * "\x223D" + ,"bsime;" * "\x22CD" + ,"bsol;" * "\x005C" + ,"bsolb;" * "\x29C5" + ,"bsolhsub;" * "\x27C8" + ,"bull;" * "\x2022" + ,"bullet;" * "\x2022" + ,"bump;" * "\x224E" + ,"bumpe;" * "\x224F" + ,"bumpE;" * "\x2AAE" + ,"Bumpeq;" * "\x224E" + ,"bumpeq;" * "\x224F" + ,"Cacute;" * "\x0106" + ,"cacute;" * "\x0107" + ,"cap;" * "\x2229" + ,"Cap;" * "\x22D2" + ,"capand;" * "\x2A44" + ,"capbrcup;" * "\x2A49" + ,"capcap;" * "\x2A4B" + ,"capcup;" * "\x2A47" + ,"capdot;" * "\x2A40" + ,"CapitalDifferentialD;" * "\x2145" + ,"caps;" * "\x2229\xFE00" + ,"caret;" * "\x2041" + ,"caron;" * "\x02C7" + ,"Cayleys;" * "\x212D" + ,"ccaps;" * "\x2A4D" + ,"Ccaron;" * "\x010C" + ,"ccaron;" * "\x010D" + ,"Ccedil" * "\x00C7" + ,"ccedil" * "\x00E7" + ,"Ccedil;" * "\x00C7" + ,"ccedil;" * "\x00E7" + ,"Ccirc;" * "\x0108" + ,"ccirc;" * "\x0109" + ,"Cconint;" * "\x2230" + ,"ccups;" * "\x2A4C" + ,"ccupssm;" * "\x2A50" + ,"Cdot;" * "\x010A" + ,"cdot;" * "\x010B" + ,"cedil" * "\x00B8" + ,"cedil;" * "\x00B8" + ,"Cedilla;" * "\x00B8" + ,"cemptyv;" * "\x29B2" + ,"cent" * "\x00A2" + ,"cent;" * "\x00A2" + ,"CenterDot;" * "\x00B7" + ,"centerdot;" * "\x00B7" + ,"Cfr;" * "\x212D" + ,"cfr;" * "\x1D520" + ,"CHcy;" * "\x0427" + ,"chcy;" * "\x0447" + ,"check;" * "\x2713" + ,"checkmark;" * "\x2713" + ,"Chi;" * "\x03A7" + ,"chi;" * "\x03C7" + ,"cir;" * "\x25CB" + ,"circ;" * "\x02C6" + ,"circeq;" * "\x2257" + ,"circlearrowleft;" * "\x21BA" + ,"circlearrowright;" * "\x21BB" + ,"circledast;" * "\x229B" + ,"circledcirc;" * "\x229A" + ,"circleddash;" * "\x229D" + ,"CircleDot;" * "\x2299" + ,"circledR;" * "\x00AE" + ,"circledS;" * "\x24C8" + ,"CircleMinus;" * "\x2296" + ,"CirclePlus;" * "\x2295" + ,"CircleTimes;" * "\x2297" + ,"cire;" * "\x2257" + ,"cirE;" * "\x29C3" + ,"cirfnint;" * "\x2A10" + ,"cirmid;" * "\x2AEF" + ,"cirscir;" * "\x29C2" + ,"ClockwiseContourIntegral;" * "\x2232" + ,"CloseCurlyDoubleQuote;" * "\x201D" + ,"CloseCurlyQuote;" * "\x2019" + ,"clubs;" * "\x2663" + ,"clubsuit;" * "\x2663" + ,"colon;" * "\x003A" + ,"Colon;" * "\x2237" + ,"colone;" * "\x2254" + ,"Colone;" * "\x2A74" + ,"coloneq;" * "\x2254" + ,"comma;" * "\x002C" + ,"commat;" * "\x0040" + ,"comp;" * "\x2201" + ,"compfn;" * "\x2218" + ,"complement;" * "\x2201" + ,"complexes;" * "\x2102" + ,"cong;" * "\x2245" + ,"congdot;" * "\x2A6D" + ,"Congruent;" * "\x2261" + ,"conint;" * "\x222E" + ,"Conint;" * "\x222F" + ,"ContourIntegral;" * "\x222E" + ,"Copf;" * "\x2102" + ,"copf;" * "\x1D554" + ,"coprod;" * "\x2210" + ,"Coproduct;" * "\x2210" + ,"COPY" * "\x00A9" + ,"copy" * "\x00A9" + ,"COPY;" * "\x00A9" + ,"copy;" * "\x00A9" + ,"copysr;" * "\x2117" + ,"CounterClockwiseContourIntegral;" * "\x2233" + ,"crarr;" * "\x21B5" + ,"cross;" * "\x2717" + ,"Cross;" * "\x2A2F" + ,"Cscr;" * "\x1D49E" + ,"cscr;" * "\x1D4B8" + ,"csub;" * "\x2ACF" + ,"csube;" * "\x2AD1" + ,"csup;" * "\x2AD0" + ,"csupe;" * "\x2AD2" + ,"ctdot;" * "\x22EF" + ,"cudarrl;" * "\x2938" + ,"cudarrr;" * "\x2935" + ,"cuepr;" * "\x22DE" + ,"cuesc;" * "\x22DF" + ,"cularr;" * "\x21B6" + ,"cularrp;" * "\x293D" + ,"cup;" * "\x222A" + ,"Cup;" * "\x22D3" + ,"cupbrcap;" * "\x2A48" + ,"CupCap;" * "\x224D" + ,"cupcap;" * "\x2A46" + ,"cupcup;" * "\x2A4A" + ,"cupdot;" * "\x228D" + ,"cupor;" * "\x2A45" + ,"cups;" * "\x222A\xFE00" + ,"curarr;" * "\x21B7" + ,"curarrm;" * "\x293C" + ,"curlyeqprec;" * "\x22DE" + ,"curlyeqsucc;" * "\x22DF" + ,"curlyvee;" * "\x22CE" + ,"curlywedge;" * "\x22CF" + ,"curren" * "\x00A4" + ,"curren;" * "\x00A4" + ,"curvearrowleft;" * "\x21B6" + ,"curvearrowright;" * "\x21B7" + ,"cuvee;" * "\x22CE" + ,"cuwed;" * "\x22CF" + ,"cwconint;" * "\x2232" + ,"cwint;" * "\x2231" + ,"cylcty;" * "\x232D" + ,"dagger;" * "\x2020" + ,"Dagger;" * "\x2021" + ,"daleth;" * "\x2138" + ,"darr;" * "\x2193" + ,"Darr;" * "\x21A1" + ,"dArr;" * "\x21D3" + ,"dash;" * "\x2010" + ,"dashv;" * "\x22A3" + ,"Dashv;" * "\x2AE4" + ,"dbkarow;" * "\x290F" + ,"dblac;" * "\x02DD" + ,"Dcaron;" * "\x010E" + ,"dcaron;" * "\x010F" + ,"Dcy;" * "\x0414" + ,"dcy;" * "\x0434" + ,"DD;" * "\x2145" + ,"dd;" * "\x2146" + ,"ddagger;" * "\x2021" + ,"ddarr;" * "\x21CA" + ,"DDotrahd;" * "\x2911" + ,"ddotseq;" * "\x2A77" + ,"deg" * "\x00B0" + ,"deg;" * "\x00B0" + ,"Del;" * "\x2207" + ,"Delta;" * "\x0394" + ,"delta;" * "\x03B4" + ,"demptyv;" * "\x29B1" + ,"dfisht;" * "\x297F" + ,"Dfr;" * "\x1D507" + ,"dfr;" * "\x1D521" + ,"dHar;" * "\x2965" + ,"dharl;" * "\x21C3" + ,"dharr;" * "\x21C2" + ,"DiacriticalAcute;" * "\x00B4" + ,"DiacriticalDot;" * "\x02D9" + ,"DiacriticalDoubleAcute;" * "\x02DD" + ,"DiacriticalGrave;" * "\x0060" + ,"DiacriticalTilde;" * "\x02DC" + ,"diam;" * "\x22C4" + ,"Diamond;" * "\x22C4" + ,"diamond;" * "\x22C4" + ,"diamondsuit;" * "\x2666" + ,"diams;" * "\x2666" + ,"die;" * "\x00A8" + ,"DifferentialD;" * "\x2146" + ,"digamma;" * "\x03DD" + ,"disin;" * "\x22F2" + ,"div;" * "\x00F7" + ,"divide" * "\x00F7" + ,"divide;" * "\x00F7" + ,"divideontimes;" * "\x22C7" + ,"divonx;" * "\x22C7" + ,"DJcy;" * "\x0402" + ,"djcy;" * "\x0452" + ,"dlcorn;" * "\x231E" + ,"dlcrop;" * "\x230D" + ,"dollar;" * "\x0024" + ,"Dopf;" * "\x1D53B" + ,"dopf;" * "\x1D555" + ,"Dot;" * "\x00A8" + ,"dot;" * "\x02D9" + ,"DotDot;" * "\x20DC" + ,"doteq;" * "\x2250" + ,"doteqdot;" * "\x2251" + ,"DotEqual;" * "\x2250" + ,"dotminus;" * "\x2238" + ,"dotplus;" * "\x2214" + ,"dotsquare;" * "\x22A1" + ,"doublebarwedge;" * "\x2306" + ,"DoubleContourIntegral;" * "\x222F" + ,"DoubleDot;" * "\x00A8" + ,"DoubleDownArrow;" * "\x21D3" + ,"DoubleLeftArrow;" * "\x21D0" + ,"DoubleLeftRightArrow;" * "\x21D4" + ,"DoubleLeftTee;" * "\x2AE4" + ,"DoubleLongLeftArrow;" * "\x27F8" + ,"DoubleLongLeftRightArrow;" * "\x27FA" + ,"DoubleLongRightArrow;" * "\x27F9" + ,"DoubleRightArrow;" * "\x21D2" + ,"DoubleRightTee;" * "\x22A8" + ,"DoubleUpArrow;" * "\x21D1" + ,"DoubleUpDownArrow;" * "\x21D5" + ,"DoubleVerticalBar;" * "\x2225" + ,"DownArrow;" * "\x2193" + ,"downarrow;" * "\x2193" + ,"Downarrow;" * "\x21D3" + ,"DownArrowBar;" * "\x2913" + ,"DownArrowUpArrow;" * "\x21F5" + ,"DownBreve;" * "\x0311" + ,"downdownarrows;" * "\x21CA" + ,"downharpoonleft;" * "\x21C3" + ,"downharpoonright;" * "\x21C2" + ,"DownLeftRightVector;" * "\x2950" + ,"DownLeftTeeVector;" * "\x295E" + ,"DownLeftVector;" * "\x21BD" + ,"DownLeftVectorBar;" * "\x2956" + ,"DownRightTeeVector;" * "\x295F" + ,"DownRightVector;" * "\x21C1" + ,"DownRightVectorBar;" * "\x2957" + ,"DownTee;" * "\x22A4" + ,"DownTeeArrow;" * "\x21A7" + ,"drbkarow;" * "\x2910" + ,"drcorn;" * "\x231F" + ,"drcrop;" * "\x230C" + ,"Dscr;" * "\x1D49F" + ,"dscr;" * "\x1D4B9" + ,"DScy;" * "\x0405" + ,"dscy;" * "\x0455" + ,"dsol;" * "\x29F6" + ,"Dstrok;" * "\x0110" + ,"dstrok;" * "\x0111" + ,"dtdot;" * "\x22F1" + ,"dtri;" * "\x25BF" + ,"dtrif;" * "\x25BE" + ,"duarr;" * "\x21F5" + ,"duhar;" * "\x296F" + ,"dwangle;" * "\x29A6" + ,"DZcy;" * "\x040F" + ,"dzcy;" * "\x045F" + ,"dzigrarr;" * "\x27FF" + ,"Eacute" * "\x00C9" + ,"eacute" * "\x00E9" + ,"Eacute;" * "\x00C9" + ,"eacute;" * "\x00E9" + ,"easter;" * "\x2A6E" + ,"Ecaron;" * "\x011A" + ,"ecaron;" * "\x011B" + ,"ecir;" * "\x2256" + ,"Ecirc" * "\x00CA" + ,"ecirc" * "\x00EA" + ,"Ecirc;" * "\x00CA" + ,"ecirc;" * "\x00EA" + ,"ecolon;" * "\x2255" + ,"Ecy;" * "\x042D" + ,"ecy;" * "\x044D" + ,"eDDot;" * "\x2A77" + ,"Edot;" * "\x0116" + ,"edot;" * "\x0117" + ,"eDot;" * "\x2251" + ,"ee;" * "\x2147" + ,"efDot;" * "\x2252" + ,"Efr;" * "\x1D508" + ,"efr;" * "\x1D522" + ,"eg;" * "\x2A9A" + ,"Egrave" * "\x00C8" + ,"egrave" * "\x00E8" + ,"Egrave;" * "\x00C8" + ,"egrave;" * "\x00E8" + ,"egs;" * "\x2A96" + ,"egsdot;" * "\x2A98" + ,"el;" * "\x2A99" + ,"Element;" * "\x2208" + ,"elinters;" * "\x23E7" + ,"ell;" * "\x2113" + ,"els;" * "\x2A95" + ,"elsdot;" * "\x2A97" + ,"Emacr;" * "\x0112" + ,"emacr;" * "\x0113" + ,"empty;" * "\x2205" + ,"emptyset;" * "\x2205" + ,"EmptySmallSquare;" * "\x25FB" + ,"emptyv;" * "\x2205" + ,"EmptyVerySmallSquare;" * "\x25AB" + ,"emsp13;" * "\x2004" + ,"emsp14;" * "\x2005" + ,"emsp;" * "\x2003" + ,"ENG;" * "\x014A" + ,"eng;" * "\x014B" + ,"ensp;" * "\x2002" + ,"Eogon;" * "\x0118" + ,"eogon;" * "\x0119" + ,"Eopf;" * "\x1D53C" + ,"eopf;" * "\x1D556" + ,"epar;" * "\x22D5" + ,"eparsl;" * "\x29E3" + ,"eplus;" * "\x2A71" + ,"epsi;" * "\x03B5" + ,"Epsilon;" * "\x0395" + ,"epsilon;" * "\x03B5" + ,"epsiv;" * "\x03F5" + ,"eqcirc;" * "\x2256" + ,"eqcolon;" * "\x2255" + ,"eqsim;" * "\x2242" + ,"eqslantgtr;" * "\x2A96" + ,"eqslantless;" * "\x2A95" + ,"Equal;" * "\x2A75" + ,"equals;" * "\x003D" + ,"EqualTilde;" * "\x2242" + ,"equest;" * "\x225F" + ,"Equilibrium;" * "\x21CC" + ,"equiv;" * "\x2261" + ,"equivDD;" * "\x2A78" + ,"eqvparsl;" * "\x29E5" + ,"erarr;" * "\x2971" + ,"erDot;" * "\x2253" + ,"escr;" * "\x212F" + ,"Escr;" * "\x2130" + ,"esdot;" * "\x2250" + ,"esim;" * "\x2242" + ,"Esim;" * "\x2A73" + ,"Eta;" * "\x0397" + ,"eta;" * "\x03B7" + ,"ETH" * "\x00D0" + ,"eth" * "\x00F0" + ,"ETH;" * "\x00D0" + ,"eth;" * "\x00F0" + ,"Euml" * "\x00CB" + ,"euml" * "\x00EB" + ,"Euml;" * "\x00CB" + ,"euml;" * "\x00EB" + ,"euro;" * "\x20AC" + ,"excl;" * "\x0021" + ,"exist;" * "\x2203" + ,"Exists;" * "\x2203" + ,"expectation;" * "\x2130" + ,"ExponentialE;" * "\x2147" + ,"exponentiale;" * "\x2147" + ,"fallingdotseq;" * "\x2252" + ,"Fcy;" * "\x0424" + ,"fcy;" * "\x0444" + ,"female;" * "\x2640" + ,"ffilig;" * "\xFB03" + ,"fflig;" * "\xFB00" + ,"ffllig;" * "\xFB04" + ,"Ffr;" * "\x1D509" + ,"ffr;" * "\x1D523" + ,"filig;" * "\xFB01" + ,"FilledSmallSquare;" * "\x25FC" + ,"FilledVerySmallSquare;" * "\x25AA" + ,"fjlig;" * "\x0066\x006A" + ,"flat;" * "\x266D" + ,"fllig;" * "\xFB02" + ,"fltns;" * "\x25B1" + ,"fnof;" * "\x0192" + ,"Fopf;" * "\x1D53D" + ,"fopf;" * "\x1D557" + ,"ForAll;" * "\x2200" + ,"forall;" * "\x2200" + ,"fork;" * "\x22D4" + ,"forkv;" * "\x2AD9" + ,"Fouriertrf;" * "\x2131" + ,"fpartint;" * "\x2A0D" + ,"frac12" * "\x00BD" + ,"frac12;" * "\x00BD" + ,"frac13;" * "\x2153" + ,"frac14" * "\x00BC" + ,"frac14;" * "\x00BC" + ,"frac15;" * "\x2155" + ,"frac16;" * "\x2159" + ,"frac18;" * "\x215B" + ,"frac23;" * "\x2154" + ,"frac25;" * "\x2156" + ,"frac34" * "\x00BE" + ,"frac34;" * "\x00BE" + ,"frac35;" * "\x2157" + ,"frac38;" * "\x215C" + ,"frac45;" * "\x2158" + ,"frac56;" * "\x215A" + ,"frac58;" * "\x215D" + ,"frac78;" * "\x215E" + ,"frasl;" * "\x2044" + ,"frown;" * "\x2322" + ,"Fscr;" * "\x2131" + ,"fscr;" * "\x1D4BB" + ,"gacute;" * "\x01F5" + ,"Gamma;" * "\x0393" + ,"gamma;" * "\x03B3" + ,"Gammad;" * "\x03DC" + ,"gammad;" * "\x03DD" + ,"gap;" * "\x2A86" + ,"Gbreve;" * "\x011E" + ,"gbreve;" * "\x011F" + ,"Gcedil;" * "\x0122" + ,"Gcirc;" * "\x011C" + ,"gcirc;" * "\x011D" + ,"Gcy;" * "\x0413" + ,"gcy;" * "\x0433" + ,"Gdot;" * "\x0120" + ,"gdot;" * "\x0121" + ,"ge;" * "\x2265" + ,"gE;" * "\x2267" + ,"gel;" * "\x22DB" + ,"gEl;" * "\x2A8C" + ,"geq;" * "\x2265" + ,"geqq;" * "\x2267" + ,"geqslant;" * "\x2A7E" + ,"ges;" * "\x2A7E" + ,"gescc;" * "\x2AA9" + ,"gesdot;" * "\x2A80" + ,"gesdoto;" * "\x2A82" + ,"gesdotol;" * "\x2A84" + ,"gesl;" * "\x22DB\xFE00" + ,"gesles;" * "\x2A94" + ,"Gfr;" * "\x1D50A" + ,"gfr;" * "\x1D524" + ,"gg;" * "\x226B" + ,"Gg;" * "\x22D9" + ,"ggg;" * "\x22D9" + ,"gimel;" * "\x2137" + ,"GJcy;" * "\x0403" + ,"gjcy;" * "\x0453" + ,"gl;" * "\x2277" + ,"gla;" * "\x2AA5" + ,"glE;" * "\x2A92" + ,"glj;" * "\x2AA4" + ,"gnap;" * "\x2A8A" + ,"gnapprox;" * "\x2A8A" + ,"gnE;" * "\x2269" + ,"gne;" * "\x2A88" + ,"gneq;" * "\x2A88" + ,"gneqq;" * "\x2269" + ,"gnsim;" * "\x22E7" + ,"Gopf;" * "\x1D53E" + ,"gopf;" * "\x1D558" + ,"grave;" * "\x0060" + ,"GreaterEqual;" * "\x2265" + ,"GreaterEqualLess;" * "\x22DB" + ,"GreaterFullEqual;" * "\x2267" + ,"GreaterGreater;" * "\x2AA2" + ,"GreaterLess;" * "\x2277" + ,"GreaterSlantEqual;" * "\x2A7E" + ,"GreaterTilde;" * "\x2273" + ,"gscr;" * "\x210A" + ,"Gscr;" * "\x1D4A2" + ,"gsim;" * "\x2273" + ,"gsime;" * "\x2A8E" + ,"gsiml;" * "\x2A90" + ,"GT" * "\x003E" + ,"gt" * "\x003E" + ,"GT;" * "\x003E" + ,"gt;" * "\x003E" + ,"Gt;" * "\x226B" + ,"gtcc;" * "\x2AA7" + ,"gtcir;" * "\x2A7A" + ,"gtdot;" * "\x22D7" + ,"gtlPar;" * "\x2995" + ,"gtquest;" * "\x2A7C" + ,"gtrapprox;" * "\x2A86" + ,"gtrarr;" * "\x2978" + ,"gtrdot;" * "\x22D7" + ,"gtreqless;" * "\x22DB" + ,"gtreqqless;" * "\x2A8C" + ,"gtrless;" * "\x2277" + ,"gtrsim;" * "\x2273" + ,"gvertneqq;" * "\x2269\xFE00" + ,"gvnE;" * "\x2269\xFE00" + ,"Hacek;" * "\x02C7" + ,"hairsp;" * "\x200A" + ,"half;" * "\x00BD" + ,"hamilt;" * "\x210B" + ,"HARDcy;" * "\x042A" + ,"hardcy;" * "\x044A" + ,"harr;" * "\x2194" + ,"hArr;" * "\x21D4" + ,"harrcir;" * "\x2948" + ,"harrw;" * "\x21AD" + ,"Hat;" * "\x005E" + ,"hbar;" * "\x210F" + ,"Hcirc;" * "\x0124" + ,"hcirc;" * "\x0125" + ,"hearts;" * "\x2665" + ,"heartsuit;" * "\x2665" + ,"hellip;" * "\x2026" + ,"hercon;" * "\x22B9" + ,"Hfr;" * "\x210C" + ,"hfr;" * "\x1D525" + ,"HilbertSpace;" * "\x210B" + ,"hksearow;" * "\x2925" + ,"hkswarow;" * "\x2926" + ,"hoarr;" * "\x21FF" + ,"homtht;" * "\x223B" + ,"hookleftarrow;" * "\x21A9" + ,"hookrightarrow;" * "\x21AA" + ,"Hopf;" * "\x210D" + ,"hopf;" * "\x1D559" + ,"horbar;" * "\x2015" + ,"HorizontalLine;" * "\x2500" + ,"Hscr;" * "\x210B" + ,"hscr;" * "\x1D4BD" + ,"hslash;" * "\x210F" + ,"Hstrok;" * "\x0126" + ,"hstrok;" * "\x0127" + ,"HumpDownHump;" * "\x224E" + ,"HumpEqual;" * "\x224F" + ,"hybull;" * "\x2043" + ,"hyphen;" * "\x2010" + ,"Iacute" * "\x00CD" + ,"iacute" * "\x00ED" + ,"Iacute;" * "\x00CD" + ,"iacute;" * "\x00ED" + ,"ic;" * "\x2063" + ,"Icirc" * "\x00CE" + ,"icirc" * "\x00EE" + ,"Icirc;" * "\x00CE" + ,"icirc;" * "\x00EE" + ,"Icy;" * "\x0418" + ,"icy;" * "\x0438" + ,"Idot;" * "\x0130" + ,"IEcy;" * "\x0415" + ,"iecy;" * "\x0435" + ,"iexcl" * "\x00A1" + ,"iexcl;" * "\x00A1" + ,"iff;" * "\x21D4" + ,"Ifr;" * "\x2111" + ,"ifr;" * "\x1D526" + ,"Igrave" * "\x00CC" + ,"igrave" * "\x00EC" + ,"Igrave;" * "\x00CC" + ,"igrave;" * "\x00EC" + ,"ii;" * "\x2148" + ,"iiiint;" * "\x2A0C" + ,"iiint;" * "\x222D" + ,"iinfin;" * "\x29DC" + ,"iiota;" * "\x2129" + ,"IJlig;" * "\x0132" + ,"ijlig;" * "\x0133" + ,"Im;" * "\x2111" + ,"Imacr;" * "\x012A" + ,"imacr;" * "\x012B" + ,"image;" * "\x2111" + ,"ImaginaryI;" * "\x2148" + ,"imagline;" * "\x2110" + ,"imagpart;" * "\x2111" + ,"imath;" * "\x0131" + ,"imof;" * "\x22B7" + ,"imped;" * "\x01B5" + ,"Implies;" * "\x21D2" + ,"in;" * "\x2208" + ,"incare;" * "\x2105" + ,"infin;" * "\x221E" + ,"infintie;" * "\x29DD" + ,"inodot;" * "\x0131" + ,"int;" * "\x222B" + ,"Int;" * "\x222C" + ,"intcal;" * "\x22BA" + ,"integers;" * "\x2124" + ,"Integral;" * "\x222B" + ,"intercal;" * "\x22BA" + ,"Intersection;" * "\x22C2" + ,"intlarhk;" * "\x2A17" + ,"intprod;" * "\x2A3C" + ,"InvisibleComma;" * "\x2063" + ,"InvisibleTimes;" * "\x2062" + ,"IOcy;" * "\x0401" + ,"iocy;" * "\x0451" + ,"Iogon;" * "\x012E" + ,"iogon;" * "\x012F" + ,"Iopf;" * "\x1D540" + ,"iopf;" * "\x1D55A" + ,"Iota;" * "\x0399" + ,"iota;" * "\x03B9" + ,"iprod;" * "\x2A3C" + ,"iquest" * "\x00BF" + ,"iquest;" * "\x00BF" + ,"Iscr;" * "\x2110" + ,"iscr;" * "\x1D4BE" + ,"isin;" * "\x2208" + ,"isindot;" * "\x22F5" + ,"isinE;" * "\x22F9" + ,"isins;" * "\x22F4" + ,"isinsv;" * "\x22F3" + ,"isinv;" * "\x2208" + ,"it;" * "\x2062" + ,"Itilde;" * "\x0128" + ,"itilde;" * "\x0129" + ,"Iukcy;" * "\x0406" + ,"iukcy;" * "\x0456" + ,"Iuml" * "\x00CF" + ,"iuml" * "\x00EF" + ,"Iuml;" * "\x00CF" + ,"iuml;" * "\x00EF" + ,"Jcirc;" * "\x0134" + ,"jcirc;" * "\x0135" + ,"Jcy;" * "\x0419" + ,"jcy;" * "\x0439" + ,"Jfr;" * "\x1D50D" + ,"jfr;" * "\x1D527" + ,"jmath;" * "\x0237" + ,"Jopf;" * "\x1D541" + ,"jopf;" * "\x1D55B" + ,"Jscr;" * "\x1D4A5" + ,"jscr;" * "\x1D4BF" + ,"Jsercy;" * "\x0408" + ,"jsercy;" * "\x0458" + ,"Jukcy;" * "\x0404" + ,"jukcy;" * "\x0454" + ,"Kappa;" * "\x039A" + ,"kappa;" * "\x03BA" + ,"kappav;" * "\x03F0" + ,"Kcedil;" * "\x0136" + ,"kcedil;" * "\x0137" + ,"Kcy;" * "\x041A" + ,"kcy;" * "\x043A" + ,"Kfr;" * "\x1D50E" + ,"kfr;" * "\x1D528" + ,"kgreen;" * "\x0138" + ,"KHcy;" * "\x0425" + ,"khcy;" * "\x0445" + ,"KJcy;" * "\x040C" + ,"kjcy;" * "\x045C" + ,"Kopf;" * "\x1D542" + ,"kopf;" * "\x1D55C" + ,"Kscr;" * "\x1D4A6" + ,"kscr;" * "\x1D4C0" + ,"lAarr;" * "\x21DA" + ,"Lacute;" * "\x0139" + ,"lacute;" * "\x013A" + ,"laemptyv;" * "\x29B4" + ,"lagran;" * "\x2112" + ,"Lambda;" * "\x039B" + ,"lambda;" * "\x03BB" + ,"lang;" * "\x27E8" + ,"Lang;" * "\x27EA" + ,"langd;" * "\x2991" + ,"langle;" * "\x27E8" + ,"lap;" * "\x2A85" + ,"Laplacetrf;" * "\x2112" + ,"laquo" * "\x00AB" + ,"laquo;" * "\x00AB" + ,"larr;" * "\x2190" + ,"Larr;" * "\x219E" + ,"lArr;" * "\x21D0" + ,"larrb;" * "\x21E4" + ,"larrbfs;" * "\x291F" + ,"larrfs;" * "\x291D" + ,"larrhk;" * "\x21A9" + ,"larrlp;" * "\x21AB" + ,"larrpl;" * "\x2939" + ,"larrsim;" * "\x2973" + ,"larrtl;" * "\x21A2" + ,"lat;" * "\x2AAB" + ,"latail;" * "\x2919" + ,"lAtail;" * "\x291B" + ,"late;" * "\x2AAD" + ,"lates;" * "\x2AAD\xFE00" + ,"lbarr;" * "\x290C" + ,"lBarr;" * "\x290E" + ,"lbbrk;" * "\x2772" + ,"lbrace;" * "\x007B" + ,"lbrack;" * "\x005B" + ,"lbrke;" * "\x298B" + ,"lbrksld;" * "\x298F" + ,"lbrkslu;" * "\x298D" + ,"Lcaron;" * "\x013D" + ,"lcaron;" * "\x013E" + ,"Lcedil;" * "\x013B" + ,"lcedil;" * "\x013C" + ,"lceil;" * "\x2308" + ,"lcub;" * "\x007B" + ,"Lcy;" * "\x041B" + ,"lcy;" * "\x043B" + ,"ldca;" * "\x2936" + ,"ldquo;" * "\x201C" + ,"ldquor;" * "\x201E" + ,"ldrdhar;" * "\x2967" + ,"ldrushar;" * "\x294B" + ,"ldsh;" * "\x21B2" + ,"le;" * "\x2264" + ,"lE;" * "\x2266" + ,"LeftAngleBracket;" * "\x27E8" + ,"LeftArrow;" * "\x2190" + ,"leftarrow;" * "\x2190" + ,"Leftarrow;" * "\x21D0" + ,"LeftArrowBar;" * "\x21E4" + ,"LeftArrowRightArrow;" * "\x21C6" + ,"leftarrowtail;" * "\x21A2" + ,"LeftCeiling;" * "\x2308" + ,"LeftDoubleBracket;" * "\x27E6" + ,"LeftDownTeeVector;" * "\x2961" + ,"LeftDownVector;" * "\x21C3" + ,"LeftDownVectorBar;" * "\x2959" + ,"LeftFloor;" * "\x230A" + ,"leftharpoondown;" * "\x21BD" + ,"leftharpoonup;" * "\x21BC" + ,"leftleftarrows;" * "\x21C7" + ,"LeftRightArrow;" * "\x2194" + ,"leftrightarrow;" * "\x2194" + ,"Leftrightarrow;" * "\x21D4" + ,"leftrightarrows;" * "\x21C6" + ,"leftrightharpoons;" * "\x21CB" + ,"leftrightsquigarrow;" * "\x21AD" + ,"LeftRightVector;" * "\x294E" + ,"LeftTee;" * "\x22A3" + ,"LeftTeeArrow;" * "\x21A4" + ,"LeftTeeVector;" * "\x295A" + ,"leftthreetimes;" * "\x22CB" + ,"LeftTriangle;" * "\x22B2" + ,"LeftTriangleBar;" * "\x29CF" + ,"LeftTriangleEqual;" * "\x22B4" + ,"LeftUpDownVector;" * "\x2951" + ,"LeftUpTeeVector;" * "\x2960" + ,"LeftUpVector;" * "\x21BF" + ,"LeftUpVectorBar;" * "\x2958" + ,"LeftVector;" * "\x21BC" + ,"LeftVectorBar;" * "\x2952" + ,"leg;" * "\x22DA" + ,"lEg;" * "\x2A8B" + ,"leq;" * "\x2264" + ,"leqq;" * "\x2266" + ,"leqslant;" * "\x2A7D" + ,"les;" * "\x2A7D" + ,"lescc;" * "\x2AA8" + ,"lesdot;" * "\x2A7F" + ,"lesdoto;" * "\x2A81" + ,"lesdotor;" * "\x2A83" + ,"lesg;" * "\x22DA\xFE00" + ,"lesges;" * "\x2A93" + ,"lessapprox;" * "\x2A85" + ,"lessdot;" * "\x22D6" + ,"lesseqgtr;" * "\x22DA" + ,"lesseqqgtr;" * "\x2A8B" + ,"LessEqualGreater;" * "\x22DA" + ,"LessFullEqual;" * "\x2266" + ,"LessGreater;" * "\x2276" + ,"lessgtr;" * "\x2276" + ,"LessLess;" * "\x2AA1" + ,"lesssim;" * "\x2272" + ,"LessSlantEqual;" * "\x2A7D" + ,"LessTilde;" * "\x2272" + ,"lfisht;" * "\x297C" + ,"lfloor;" * "\x230A" + ,"Lfr;" * "\x1D50F" + ,"lfr;" * "\x1D529" + ,"lg;" * "\x2276" + ,"lgE;" * "\x2A91" + ,"lHar;" * "\x2962" + ,"lhard;" * "\x21BD" + ,"lharu;" * "\x21BC" + ,"lharul;" * "\x296A" + ,"lhblk;" * "\x2584" + ,"LJcy;" * "\x0409" + ,"ljcy;" * "\x0459" + ,"ll;" * "\x226A" + ,"Ll;" * "\x22D8" + ,"llarr;" * "\x21C7" + ,"llcorner;" * "\x231E" + ,"Lleftarrow;" * "\x21DA" + ,"llhard;" * "\x296B" + ,"lltri;" * "\x25FA" + ,"Lmidot;" * "\x013F" + ,"lmidot;" * "\x0140" + ,"lmoust;" * "\x23B0" + ,"lmoustache;" * "\x23B0" + ,"lnap;" * "\x2A89" + ,"lnapprox;" * "\x2A89" + ,"lnE;" * "\x2268" + ,"lne;" * "\x2A87" + ,"lneq;" * "\x2A87" + ,"lneqq;" * "\x2268" + ,"lnsim;" * "\x22E6" + ,"loang;" * "\x27EC" + ,"loarr;" * "\x21FD" + ,"lobrk;" * "\x27E6" + ,"LongLeftArrow;" * "\x27F5" + ,"longleftarrow;" * "\x27F5" + ,"Longleftarrow;" * "\x27F8" + ,"LongLeftRightArrow;" * "\x27F7" + ,"longleftrightarrow;" * "\x27F7" + ,"Longleftrightarrow;" * "\x27FA" + ,"longmapsto;" * "\x27FC" + ,"LongRightArrow;" * "\x27F6" + ,"longrightarrow;" * "\x27F6" + ,"Longrightarrow;" * "\x27F9" + ,"looparrowleft;" * "\x21AB" + ,"looparrowright;" * "\x21AC" + ,"lopar;" * "\x2985" + ,"Lopf;" * "\x1D543" + ,"lopf;" * "\x1D55D" + ,"loplus;" * "\x2A2D" + ,"lotimes;" * "\x2A34" + ,"lowast;" * "\x2217" + ,"lowbar;" * "\x005F" + ,"LowerLeftArrow;" * "\x2199" + ,"LowerRightArrow;" * "\x2198" + ,"loz;" * "\x25CA" + ,"lozenge;" * "\x25CA" + ,"lozf;" * "\x29EB" + ,"lpar;" * "\x0028" + ,"lparlt;" * "\x2993" + ,"lrarr;" * "\x21C6" + ,"lrcorner;" * "\x231F" + ,"lrhar;" * "\x21CB" + ,"lrhard;" * "\x296D" + ,"lrm;" * "\x200E" + ,"lrtri;" * "\x22BF" + ,"lsaquo;" * "\x2039" + ,"Lscr;" * "\x2112" + ,"lscr;" * "\x1D4C1" + ,"Lsh;" * "\x21B0" + ,"lsh;" * "\x21B0" + ,"lsim;" * "\x2272" + ,"lsime;" * "\x2A8D" + ,"lsimg;" * "\x2A8F" + ,"lsqb;" * "\x005B" + ,"lsquo;" * "\x2018" + ,"lsquor;" * "\x201A" + ,"Lstrok;" * "\x0141" + ,"lstrok;" * "\x0142" + ,"LT" * "\x003C" + ,"lt" * "\x003C" + ,"LT;" * "\x003C" + ,"lt;" * "\x003C" + ,"Lt;" * "\x226A" + ,"ltcc;" * "\x2AA6" + ,"ltcir;" * "\x2A79" + ,"ltdot;" * "\x22D6" + ,"lthree;" * "\x22CB" + ,"ltimes;" * "\x22C9" + ,"ltlarr;" * "\x2976" + ,"ltquest;" * "\x2A7B" + ,"ltri;" * "\x25C3" + ,"ltrie;" * "\x22B4" + ,"ltrif;" * "\x25C2" + ,"ltrPar;" * "\x2996" + ,"lurdshar;" * "\x294A" + ,"luruhar;" * "\x2966" + ,"lvertneqq;" * "\x2268\xFE00" + ,"lvnE;" * "\x2268\xFE00" + ,"macr" * "\x00AF" + ,"macr;" * "\x00AF" + ,"male;" * "\x2642" + ,"malt;" * "\x2720" + ,"maltese;" * "\x2720" + ,"map;" * "\x21A6" + ,"Map;" * "\x2905" + ,"mapsto;" * "\x21A6" + ,"mapstodown;" * "\x21A7" + ,"mapstoleft;" * "\x21A4" + ,"mapstoup;" * "\x21A5" + ,"marker;" * "\x25AE" + ,"mcomma;" * "\x2A29" + ,"Mcy;" * "\x041C" + ,"mcy;" * "\x043C" + ,"mdash;" * "\x2014" + ,"mDDot;" * "\x223A" + ,"measuredangle;" * "\x2221" + ,"MediumSpace;" * "\x205F" + ,"Mellintrf;" * "\x2133" + ,"Mfr;" * "\x1D510" + ,"mfr;" * "\x1D52A" + ,"mho;" * "\x2127" + ,"micro" * "\x00B5" + ,"micro;" * "\x00B5" + ,"mid;" * "\x2223" + ,"midast;" * "\x002A" + ,"midcir;" * "\x2AF0" + ,"middot" * "\x00B7" + ,"middot;" * "\x00B7" + ,"minus;" * "\x2212" + ,"minusb;" * "\x229F" + ,"minusd;" * "\x2238" + ,"minusdu;" * "\x2A2A" + ,"MinusPlus;" * "\x2213" + ,"mlcp;" * "\x2ADB" + ,"mldr;" * "\x2026" + ,"mnplus;" * "\x2213" + ,"models;" * "\x22A7" + ,"Mopf;" * "\x1D544" + ,"mopf;" * "\x1D55E" + ,"mp;" * "\x2213" + ,"Mscr;" * "\x2133" + ,"mscr;" * "\x1D4C2" + ,"mstpos;" * "\x223E" + ,"Mu;" * "\x039C" + ,"mu;" * "\x03BC" + ,"multimap;" * "\x22B8" + ,"mumap;" * "\x22B8" + ,"nabla;" * "\x2207" + ,"Nacute;" * "\x0143" + ,"nacute;" * "\x0144" + ,"nang;" * "\x2220\x20D2" + ,"nap;" * "\x2249" + ,"napE;" * "\x2A70\x0338" + ,"napid;" * "\x224B\x0338" + ,"napos;" * "\x0149" + ,"napprox;" * "\x2249" + ,"natur;" * "\x266E" + ,"natural;" * "\x266E" + ,"naturals;" * "\x2115" + ,"nbsp" * "\x00A0" + ,"nbsp;" * "\x00A0" + ,"nbump;" * "\x224E\x0338" + ,"nbumpe;" * "\x224F\x0338" + ,"ncap;" * "\x2A43" + ,"Ncaron;" * "\x0147" + ,"ncaron;" * "\x0148" + ,"Ncedil;" * "\x0145" + ,"ncedil;" * "\x0146" + ,"ncong;" * "\x2247" + ,"ncongdot;" * "\x2A6D\x0338" + ,"ncup;" * "\x2A42" + ,"Ncy;" * "\x041D" + ,"ncy;" * "\x043D" + ,"ndash;" * "\x2013" + ,"ne;" * "\x2260" + ,"nearhk;" * "\x2924" + ,"nearr;" * "\x2197" + ,"neArr;" * "\x21D7" + ,"nearrow;" * "\x2197" + ,"nedot;" * "\x2250\x0338" + ,"NegativeMediumSpace;" * "\x200B" + ,"NegativeThickSpace;" * "\x200B" + ,"NegativeThinSpace;" * "\x200B" + ,"NegativeVeryThinSpace;" * "\x200B" + ,"nequiv;" * "\x2262" + ,"nesear;" * "\x2928" + ,"nesim;" * "\x2242\x0338" + ,"NestedGreaterGreater;" * "\x226B" + ,"NestedLessLess;" * "\x226A" + ,"NewLine;" * "\x000A" + ,"nexist;" * "\x2204" + ,"nexists;" * "\x2204" + ,"Nfr;" * "\x1D511" + ,"nfr;" * "\x1D52B" + ,"ngE;" * "\x2267\x0338" + ,"nge;" * "\x2271" + ,"ngeq;" * "\x2271" + ,"ngeqq;" * "\x2267\x0338" + ,"ngeqslant;" * "\x2A7E\x0338" + ,"nges;" * "\x2A7E\x0338" + ,"nGg;" * "\x22D9\x0338" + ,"ngsim;" * "\x2275" + ,"nGt;" * "\x226B\x20D2" + ,"ngt;" * "\x226F" + ,"ngtr;" * "\x226F" + ,"nGtv;" * "\x226B\x0338" + ,"nharr;" * "\x21AE" + ,"nhArr;" * "\x21CE" + ,"nhpar;" * "\x2AF2" + ,"ni;" * "\x220B" + ,"nis;" * "\x22FC" + ,"nisd;" * "\x22FA" + ,"niv;" * "\x220B" + ,"NJcy;" * "\x040A" + ,"njcy;" * "\x045A" + ,"nlarr;" * "\x219A" + ,"nlArr;" * "\x21CD" + ,"nldr;" * "\x2025" + ,"nlE;" * "\x2266\x0338" + ,"nle;" * "\x2270" + ,"nleftarrow;" * "\x219A" + ,"nLeftarrow;" * "\x21CD" + ,"nleftrightarrow;" * "\x21AE" + ,"nLeftrightarrow;" * "\x21CE" + ,"nleq;" * "\x2270" + ,"nleqq;" * "\x2266\x0338" + ,"nleqslant;" * "\x2A7D\x0338" + ,"nles;" * "\x2A7D\x0338" + ,"nless;" * "\x226E" + ,"nLl;" * "\x22D8\x0338" + ,"nlsim;" * "\x2274" + ,"nLt;" * "\x226A\x20D2" + ,"nlt;" * "\x226E" + ,"nltri;" * "\x22EA" + ,"nltrie;" * "\x22EC" + ,"nLtv;" * "\x226A\x0338" + ,"nmid;" * "\x2224" + ,"NoBreak;" * "\x2060" + ,"NonBreakingSpace;" * "\x00A0" + ,"Nopf;" * "\x2115" + ,"nopf;" * "\x1D55F" + ,"not" * "\x00AC" + ,"not;" * "\x00AC" + ,"Not;" * "\x2AEC" + ,"NotCongruent;" * "\x2262" + ,"NotCupCap;" * "\x226D" + ,"NotDoubleVerticalBar;" * "\x2226" + ,"NotElement;" * "\x2209" + ,"NotEqual;" * "\x2260" + ,"NotEqualTilde;" * "\x2242\x0338" + ,"NotExists;" * "\x2204" + ,"NotGreater;" * "\x226F" + ,"NotGreaterEqual;" * "\x2271" + ,"NotGreaterFullEqual;" * "\x2267\x0338" + ,"NotGreaterGreater;" * "\x226B\x0338" + ,"NotGreaterLess;" * "\x2279" + ,"NotGreaterSlantEqual;" * "\x2A7E\x0338" + ,"NotGreaterTilde;" * "\x2275" + ,"NotHumpDownHump;" * "\x224E\x0338" + ,"NotHumpEqual;" * "\x224F\x0338" + ,"notin;" * "\x2209" + ,"notindot;" * "\x22F5\x0338" + ,"notinE;" * "\x22F9\x0338" + ,"notinva;" * "\x2209" + ,"notinvb;" * "\x22F7" + ,"notinvc;" * "\x22F6" + ,"NotLeftTriangle;" * "\x22EA" + ,"NotLeftTriangleBar;" * "\x29CF\x0338" + ,"NotLeftTriangleEqual;" * "\x22EC" + ,"NotLess;" * "\x226E" + ,"NotLessEqual;" * "\x2270" + ,"NotLessGreater;" * "\x2278" + ,"NotLessLess;" * "\x226A\x0338" + ,"NotLessSlantEqual;" * "\x2A7D\x0338" + ,"NotLessTilde;" * "\x2274" + ,"NotNestedGreaterGreater;" * "\x2AA2\x0338" + ,"NotNestedLessLess;" * "\x2AA1\x0338" + ,"notni;" * "\x220C" + ,"notniva;" * "\x220C" + ,"notnivb;" * "\x22FE" + ,"notnivc;" * "\x22FD" + ,"NotPrecedes;" * "\x2280" + ,"NotPrecedesEqual;" * "\x2AAF\x0338" + ,"NotPrecedesSlantEqual;" * "\x22E0" + ,"NotReverseElement;" * "\x220C" + ,"NotRightTriangle;" * "\x22EB" + ,"NotRightTriangleBar;" * "\x29D0\x0338" + ,"NotRightTriangleEqual;" * "\x22ED" + ,"NotSquareSubset;" * "\x228F\x0338" + ,"NotSquareSubsetEqual;" * "\x22E2" + ,"NotSquareSuperset;" * "\x2290\x0338" + ,"NotSquareSupersetEqual;" * "\x22E3" + ,"NotSubset;" * "\x2282\x20D2" + ,"NotSubsetEqual;" * "\x2288" + ,"NotSucceeds;" * "\x2281" + ,"NotSucceedsEqual;" * "\x2AB0\x0338" + ,"NotSucceedsSlantEqual;" * "\x22E1" + ,"NotSucceedsTilde;" * "\x227F\x0338" + ,"NotSuperset;" * "\x2283\x20D2" + ,"NotSupersetEqual;" * "\x2289" + ,"NotTilde;" * "\x2241" + ,"NotTildeEqual;" * "\x2244" + ,"NotTildeFullEqual;" * "\x2247" + ,"NotTildeTilde;" * "\x2249" + ,"NotVerticalBar;" * "\x2224" + ,"npar;" * "\x2226" + ,"nparallel;" * "\x2226" + ,"nparsl;" * "\x2AFD\x20E5" + ,"npart;" * "\x2202\x0338" + ,"npolint;" * "\x2A14" + ,"npr;" * "\x2280" + ,"nprcue;" * "\x22E0" + ,"npre;" * "\x2AAF\x0338" + ,"nprec;" * "\x2280" + ,"npreceq;" * "\x2AAF\x0338" + ,"nrarr;" * "\x219B" + ,"nrArr;" * "\x21CF" + ,"nrarrc;" * "\x2933\x0338" + ,"nrarrw;" * "\x219D\x0338" + ,"nrightarrow;" * "\x219B" + ,"nRightarrow;" * "\x21CF" + ,"nrtri;" * "\x22EB" + ,"nrtrie;" * "\x22ED" + ,"nsc;" * "\x2281" + ,"nsccue;" * "\x22E1" + ,"nsce;" * "\x2AB0\x0338" + ,"Nscr;" * "\x1D4A9" + ,"nscr;" * "\x1D4C3" + ,"nshortmid;" * "\x2224" + ,"nshortparallel;" * "\x2226" + ,"nsim;" * "\x2241" + ,"nsime;" * "\x2244" + ,"nsimeq;" * "\x2244" + ,"nsmid;" * "\x2224" + ,"nspar;" * "\x2226" + ,"nsqsube;" * "\x22E2" + ,"nsqsupe;" * "\x22E3" + ,"nsub;" * "\x2284" + ,"nsube;" * "\x2288" + ,"nsubE;" * "\x2AC5\x0338" + ,"nsubset;" * "\x2282\x20D2" + ,"nsubseteq;" * "\x2288" + ,"nsubseteqq;" * "\x2AC5\x0338" + ,"nsucc;" * "\x2281" + ,"nsucceq;" * "\x2AB0\x0338" + ,"nsup;" * "\x2285" + ,"nsupe;" * "\x2289" + ,"nsupE;" * "\x2AC6\x0338" + ,"nsupset;" * "\x2283\x20D2" + ,"nsupseteq;" * "\x2289" + ,"nsupseteqq;" * "\x2AC6\x0338" + ,"ntgl;" * "\x2279" + ,"Ntilde" * "\x00D1" + ,"ntilde" * "\x00F1" + ,"Ntilde;" * "\x00D1" + ,"ntilde;" * "\x00F1" + ,"ntlg;" * "\x2278" + ,"ntriangleleft;" * "\x22EA" + ,"ntrianglelefteq;" * "\x22EC" + ,"ntriangleright;" * "\x22EB" + ,"ntrianglerighteq;" * "\x22ED" + ,"Nu;" * "\x039D" + ,"nu;" * "\x03BD" + ,"num;" * "\x0023" + ,"numero;" * "\x2116" + ,"numsp;" * "\x2007" + ,"nvap;" * "\x224D\x20D2" + ,"nvdash;" * "\x22AC" + ,"nvDash;" * "\x22AD" + ,"nVdash;" * "\x22AE" + ,"nVDash;" * "\x22AF" + ,"nvge;" * "\x2265\x20D2" + ,"nvgt;" * "\x003E\x20D2" + ,"nvHarr;" * "\x2904" + ,"nvinfin;" * "\x29DE" + ,"nvlArr;" * "\x2902" + ,"nvle;" * "\x2264\x20D2" + ,"nvlt;" * "\x003C\x20D2" + ,"nvltrie;" * "\x22B4\x20D2" + ,"nvrArr;" * "\x2903" + ,"nvrtrie;" * "\x22B5\x20D2" + ,"nvsim;" * "\x223C\x20D2" + ,"nwarhk;" * "\x2923" + ,"nwarr;" * "\x2196" + ,"nwArr;" * "\x21D6" + ,"nwarrow;" * "\x2196" + ,"nwnear;" * "\x2927" + ,"Oacute" * "\x00D3" + ,"oacute" * "\x00F3" + ,"Oacute;" * "\x00D3" + ,"oacute;" * "\x00F3" + ,"oast;" * "\x229B" + ,"ocir;" * "\x229A" + ,"Ocirc" * "\x00D4" + ,"ocirc" * "\x00F4" + ,"Ocirc;" * "\x00D4" + ,"ocirc;" * "\x00F4" + ,"Ocy;" * "\x041E" + ,"ocy;" * "\x043E" + ,"odash;" * "\x229D" + ,"Odblac;" * "\x0150" + ,"odblac;" * "\x0151" + ,"odiv;" * "\x2A38" + ,"odot;" * "\x2299" + ,"odsold;" * "\x29BC" + ,"OElig;" * "\x0152" + ,"oelig;" * "\x0153" + ,"ofcir;" * "\x29BF" + ,"Ofr;" * "\x1D512" + ,"ofr;" * "\x1D52C" + ,"ogon;" * "\x02DB" + ,"Ograve" * "\x00D2" + ,"ograve" * "\x00F2" + ,"Ograve;" * "\x00D2" + ,"ograve;" * "\x00F2" + ,"ogt;" * "\x29C1" + ,"ohbar;" * "\x29B5" + ,"ohm;" * "\x03A9" + ,"oint;" * "\x222E" + ,"olarr;" * "\x21BA" + ,"olcir;" * "\x29BE" + ,"olcross;" * "\x29BB" + ,"oline;" * "\x203E" + ,"olt;" * "\x29C0" + ,"Omacr;" * "\x014C" + ,"omacr;" * "\x014D" + ,"Omega;" * "\x03A9" + ,"omega;" * "\x03C9" + ,"Omicron;" * "\x039F" + ,"omicron;" * "\x03BF" + ,"omid;" * "\x29B6" + ,"ominus;" * "\x2296" + ,"Oopf;" * "\x1D546" + ,"oopf;" * "\x1D560" + ,"opar;" * "\x29B7" + ,"OpenCurlyDoubleQuote;" * "\x201C" + ,"OpenCurlyQuote;" * "\x2018" + ,"operp;" * "\x29B9" + ,"oplus;" * "\x2295" + ,"or;" * "\x2228" + ,"Or;" * "\x2A54" + ,"orarr;" * "\x21BB" + ,"ord;" * "\x2A5D" + ,"order;" * "\x2134" + ,"orderof;" * "\x2134" + ,"ordf" * "\x00AA" + ,"ordf;" * "\x00AA" + ,"ordm" * "\x00BA" + ,"ordm;" * "\x00BA" + ,"origof;" * "\x22B6" + ,"oror;" * "\x2A56" + ,"orslope;" * "\x2A57" + ,"orv;" * "\x2A5B" + ,"oS;" * "\x24C8" + ,"oscr;" * "\x2134" + ,"Oscr;" * "\x1D4AA" + ,"Oslash" * "\x00D8" + ,"oslash" * "\x00F8" + ,"Oslash;" * "\x00D8" + ,"oslash;" * "\x00F8" + ,"osol;" * "\x2298" + ,"Otilde" * "\x00D5" + ,"otilde" * "\x00F5" + ,"Otilde;" * "\x00D5" + ,"otilde;" * "\x00F5" + ,"otimes;" * "\x2297" + ,"Otimes;" * "\x2A37" + ,"otimesas;" * "\x2A36" + ,"Ouml" * "\x00D6" + ,"ouml" * "\x00F6" + ,"Ouml;" * "\x00D6" + ,"ouml;" * "\x00F6" + ,"ovbar;" * "\x233D" + ,"OverBar;" * "\x203E" + ,"OverBrace;" * "\x23DE" + ,"OverBracket;" * "\x23B4" + ,"OverParenthesis;" * "\x23DC" + ,"par;" * "\x2225" + ,"para" * "\x00B6" + ,"para;" * "\x00B6" + ,"parallel;" * "\x2225" + ,"parsim;" * "\x2AF3" + ,"parsl;" * "\x2AFD" + ,"part;" * "\x2202" + ,"PartialD;" * "\x2202" + ,"Pcy;" * "\x041F" + ,"pcy;" * "\x043F" + ,"percnt;" * "\x0025" + ,"period;" * "\x002E" + ,"permil;" * "\x2030" + ,"perp;" * "\x22A5" + ,"pertenk;" * "\x2031" + ,"Pfr;" * "\x1D513" + ,"pfr;" * "\x1D52D" + ,"Phi;" * "\x03A6" + ,"phi;" * "\x03C6" + ,"phiv;" * "\x03D5" + ,"phmmat;" * "\x2133" + ,"phone;" * "\x260E" + ,"Pi;" * "\x03A0" + ,"pi;" * "\x03C0" + ,"pitchfork;" * "\x22D4" + ,"piv;" * "\x03D6" + ,"planck;" * "\x210F" + ,"planckh;" * "\x210E" + ,"plankv;" * "\x210F" + ,"plus;" * "\x002B" + ,"plusacir;" * "\x2A23" + ,"plusb;" * "\x229E" + ,"pluscir;" * "\x2A22" + ,"plusdo;" * "\x2214" + ,"plusdu;" * "\x2A25" + ,"pluse;" * "\x2A72" + ,"PlusMinus;" * "\x00B1" + ,"plusmn" * "\x00B1" + ,"plusmn;" * "\x00B1" + ,"plussim;" * "\x2A26" + ,"plustwo;" * "\x2A27" + ,"pm;" * "\x00B1" + ,"Poincareplane;" * "\x210C" + ,"pointint;" * "\x2A15" + ,"Popf;" * "\x2119" + ,"popf;" * "\x1D561" + ,"pound" * "\x00A3" + ,"pound;" * "\x00A3" + ,"pr;" * "\x227A" + ,"Pr;" * "\x2ABB" + ,"prap;" * "\x2AB7" + ,"prcue;" * "\x227C" + ,"pre;" * "\x2AAF" + ,"prE;" * "\x2AB3" + ,"prec;" * "\x227A" + ,"precapprox;" * "\x2AB7" + ,"preccurlyeq;" * "\x227C" + ,"Precedes;" * "\x227A" + ,"PrecedesEqual;" * "\x2AAF" + ,"PrecedesSlantEqual;" * "\x227C" + ,"PrecedesTilde;" * "\x227E" + ,"preceq;" * "\x2AAF" + ,"precnapprox;" * "\x2AB9" + ,"precneqq;" * "\x2AB5" + ,"precnsim;" * "\x22E8" + ,"precsim;" * "\x227E" + ,"prime;" * "\x2032" + ,"Prime;" * "\x2033" + ,"primes;" * "\x2119" + ,"prnap;" * "\x2AB9" + ,"prnE;" * "\x2AB5" + ,"prnsim;" * "\x22E8" + ,"prod;" * "\x220F" + ,"Product;" * "\x220F" + ,"profalar;" * "\x232E" + ,"profline;" * "\x2312" + ,"profsurf;" * "\x2313" + ,"prop;" * "\x221D" + ,"Proportion;" * "\x2237" + ,"Proportional;" * "\x221D" + ,"propto;" * "\x221D" + ,"prsim;" * "\x227E" + ,"prurel;" * "\x22B0" + ,"Pscr;" * "\x1D4AB" + ,"pscr;" * "\x1D4C5" + ,"Psi;" * "\x03A8" + ,"psi;" * "\x03C8" + ,"puncsp;" * "\x2008" + ,"Qfr;" * "\x1D514" + ,"qfr;" * "\x1D52E" + ,"qint;" * "\x2A0C" + ,"Qopf;" * "\x211A" + ,"qopf;" * "\x1D562" + ,"qprime;" * "\x2057" + ,"Qscr;" * "\x1D4AC" + ,"qscr;" * "\x1D4C6" + ,"quaternions;" * "\x210D" + ,"quatint;" * "\x2A16" + ,"quest;" * "\x003F" + ,"questeq;" * "\x225F" + ,"QUOT" * "\x0022" + ,"quot" * "\x0022" + ,"QUOT;" * "\x0022" + ,"quot;" * "\x0022" + ,"rAarr;" * "\x21DB" + ,"race;" * "\x223D\x0331" + ,"Racute;" * "\x0154" + ,"racute;" * "\x0155" + ,"radic;" * "\x221A" + ,"raemptyv;" * "\x29B3" + ,"rang;" * "\x27E9" + ,"Rang;" * "\x27EB" + ,"rangd;" * "\x2992" + ,"range;" * "\x29A5" + ,"rangle;" * "\x27E9" + ,"raquo" * "\x00BB" + ,"raquo;" * "\x00BB" + ,"rarr;" * "\x2192" + ,"Rarr;" * "\x21A0" + ,"rArr;" * "\x21D2" + ,"rarrap;" * "\x2975" + ,"rarrb;" * "\x21E5" + ,"rarrbfs;" * "\x2920" + ,"rarrc;" * "\x2933" + ,"rarrfs;" * "\x291E" + ,"rarrhk;" * "\x21AA" + ,"rarrlp;" * "\x21AC" + ,"rarrpl;" * "\x2945" + ,"rarrsim;" * "\x2974" + ,"rarrtl;" * "\x21A3" + ,"Rarrtl;" * "\x2916" + ,"rarrw;" * "\x219D" + ,"ratail;" * "\x291A" + ,"rAtail;" * "\x291C" + ,"ratio;" * "\x2236" + ,"rationals;" * "\x211A" + ,"rbarr;" * "\x290D" + ,"rBarr;" * "\x290F" + ,"RBarr;" * "\x2910" + ,"rbbrk;" * "\x2773" + ,"rbrace;" * "\x007D" + ,"rbrack;" * "\x005D" + ,"rbrke;" * "\x298C" + ,"rbrksld;" * "\x298E" + ,"rbrkslu;" * "\x2990" + ,"Rcaron;" * "\x0158" + ,"rcaron;" * "\x0159" + ,"Rcedil;" * "\x0156" + ,"rcedil;" * "\x0157" + ,"rceil;" * "\x2309" + ,"rcub;" * "\x007D" + ,"Rcy;" * "\x0420" + ,"rcy;" * "\x0440" + ,"rdca;" * "\x2937" + ,"rdldhar;" * "\x2969" + ,"rdquo;" * "\x201D" + ,"rdquor;" * "\x201D" + ,"rdsh;" * "\x21B3" + ,"Re;" * "\x211C" + ,"real;" * "\x211C" + ,"realine;" * "\x211B" + ,"realpart;" * "\x211C" + ,"reals;" * "\x211D" + ,"rect;" * "\x25AD" + ,"REG" * "\x00AE" + ,"reg" * "\x00AE" + ,"REG;" * "\x00AE" + ,"reg;" * "\x00AE" + ,"ReverseElement;" * "\x220B" + ,"ReverseEquilibrium;" * "\x21CB" + ,"ReverseUpEquilibrium;" * "\x296F" + ,"rfisht;" * "\x297D" + ,"rfloor;" * "\x230B" + ,"Rfr;" * "\x211C" + ,"rfr;" * "\x1D52F" + ,"rHar;" * "\x2964" + ,"rhard;" * "\x21C1" + ,"rharu;" * "\x21C0" + ,"rharul;" * "\x296C" + ,"Rho;" * "\x03A1" + ,"rho;" * "\x03C1" + ,"rhov;" * "\x03F1" + ,"RightAngleBracket;" * "\x27E9" + ,"RightArrow;" * "\x2192" + ,"rightarrow;" * "\x2192" + ,"Rightarrow;" * "\x21D2" + ,"RightArrowBar;" * "\x21E5" + ,"RightArrowLeftArrow;" * "\x21C4" + ,"rightarrowtail;" * "\x21A3" + ,"RightCeiling;" * "\x2309" + ,"RightDoubleBracket;" * "\x27E7" + ,"RightDownTeeVector;" * "\x295D" + ,"RightDownVector;" * "\x21C2" + ,"RightDownVectorBar;" * "\x2955" + ,"RightFloor;" * "\x230B" + ,"rightharpoondown;" * "\x21C1" + ,"rightharpoonup;" * "\x21C0" + ,"rightleftarrows;" * "\x21C4" + ,"rightleftharpoons;" * "\x21CC" + ,"rightrightarrows;" * "\x21C9" + ,"rightsquigarrow;" * "\x219D" + ,"RightTee;" * "\x22A2" + ,"RightTeeArrow;" * "\x21A6" + ,"RightTeeVector;" * "\x295B" + ,"rightthreetimes;" * "\x22CC" + ,"RightTriangle;" * "\x22B3" + ,"RightTriangleBar;" * "\x29D0" + ,"RightTriangleEqual;" * "\x22B5" + ,"RightUpDownVector;" * "\x294F" + ,"RightUpTeeVector;" * "\x295C" + ,"RightUpVector;" * "\x21BE" + ,"RightUpVectorBar;" * "\x2954" + ,"RightVector;" * "\x21C0" + ,"RightVectorBar;" * "\x2953" + ,"ring;" * "\x02DA" + ,"risingdotseq;" * "\x2253" + ,"rlarr;" * "\x21C4" + ,"rlhar;" * "\x21CC" + ,"rlm;" * "\x200F" + ,"rmoust;" * "\x23B1" + ,"rmoustache;" * "\x23B1" + ,"rnmid;" * "\x2AEE" + ,"roang;" * "\x27ED" + ,"roarr;" * "\x21FE" + ,"robrk;" * "\x27E7" + ,"ropar;" * "\x2986" + ,"Ropf;" * "\x211D" + ,"ropf;" * "\x1D563" + ,"roplus;" * "\x2A2E" + ,"rotimes;" * "\x2A35" + ,"RoundImplies;" * "\x2970" + ,"rpar;" * "\x0029" + ,"rpargt;" * "\x2994" + ,"rppolint;" * "\x2A12" + ,"rrarr;" * "\x21C9" + ,"Rrightarrow;" * "\x21DB" + ,"rsaquo;" * "\x203A" + ,"Rscr;" * "\x211B" + ,"rscr;" * "\x1D4C7" + ,"Rsh;" * "\x21B1" + ,"rsh;" * "\x21B1" + ,"rsqb;" * "\x005D" + ,"rsquo;" * "\x2019" + ,"rsquor;" * "\x2019" + ,"rthree;" * "\x22CC" + ,"rtimes;" * "\x22CA" + ,"rtri;" * "\x25B9" + ,"rtrie;" * "\x22B5" + ,"rtrif;" * "\x25B8" + ,"rtriltri;" * "\x29CE" + ,"RuleDelayed;" * "\x29F4" + ,"ruluhar;" * "\x2968" + ,"rx;" * "\x211E" + ,"Sacute;" * "\x015A" + ,"sacute;" * "\x015B" + ,"sbquo;" * "\x201A" + ,"sc;" * "\x227B" + ,"Sc;" * "\x2ABC" + ,"scap;" * "\x2AB8" + ,"Scaron;" * "\x0160" + ,"scaron;" * "\x0161" + ,"sccue;" * "\x227D" + ,"sce;" * "\x2AB0" + ,"scE;" * "\x2AB4" + ,"Scedil;" * "\x015E" + ,"scedil;" * "\x015F" + ,"Scirc;" * "\x015C" + ,"scirc;" * "\x015D" + ,"scnap;" * "\x2ABA" + ,"scnE;" * "\x2AB6" + ,"scnsim;" * "\x22E9" + ,"scpolint;" * "\x2A13" + ,"scsim;" * "\x227F" + ,"Scy;" * "\x0421" + ,"scy;" * "\x0441" + ,"sdot;" * "\x22C5" + ,"sdotb;" * "\x22A1" + ,"sdote;" * "\x2A66" + ,"searhk;" * "\x2925" + ,"searr;" * "\x2198" + ,"seArr;" * "\x21D8" + ,"searrow;" * "\x2198" + ,"sect" * "\x00A7" + ,"sect;" * "\x00A7" + ,"semi;" * "\x003B" + ,"seswar;" * "\x2929" + ,"setminus;" * "\x2216" + ,"setmn;" * "\x2216" + ,"sext;" * "\x2736" + ,"Sfr;" * "\x1D516" + ,"sfr;" * "\x1D530" + ,"sfrown;" * "\x2322" + ,"sharp;" * "\x266F" + ,"SHCHcy;" * "\x0429" + ,"shchcy;" * "\x0449" + ,"SHcy;" * "\x0428" + ,"shcy;" * "\x0448" + ,"ShortDownArrow;" * "\x2193" + ,"ShortLeftArrow;" * "\x2190" + ,"shortmid;" * "\x2223" + ,"shortparallel;" * "\x2225" + ,"ShortRightArrow;" * "\x2192" + ,"ShortUpArrow;" * "\x2191" + ,"shy" * "\x00AD" + ,"shy;" * "\x00AD" + ,"Sigma;" * "\x03A3" + ,"sigma;" * "\x03C3" + ,"sigmaf;" * "\x03C2" + ,"sigmav;" * "\x03C2" + ,"sim;" * "\x223C" + ,"simdot;" * "\x2A6A" + ,"sime;" * "\x2243" + ,"simeq;" * "\x2243" + ,"simg;" * "\x2A9E" + ,"simgE;" * "\x2AA0" + ,"siml;" * "\x2A9D" + ,"simlE;" * "\x2A9F" + ,"simne;" * "\x2246" + ,"simplus;" * "\x2A24" + ,"simrarr;" * "\x2972" + ,"slarr;" * "\x2190" + ,"SmallCircle;" * "\x2218" + ,"smallsetminus;" * "\x2216" + ,"smashp;" * "\x2A33" + ,"smeparsl;" * "\x29E4" + ,"smid;" * "\x2223" + ,"smile;" * "\x2323" + ,"smt;" * "\x2AAA" + ,"smte;" * "\x2AAC" + ,"smtes;" * "\x2AAC\xFE00" + ,"SOFTcy;" * "\x042C" + ,"softcy;" * "\x044C" + ,"sol;" * "\x002F" + ,"solb;" * "\x29C4" + ,"solbar;" * "\x233F" + ,"Sopf;" * "\x1D54A" + ,"sopf;" * "\x1D564" + ,"spades;" * "\x2660" + ,"spadesuit;" * "\x2660" + ,"spar;" * "\x2225" + ,"sqcap;" * "\x2293" + ,"sqcaps;" * "\x2293\xFE00" + ,"sqcup;" * "\x2294" + ,"sqcups;" * "\x2294\xFE00" + ,"Sqrt;" * "\x221A" + ,"sqsub;" * "\x228F" + ,"sqsube;" * "\x2291" + ,"sqsubset;" * "\x228F" + ,"sqsubseteq;" * "\x2291" + ,"sqsup;" * "\x2290" + ,"sqsupe;" * "\x2292" + ,"sqsupset;" * "\x2290" + ,"sqsupseteq;" * "\x2292" + ,"squ;" * "\x25A1" + ,"Square;" * "\x25A1" + ,"square;" * "\x25A1" + ,"SquareIntersection;" * "\x2293" + ,"SquareSubset;" * "\x228F" + ,"SquareSubsetEqual;" * "\x2291" + ,"SquareSuperset;" * "\x2290" + ,"SquareSupersetEqual;" * "\x2292" + ,"SquareUnion;" * "\x2294" + ,"squarf;" * "\x25AA" + ,"squf;" * "\x25AA" + ,"srarr;" * "\x2192" + ,"Sscr;" * "\x1D4AE" + ,"sscr;" * "\x1D4C8" + ,"ssetmn;" * "\x2216" + ,"ssmile;" * "\x2323" + ,"sstarf;" * "\x22C6" + ,"Star;" * "\x22C6" + ,"star;" * "\x2606" + ,"starf;" * "\x2605" + ,"straightepsilon;" * "\x03F5" + ,"straightphi;" * "\x03D5" + ,"strns;" * "\x00AF" + ,"sub;" * "\x2282" + ,"Sub;" * "\x22D0" + ,"subdot;" * "\x2ABD" + ,"sube;" * "\x2286" + ,"subE;" * "\x2AC5" + ,"subedot;" * "\x2AC3" + ,"submult;" * "\x2AC1" + ,"subne;" * "\x228A" + ,"subnE;" * "\x2ACB" + ,"subplus;" * "\x2ABF" + ,"subrarr;" * "\x2979" + ,"subset;" * "\x2282" + ,"Subset;" * "\x22D0" + ,"subseteq;" * "\x2286" + ,"subseteqq;" * "\x2AC5" + ,"SubsetEqual;" * "\x2286" + ,"subsetneq;" * "\x228A" + ,"subsetneqq;" * "\x2ACB" + ,"subsim;" * "\x2AC7" + ,"subsub;" * "\x2AD5" + ,"subsup;" * "\x2AD3" + ,"succ;" * "\x227B" + ,"succapprox;" * "\x2AB8" + ,"succcurlyeq;" * "\x227D" + ,"Succeeds;" * "\x227B" + ,"SucceedsEqual;" * "\x2AB0" + ,"SucceedsSlantEqual;" * "\x227D" + ,"SucceedsTilde;" * "\x227F" + ,"succeq;" * "\x2AB0" + ,"succnapprox;" * "\x2ABA" + ,"succneqq;" * "\x2AB6" + ,"succnsim;" * "\x22E9" + ,"succsim;" * "\x227F" + ,"SuchThat;" * "\x220B" + ,"Sum;" * "\x2211" + ,"sum;" * "\x2211" + ,"sung;" * "\x266A" + ,"sup1" * "\x00B9" + ,"sup1;" * "\x00B9" + ,"sup2" * "\x00B2" + ,"sup2;" * "\x00B2" + ,"sup3" * "\x00B3" + ,"sup3;" * "\x00B3" + ,"sup;" * "\x2283" + ,"Sup;" * "\x22D1" + ,"supdot;" * "\x2ABE" + ,"supdsub;" * "\x2AD8" + ,"supe;" * "\x2287" + ,"supE;" * "\x2AC6" + ,"supedot;" * "\x2AC4" + ,"Superset;" * "\x2283" + ,"SupersetEqual;" * "\x2287" + ,"suphsol;" * "\x27C9" + ,"suphsub;" * "\x2AD7" + ,"suplarr;" * "\x297B" + ,"supmult;" * "\x2AC2" + ,"supne;" * "\x228B" + ,"supnE;" * "\x2ACC" + ,"supplus;" * "\x2AC0" + ,"supset;" * "\x2283" + ,"Supset;" * "\x22D1" + ,"supseteq;" * "\x2287" + ,"supseteqq;" * "\x2AC6" + ,"supsetneq;" * "\x228B" + ,"supsetneqq;" * "\x2ACC" + ,"supsim;" * "\x2AC8" + ,"supsub;" * "\x2AD4" + ,"supsup;" * "\x2AD6" + ,"swarhk;" * "\x2926" + ,"swarr;" * "\x2199" + ,"swArr;" * "\x21D9" + ,"swarrow;" * "\x2199" + ,"swnwar;" * "\x292A" + ,"szlig" * "\x00DF" + ,"szlig;" * "\x00DF" + ,"Tab;" * "\x0009" + ,"target;" * "\x2316" + ,"Tau;" * "\x03A4" + ,"tau;" * "\x03C4" + ,"tbrk;" * "\x23B4" + ,"Tcaron;" * "\x0164" + ,"tcaron;" * "\x0165" + ,"Tcedil;" * "\x0162" + ,"tcedil;" * "\x0163" + ,"Tcy;" * "\x0422" + ,"tcy;" * "\x0442" + ,"tdot;" * "\x20DB" + ,"telrec;" * "\x2315" + ,"Tfr;" * "\x1D517" + ,"tfr;" * "\x1D531" + ,"there4;" * "\x2234" + ,"Therefore;" * "\x2234" + ,"therefore;" * "\x2234" + ,"Theta;" * "\x0398" + ,"theta;" * "\x03B8" + ,"thetasym;" * "\x03D1" + ,"thetav;" * "\x03D1" + ,"thickapprox;" * "\x2248" + ,"thicksim;" * "\x223C" + ,"ThickSpace;" * "\x205F\x200A" + ,"thinsp;" * "\x2009" + ,"ThinSpace;" * "\x2009" + ,"thkap;" * "\x2248" + ,"thksim;" * "\x223C" + ,"THORN" * "\x00DE" + ,"thorn" * "\x00FE" + ,"THORN;" * "\x00DE" + ,"thorn;" * "\x00FE" + ,"tilde;" * "\x02DC" + ,"Tilde;" * "\x223C" + ,"TildeEqual;" * "\x2243" + ,"TildeFullEqual;" * "\x2245" + ,"TildeTilde;" * "\x2248" + ,"times" * "\x00D7" + ,"times;" * "\x00D7" + ,"timesb;" * "\x22A0" + ,"timesbar;" * "\x2A31" + ,"timesd;" * "\x2A30" + ,"tint;" * "\x222D" + ,"toea;" * "\x2928" + ,"top;" * "\x22A4" + ,"topbot;" * "\x2336" + ,"topcir;" * "\x2AF1" + ,"Topf;" * "\x1D54B" + ,"topf;" * "\x1D565" + ,"topfork;" * "\x2ADA" + ,"tosa;" * "\x2929" + ,"tprime;" * "\x2034" + ,"TRADE;" * "\x2122" + ,"trade;" * "\x2122" + ,"triangle;" * "\x25B5" + ,"triangledown;" * "\x25BF" + ,"triangleleft;" * "\x25C3" + ,"trianglelefteq;" * "\x22B4" + ,"triangleq;" * "\x225C" + ,"triangleright;" * "\x25B9" + ,"trianglerighteq;" * "\x22B5" + ,"tridot;" * "\x25EC" + ,"trie;" * "\x225C" + ,"triminus;" * "\x2A3A" + ,"TripleDot;" * "\x20DB" + ,"triplus;" * "\x2A39" + ,"trisb;" * "\x29CD" + ,"tritime;" * "\x2A3B" + ,"trpezium;" * "\x23E2" + ,"Tscr;" * "\x1D4AF" + ,"tscr;" * "\x1D4C9" + ,"TScy;" * "\x0426" + ,"tscy;" * "\x0446" + ,"TSHcy;" * "\x040B" + ,"tshcy;" * "\x045B" + ,"Tstrok;" * "\x0166" + ,"tstrok;" * "\x0167" + ,"twixt;" * "\x226C" + ,"twoheadleftarrow;" * "\x219E" + ,"twoheadrightarrow;" * "\x21A0" + ,"Uacute" * "\x00DA" + ,"uacute" * "\x00FA" + ,"Uacute;" * "\x00DA" + ,"uacute;" * "\x00FA" + ,"uarr;" * "\x2191" + ,"Uarr;" * "\x219F" + ,"uArr;" * "\x21D1" + ,"Uarrocir;" * "\x2949" + ,"Ubrcy;" * "\x040E" + ,"ubrcy;" * "\x045E" + ,"Ubreve;" * "\x016C" + ,"ubreve;" * "\x016D" + ,"Ucirc" * "\x00DB" + ,"ucirc" * "\x00FB" + ,"Ucirc;" * "\x00DB" + ,"ucirc;" * "\x00FB" + ,"Ucy;" * "\x0423" + ,"ucy;" * "\x0443" + ,"udarr;" * "\x21C5" + ,"Udblac;" * "\x0170" + ,"udblac;" * "\x0171" + ,"udhar;" * "\x296E" + ,"ufisht;" * "\x297E" + ,"Ufr;" * "\x1D518" + ,"ufr;" * "\x1D532" + ,"Ugrave" * "\x00D9" + ,"ugrave" * "\x00F9" + ,"Ugrave;" * "\x00D9" + ,"ugrave;" * "\x00F9" + ,"uHar;" * "\x2963" + ,"uharl;" * "\x21BF" + ,"uharr;" * "\x21BE" + ,"uhblk;" * "\x2580" + ,"ulcorn;" * "\x231C" + ,"ulcorner;" * "\x231C" + ,"ulcrop;" * "\x230F" + ,"ultri;" * "\x25F8" + ,"Umacr;" * "\x016A" + ,"umacr;" * "\x016B" + ,"uml" * "\x00A8" + ,"uml;" * "\x00A8" + ,"UnderBar;" * "\x005F" + ,"UnderBrace;" * "\x23DF" + ,"UnderBracket;" * "\x23B5" + ,"UnderParenthesis;" * "\x23DD" + ,"Union;" * "\x22C3" + ,"UnionPlus;" * "\x228E" + ,"Uogon;" * "\x0172" + ,"uogon;" * "\x0173" + ,"Uopf;" * "\x1D54C" + ,"uopf;" * "\x1D566" + ,"UpArrow;" * "\x2191" + ,"uparrow;" * "\x2191" + ,"Uparrow;" * "\x21D1" + ,"UpArrowBar;" * "\x2912" + ,"UpArrowDownArrow;" * "\x21C5" + ,"UpDownArrow;" * "\x2195" + ,"updownarrow;" * "\x2195" + ,"Updownarrow;" * "\x21D5" + ,"UpEquilibrium;" * "\x296E" + ,"upharpoonleft;" * "\x21BF" + ,"upharpoonright;" * "\x21BE" + ,"uplus;" * "\x228E" + ,"UpperLeftArrow;" * "\x2196" + ,"UpperRightArrow;" * "\x2197" + ,"upsi;" * "\x03C5" + ,"Upsi;" * "\x03D2" + ,"upsih;" * "\x03D2" + ,"Upsilon;" * "\x03A5" + ,"upsilon;" * "\x03C5" + ,"UpTee;" * "\x22A5" + ,"UpTeeArrow;" * "\x21A5" + ,"upuparrows;" * "\x21C8" + ,"urcorn;" * "\x231D" + ,"urcorner;" * "\x231D" + ,"urcrop;" * "\x230E" + ,"Uring;" * "\x016E" + ,"uring;" * "\x016F" + ,"urtri;" * "\x25F9" + ,"Uscr;" * "\x1D4B0" + ,"uscr;" * "\x1D4CA" + ,"utdot;" * "\x22F0" + ,"Utilde;" * "\x0168" + ,"utilde;" * "\x0169" + ,"utri;" * "\x25B5" + ,"utrif;" * "\x25B4" + ,"uuarr;" * "\x21C8" + ,"Uuml" * "\x00DC" + ,"uuml" * "\x00FC" + ,"Uuml;" * "\x00DC" + ,"uuml;" * "\x00FC" + ,"uwangle;" * "\x29A7" + ,"vangrt;" * "\x299C" + ,"varepsilon;" * "\x03F5" + ,"varkappa;" * "\x03F0" + ,"varnothing;" * "\x2205" + ,"varphi;" * "\x03D5" + ,"varpi;" * "\x03D6" + ,"varpropto;" * "\x221D" + ,"varr;" * "\x2195" + ,"vArr;" * "\x21D5" + ,"varrho;" * "\x03F1" + ,"varsigma;" * "\x03C2" + ,"varsubsetneq;" * "\x228A\xFE00" + ,"varsubsetneqq;" * "\x2ACB\xFE00" + ,"varsupsetneq;" * "\x228B\xFE00" + ,"varsupsetneqq;" * "\x2ACC\xFE00" + ,"vartheta;" * "\x03D1" + ,"vartriangleleft;" * "\x22B2" + ,"vartriangleright;" * "\x22B3" + ,"vBar;" * "\x2AE8" + ,"Vbar;" * "\x2AEB" + ,"vBarv;" * "\x2AE9" + ,"Vcy;" * "\x0412" + ,"vcy;" * "\x0432" + ,"vdash;" * "\x22A2" + ,"vDash;" * "\x22A8" + ,"Vdash;" * "\x22A9" + ,"VDash;" * "\x22AB" + ,"Vdashl;" * "\x2AE6" + ,"vee;" * "\x2228" + ,"Vee;" * "\x22C1" + ,"veebar;" * "\x22BB" + ,"veeeq;" * "\x225A" + ,"vellip;" * "\x22EE" + ,"verbar;" * "\x007C" + ,"Verbar;" * "\x2016" + ,"vert;" * "\x007C" + ,"Vert;" * "\x2016" + ,"VerticalBar;" * "\x2223" + ,"VerticalLine;" * "\x007C" + ,"VerticalSeparator;" * "\x2758" + ,"VerticalTilde;" * "\x2240" + ,"VeryThinSpace;" * "\x200A" + ,"Vfr;" * "\x1D519" + ,"vfr;" * "\x1D533" + ,"vltri;" * "\x22B2" + ,"vnsub;" * "\x2282\x20D2" + ,"vnsup;" * "\x2283\x20D2" + ,"Vopf;" * "\x1D54D" + ,"vopf;" * "\x1D567" + ,"vprop;" * "\x221D" + ,"vrtri;" * "\x22B3" + ,"Vscr;" * "\x1D4B1" + ,"vscr;" * "\x1D4CB" + ,"vsubne;" * "\x228A\xFE00" + ,"vsubnE;" * "\x2ACB\xFE00" + ,"vsupne;" * "\x228B\xFE00" + ,"vsupnE;" * "\x2ACC\xFE00" + ,"Vvdash;" * "\x22AA" + ,"vzigzag;" * "\x299A" + ,"Wcirc;" * "\x0174" + ,"wcirc;" * "\x0175" + ,"wedbar;" * "\x2A5F" + ,"wedge;" * "\x2227" + ,"Wedge;" * "\x22C0" + ,"wedgeq;" * "\x2259" + ,"weierp;" * "\x2118" + ,"Wfr;" * "\x1D51A" + ,"wfr;" * "\x1D534" + ,"Wopf;" * "\x1D54E" + ,"wopf;" * "\x1D568" + ,"wp;" * "\x2118" + ,"wr;" * "\x2240" + ,"wreath;" * "\x2240" + ,"Wscr;" * "\x1D4B2" + ,"wscr;" * "\x1D4CC" + ,"xcap;" * "\x22C2" + ,"xcirc;" * "\x25EF" + ,"xcup;" * "\x22C3" + ,"xdtri;" * "\x25BD" + ,"Xfr;" * "\x1D51B" + ,"xfr;" * "\x1D535" + ,"xharr;" * "\x27F7" + ,"xhArr;" * "\x27FA" + ,"Xi;" * "\x039E" + ,"xi;" * "\x03BE" + ,"xlarr;" * "\x27F5" + ,"xlArr;" * "\x27F8" + ,"xmap;" * "\x27FC" + ,"xnis;" * "\x22FB" + ,"xodot;" * "\x2A00" + ,"Xopf;" * "\x1D54F" + ,"xopf;" * "\x1D569" + ,"xoplus;" * "\x2A01" + ,"xotime;" * "\x2A02" + ,"xrarr;" * "\x27F6" + ,"xrArr;" * "\x27F9" + ,"Xscr;" * "\x1D4B3" + ,"xscr;" * "\x1D4CD" + ,"xsqcup;" * "\x2A06" + ,"xuplus;" * "\x2A04" + ,"xutri;" * "\x25B3" + ,"xvee;" * "\x22C1" + ,"xwedge;" * "\x22C0" + ,"Yacute" * "\x00DD" + ,"yacute" * "\x00FD" + ,"Yacute;" * "\x00DD" + ,"yacute;" * "\x00FD" + ,"YAcy;" * "\x042F" + ,"yacy;" * "\x044F" + ,"Ycirc;" * "\x0176" + ,"ycirc;" * "\x0177" + ,"Ycy;" * "\x042B" + ,"ycy;" * "\x044B" + ,"yen" * "\x00A5" + ,"yen;" * "\x00A5" + ,"Yfr;" * "\x1D51C" + ,"yfr;" * "\x1D536" + ,"YIcy;" * "\x0407" + ,"yicy;" * "\x0457" + ,"Yopf;" * "\x1D550" + ,"yopf;" * "\x1D56A" + ,"Yscr;" * "\x1D4B4" + ,"yscr;" * "\x1D4CE" + ,"YUcy;" * "\x042E" + ,"yucy;" * "\x044E" + ,"yuml" * "\x00FF" + ,"yuml;" * "\x00FF" + ,"Yuml;" * "\x0178" + ,"Zacute;" * "\x0179" + ,"zacute;" * "\x017A" + ,"Zcaron;" * "\x017D" + ,"zcaron;" * "\x017E" + ,"Zcy;" * "\x0417" + ,"zcy;" * "\x0437" + ,"Zdot;" * "\x017B" + ,"zdot;" * "\x017C" + ,"zeetrf;" * "\x2128" + ,"ZeroWidthSpace;" * "\x200B" + ,"Zeta;" * "\x0396" + ,"zeta;" * "\x03B6" + ,"Zfr;" * "\x2128" + ,"zfr;" * "\x1D537" + ,"ZHcy;" * "\x0416" + ,"zhcy;" * "\x0436" + ,"zigrarr;" * "\x21DD" + ,"Zopf;" * "\x2124" + ,"zopf;" * "\x1D56B" + ,"Zscr;" * "\x1D4B5" + ,"zscr;" * "\x1D4CF" + ,"zwj;" * "\x200D" + ,"zwnj;" * "\x200C" + ] diff --git a/src/Text/HTML/TagSoup/Generated.hs b/src/Text/HTML/TagSoup/Generated.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Generated.hs @@ -0,0 +1,2 @@ +module Text.HTML.TagSoup.Generated(parseTagsOptions) where +import Text.HTML.TagSoup.Manual diff --git a/src/Text/HTML/TagSoup/Implementation.hs b/src/Text/HTML/TagSoup/Implementation.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Implementation.hs @@ -0,0 +1,193 @@ +{-# LANGUAGE RecordWildCards, PatternGuards, ScopedTypeVariables #-} + +module Text.HTML.TagSoup.Implementation where + +import Text.HTML.TagSoup.Type +import Text.HTML.TagSoup.Options +import Text.StringLike as Str +import Numeric (readHex) +import Data.Char (chr, ord) +import Data.Ix +import Control.Exception(assert) +import Control.Arrow + +--------------------------------------------------------------------- +-- BOTTOM LAYER + +data Out + = Char Char + | Tag -- < + | TagShut -- + | TagEndClose -- /> + | Comment -- + | EntityName -- & + | EntityNum -- &# + | EntityHex -- &#x + | EntityEnd Bool -- Attributed followed by ; for True, missing ; for False + | Warn String + | Pos Position + deriving (Show,Eq) + +errSeen x = Warn $ "Unexpected " ++ show x +errWant x = Warn $ "Expected " ++ show x + +data S = S + {s :: S + ,tl :: S + ,hd :: Char + ,eof :: Bool + ,next :: String -> Maybe S + ,pos :: [Out] -> [Out] + } + + +expand :: Position -> String -> S +expand p text = p `seq` res + where res = S{s = res + ,tl = expand (positionChar p (head text)) (tail text) + ,hd = if null text then '\0' else head text + ,eof = null text + ,next = next p text + ,pos = (Pos p:) + } + + next p (t:ext) (s:tr) | t == s = next (positionChar p t) ext tr + next p text [] = Just $ expand p text + next _ _ _ = Nothing + + +infixr & + +class Outable a where (&) :: a -> [Out] -> [Out] +instance Outable Char where (&) = ampChar +instance Outable Out where (&) = ampOut +ampChar x y = Char x : y +ampOut x y = x : y + + +state :: String -> S +state s = expand nullPosition s + +--------------------------------------------------------------------- +-- TOP LAYER + + +output :: forall str . StringLike str => ParseOptions str -> [Out] -> [Tag str] +output ParseOptions{..} x = (if optTagTextMerge then tagTextMerge else id) $ go ((nullPosition,[]),x) + where + -- main choice loop + go :: ((Position,[Tag str]),[Out]) -> [Tag str] + go ((p,ws),xs) | p `seq` False = [] -- otherwise p is a space leak when optTagPosition == False + go ((p,ws),xs) | not $ null ws = (if optTagWarning then (reverse ws++) else id) $ go ((p,[]),xs) + go ((p,ws),Pos p2:xs) = go ((p2,ws),xs) + + go x | isChar x = pos x $ TagText a : go y + where (y,a) = charsStr x + go x | isTag x = pos x $ TagOpen a b : (if isTagEndClose z then pos x $ TagClose a : go (next z) else go (skip isTagEnd z)) + where (y,a) = charsStr $ next x + (z,b) = atts y + go x | isTagShut x = pos x $ (TagClose a:) $ + (if not (null b) then warn x "Unexpected attributes in close tag" else id) $ + if isTagEndClose z then warn x "Unexpected self-closing in close tag" $ go (next z) else go (skip isTagEnd z) + where (y,a) = charsStr $ next x + (z,b) = atts y + go x | isComment x = pos x $ TagComment a : go (skip isCommentEnd y) + where (y,a) = charsStr $ next x + go x | isEntityName x = poss x ((if optTagWarning then id else filter (not . isTagWarning)) $ optEntityData (a, getEntityEnd y)) ++ go (skip isEntityEnd y) + where (y,a) = charsStr $ next x + go x | isEntityNumHex x = pos x $ TagText (fromChar $ entityChr x a) : go (skip isEntityEnd y) + where (y,a) = chars $ next x + go x | Just a <- fromWarn x = if optTagWarning then pos x $ TagWarning (fromString a) : go (next x) else go (next x) + go x | isEof x = [] + + atts :: ((Position,[Tag str]),[Out]) -> ( ((Position,[Tag str]),[Out]) , [(str,str)] ) + atts x | isAttName x = second ((a,b):) $ atts z + where (y,a) = charsStr (next x) + (z,b) = if isAttVal y then charsEntsStr (next y) else (y, empty) + atts x | isAttVal x = second ((empty,a):) $ atts y + where (y,a) = charsEntsStr (next x) + atts x = (x, []) + + -- chars + chars x = charss False x + charsStr x = (id *** fromString) $ chars x + charsEntsStr x = (id *** fromString) $ charss True x + + -- loop round collecting characters, if the b is set including entity + charss :: Bool -> ((Position,[Tag str]),[Out]) -> ( ((Position,[Tag str]),[Out]) , String) + charss t x | Just a <- fromChr x = (y, a:b) + where (y,b) = charss t (next x) + charss t x | t, isEntityName x = second (toString n ++) $ charss t $ addWarns m z + where (y,a) = charsStr $ next x + b = getEntityEnd y + z = skip isEntityEnd y + (n,m) = optEntityAttrib (a,b) + charss t x | t, isEntityNumHex x = second (entityChr x a:) $ charss t z + where (y,a) = chars $ next x + z = skip isEntityEnd y + charss t ((_,w),Pos p:xs) = charss t ((p,w),xs) + charss t x | Just a <- fromWarn x = charss t $ (if optTagWarning then addWarns [TagWarning $ fromString a] else id) $ next x + charss t x = (x, []) + + -- utility functions + next x = second (drop 1) x + skip f x = assert (isEof x || f x) (next x) + addWarns ws x@((p,w),y) = ((p, reverse (poss x ws) ++ w), y) + pos ((p,_),_) rest = if optTagPosition then tagPosition p : rest else rest + warn x s rest = if optTagWarning then pos x $ TagWarning (fromString s) : rest else rest + poss x = concatMap (\w -> pos x [w]) + + +entityChr x s | isEntityNum x = chr_ $ read s + | isEntityHex x = chr_ $ fst $ head $ readHex s + where chr_ x | inRange (toInteger $ ord minBound, toInteger $ ord maxBound) x = chr $ fromInteger x + | otherwise = '?' + + +isEof (_,[]) = True; isEof _ = False +isChar (_,Char{}:_) = True; isChar _ = False +isTag (_,Tag{}:_) = True; isTag _ = False +isTagShut (_,TagShut{}:_) = True; isTagShut _ = False +isAttName (_,AttName{}:_) = True; isAttName _ = False +isAttVal (_,AttVal{}:_) = True; isAttVal _ = False +isTagEnd (_,TagEnd{}:_) = True; isTagEnd _ = False +isTagEndClose (_,TagEndClose{}:_) = True; isTagEndClose _ = False +isComment (_,Comment{}:_) = True; isComment _ = False +isCommentEnd (_,CommentEnd{}:_) = True; isCommentEnd _ = False +isEntityName (_,EntityName{}:_) = True; isEntityName _ = False +isEntityNumHex (_,EntityNum{}:_) = True; isEntityNumHex (_,EntityHex{}:_) = True; isEntityNumHex _ = False +isEntityNum (_,EntityNum{}:_) = True; isEntityNum _ = False +isEntityHex (_,EntityHex{}:_) = True; isEntityHex _ = False +isEntityEnd (_,EntityEnd{}:_) = True; isEntityEnd _ = False +isWarn (_,Warn{}:_) = True; isWarn _ = False + +fromChr (_,Char x:_) = Just x ; fromChr _ = Nothing +fromWarn (_,Warn x:_) = Just x ; fromWarn _ = Nothing + +getEntityEnd (_,EntityEnd b:_) = b + + +-- Merge all adjacent TagText bits +tagTextMerge :: StringLike str => [Tag str] -> [Tag str] +tagTextMerge (TagText x:xs) = TagText (strConcat (x:a)) : tagTextMerge b + where + (a,b) = f xs + + -- additional brackets on 3 lines to work around HSE 1.3.2 bugs with pattern fixities + f (TagText x:xs) = (x:a,b) + where (a,b) = f xs + f (TagPosition{}:(x@TagText{}:xs)) = f $ x : xs + f x = g x id x + + g o op (p@TagPosition{}:(w@TagWarning{}:xs)) = g o (op . (p:) . (w:)) xs + g o op (w@TagWarning{}:xs) = g o (op . (w:)) xs + g o op (p@TagPosition{}:(x@TagText{}:xs)) = f $ p : x : op xs + g o op (x@TagText{}:xs) = f $ x : op xs + g o op _ = ([], o) + +tagTextMerge (x:xs) = x : tagTextMerge xs +tagTextMerge [] = [] diff --git a/src/Text/HTML/TagSoup/Manual.hs b/src/Text/HTML/TagSoup/Manual.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Manual.hs @@ -0,0 +1,13 @@ + +module Text.HTML.TagSoup.Manual(parseTagsOptions) where + +import Text.HTML.TagSoup.Specification +import Text.HTML.TagSoup.Implementation +import Text.HTML.TagSoup.Type +import Text.HTML.TagSoup.Options +import Text.StringLike + + +parseTagsOptions :: StringLike str => ParseOptions str -> str -> [Tag str] +parseTagsOptions opts = output opts . parse . toString + diff --git a/src/Text/HTML/TagSoup/Match.hs b/src/Text/HTML/TagSoup/Match.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Match.hs @@ -0,0 +1,198 @@ +-- | Combinators to match tags. Some people prefer to use @(~==)@ from +-- "Text.HTML.TagSoup", others prefer these more structured combinators. +-- Which you use is personal preference. +-- +-- The functions below offer maximum flexibility for matching tags. +-- Using 'tagOpen', for example, you can match all links or buttons that have the "btn" class. +-- +-- For simple uses cases—like matching all comment tags, or matching opening @\@ tags, +-- use the tag identification functions in "Text.HTML.TagSoup#tag-identification". +module Text.HTML.TagSoup.Match where + +import Text.HTML.TagSoup.Type (Tag(..), Attribute) +import Data.List (tails) + +-- * Matching Tags + +-- | Match an opening tag +-- +-- ==== __Examples__ +-- +-- /Matching an opening @\@ tag with a @"btn"@ class:/ +-- +-- >>> let tag = TagOpen "a" [("class", "btn")] +-- >>> tagOpen (== "a") (\attrs -> any (== ("class", "btn")) attrs) tag +-- True +tagOpen :: (str -> Bool) -> ([Attribute str] -> Bool) -> Tag str -> Bool +tagOpen pName pAttrs (TagOpen name attrs) = + pName name && pAttrs attrs +tagOpen _ _ _ = False + +-- | Match a closing tag +-- +-- ==== __Examples__ +-- +-- /Matching a closing @\<\/a>@ tag:/ +-- +-- >>> tagClose (== "a") (TagClose "a") +-- True +-- +-- >>> tagClose (== "a") (TagOpen "a" []) +-- False +tagClose :: (str -> Bool) -> Tag str -> Bool +tagClose pName (TagClose name) = pName name +tagClose _ _ = False + +-- | Match text tags +-- +-- ==== __Examples__ +-- +-- /Match all text tags:/ +-- +-- >>> let tags = parseTags "

    This is a paragraph

    " +-- [TagOpen "p" [],TagText "This is a paragraph",TagClose "p"] +-- >>> filter (tagText (const True)) tags +-- [TagText "This is a paragraph"] +tagText :: (str -> Bool) -> Tag str -> Bool +tagText p (TagText text) = p text +tagText _ _ = False + +-- | Match comment tags +-- +-- ==== __Examples__ +-- +-- /Matching comment tags that include an exclamation mark:/ +-- +-- >>> let tags = parseTags "" +-- [TagComment "This is a comment!"] +-- >>> all (tagComment (\s -> '!' `elem` s)) tags +-- True +tagComment :: (str -> Bool) -> Tag str -> Bool +tagComment p (TagComment text) = p text +tagComment _ _ = False + + +-- | Match an opening tag's name literally +-- +-- ==== __Examples__ +-- +-- /Matching @\    @ tags with the @id@ "foo":/ +-- +-- >>> let tag = TagOpen "a" [("id", "foo")] +-- TagOpen "a" [("id","foo")] +-- >>> tagOpenLit "a" (\attrs -> any (== ("id", "foo")) attrs) tag +-- True +-- +tagOpenLit :: Eq str => str -> ([Attribute str] -> Bool) -> Tag str -> Bool +tagOpenLit name = tagOpen (name==) + +-- | Match a closing tag's name literally +-- +-- ==== __Examples__ +-- +-- /Match a closing @\@ tag:/ +-- +-- >>> tagCloseLit "a" (TagClose "a") +-- True +-- +-- >>> tagCloseLit "a" (TagClose "em") +-- False +tagCloseLit :: Eq str => str -> Tag str -> Bool +tagCloseLit name = tagClose (name==) + +-- | Match an opening tag's name literally, and at least one of its attributes +-- +-- ==== __Examples__ +-- +-- /Matching a @\
    @ tag with the @id@ "foo":/ +-- +-- >>> tagOpenAttrLit "div" ("id", "foo") (TagOpen "div" [("id", "foo")]) +-- True +tagOpenAttrLit :: Eq str => str -> Attribute str -> Tag str -> Bool +tagOpenAttrLit name attr = + tagOpenLit name (anyAttrLit attr) + +{- | +Match a tag with given name, that contains an attribute +with given name, that satisfies a predicate. +If an attribute occurs multiple times, +all occurrences are checked. + +==== __Examples__ + +/Matching an @\@ tag with an ID that starts with "comment-":/ + +>>> let commentTag = TagOpen "a" [("id", "comment-45678")] +>>> tagOpenAttrNameLit "a" "id" (\idValue -> "comment-" `Data.List.isPrefixOf` idValue) commentTag +True +-} +tagOpenAttrNameLit :: Eq str => str -> str -> (str -> Bool) -> Tag str -> Bool +tagOpenAttrNameLit tagName attrName pAttrValue = + tagOpenLit tagName + (anyAttr (\(name,value) -> name==attrName && pAttrValue value)) + + +-- | Check if the 'Tag str' is 'TagOpen' and matches the given name +-- +-- ==== __Examples__ +-- +-- /Matching an @\@ tag:/ +-- +-- >>> tagOpenNameLit "a" (TagOpen "a" []) +-- True +-- +-- >>> tagOpenNameLit "a" (TagOpen "div" []) +-- False +tagOpenNameLit :: Eq str => str -> Tag str -> Bool +tagOpenNameLit name = tagOpenLit name (const True) + +-- | Check if the 'Tag str' is 'TagClose' and matches the given name +-- +-- ==== __Examples__ +-- +-- /Matching a closing @\<\/a>@ tag:/ +-- +-- >>> tagCloseNameLit "a" (TagClose "a") +-- True +-- +-- >>> tagCloseNameLit "a" (TagClose "div") +-- False +tagCloseNameLit :: Eq str => str -> Tag str -> Bool +tagCloseNameLit name = tagCloseLit name + + +-- * Matching attributes + +-- | Does any attribute name/value match the predicate. +anyAttr :: ((str,str) -> Bool) -> [Attribute str] -> Bool +anyAttr = any + +-- | Does any attribute name match the predicate. +anyAttrName :: (str -> Bool) -> [Attribute str] -> Bool +anyAttrName p = any (p . fst) + +-- | Does any attribute value match the predicate. +anyAttrValue :: (str -> Bool) -> [Attribute str] -> Bool +anyAttrValue p = any (p . snd) + + +-- | Does any attribute name/value match. +anyAttrLit :: Eq str => (str,str) -> [Attribute str] -> Bool +anyAttrLit attr = anyAttr (attr==) + +-- | Does any attribute name match. +anyAttrNameLit :: Eq str => str -> [Attribute str] -> Bool +anyAttrNameLit name = anyAttrName (name==) + +-- | Does any attribute value match. +anyAttrValueLit :: Eq str => str -> [Attribute str] -> Bool +anyAttrValueLit value = anyAttrValue (value==) + + + +-- | Get the tags under tags with a given name where the attributes match some predicate. +getTagContent :: Eq str => str -> ([Attribute str] -> Bool) -> [Tag str] -> [Tag str] +getTagContent name pAttrs = + takeWhile (not . tagCloseLit name) . drop 1 . + head . sections (tagOpenLit name pAttrs) + where sections p = filter (p . head) . init . tails diff --git a/src/Text/HTML/TagSoup/Options.hs b/src/Text/HTML/TagSoup/Options.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Options.hs @@ -0,0 +1,80 @@ +{-# LANGUAGE DeriveDataTypeable #-} + +module Text.HTML.TagSoup.Options where + +import Data.Typeable +import Text.HTML.TagSoup.Type +import Text.HTML.TagSoup.Entity +import Text.StringLike + + +-- | These options control how 'parseTags' works. The 'ParseOptions' type is usually generated by one of +-- 'parseOptions', 'parseOptionsFast' or 'parseOptionsEntities', then selected fields may be overriden. +-- +-- The options 'optTagPosition' and 'optTagWarning' specify whether to generate +-- 'TagPosition' or 'TagWarning' elements respectively. Usually these options should be set to @False@ +-- to simplify future stages, unless you rely on position information or want to give malformed HTML +-- messages to the end user. +-- +-- The options 'optEntityData' and 'optEntityAttrib' control how entities, for example @ @ are handled. +-- Both take a string, and a boolean, where @True@ indicates that the entity ended with a semi-colon @;@. +-- Inside normal text 'optEntityData' will be called, and the results will be inserted in the tag stream. +-- Inside a tag attribute 'optEntityAttrib' will be called, and the first component of the result will be used +-- in the attribute, and the second component will be appended after the 'TagOpen' value (usually the second +-- component is @[]@). As an example, to not decode any entities, pass: +-- +-- > parseOptions +-- > {optEntityData=\(str,b) -> [TagText $ "&" ++ str ++ [';' | b]] +-- > ,optEntityAttrib\(str,b) -> ("&" ++ str ++ [';' | b], []) + +-- The 'optTagTextMerge' value specifies if you always want adjacent 'TagText' values to be merged. +-- Merging adjacent pieces of text has a small performance penalty, but will usually make subsequent analysis +-- simpler. Contiguous runs of characters without entities or tags will also be generated as single 'TagText' +-- values. +data ParseOptions str = ParseOptions + {optTagPosition :: Bool -- ^ Should 'TagPosition' values be given before some items (default=False,fast=False). + ,optTagWarning :: Bool -- ^ Should 'TagWarning' values be given (default=False,fast=False) + ,optEntityData :: (str,Bool) -> [Tag str] -- ^ How to lookup an entity (Bool = has ending @';'@) + ,optEntityAttrib :: (str,Bool) -> (str,[Tag str]) -- ^ How to lookup an entity in an attribute (Bool = has ending @';'@?) + ,optTagTextMerge :: Bool -- ^ Require no adjacent 'TagText' values (default=True,fast=False) + } + deriving Typeable + + +-- | A 'ParseOptions' structure using a custom function to lookup attributes. Any attribute +-- that is not found will be left intact, and a 'TagWarning' given (if 'optTagWarning' is set). +-- +-- If you do not want to resolve any entities, simpliy pass @const Nothing@ for the lookup function. +parseOptionsEntities :: StringLike str => (str -> Maybe str) -> ParseOptions str +parseOptionsEntities lookupEntity = ParseOptions False False entityData entityAttrib True + where + entityData x = TagText a : b + where (a,b) = entityAttrib x + + entityAttrib ~(x,b) = + let x' = x `append` fromString [';'|b] + in case lookupEntity x' of + Just y -> (y, []) + Nothing -> (fromChar '&' `append` x' + ,[TagWarning $ fromString "Unknown entity: " `append` x]) + + +-- | The default parse options value, described in 'ParseOptions'. Equivalent to +-- @'parseOptionsEntities' 'lookupEntity'@. +parseOptions :: StringLike str => ParseOptions str +parseOptions = parseOptionsEntities $ fmap fromString . lookupEntity . toString + + +-- | A 'ParseOptions' structure optimised for speed, following the fast options. +parseOptionsFast :: StringLike str => ParseOptions str +parseOptionsFast = parseOptions{optTagTextMerge=False} + + +-- | Change the underlying string type of a 'ParseOptions' value. +fmapParseOptions :: (StringLike from, StringLike to) => ParseOptions from -> ParseOptions to +fmapParseOptions (ParseOptions a b c d e) = ParseOptions a b c2 d2 e + where + c2 ~(x,y) = map (fmap castString) $ c (castString x, y) + d2 ~(x,y) = (castString r, map (fmap castString) s) + where (r,s) = d (castString x, y) + diff --git a/src/Text/HTML/TagSoup/Parser.hs b/src/Text/HTML/TagSoup/Parser.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Parser.hs @@ -0,0 +1,25 @@ + +module Text.HTML.TagSoup.Parser( + parseTags, parseTagsOptions, + ParseOptions(..), parseOptions, parseOptionsFast, parseOptionsEntities + ) where + +import Text.HTML.TagSoup.Type +import Text.HTML.TagSoup.Options +import qualified Text.HTML.TagSoup.Generated as Gen + + +-- | Parse a string to a list of tags, using an HTML 5 compliant parser. +-- +-- > parseTags "my&" == [TagOpen "hello" [],TagText "my&",TagClose "world"] +parseTags :: StringLike str => str -> [Tag str] +parseTags = parseTagsOptions parseOptions + + +-- | Parse a string to a list of tags, using settings supplied by the 'ParseOptions' parameter, +-- eg. to output position information: +-- +-- > parseTagsOptions parseOptions{optTagPosition = True} "my&" == +-- > [TagPosition 1 1,TagOpen "hello" [],TagPosition 1 8,TagText "my&",TagPosition 1 15,TagClose "world"] +parseTagsOptions :: StringLike str => ParseOptions str -> str -> [Tag str] +parseTagsOptions = Gen.parseTagsOptions diff --git a/src/Text/HTML/TagSoup/Render.hs b/src/Text/HTML/TagSoup/Render.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Render.hs @@ -0,0 +1,80 @@ +{-# LANGUAGE PatternGuards, OverloadedStrings #-} +{-| + This module converts a list of 'Tag' back into a string. +-} + +module Text.HTML.TagSoup.Render + ( + renderTags, renderTagsOptions, escapeHTML, + RenderOptions(..), renderOptions + ) where + +import Text.HTML.TagSoup.Entity +import Text.HTML.TagSoup.Type +import Text.StringLike + + +-- | These options control how 'renderTags' works. +-- +-- The strange quirk of only minimizing @\@ tags is due to Internet Explorer treating +-- @\\<\/br\>@ as @\\@. +data RenderOptions str = RenderOptions + {optEscape :: str -> str -- ^ Escape a piece of text (default = escape the four characters @&\"\<\>@) + ,optMinimize :: str -> Bool -- ^ Minimise \\<\/b\> -> \ (default = minimise only @\@ tags) + ,optRawTag :: str -> Bool -- ^ Should a tag be output with no escaping (default = true only for @script@) + } + + +-- | Replace the four characters @&\"\<\>@ with their HTML entities ('escapeXML' lifted to 'StringLike'). +escapeHTML :: StringLike str => str -> str +escapeHTML = fromString . escapeXML . toString + +-- | The default render options value, described in 'RenderOptions'. +renderOptions :: StringLike str => RenderOptions str +renderOptions = RenderOptions escapeHTML (\x -> toString x == "br") (\x -> toString x == "script") + + +-- | Show a list of tags, as they might have been parsed, using the default settings given in +-- 'RenderOptions'. +-- +-- > renderTags [TagOpen "hello" [],TagText "my&",TagClose "world"] == "my&" +renderTags :: StringLike str => [Tag str] -> str +renderTags = renderTagsOptions renderOptions + + +-- | Show a list of tags using settings supplied by the 'RenderOptions' parameter, +-- eg. to avoid escaping any characters one could do: +-- +-- > renderTagsOptions renderOptions{optEscape = id} [TagText "my&"] == "my&" +renderTagsOptions :: StringLike str => RenderOptions str -> [Tag str] -> str +renderTagsOptions opts = strConcat . tags + where + ss x = [x] + + tags (TagOpen name atts:TagClose name2:xs) + | name == name2 && optMinimize opts name = open name atts " /" ++ tags xs + tags (TagOpen name atts:xs) + | Just ('?',_) <- uncons name = open name atts " ?" ++ tags xs + | optRawTag opts name = + let (a,b) = break (== TagClose name) (TagOpen name atts:xs) + in concatMap (\x -> case x of TagText s -> [s]; _ -> tag x) a ++ tags b + tags (x:xs) = tag x ++ tags xs + tags [] = [] + + tag (TagOpen name atts) = open name atts "" + tag (TagClose name) = [""] + tag (TagText text) = [txt text] + tag (TagComment text) = ss "" + tag _ = ss "" + + txt = optEscape opts + open name atts shut = ["<",name] ++ concatMap att atts ++ [shut,">"] + att ("","") = [" \"\""] + att (x ,"") = [" ", x] + att ("", y) = [" \"",txt y,"\""] + att (x , y) = [" ",x,"=\"",txt y,"\""] + + com xs | Just ('-',xs) <- uncons xs, Just ('-',xs) <- uncons xs, Just ('>',xs) <- uncons xs = "-- >" : com xs + com xs = case uncons xs of + Nothing -> [] + Just (x,xs) -> fromChar x : com xs diff --git a/src/Text/HTML/TagSoup/Specification.hs b/src/Text/HTML/TagSoup/Specification.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Specification.hs @@ -0,0 +1,332 @@ +{-# LANGUAGE RecordWildCards, PatternGuards #-} + +module Text.HTML.TagSoup.Specification(parse) where + +import Text.HTML.TagSoup.Implementation +import Data.Char (isAlpha, isAlphaNum, isDigit, toLower) + +-- We make some generalisations: +-- +-- +-- is a valid closing tag +-- is a valid closing tag +-- is a valid tag attibute in ! and ?, i.e missing an attribute name +-- We also don't do lowercase conversion +-- Entities are handled without a list of known entity names +-- We don't have RCData, CData or Escape modes (only effects dat and tagOpen) + + +data TypeTag = TypeNormal -- [Out] + +parse :: String -> [Out] +parse = dat . state + +-- 8.2.4.1 Data state +dat :: Parser +dat S{..} = pos $ case hd of + '&' -> charReference tl + '<' -> tagOpen tl + _ | eof -> [] + _ -> hd & dat tl + + +-- 8.2.4.2 Character reference data state +charReference s = charRef dat False Nothing s + + +-- 8.2.4.3 Tag open state +tagOpen S{..} = case hd of + '!' -> markupDeclOpen tl + '/' -> closeTagOpen tl + _ | isAlpha hd -> Tag & hd & tagName (if isScript s then TypeScript else TypeNormal) tl + '>' -> errSeen "<>" & '<' & '>' & dat tl + '?' -> neilXmlTagOpen tl -- NEIL + _ -> errSeen "<" & '<' & dat s + +isScript = f "script" + where + f (c:cs) S{..} = toLower hd == c && f cs tl + f [] S{..} = white hd || hd == '/' || hd == '>' || hd == '?' || eof + + +-- seen " Tag & '?' & hd & tagName TypeXml tl + _ -> errSeen "" +neilXmlTagClose S{..} = pos $ case hd of + '>' -> TagEnd & dat tl + _ -> errSeen "?" & beforeAttName TypeXml s + + +-- just seen ">" at the end, am given tl +neilTagEnd typ S{..} + | typ == TypeXml = pos $ errWant "?>" & TagEnd & dat s + | typ == TypeScript = pos $ TagEnd & neilScriptBody s + | otherwise = pos $ TagEnd & dat s + +-- Inside a we output to the text +-- Deviation: is a closing tag, not a bogus comment +closeTagOpen S{..} = case hd of + _ | isAlpha hd || hd `elem` "?!" -> TagShut & hd & tagName TypeNormal tl + '>' -> errSeen "" & '<' & '/' & '>' & dat tl + _ | eof -> '<' & '/' & dat s + _ -> errWant "tag name" & bogusComment s + + +-- 8.2.4.5 Tag name state +tagName typ S{..} = pos $ case hd of + _ | white hd -> beforeAttName typ tl + '/' -> selfClosingStartTag typ tl + '>' -> neilTagEnd typ tl + '?' | typ == TypeXml -> neilXmlTagClose tl + _ | isAlpha hd -> hd & tagName typ tl + _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s + _ -> hd & tagName typ tl + + +-- 8.2.4.6 Before attribute name state +beforeAttName typ S{..} = pos $ case hd of + _ | white hd -> beforeAttName typ tl + '/' -> selfClosingStartTag typ tl + '>' -> neilTagEnd typ tl + '?' | typ == TypeXml -> neilXmlTagClose tl + _ | typ /= TypeNormal && hd `elem` "\'\"" -> beforeAttValue typ s -- NEIL + _ | hd `elem` "\"'<=" -> errSeen [hd] & AttName & hd & attName typ tl + _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s + _ -> AttName & hd & attName typ tl + + +-- 8.2.4.7 Attribute name state +attName typ S{..} = pos $ case hd of + _ | white hd -> afterAttName typ tl + '/' -> selfClosingStartTag typ tl + '=' -> beforeAttValue typ tl + '>' -> neilTagEnd typ tl + '?' | typ == TypeXml -> neilXmlTagClose tl + _ | hd `elem` "\"'<" -> errSeen [hd] & def + _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s + _ -> def + where def = hd & attName typ tl + + +-- 8.2.4.8 After attribute name state +afterAttName typ S{..} = pos $ case hd of + _ | white hd -> afterAttName typ tl + '/' -> selfClosingStartTag typ tl + '=' -> beforeAttValue typ tl + '>' -> neilTagEnd typ tl + '?' | typ == TypeXml -> neilXmlTagClose tl + _ | typ /= TypeNormal && hd `elem` "\"'" -> AttVal & beforeAttValue typ s -- NEIL + _ | hd `elem` "\"'<" -> errSeen [hd] & def + _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s + _ -> def + where def = AttName & hd & attName typ tl + +-- 8.2.4.9 Before attribute value state +beforeAttValue typ S{..} = pos $ case hd of + _ | white hd -> beforeAttValue typ tl + '\"' -> AttVal & attValueDQuoted typ tl + '&' -> AttVal & attValueUnquoted typ s + '\'' -> AttVal & attValueSQuoted typ tl + '>' -> errSeen "=" & neilTagEnd typ tl + '?' | typ == TypeXml -> neilXmlTagClose tl + _ | hd `elem` "<=" -> errSeen [hd] & def + _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s + _ -> def + where def = AttVal & hd & attValueUnquoted typ tl + + +-- 8.2.4.10 Attribute value (double-quoted) state +attValueDQuoted typ S{..} = pos $ case hd of + '\"' -> afterAttValueQuoted typ tl + '&' -> charRefAttValue (attValueDQuoted typ) (Just '\"') tl + _ | eof -> errWant "\"" & dat s + _ -> hd & attValueDQuoted typ tl + + +-- 8.2.4.11 Attribute value (single-quoted) state +attValueSQuoted typ S{..} = pos $ case hd of + '\'' -> afterAttValueQuoted typ tl + '&' -> charRefAttValue (attValueSQuoted typ) (Just '\'') tl + _ | eof -> errWant "\'" & dat s + _ -> hd & attValueSQuoted typ tl + + +-- 8.2.4.12 Attribute value (unquoted) state +attValueUnquoted typ S{..} = pos $ case hd of + _ | white hd -> beforeAttName typ tl + '&' -> charRefAttValue (attValueUnquoted typ) Nothing tl + '>' -> neilTagEnd typ tl + '?' | typ == TypeXml -> neilXmlTagClose tl + _ | hd `elem` "\"'<=" -> errSeen [hd] & def + _ | eof -> errWant (if typ == TypeXml then "?>" else ">") & dat s + _ -> def + where def = hd & attValueUnquoted typ tl + + +-- 8.2.4.13 Character reference in attribute value state +charRefAttValue :: Parser -> Maybe Char -> Parser +charRefAttValue resume c s = charRef resume True c s + + +-- 8.2.4.14 After attribute value (quoted) state +afterAttValueQuoted typ S{..} = pos $ case hd of + _ | white hd -> beforeAttName typ tl + '/' -> selfClosingStartTag typ tl + '>' -> neilTagEnd typ tl + '?' | typ == TypeXml -> neilXmlTagClose tl + _ | eof -> dat s + _ -> errSeen [hd] & beforeAttName typ s + + +-- 8.2.4.15 Self-closing start tag state +selfClosingStartTag typ S{..} = pos $ case hd of + _ | typ == TypeXml -> errSeen "/" & beforeAttName typ s + '>' -> TagEndClose & dat tl + _ | eof -> errWant ">" & dat s + _ -> errSeen "/" & beforeAttName typ s + + +-- 8.2.4.16 Bogus comment state +bogusComment S{..} = Comment & bogusComment1 s +bogusComment1 S{..} = pos $ case hd of + '>' -> CommentEnd & dat tl + _ | eof -> CommentEnd & dat s + _ -> hd & bogusComment1 tl + + +-- 8.2.4.17 Markup declaration open state +markupDeclOpen S{..} = pos $ case hd of + _ | Just s <- next "--" -> Comment & commentStart s + _ | isAlpha hd -> Tag & '!' & hd & tagName TypeDecl tl -- NEIL + _ | Just s <- next "[CDATA[" -> cdataSection s + _ -> errWant "tag name" & bogusComment s + + +-- 8.2.4.18 Comment start state +commentStart S{..} = pos $ case hd of + '-' -> commentStartDash tl + '>' -> errSeen "" & CommentEnd & dat tl + _ | eof -> errWant "-->" & CommentEnd & dat s + _ -> hd & comment tl + + +-- 8.2.4.19 Comment start dash state +commentStartDash S{..} = pos $ case hd of + '-' -> commentEnd tl + '>' -> errSeen "" & CommentEnd & dat tl + _ | eof -> errWant "-->" & CommentEnd & dat s + _ -> '-' & hd & comment tl + + +-- 8.2.4.20 Comment state +comment S{..} = pos $ case hd of + '-' -> commentEndDash tl + _ | eof -> errWant "-->" & CommentEnd & dat s + _ -> hd & comment tl + + +-- 8.2.4.21 Comment end dash state +commentEndDash S{..} = pos $ case hd of + '-' -> commentEnd tl + _ | eof -> errWant "-->" & CommentEnd & dat s + _ -> '-' & hd & comment tl + + +-- 8.2.4.22 Comment end state +commentEnd S{..} = pos $ case hd of + '>' -> CommentEnd & dat tl + '-' -> errWant "-->" & '-' & commentEnd tl + _ | white hd -> errSeen "--" & '-' & '-' & hd & commentEndSpace tl + '!' -> errSeen "!" & commentEndBang tl + _ | eof -> errWant "-->" & CommentEnd & dat s + _ -> errSeen "--" & '-' & '-' & hd & comment tl + + +-- 8.2.4.23 Comment end bang state +commentEndBang S{..} = pos $ case hd of + '>' -> CommentEnd & dat tl + '-' -> '-' & '-' & '!' & commentEndDash tl + _ | eof -> errWant "-->" & CommentEnd & dat s + _ -> '-' & '-' & '!' & hd & comment tl + + +-- 8.2.4.24 Comment end space state +commentEndSpace S{..} = pos $ case hd of + '>' -> CommentEnd & dat tl + '-' -> commentEndDash tl + _ | white hd -> hd & commentEndSpace tl + _ | eof -> errWant "-->" & CommentEnd & dat s + _ -> hd & comment tl + + +-- 8.2.4.38 CDATA section state +cdataSection S{..} = pos $ case hd of + _ | Just s <- next "]]>" -> dat s + _ | eof -> dat s + _ | otherwise -> hd & cdataSection tl + + +-- 8.2.4.39 Tokenizing character references +-- Change from spec: this is reponsible for writing '&' if nothing is to be written +charRef :: Parser -> Bool -> Maybe Char -> S -> [Out] +charRef resume att end S{..} = case hd of + _ | eof || hd `elem` "\t\n\f <&" || maybe False (== hd) end -> '&' & resume s + '#' -> charRefNum resume s tl + _ -> charRefAlpha resume att s + +charRefNum resume o S{..} = case hd of + _ | hd `elem` "xX" -> charRefNum2 resume o True tl + _ -> charRefNum2 resume o False s + +charRefNum2 resume o hex S{..} = case hd of + _ | hexChar hex hd -> (if hex then EntityHex else EntityNum) & hd & charRefNum3 resume hex tl + _ -> errSeen "&" & '&' & resume o + +charRefNum3 resume hex S{..} = case hd of + _ | hexChar hex hd -> hd & charRefNum3 resume hex tl + ';' -> EntityEnd True & resume tl + _ -> EntityEnd False & errWant ";" & resume s + +charRefAlpha resume att S{..} = case hd of + _ | isAlpha hd -> EntityName & hd & charRefAlpha2 resume att tl + _ -> errSeen "&" & '&' & resume s + +charRefAlpha2 resume att S{..} = case hd of + _ | alphaChar hd -> hd & charRefAlpha2 resume att tl + ';' -> EntityEnd True & resume tl + _ | att -> EntityEnd False & resume s + _ -> EntityEnd False & errWant ";" & resume s + + +alphaChar x = isAlphaNum x || x `elem` ":-_" + +hexChar False x = isDigit x +hexChar True x = isDigit x || (x >= 'a' && x <= 'f') || (x >= 'A' && x <= 'F') diff --git a/src/Text/HTML/TagSoup/Tree.hs b/src/Text/HTML/TagSoup/Tree.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Tree.hs @@ -0,0 +1,118 @@ +{-| + /NOTE/: This module is preliminary and may change at a future date. + + This module is intended to help converting a list of tags into a + tree of tags. +-} + +module Text.HTML.TagSoup.Tree + ( + TagTree(..), tagTree, parseTree, parseTreeOptions, ParseOptions(..), + flattenTree, renderTree, renderTreeOptions, RenderOptions(..), transformTree, universeTree + ) where + +import Text.HTML.TagSoup (parseTags, parseTagsOptions, renderTags, renderTagsOptions, ParseOptions(..), RenderOptions(..)) +import Text.HTML.TagSoup.Type +import Control.Arrow +import GHC.Exts (build) + + +-- | A tree of 'Tag' values. +data TagTree str + = -- | A 'TagOpen'/'TagClose' pair with the 'Tag' values in between. + TagBranch str [Attribute str] [TagTree str] + | -- | Any leaf node + TagLeaf (Tag str) + deriving (Eq,Ord,Show) + +instance Functor TagTree where + fmap f (TagBranch x y z) = TagBranch (f x) (map (f***f) y) (map (fmap f) z) + fmap f (TagLeaf x) = TagLeaf (fmap f x) + + +-- | Convert a list of tags into a tree. This version is not lazy at +-- all, that is saved for version 2. +tagTree :: Eq str => [Tag str] -> [TagTree str] +tagTree = g + where + g :: Eq str => [Tag str] -> [TagTree str] + g [] = [] + g xs = a ++ map TagLeaf (take 1 b) ++ g (drop 1 b) + where (a,b) = f xs + + -- the second tuple is either null or starts with a close + f :: Eq str => [Tag str] -> ([TagTree str],[Tag str]) + f (TagOpen name atts:rest) = + case f rest of + (inner,[]) -> (TagLeaf (TagOpen name atts):inner, []) + (inner,TagClose x:xs) + | x == name -> let (a,b) = f xs in (TagBranch name atts inner:a, b) + | otherwise -> (TagLeaf (TagOpen name atts):inner, TagClose x:xs) + _ -> error "TagSoup.Tree.tagTree: safe as - forall x . isTagClose (snd (f x))" + + f (TagClose x:xs) = ([], TagClose x:xs) + f (x:xs) = (TagLeaf x:a,b) + where (a,b) = f xs + f [] = ([], []) + +-- | Build a 'TagTree' from a string. +parseTree :: StringLike str => str -> [TagTree str] +parseTree = tagTree . parseTags + +-- | Build a 'TagTree' from a string, specifying the 'ParseOptions'. +parseTreeOptions :: StringLike str => ParseOptions str -> str -> [TagTree str] +parseTreeOptions opts str = tagTree $ parseTagsOptions opts str + +-- | Flatten a 'TagTree' back to a list of 'Tag'. +flattenTree :: [TagTree str] -> [Tag str] +flattenTree xs = build $ flattenTreeFB xs + +flattenTreeFB :: [TagTree str] -> (Tag str -> lst -> lst) -> lst -> lst +flattenTreeFB xs cons nil = flattenTreeOnto xs nil + where + flattenTreeOnto [] tags = tags + flattenTreeOnto (TagBranch name atts inner:trs) tags = + TagOpen name atts `cons` flattenTreeOnto inner (TagClose name `cons` flattenTreeOnto trs tags) + flattenTreeOnto (TagLeaf x:trs) tags = x `cons` flattenTreeOnto trs tags + +-- | Render a 'TagTree'. +renderTree :: StringLike str => [TagTree str] -> str +renderTree = renderTags . flattenTree + +-- | Render a 'TagTree' with some 'RenderOptions'. +renderTreeOptions :: StringLike str => RenderOptions str -> [TagTree str] -> str +renderTreeOptions opts trees = renderTagsOptions opts $ flattenTree trees + +-- | This operation is based on the Uniplate @universe@ function. Given a +-- list of trees, it returns those trees, and all the children trees at +-- any level. For example: +-- +-- > universeTree +-- > [TagBranch "a" [("href","url")] [TagBranch "b" [] [TagLeaf (TagText "text")]]] +-- > == [TagBranch "a" [("href","url")] [TagBranch "b" [] [TagLeaf (TagText "text")]]] +-- > ,TagBranch "b" [] [TagLeaf (TagText "text")]] +-- +-- This operation is particularly useful for queries. To collect all @\"a\"@ +-- tags in a tree, simply do: +-- +-- > [x | x@(TagBranch "a" _ _) <- universeTree tree] +universeTree :: [TagTree str] -> [TagTree str] +universeTree = concatMap f + where + f t@(TagBranch _ _ inner) = t : universeTree inner + f x = [x] + + +-- | This operation is based on the Uniplate @transform@ function. Given a +-- list of trees, it applies the function to every tree in a bottom-up +-- manner. This operation is useful for manipulating a tree - for example +-- to make all tag names upper case: +-- +-- > upperCase = transformTree f +-- > where f (TagBranch name atts inner) = [TagBranch (map toUpper name) atts inner] +-- > f x = [x] +transformTree :: (TagTree str -> [TagTree str]) -> [TagTree str] -> [TagTree str] +transformTree act = concatMap f + where + f (TagBranch a b inner) = act $ TagBranch a b (transformTree act inner) + f x = act x diff --git a/src/Text/HTML/TagSoup/Type.hs b/src/Text/HTML/TagSoup/Type.hs new file mode 100644 --- /dev/null +++ b/src/Text/HTML/TagSoup/Type.hs @@ -0,0 +1,142 @@ +{-# LANGUAGE DeriveDataTypeable #-} +-- | The central type in TagSoup + +module Text.HTML.TagSoup.Type( + -- * Data structures and parsing + StringLike, Tag(..), Attribute, Row, Column, + + -- * Position manipulation + Position(..), tagPosition, nullPosition, positionChar, positionString, + + -- * Tag identification + isTagOpen, isTagClose, isTagText, isTagWarning, isTagPosition, + isTagOpenName, isTagCloseName, isTagComment, + + -- * Extraction + fromTagText, fromAttrib, + maybeTagText, maybeTagWarning, + innerText, + ) where + + +import Data.List (foldl') +import Data.Maybe (fromMaybe, mapMaybe) +import Text.StringLike +import Data.Data(Data, Typeable) + +-- | An HTML attribute @id=\"name\"@ generates @(\"id\",\"name\")@ +type Attribute str = (str,str) + +-- | The row/line of a position, starting at 1 +type Row = Int + +-- | The column of a position, starting at 1 +type Column = Int + + +--- All positions are stored as a row and a column, with (1,1) being the +--- top-left position +data Position = Position !Row !Column deriving (Show,Eq,Ord) + +nullPosition :: Position +nullPosition = Position 1 1 + +positionString :: Position -> String -> Position +positionString = foldl' positionChar + +positionChar :: Position -> Char -> Position +positionChar (Position r c) x = case x of + '\n' -> Position (r+1) 1 + '\t' -> Position r (c + 8 - mod (c-1) 8) + _ -> Position r (c+1) + +tagPosition :: Position -> Tag str +tagPosition (Position r c) = TagPosition r c + + +-- | A single HTML element. A whole document is represented by a list of @Tag@. +-- There is no requirement for 'TagOpen' and 'TagClose' to match. +data Tag str = + TagOpen str [Attribute str] -- ^ An open tag with 'Attribute's in their original order + | TagClose str -- ^ A closing tag + | TagText str -- ^ A text node, guaranteed not to be the empty string + | TagComment str -- ^ A comment + | TagWarning str -- ^ Meta: A syntax error in the input file + | TagPosition !Row !Column -- ^ Meta: The position of a parsed element + deriving (Show, Eq, Ord, Data, Typeable) + +instance Functor Tag where + fmap f (TagOpen x y) = TagOpen (f x) [(f a, f b) | (a,b) <- y] + fmap f (TagClose x) = TagClose (f x) + fmap f (TagText x) = TagText (f x) + fmap f (TagComment x) = TagComment (f x) + fmap f (TagWarning x) = TagWarning (f x) + fmap f (TagPosition x y) = TagPosition x y + + +-- | Test if a 'Tag' is a 'TagOpen' +isTagOpen :: Tag str -> Bool +isTagOpen (TagOpen {}) = True; isTagOpen _ = False + +-- | Test if a 'Tag' is a 'TagClose' +isTagClose :: Tag str -> Bool +isTagClose (TagClose {}) = True; isTagClose _ = False + +-- | Test if a 'Tag' is a 'TagText' +isTagText :: Tag str -> Bool +isTagText (TagText {}) = True; isTagText _ = False + +-- | Extract the string from within 'TagText', otherwise 'Nothing' +maybeTagText :: Tag str -> Maybe str +maybeTagText (TagText x) = Just x +maybeTagText _ = Nothing + +-- | Extract the string from within 'TagText', crashes if not a 'TagText' +fromTagText :: Show str => Tag str -> str +fromTagText (TagText x) = x +fromTagText x = error $ "(" ++ show x ++ ") is not a TagText" + +-- | Extract all text content from tags (similar to Verbatim found in HaXml) +innerText :: StringLike str => [Tag str] -> str +innerText = strConcat . mapMaybe maybeTagText + +-- | Test if a 'Tag' is a 'TagWarning' +isTagWarning :: Tag str -> Bool +isTagWarning (TagWarning {}) = True; isTagWarning _ = False + +-- | Extract the string from within 'TagWarning', otherwise 'Nothing' +maybeTagWarning :: Tag str -> Maybe str +maybeTagWarning (TagWarning x) = Just x +maybeTagWarning _ = Nothing + +-- | Test if a 'Tag' is a 'TagPosition' +isTagPosition :: Tag str -> Bool +isTagPosition TagPosition{} = True; isTagPosition _ = False + +-- | Extract an attribute, crashes if not a 'TagOpen'. +-- Returns @\"\"@ if no attribute present. +-- +-- Warning: does not distinquish between missing attribute +-- and present attribute with value @\"\"@. +fromAttrib :: (Show str, Eq str, StringLike str) => str -> Tag str -> str +fromAttrib att tag = fromMaybe empty $ maybeAttrib att tag + +-- | Extract an attribute, crashes if not a 'TagOpen'. +-- Returns @Nothing@ if no attribute present. +maybeAttrib :: (Show str, Eq str) => str -> Tag str -> Maybe str +maybeAttrib att (TagOpen _ atts) = lookup att atts +maybeAttrib _ x = error ("(" ++ show x ++ ") is not a TagOpen") + +-- | Returns True if the 'Tag' is 'TagOpen' and matches the given name +isTagOpenName :: Eq str => str -> Tag str -> Bool +isTagOpenName name (TagOpen n _) = n == name +isTagOpenName _ _ = False + +-- | Returns True if the 'Tag' is 'TagClose' and matches the given name +isTagCloseName :: Eq str => str -> Tag str -> Bool +isTagCloseName name (TagClose n) = n == name +isTagCloseName _ _ = False + +-- | Test if a 'Tag' is a 'TagComment' +isTagComment :: Tag str -> Bool +isTagComment TagComment {} = True; isTagComment _ = False diff --git a/src/Text/StringLike.hs b/src/Text/StringLike.hs new file mode 100644 --- /dev/null +++ b/src/Text/StringLike.hs @@ -0,0 +1,96 @@ +{-# LANGUAGE TypeSynonymInstances, FlexibleInstances #-} + +-- | /WARNING/: This module is /not/ intended for use outside the TagSoup library. +-- +-- This module provides an abstraction for String's as used inside TagSoup. It allows +-- TagSoup to work with String (list of Char), ByteString.Char8, ByteString.Lazy.Char8, +-- Data.Text and Data.Text.Lazy. +module Text.StringLike (StringLike(..), fromString, castString) where + +import Data.String +import Data.Typeable + +import qualified Data.ByteString.Char8 as BS +import qualified Data.ByteString.Lazy.Char8 as LBS +import qualified Data.Text as T +import qualified Data.Text.Lazy as LT + + +-- | A class to generalise TagSoup parsing over many types of string-like types. +-- Examples are given for the String type. +class (Typeable a, Eq a, IsString a) => StringLike a where + -- | > empty = "" + empty :: a + -- | > cons = (:) + cons :: Char -> a -> a + -- | > uncons [] = Nothing + -- > uncons (x:xs) = Just (x, xs) + uncons :: a -> Maybe (Char, a) + + -- | > toString = id + toString :: a -> String + -- | > fromChar = return + fromChar :: Char -> a + -- | > strConcat = concat + strConcat :: [a] -> a + -- | > strNull = null + strNull :: a -> Bool + -- | > append = (++) + append :: a -> a -> a + + +-- | Convert a String from one type to another. +castString :: (StringLike a, StringLike b) => a -> b +castString = fromString . toString + + +instance StringLike String where + uncons [] = Nothing + uncons (x:xs) = Just (x, xs) + toString = id + fromChar = (:[]) + strConcat = concat + empty = [] + strNull = null + cons c = (c:) + append = (++) + +instance StringLike BS.ByteString where + uncons = BS.uncons + toString = BS.unpack + fromChar = BS.singleton + strConcat = BS.concat + empty = BS.empty + strNull = BS.null + cons = BS.cons + append = BS.append + +instance StringLike LBS.ByteString where + uncons = LBS.uncons + toString = LBS.unpack + fromChar = LBS.singleton + strConcat = LBS.concat + empty = LBS.empty + strNull = LBS.null + cons = LBS.cons + append = LBS.append + +instance StringLike T.Text where + uncons = T.uncons + toString = T.unpack + fromChar = T.singleton + strConcat = T.concat + empty = T.empty + strNull = T.null + cons = T.cons + append = T.append + +instance StringLike LT.Text where + uncons = LT.uncons + toString = LT.unpack + fromChar = LT.singleton + strConcat = LT.concat + empty = LT.empty + strNull = LT.null + cons = LT.cons + append = LT.append diff --git a/tagsoup.cabal b/tagsoup.cabal --- a/tagsoup.cabal +++ b/tagsoup.cabal @@ -1,6 +1,6 @@ cabal-version: >= 1.18 name: tagsoup -version: 0.14.1 +version: 0.14.2 copyright: Neil Mitchell 2006-2017 author: Neil Mitchell maintainer: Neil Mitchell @@ -11,7 +11,7 @@ license-file: LICENSE build-type: Simple synopsis: Parsing and extracting information from (possibly malformed) HTML/XML documents -tested-with: GHC==8.0.2, GHC==7.10.3, GHC==7.8.4, GHC==7.6.3, GHC==7.4.2 +tested-with: GHC==8.2.1, GHC==8.0.2, GHC==7.10.3, GHC==7.8.4, GHC==7.6.3, GHC==7.4.2 description: TagSoup is a library for parsing HTML/XML. It supports the HTML 5 specification, and can be used to parse either well-formed XML, or unstructured and malformed HTML @@ -27,14 +27,10 @@ type: git location: https://github.com/ndmitchell/tagsoup.git -flag testprog - default: False - manual: True - description: Build the test program - library default-language: Haskell2010 build-depends: base == 4.*, containers, bytestring, text + hs-source-dirs: src exposed-modules: Text.HTML.TagSoup @@ -52,19 +48,18 @@ Text.HTML.TagSoup.Specification Text.HTML.TagSoup.Type -executable test-tagsoup +test-suite test-tagsoup + type: exitcode-stdio-1.0 default-language: Haskell2010 - if flag(testprog) - buildable: True - build-depends: - base == 4.*, containers, bytestring, text, - QuickCheck >= 2.4, - deepseq >= 1.1, - time, directory, process - else - buildable: False + build-depends: + base == 4.*, containers, bytestring, text, + QuickCheck >= 2.4, + deepseq >= 1.1, + tagsoup, + time, directory, process main-is: Main.hs + hs-source-dirs: test other-modules: TagSoup.Benchmark TagSoup.Sample diff --git a/test/Main.hs b/test/Main.hs new file mode 100644 --- /dev/null +++ b/test/Main.hs @@ -0,0 +1,63 @@ + +module Main(main) where + +import System.Environment +import TagSoup.Sample +import TagSoup.Test +import TagSoup.Benchmark +import Data.Char(toLower) + + +helpMsg :: IO () +helpMsg = putStr $ unlines $ + ["TagSoup, (C) Neil Mitchell 2006-2009" + ,"" + ," tagsoup arguments" + ,"" + ," may either be a local file, or a http[s]:// page" + ,"" + ] ++ map f res + where + width = maximum $ map (length . fst) res + res = map g actions + + g (nam,msg,Left _) = (nam,msg) + g (nam,msg,Right _) = (nam ++ " ",msg) + + f (lhs,rhs) = " " ++ lhs ++ replicate (4 + width - length lhs) ' ' ++ rhs + + +actions :: [(String, String, Either (IO ()) (String -> IO ()))] +actions = [("test","Run the test suite",Left test) + ,("grab","Grab a web page",Right grab) + ,("parse","Parse a web page",Right parse) + ,("bench","Benchmark the parsing",Left time) + ,("benchfile","Benchmark the parsing of a file",Right timefile) + ,("validate","Validate a page",Right validate) + ,("lastmodifieddate","Get the wiki.haskell.org last modified date",Left haskellLastModifiedDateTime) + ,("spj","Simon Peyton Jones' papers",Left spjPapers) + ,("ndm","Neil Mitchell's papers",Left ndmPapers) + ,("time","Current time",Left currentTime) + ,("google","Google Tech News",Left googleTechNews) + ,("sequence","Creators on sequence.complete.org",Left rssCreators) + ,("help","This help message",Left helpMsg) + ] + +main :: IO () +main = do + args <- getArgs + case (args, lookup (map toLower $ head args) $ map (\(a,_,c) -> (a,c)) actions) of + ([],_) -> do + putStrLn "No arguments specifying, defaulting to test" + helpMsg + putStrLn $ replicate 70 '-' + test + (x:_,Nothing) -> putStrLn ("Error: unknown command " ++ x) >> helpMsg + ([_],Just (Left a)) -> a + (x:xs,Just (Left a)) -> do + putStrLn $ "Warning: expected no arguments to " ++ x ++ " but got: " ++ unwords xs + a + ([_,y],Just (Right a)) -> a y + (x:xs,Just (Right _)) -> do + putStrLn $ "Error: expected exactly one argument to " ++ x ++ " but got: " ++ unwords xs + helpMsg diff --git a/test/TagSoup/Benchmark.hs b/test/TagSoup/Benchmark.hs new file mode 100644 --- /dev/null +++ b/test/TagSoup/Benchmark.hs @@ -0,0 +1,202 @@ +{-# LANGUAGE CPP #-} +{-# OPTIONS_GHC -fno-warn-orphans #-} -- test file, so OK + +module TagSoup.Benchmark where + +import Text.HTML.TagSoup + +import Control.DeepSeq +import Control.Monad +import Data.List +import Data.Maybe +import System.IO.Unsafe(unsafeInterleaveIO) +import qualified Data.ByteString.Char8 as BS +import qualified Data.ByteString.Lazy.Char8 as LBS +import Data.Time.Clock.POSIX(getPOSIXTime) + +conf = 0.95 + + +timefile :: FilePath -> IO () +timefile file = do + -- use LBS to be most representative of real life + lbs <- LBS.readFile file + let str = LBS.unpack lbs + bs = BS.concat $ LBS.toChunks lbs + () <- LBS.length lbs `seq` length str `seq` BS.length bs `seq` return () + benchWith (const str, const bs, const lbs) $ benchStatic (toInteger $ LBS.length lbs) + + +sample :: String +sample = " is " ++ + " and some just random & test ><" + +nsample = genericLength sample :: Integer + +time :: IO () +time = benchWith (str,bs,lbs) benchVariable + where + str = \i -> concat $ genericReplicate i sample + bs = let s = BS.pack sample in \i -> BS.concat (genericReplicate i s) + lbs = let s = LBS.pack sample in \i -> LBS.concat (genericReplicate i s) + + + +benchWith :: (Integer -> String, Integer -> BS.ByteString, Integer -> LBS.ByteString) + -> ((Integer -> ()) -> IO [String]) -> IO () +benchWith (str,bs,lbs) bench = do + putStrLn "Timing parseTags in characters/second" + let header = map (:[]) ["(" ++ show (round $ conf * 100) ++ "% confidence)","String","BS","LBS"] + rows <- mapM row $ replicateM 3 [False,True] + mapM_ (putStrLn . strict . grid) $ delay2 $ header : rows + where + row [a,b,c] = do + let header = intercalate "," [g a "pos", g b "warn", g c "merge"] + g b x = (if b then ' ' else '!') : x + f x = bench $ \i -> rnf $ parseTagsOptions parseOptions{optTagPosition=a,optTagWarning=b,optTagTextMerge=c} $ x i + c1 <- f str + c2 <- f bs + c3 <- f lbs + return [[header],c1,c2,c3] + + strict = reverse . reverse + + +--------------------------------------------------------------------- +-- BENCHMARK ON THE SAMPLE INPUT + +disp xs = showUnit (floor xbar) ++ " (~" ++ rng ++ "%)" + where xbar = mean xs + rng = if length xs <= 1 then "?" else show (ceiling $ (range conf xs) * 100 / xbar) + +cons x = fmap (x:) + + +aimTime = 0.3 :: Double -- seconds to aim for +minTime = 0.2 :: Double -- below this a test is considered invalid + + +-- given a number of times to repeat sample, return a list of what +-- to display +benchVariable :: (Integer -> ()) -> IO [String] +benchVariable op = cons "?" $ f 10 [] + where + f i seen | length seen > 9 = cons (" " ++ disp seen) $ return [] + | otherwise = unsafeInterleaveIO $ do + now <- timer $ op i + let cps = if now == 0 then 0 else fromInteger (i * nsample) / now + if now < minTime || (null seen && now < aimTime) then do + let factor = min 7 $ max 2 $ floor $ aimTime / now + cons ("? " ++ disp [cps]) $ f (i * factor) [] + else + cons (show (9 - length seen) ++ " " ++ disp (cps:seen)) $ f i (cps:seen) + + + +benchStatic :: Integer -> (Integer -> ()) -> IO [String] +benchStatic nsample op = cons "?" $ f [] + where + f seen | length seen > 9 = cons (" " ++ disp seen) $ return [] + | otherwise = unsafeInterleaveIO $ do + now <- timer $ op $ genericLength seen + let cps = if now == 0 then 0 else fromInteger nsample / now + cons (show (9 - length seen) ++ " " ++ disp (cps:seen)) $ f (cps:seen) + + +--------------------------------------------------------------------- +-- UTILITY FUNCTIONS + +-- | Given a number, show it using a unit and decimal place +showUnit :: Integer -> String +showUnit x = num ++ unit + where + units = " KMGTPEZY" + (use,skip) = splitAt 3 $ show x + + unit = [units !! ((length skip + 2) `div` 3)] + + dot = ((length skip - 1) `mod` 3) + 1 + num = a ++ ['.' | b /= ""] ++ b + where (a,b) = splitAt dot use + + +-- copied from the criterion package +getTime :: IO Double +getTime = (fromRational . toRational) `fmap` getPOSIXTime + +timer :: () -> IO Double +timer x = do + start <- getTime + () <- return x + end <- getTime + return $ end - start + + +-- display a grid +grid :: [[String]] -> String +grid xs = unlines $ map (concat . zipWith f cols) xs + where cols = map (maximum . map length) $ transpose xs + f n x = x ++ replicate (n+1 - length x) ' ' + + +-- display a series of grids over time +-- when a grid gets to [] keep its value at that +-- when all grids get to [] return [] +delay2 :: [[[String]]] -> [[[String]]] +delay2 xs = map (map head) xs : (if all (null . tail) (concat xs) then [] else delay2 $ map (map tl) xs) + where tl (x:xs) = if null xs then x:xs else xs + + +--------------------------------------------------------------------- +-- INSTANCES + +instance NFData a => NFData (Tag a) where + rnf (TagOpen x y) = rnf x `seq` rnf y + rnf (TagClose x) = rnf x + rnf (TagText x) = rnf x + rnf (TagComment x) = rnf x + rnf (TagWarning x) = rnf x + rnf (TagPosition x y) = () -- both are already ! bound + + +#ifndef BYTESTRING_HAS_NFDATA +# ifdef MIN_VERSION_bytestring +# define BYTESTRING_HAS_NFDATA (MIN_VERSION_bytestring(0,10,0)) +# else +# define BYTESTRING_HAS_NFDATA (__GLASGOW_HASKELL__ >= 706) +# endif +#endif + +#if !BYTESTRING_HAS_NFDATA +instance NFData LBS.ByteString where + rnf x = LBS.length x `seq` () + +instance NFData BS.ByteString where + rnf x = BS.length x `seq` () +#endif + + +--------------------------------------------------------------------- +-- STATISTICS +-- Provided by Emily Mitchell + +confNs = let (*) = (,) in + [0.95 * 1.96 + ,0.90 * 1.644] + +size :: [Double] -> Double +size = genericLength + +mean :: [Double] -> Double +mean xs = sum xs / size xs + +stddev :: [Double] -> Double +stddev xs = sqrt $ sum [sqr (x - xbar) | x <- xs] / size xs + where xbar = mean xs + sqr x = x * x + +-- given a sample, and a required confidence +-- of the mean (i.e. 2.5% = 0.025) +range ::Double -> [Double] -> Double +range conf xs = conf2 * stddev xs / sqrt (size xs) + where conf2 = fromMaybe (error $ "Unknown confidence interval: " ++ show conf) $ lookup conf confNs diff --git a/test/TagSoup/Sample.hs b/test/TagSoup/Sample.hs new file mode 100644 --- /dev/null +++ b/test/TagSoup/Sample.hs @@ -0,0 +1,158 @@ + +module TagSoup.Sample where + +import Text.HTML.TagSoup + +import Control.Exception +import Control.Monad +import Data.List +import System.Process +import System.Directory +import System.Exit +import System.IO +import Data.Functor +import Prelude + + +openItem :: String -> IO String +openItem url + | not $ "http://" `isPrefixOf` url || "https://" `isPrefixOf` url = + readFile url +openItem url = bracket + (openTempFile "." "tagsoup.tmp") + (\(file,hndl) -> removeFile file) + $ \(file,hndl) -> do + hClose hndl + putStrLn $ "Downloading: " ++ url + res <- system $ "wget " ++ url ++ " -O " ++ file + when (res /= ExitSuccess) $ error $ "Failed to download using wget: " ++ url + src <- readFile file + length src `seq` return src + + +grab :: String -> IO () +grab x = openItem x >>= putStr + +parse :: String -> IO () +parse x = openItem x >>= putStr . show2 . parseTags + where + show2 [] = "[]" + show2 xs = "[" ++ concat (intersperseNotBroken "\n," $ map show xs) ++ "\n]\n" + + +-- the standard intersperse has a strictness bug which sucks! +intersperseNotBroken :: a -> [a] -> [a] +intersperseNotBroken _ [] = [] +intersperseNotBroken sep (x:xs) = x : is xs + where + is [] = [] + is (y:ys) = sep : y : is ys + + +{- +
  • This page was last modified on 9 September 2013, at 22:38.
    • +-} +haskellLastModifiedDateTime :: IO () +haskellLastModifiedDateTime = do + src <- openItem "http://wiki.haskell.org/Haskell" + let lastModifiedDateTime = fromFooter $ parseTags src + putStrLn $ "wiki.haskell.org was last modified on " ++ lastModifiedDateTime + where fromFooter = unwords . drop 6 . words . innerText . take 2 . dropWhile (~/= "
  • ") + + +googleTechNews :: IO () +googleTechNews = do + tags <- fmap parseTags $ openItem "http://news.google.com/?ned=us&topic=t" + let links = [ ascii name ++ " <" ++ maybe "unknown" shortUrl (lookup "href" atts) ++ ">" + | TagOpen "h2" [("class","title")]:TagText spaces:TagOpen "a" atts:TagText name:_ <- tails tags] + putStr $ unlines links + where + shortUrl x | "http://" `isPrefixOf` x = shortUrl $ drop 7 x + | "www." `isPrefixOf` x = shortUrl $ drop 4 x + | otherwise = takeWhile (/= '/') x + + ascii ('\226':'\128':'\147':xs) = '-' : ascii xs + ascii ('\194':'\163':xs) = "#GBP " ++ ascii xs + ascii (x:xs) = x : ascii xs + ascii [] = [] + + +spjPapers :: IO () +spjPapers = do + tags <- parseTags <$> openItem "http://research.microsoft.com/en-us/people/simonpj/" + let links = map f $ sections (~== "") $ + takeWhile (~/= "") $ + drop 5 $ dropWhile (~/= "") tags + putStr $ unlines links + where + f :: [Tag String] -> String + f = dequote . unwords . words . fromTagText . head . filter isTagText + + dequote ('\"':xs) | last xs == '\"' = init xs + dequote x = x + + +ndmPapers :: IO () +ndmPapers = do + tags <- parseTags <$> openItem "http://community.haskell.org/~ndm/downloads/" + let papers = map f $ sections (~== "
  • ") tags + putStr $ unlines papers + where + f :: [Tag String] -> String + f xs = fromTagText (xs !! 2) + + +currentTime :: IO () +currentTime = do + tags <- parseTags <$> openItem "http://www.timeanddate.com/worldclock/uk/london" + let time = fromTagText (dropWhile (~/= "") tags !! 1) + putStrLn time + + + +type Section = String +data Package = Package {name :: String, desc :: String, href :: String} + deriving Show + +hackage :: IO [(Section,[Package])] +hackage = do + tags <- fmap parseTags $ openItem "http://hackage.haskell.org/packages/archive/pkg-list.html" + return $ map parseSect $ partitions (~== "

    ") tags + where + parseSect xs = (nam, packs) + where + nam = fromTagText $ xs !! 2 + packs = map parsePackage $ partitions (~== "
  • ") xs + + parsePackage xs = + Package + (fromTagText $ xs !! 2) + (drop 2 $ dropWhile (/= ':') $ fromTagText $ xs !! 4) + (fromAttrib "href" $ xs !! 1) + +-- rssCreators Example: prints names of story contributors on +-- sequence.complete.org. This content is RSS (not HTML), and the selected +-- tag uses a different XML namespace "dc:creator". +rssCreators :: IO () +rssCreators = do + tags <- fmap parseTags $ openItem "http://sequence.complete.org/node/feed" + putStrLn $ unlines $ map names $ partitions (~== "") tags + where names xs = fromTagText $ xs !! 1 + + +validate :: String -> IO () +validate x = putStr . unlines . g . f . parseTagsOptions opts =<< openItem x + where + opts = parseOptions{optTagPosition=True, optTagWarning=True} + + f :: [Tag String] -> [String] + f (TagPosition row col:TagWarning warn:rest) = + ("Warning (" ++ show row ++ "," ++ show col ++ "): " ++ warn) : f rest + f (TagWarning warn:rest) = + ("Warning (?,?): " ++ warn) : f rest + f (_:rest) = f rest + f [] = [] + + g xs = xs ++ [if n == 0 then "Success, no warnings" + else "Failed, " ++ show n ++ " warning" ++ ['s'|n>1]] + where n = length xs diff --git a/test/TagSoup/Test.hs b/test/TagSoup/Test.hs new file mode 100644 --- /dev/null +++ b/test/TagSoup/Test.hs @@ -0,0 +1,257 @@ +{-# OPTIONS_GHC -fno-warn-deprecations #-} + +module TagSoup.Test(test) where + +import Text.HTML.TagSoup +import Text.HTML.TagSoup.Entity +import Text.HTML.TagSoup.Match + +import Control.Monad +import Data.List +import Test.QuickCheck(Arbitrary(..), Testable(..), quickCheckWithResult, stdArgs, + Args(..), listOf, elements, Result(..)) + +-- * The Test Monad + +type Test a = IO a + +pass :: Test () +pass = return () + +runTest :: Test () -> IO () +runTest x = x >> putStrLn "All tests passed" + +(===) :: (Show a, Eq a) => a -> a -> IO () +a === b = if a == b then pass else fail $ "Does not equal: " ++ show a ++ " =/= " ++ show b + +check :: Testable prop => prop -> IO () +check prop = do + res <- quickCheckWithResult stdArgs{maxSuccess=1000} prop + case res of + Success{} -> pass + _ -> fail "Property failed" + +newtype HTML = HTML String deriving Show +instance Arbitrary HTML where + arbitrary = fmap (HTML . concat) $ listOf $ elements frags + where frags = map (:[]) " \n!-#&;xy01[]?'\"" ++ ["CDATA","amp","gt","lt"] + shrink (HTML x) = map HTML $ zipWith (++) (inits x) (tail $ tails x) + + +-- * The Main section + +test :: IO () +test = runTest $ do + warnTests + parseTests + optionsTests + renderTests + combiTests + positionTests + entityTests + lazyTags == lazyTags `seq` pass + matchCombinators + + +{- | +This routine tests the laziness of the TagSoup parser. +For each critical part of the parser we provide a test input +with a token of infinite size. +Then the output must be infinite too. +If the laziness is broken, then the output will stop early. +We collect the thousandth character of the output of each test case. +If computation of the list stops somewhere, +you have found a laziness stopper. +-} + + +lazyTags :: [Char] +lazyTags = map ((!!1000) . show . parseTags) + [cycle "Rhabarber" + ,repeat '&' + ,"<"++cycle "html" + ,"" === [TagOpen "!DOCTYPE" [("TEST","")]] + parseTags "" === [TagOpen "test" [("\"foo",""),("bar\"","")]] + parseTags "" === [TagOpen "test" [("baz",""),("\"foo\"","")]] + parseTags "" === [TagOpen "test" [("'foo",""),("bar'","")]] + parseTags "" === [TagOpen "test" [("bar",""),("'","")], TagClose "test"] + parseTags "" === [TagOpen "test2" [("a",""),("b","")]] + parseTags "" === [TagOpen "test2" [("''","")]] + parseTags "" === [TagClose "test"] + parseTags "" === [TagOpen "test" [], TagClose "test"] + parseTags "" === [TagOpen "test1" [("a","b")]] + parseTags "hello & world" === [TagText "hello & world"] + parseTags "hello @ world" === [TagText "hello @ world"] + parseTags "hello @ world" === [TagText "hello @ world"] + parseTags "hello @ world" === [TagText "hello @ world"] + parseTags "hello &haskell; world" === [TagText "hello &haskell; world"] + parseTags "hello \n\t world" === [TagText "hello \n\t world"] + parseTags "" === [TagOpen "a" [("href","http://www.google.com")]] + parseTags "" === [TagOpen "foo" [("bar","bar6baz")]] + parseTags "" === [TagOpen "foo" [("bar","bar&baz")]] + parseTags "hey &how are you" === [TagText "hey &how are you"] + parseTags "hey &how; are you" === [TagText "hey &how; are you"] + parseTags "hey & are you" === [TagText "hey & are you"] + parseTags "hey & are you" === [TagText "hey & are you"] + + -- real cases reported by users + parseTags "↖x≧̸" === [TagText ['\x2196','x','\x2267','\x0338']] + parseTags "test � test" === [TagText "test ? test"] + + parseTags "" === [TagOpen "a" [("href","series.php?view=single&ID=72710")]] + + parseTags "" === + [TagOpen "!DOCTYPE" [("HTML",""),("PUBLIC",""),("","-//W3C//DTD HTML 4.01//EN"),("","http://www.w3.org/TR/html4/strict.dtd")]] + + parseTags "" === [TagOpen "script" [], TagText " if (x if (x if (x" === [TagOpen "SCRIPT" [("language","foo")], TagText " if (x" === [TagOpen "script" [], TagClose "script", TagOpen "test" []] + + -- some escapes require trailing semicolons, see #28 and #27. + parseTags "one ∣ two" === [TagText "one \8739 two"] + parseTags "one &mid two" === [TagText "one &mid two"] + parseTags "one µ two" === [TagText "one \181 two"] + parseTags "one µ two" === [TagText "one \181 two"] + +optionsTests :: Test () +optionsTests = check $ \(HTML x) -> all (f x) $ replicateM 3 [False,True] + where + f str [pos,warn,merge] = + bool "merge" (not merge || adjacentTagText tags) && + bool "warn" (warn || all (not . isTagWarning) tags) && + bool "pos" (if pos then alternatePos tags else all (not . isTagPosition) tags) + where tags = parseTagsOptions parseOptions{optTagPosition=pos,optTagWarning=warn,optTagTextMerge=merge} str + bool x b = b || error ("optionsTests failed with " ++ x ++ " on " ++ show (pos,warn,merge,str,tags)) + + -- optTagTextMerge implies no adjacent TagText cells + -- and none separated by only warnings or positions + adjacentTagText = g True -- can the next be a tag text + where g i (x:xs) | isTagText x = i && g False xs + | isTagPosition x || isTagWarning x = g i xs + | otherwise = g True xs + g i [] = True + + -- optTagPosition implies every element must be followed + -- by a position node, no two position nodes must be adjacent + -- and all positions must be increasing + alternatePos (TagPosition l1 c1 : x : TagPosition l2 c2 : xs) + | (l1,c1) <= (l2,c2) && not (isTagPosition x) = alternatePos $ TagPosition l2 c2 : xs + alternatePos [TagPosition l1 c1, x] | not $ isTagPosition x = True + alternatePos [] = True + alternatePos _ = False + + +renderTests :: Test () +renderTests = do + let rp = renderTags . parseTags + rp "" === "" + rp "

    " === "
    " + rp "" === "" + rp "hello & world" === "hello & world" + rp "    " === "" + rp "" === "" + rp "" === "" + rp "" === "" + rp "" === "" + rp "" === "" + rp "" === "" + escapeHTML "this is a &\" '" === "this is a &" <test> '" + check $ \(HTML x) -> let y = rp x in rp y == (y :: String) + + +entityTests :: Test () +entityTests = do + lookupNumericEntity "65" === Just "A" + lookupNumericEntity "x41" === Just "A" + lookupNumericEntity "x4E" === Just "N" + lookupNumericEntity "x4e" === Just "N" + lookupNumericEntity "X4e" === Just "N" + lookupNumericEntity "Haskell" === Nothing + lookupNumericEntity "" === Nothing + lookupNumericEntity "89439085908539082" === Nothing + lookupNamedEntity "amp" === Just "&" + lookupNamedEntity "haskell" === Nothing + escapeXML "hello world" === "hello world" + escapeXML "hello & world" === "hello & world" + + +combiTests :: Test () +combiTests = do + (TagText "test" ~== TagText "" ) === True + (TagText "test" ~== TagText "test") === True + (TagText "test" ~== TagText "soup") === False + (TagText "test" ~== "test") === True + (TagOpen "test" [] ~== "") === True + (TagOpen "test" [] ~== "") === False + (TagOpen "test" [] ~/= "") === True + (TagComment "foo" ~== "") === True + (TagComment "bar" ~== "") === True + + +positionTests :: Test () +positionTests = do + let p = parseTagsOptions parseOptions{optTagPosition=True,optTagWarning=False} + p "&" === [TagPosition 1 1,TagOpen "a" [],TagPosition 1 4,TagText "&",TagPosition 1 5,TagClose "a"] + p "&#z" === [TagPosition 1 1,TagOpen "a" [],TagPosition 1 4,TagText "&#z"] + p "&xz" === [TagPosition 1 1,TagOpen "a" [],TagPosition 1 4,TagText "&xz"] + p "&" === [TagPosition 1 1,TagOpen "a" [],TagPosition 1 4,TagText "&"] + p "&1" === [TagPosition 1 1,TagOpen "a" [],TagPosition 1 4,TagText "&1"] + p "&" === [TagPosition 1 1,TagOpen "a" [],TagPosition 1 4,TagText "&"] + + +warnTests :: Test () +warnTests = do + let p = parseTagsOptions parseOptions{optTagPosition=True,optTagWarning=True} + wt x = [(msg,c) | TagWarning msg:TagPosition _ c:_ <- tails $ p x] + wt "neil &foo bar" === [("Unknown entity: foo",6)]