hPDB 0.99 → 0.999

raw patch · 54 files changed

+287/−383 lines, 54 filesdep +iterabledep +mmapdep −bytestring-mmapdep ~text-formatsetup-changedPVP ok

version bump matches the API change (PVP)

Dependencies added: iterable, mmap

Dependencies removed: bytestring-mmap

Dependency ranges changed: text-format

API changes (from Hackage documentation)

Files

• AUTHORS +3/−0
• Bio/PDB/Common.hs +0/−1
• Bio/PDB/EventParser/FastParse.hs +1/−0
• Bio/PDB/EventParser/HelixTypes.hs +4/−4
• Bio/PDB/EventParser/PDBEventParser.hs +2/−2
• Bio/PDB/EventParser/PDBEventPrinter.hs +44/−31
• Bio/PDB/EventParser/PDBParsingAbstractions.hs +2/−2
• Bio/PDB/EventParser/ParseATOM.hs +2/−2
• Bio/PDB/EventParser/ParseCAVEAT.hs +1/−1
• Bio/PDB/EventParser/ParseCISPEP.hs +1/−1
• Bio/PDB/EventParser/ParseCONECT.hs +1/−1
• Bio/PDB/EventParser/ParseCRYST1.hs +2/−2
• Bio/PDB/EventParser/ParseDBREF.hs +2/−2
• Bio/PDB/EventParser/ParseFORMUL.hs +1/−1
• Bio/PDB/EventParser/ParseHEADER.hs +1/−1
• Bio/PDB/EventParser/ParseHELIX.hs +1/−1
• Bio/PDB/EventParser/ParseHET.hs +1/−1
• Bio/PDB/EventParser/ParseHETNAM.hs +1/−1
• Bio/PDB/EventParser/ParseHYDBND.hs +1/−1
• Bio/PDB/EventParser/ParseIntRecord.hs +1/−1
• Bio/PDB/EventParser/ParseJRNL.hs +1/−1
• Bio/PDB/EventParser/ParseLINK.hs +2/−2
• Bio/PDB/EventParser/ParseListRecord.hs +1/−1
• Bio/PDB/EventParser/ParseMASTER.hs +1/−1
• Bio/PDB/EventParser/ParseMODRES.hs +2/−2
• Bio/PDB/EventParser/ParseMatrixRecord.hs +1/−1
• Bio/PDB/EventParser/ParseObsoleting.hs +1/−1
• Bio/PDB/EventParser/ParseREMARK.hs +1/−1
• Bio/PDB/EventParser/ParseREVDAT.hs +1/−1
• Bio/PDB/EventParser/ParseSEQADV.hs +2/−2
• Bio/PDB/EventParser/ParseSEQRES.hs +1/−1
• Bio/PDB/EventParser/ParseSHEET.hs +1/−1
• Bio/PDB/EventParser/ParseSITE.hs +2/−2
• Bio/PDB/EventParser/ParseSLTBRG.hs +1/−1
• Bio/PDB/EventParser/ParseSPLIT.hs +1/−1
• Bio/PDB/EventParser/ParseSSBOND.hs +1/−1
• Bio/PDB/EventParser/ParseSpecListRecord.hs +1/−1
• Bio/PDB/EventParser/ParseTER.hs +1/−1
• Bio/PDB/EventParser/ParseTITLE.hs +1/−1
• Bio/PDB/EventParser/ParseTVECT.hs +1/−1
• Bio/PDB/IO.hs +19/−15
• Bio/PDB/IO/OpenAnyFile.hs +9/−9
• Bio/PDB/InstantiateIterable.hs +0/−68
• Bio/PDB/Iterable.hs +9/−6
• Bio/PDB/Structure.hs +1/−1
• Bio/PDB/Structure/Elements.hs +1/−1
• Bio/PDB/Structure/List.hs +1/−1
• Bio/PDB/Structure/Vector.hs +15/−18
• Bio/PDB/StructureBuilder.hs +45/−43
• Bio/PDB/Util/MissingInstances.hs +1/−114
• INSTALL +32/−0
• README.md +13/−0
• Setup.hs +15/−1
• hPDB.cabal +30/−26

@@ -0,0 +1,3 @@+This parser and associated example programs were created by:+Michal J. Gajda 2010-2013+In his free time, unencumbered by work duties.

@@ -1,4 +1,3 @@-{-# LANGUAGE StandaloneDeriving, BangPatterns #-} module Bio.PDB.Common(String(..), Vector3(..))  where

@@ -33,6 +33,7 @@ digitValue !c = ord c - ord '0'  {-# INLINE final #-}+{-# ANN final "HLint: ignore Too strict if" #-} final :: Bool -> Double -> Maybe Double final !sign !f = if sign then Just (-f) else Just f 

@@ -1,12 +1,12 @@ -- | Module contains enumeration of helix types, and auxiliary functions--- for converting these into numeric PDB CLASS code.+-- for converting these into PDB CLASS codes. module Bio.PDB.EventParser.HelixTypes(HelixT, helix2code, code2helix) where {-| Enumeration of helix types  PDB Class number in columns 39-40 for each type of helix in HELIX record: - (1) Right-handed alpha (default)+ (1) Right-handed alpha (default, most common)   (2) Right-handed omega @@ -40,7 +40,7 @@               Polyproline   deriving (Eq, Ord, Show, Read) --- | helix2code converts a 'HelixT' enumeration into an PDB CLASS number.+-- | helix2code converts a 'HelixT' enumeration into an PDB CLASS code. helix2code RightAlpha  =  1 helix2code RightOmega  =  2 helix2code RightPi     =  3@@ -52,7 +52,7 @@ helix2code Ribbon2_7   =  9 helix2code Polyproline = 10 --- | helix2code converts an PDB CLASS number into a 'HelixT' enumeration.+-- | helix2code converts an PDB CLASS code into a 'HelixT' enumeration. code2helix  1 = RightAlpha code2helix  2 = RightOmega code2helix  3 = RightPi

@@ -76,7 +76,7 @@       a | "ENDMDL" `BS.isPrefixOf` a -> cont1 $! return [ENDMDL]        a | "END"    `BS.isPrefixOf` a -> cont1 $! return [END]       -- common error in treatment of TER - omitting rest of the record-      "TER"                          -> cont1 $! return [TER { num = (-1), resname = "", chain = ' ', resid = (-1), insCode = ' ' }]+      "TER"                          -> cont1 $! return [TER { num = -1, resname = "", chain = ' ', resid = -1, insCode = ' ' }]       -- proper TER       a | "TER"    `BS.isPrefixOf` a -> cont1 $! parseTER    line line_no       a | "MASTER" `BS.isPrefixOf` a -> cont1 $! parseMASTER line line_no@@ -140,7 +140,7 @@ -- | Parses a strict ByteString 'contents' named 'fname' and performs 'action' -- on events given by parsing chunks, returning accumulated results. Accumulator -- is primed by 'acc'.-parsePDBRecords fname contents action acc = parsePDBLines fname contents 0 action acc+parsePDBRecords fname contents = parsePDBLines fname contents 0  -- | Checks whether line was ignored as unknown record type ignoreLine (PDBIgnoredLine _) = False

@@ -1,4 +1,4 @@-{-# LANGUAGE OverloadedStrings, PatternGuards #-}+{-# LANGUAGE OverloadedStrings, PatternGuards, CPP #-} module Bio.PDB.EventParser.PDBEventPrinter(print, isPrintable)  where@@ -9,17 +9,19 @@ import System.IO(Handle, IO, stderr) import qualified Data.ByteString.Char8 as BS import Data.String(IsString)-import Control.Monad(mapM, return)+import Control.Monad(mapM_, return) -import Bio.PDB.EventParser.PDBEvents+import           Bio.PDB.EventParser.PDBEvents import qualified Bio.PDB.EventParser.ExperimentalMethods as ExperimentalMethods+#ifdef HAVE_TEXT_FORMAT import qualified Data.ByteString.Lazy as L-import Data.Text.Lazy.Encoding(encodeUtf8)-import Data.Text.Encoding     (decodeUtf8)+import           Data.Text.Lazy.Encoding(encodeUtf8)+import           Data.Text.Encoding     (decodeUtf8) import qualified Data.Text.Lazy as LT-import Data.Text.Lazy.Builder as B+import           Data.Text.Lazy.Builder as B import qualified Data.Text.Format as F import qualified Data.Text.Buildable as BD+#endif  -- | Prints a PDBEvent to a filehandle. print :: Handle -> PDBEvent -> IO ()@@ -37,18 +39,30 @@                     elt       = e,                     charge    = ch,                     hetatm    = isHet-                  } = do L.hPutStr handle . encodeUtf8 $ F.format "{}{} {}{}{} {}{}{}   {}{}{}{}{}       {}{}{}\n" args+                  } =+#ifndef HAVE_TEXT_FORMAT+    hPrintf handle+           "%6s%5d  %-3s%c%-3s %c%4d%c   %8.3f%8.3f%8.3f%6.2f%6.2f       %-4s%-2s%-2s\n"+                   recname+                   num (BS.unpack atype) al (BS.unpack rtype) c rid rins+                   x y z occ bf+                   (BS.unpack sid) (BS.unpack e) (BS.unpack ch)   where+    recname :: Prelude.String+    recname = if isHet then "HETATM" else "ATOM  "+#else+    L.hPutStr handle . encodeUtf8 $ F.format "{}{} {}{}{} {}{}{}   {}{}{}{}{}       {}{}{}\n" args+  where     -- ra justifies a ByteString to the right     ra i = F.right i ' ' . decodeUtf8     -- la justifies anything else (floating point or integer number) to the left     la i = F.left  i ' '     args = (recname, la 5 num, specfmt 4 3 atype,-            conv al, ra 3 $ rtype,+            conv al, ra 3 rtype,             conv c, la 4 rid,             conv rins,             ca x, ca y, ca z, pa occ, pa bf,-            ra 4 $ sid, ra 2 $ e, ra 2 $ ch)+            ra 4 sid, ra 2 e, ra 2 ch)     ca f = la 8 $ F.fixed 3 f -- align coordinate float     pa f = la 6 $ F.fixed 2 f -- align property float     recname = fromText $ if isHet then "HETATM" else "ATOM  "@@ -56,6 +70,7 @@     conv x = fromString [x]     -- specfmt mimics erratic alignment of PDB atom types: up to three characters are justified left, after prefixing by single space.     specfmt i j a = B.fromLazyText . LT.justifyRight i ' ' . LT.justifyLeft j ' ' . B.toLazyText . fromText . decodeUtf8 $ a+#endif  -- TODO: Note that this ANISOU code will be buggy for 4-letter atom codes that happen (rarely.) print handle ANISOU { no       = n, @@ -110,7 +125,7 @@ print handle END    = hPrintf handle "END\n" print handle ENDMDL = hPrintf handle "ENDMDL\n" print handle CONECT { atoms=ats } = do hPrintf handle "CONECT"-                                       mapM (hPrintf handle "%5d") ats+                                       mapM_ (hPrintf handle "%5d") ats                                        hPrintf handle "\n" print handle TER    { num     = n    ,                       resname = r    ,@@ -129,15 +144,14 @@                       numMaster = nmaster,                       numConect = ncon,                       numSeqres = nseq } = do hPrintf handle "MASTER    %5d    0" nr-                                              mapM (hPrintf handle "%5d")-                                                   [nhet, nhel, nsheet,-                                                    nturn, nsite, nxform, nats,-                                                    nmaster, ncon, nseq]+                                              mapM_ (hPrintf handle "%5d")+                                                    [nhet, nhel, nsheet,+                                                     nturn, nsite, nxform, nats,+                                                     nmaster, ncon, nseq]                                               hPrintf handle "\n" print handle REMARK { num  = n,-                      text = t } = do mapM (hPrintf handle "REMARK %4d %-80s\n" n .-                                            BS.unpack) t-                                      return ()+                      text = t } = mapM_ (hPrintf handle "REMARK %4d %-80s\n" n .+                                          BS.unpack) t {-              KEYWDS { continuation  :: !Int,                          aList         :: ![String] }    |                 AUTHOR { continuation  :: !Int,@@ -149,11 +163,10 @@ print handle AUTHOR { continuation = c,                       aList        = l } = printList handle "AUTHOR" "," c l print handle EXPDTA { continuation = c,-                      expMethods   = e } = do mapM (hPrintf handle "EXPDTA   %c%-80s\n"-                                                            (showContinuation c) .-                                                    BS.unpack .-                                                    ExperimentalMethods.showExpMethod) e-                                              return ()+                      expMethods   = e } = mapM_ (hPrintf handle "EXPDTA   %c%-80s\n"+                                                          (showContinuation c) .+                                                  BS.unpack .+                                                  ExperimentalMethods.showExpMethod) e print handle TITLE { continuation = c,                      title        = t } = hPrintf handle "TITLE   %c%-80s\n"                                                          (showContinuation c)@@ -162,8 +175,8 @@                       chain   = ch,                       num     = n,                       resList = l } = do hPrintf handle "SEQRES %3d %c %4d   " sn ch n-                                         mapM (hPrintf handle "%3s " .-                                               BS.unpack) l+                                         mapM_ (hPrintf handle "%3s " .+                                                BS.unpack) l                                          -- TODO: split when longer than X residues                                          hPrintf handle "\n" print handle COMPND { cont   = c,@@ -200,11 +213,11 @@     header :: String     header  = if aJRNL then "JRNL        " else "REMARK    1 "     [contd] = if c > 0 then show c else " "-    printJRNL ((k,v):cs) = do hPrintf handle "%12s%4s %c %s\n"-                                      (BS.unpack header)-                                      (BS.unpack k)-                                      contd-                                      (BS.unpack v)+    printJRNL ((k,v):cs) = hPrintf handle "%12s%4s %c %s\n"+                                   (BS.unpack header)+                                   (BS.unpack k)+                                   contd+                                   (BS.unpack v)  -- print errors: print handle (PDBParseError c r s) = hPrintf stderr "ERROR: In line %d column %d: %s" c r@@ -268,11 +281,11 @@ printMatrix :: Handle -> BS.ByteString -> Int -> [Vector3] -> [Double] -> IO () printMatrix handle ident n []         []     = return () printMatrix handle ident n (vec:vecs) (f:fs) = do hPrintf handle "%5s%c    " (BS.unpack ident) cn-                                                  mapM printEntry [a, b, c]+                                                  mapM_ printEntry [a, b, c]                                                   hPrintf handle "      %9.5f\n" f                                                   printMatrix handle ident (n+1) vecs fs   where [cn] = show n         printEntry :: Double -> IO ()-        printEntry f = hPrintf handle "%10.6f" f+        printEntry = hPrintf handle "%10.6f"         Vector3 a b c = vec 

@@ -278,9 +278,9 @@ -- -- (3) input convertColumns :: [String -> ParsedField] -> [Int] -> String -> [ParsedField]-convertColumns convs cols s = map convert (zip convs content)+convertColumns convs cols s = zipWith convert convs content   where-    convert (conv, s) = conv s+    convert conv s = conv s     content = splitByColumns s cols  {-# INLINE findColumnErrors #-}

@@ -124,7 +124,7 @@ -- Result is a monad action returning a list of 'PDBEvent's. --{-# SPECIALIZE parseATOM :: Bool -> String -> Int -> IO [PDBEvent] #-} parseATOM :: (Monad m) => String -> Int -> m [PDBEvent]-parseATOM line line_no = return $ if errs == []+parseATOM line line_no = return $ if null errs                                     then [result]                                     else errs   where@@ -234,7 +234,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseANISOU :: (Monad m) => String -> Int -> m [PDBEvent]-parseANISOU line line_no = return $ if errs == [] then result `seq` [result] else errs+parseANISOU line line_no = return $ if null errs then result `seq` [result] else errs   where     -- parse     (fields, errs) = parseFields anisouFields line line_no

@@ -41,7 +41,7 @@ -- parseCAVEAT ::  (Monad m) => String -> Int -> m [PDBEvent] -- Result is a monad action returning a list of 'PDBEvent's.-parseCAVEAT line line_no = return $ if errs == []+parseCAVEAT line line_no = return $ if null errs                                    then [result]                                    else errs   where

@@ -62,7 +62,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseCISPEP ::  (Monad m) => String -> Int -> m [PDBEvent]-parseCISPEP line line_no = return $ if errs == []+parseCISPEP line line_no = return $ if null errs                                    then [result]                                    else errs   where

@@ -44,7 +44,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseCONECT :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent]-parseCONECT line line_no = return $ if errs == []+parseCONECT line line_no = return $ if null errs                                       then [result]                                       else errs   where

@@ -48,9 +48,9 @@ -- Result is a monad action returning a list of 'PDBEvent's. {-# SPECIALIZE parseCRYST1 :: BS.ByteString -> Int -> IO [PDBEvent] #-} parseCRYST1 :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent]-parseCRYST1 line line_no = return $ if errs == []+parseCRYST1 line line_no = return $ if null errs                                       then [result]-                                      else errs--}+                                      else errs   where     -- parse     (fields, errs) = parseFields crystFields line line_no

@@ -82,7 +82,7 @@ -- Result is a monad action returning a list of 'PDBEvent's. {-# SPECIALIZE parseDBREF :: BS.ByteString -> Int -> IO [PDBEvent] #-} parseDBREF :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent]-parseDBREF line line_no = return $ if errs == []+parseDBREF line line_no = return $ if null errs                                      then [result]                                      else errs   where@@ -200,7 +200,7 @@ -- Result is a monad action returning a list of 'PDBEvent's. {-# SPECIALIZE parseDBREF12 :: (BS.ByteString, BS.ByteString) -> Int -> IO [PDBEvent] #-} parseDBREF12 :: (Monad m) => (BS.ByteString, BS.ByteString) -> Int -> m [PDBEvent]-parseDBREF12 (!line1, !line2) !line_no = return $ if errs == []+parseDBREF12 (!line1, !line2) !line_no = return $ if null errs                                                     then [result]                                                     else errs   where

@@ -44,7 +44,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseFORMUL ::  (Monad m) => String -> Int -> m [PDBEvent]-parseFORMUL line line_no = return $ if errs == []+parseFORMUL line line_no = return $ if null errs                                    then [result]                                    else errs   where

@@ -37,7 +37,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseHEADER :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent]-parseHEADER line line_no = return $ if errs == [] then [result] else errs+parseHEADER line line_no = return $ if null errs then [result] else errs   where     -- parse     (fields, errs) = parseFields headerFields line line_no

@@ -73,7 +73,7 @@ -- Result is a monad action returning a list of 'PDBEvent's. parseHELIX :: (Monad m) => String -> Int -> m [PDBEvent] parseHELIX line line_no = --return [Test $ BS.pack $ show $ ((length helixFields)::Int)]-  return $ if errs == []+  return $ if null errs                                       then [result]                                       else errs   where

@@ -48,7 +48,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseHET ::  (Monad m) => String -> Int -> m [PDBEvent]-parseHET line line_no = return $ if errs == []+parseHET line line_no = return $ if null errs                                    then [result]                                    else errs   where

@@ -42,7 +42,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseHETNAM :: (Monad m) => Bool -> String -> Int -> m [PDBEvent]-parseHETNAM isNameNotSynonym line line_no = return $ if errs == []+parseHETNAM isNameNotSynonym line line_no = return $ if null errs                                                        then [result]                                                        else errs   where

@@ -77,7 +77,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseHYDBND :: (Monad m) => String -> Int -> m [PDBEvent]-parseHYDBND line line_no = return $ if errs == []+parseHYDBND line line_no = return $ if null errs                                    then [result]                                    else errs -- return $ [PDBParseError 0 0 $ BS.pack $ show $ Prelude.length fields]   where

@@ -37,7 +37,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseIntRecord :: (Monad m) => (Int -> PDBEvent) ->  String -> Int -> m [PDBEvent]-parseIntRecord cons line line_no = return $ if errs == []+parseIntRecord cons line line_no = return $ if null errs                                               then [result]                                               else errs   where

@@ -47,7 +47,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseJournalRef :: (Monad m) => Bool -> BS.ByteString -> Int -> m [PDBEvent]-parseJournalRef isFirst line line_no = return $ if errs == []+parseJournalRef isFirst line line_no = return $ if null errs                                                   then [result]                                                   else errs   where

@@ -68,12 +68,12 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseLINK ::  (Monad m) => String -> Int -> m [PDBEvent]-parseLINK line line_no = return $ if errs == []+parseLINK line line_no = return $ if null errs                                    then [result]                                    else errs   where     -- parse-    errs = if fErrs == [] then fgErrs else fErrs+    errs = if null fErrs then fgErrs else fErrs     (fields, fErrs) = parseFields linkFields line line_no     [fRec, _,      fAtName1, fAltLoc1, fResname1, _, fChain1, fResnum1, fInsCode1, _,

@@ -53,7 +53,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseListRecord :: (Monad m) =>(Int -> [String] -> PDBEvent)-> Char-> String-> Int-> m [PDBEvent]-parseListRecord cons sep line line_no = return $ if errs == []+parseListRecord cons sep line line_no = return $ if null errs                                                    then [result]                                                    else errs   where

@@ -62,7 +62,7 @@ -- (2) input line number -- -- Result is a mionad action returning a list of 'PDBEvent's.-parseMASTER line line_no = return $ if errs == []+parseMASTER line line_no = return $ if null errs                                    then [result]                                    else errs   where

@@ -50,7 +50,7 @@ -- Result is a monad action returning a list of 'PDBEvent's. {-# SPECIALIZE parseMODRES :: BS.ByteString -> Int -> IO [PDBEvent] #-} parseMODRES :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent]-parseMODRES line line_no = return $ if errs == []+parseMODRES line line_no = return $ if null errs                                      then [result]                                      else errs   where@@ -62,7 +62,7 @@     IFStr  stdres  = fStdRes     IFStr  comment = fComment -    errs = if fErrs == [] then fgErrs else fErrs+    errs = if null fErrs then fgErrs else fErrs     fgRes     = fgResidue True "modified" 15 fModRes fChain fSeqNum fInsCode     fgErrs    = liftFgErrs line_no [fgRes]     Right res = fgRes

@@ -52,7 +52,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseMatrixRecord :: (Monad m) =>(Int -> Bool -> Int -> [Vector3] -> [Double] -> PDBEvent)-> String-> Int-> m [PDBEvent]-parseMatrixRecord cons line line_no = return $ if errs == []+parseMatrixRecord cons line line_no = return $ if null errs                                                  then [result]                                                  else errs   where

@@ -59,7 +59,7 @@ -- (3) input line number -- -- Result is a monad action returning a list of 'PDBEvent's.-parseObsoleting cons line line_no = return $ if errs == []+parseObsoleting cons line line_no = return $ if null errs                                                then [result]                                                else errs   where

@@ -43,7 +43,7 @@ -- Result is a monad action returning a list of 'PDBEvent's. parseREMARK :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent] parseREMARK line line_no = -    if errs == []+    if null errs       then (if (num == 1)                             &&                 not (BS.all (==' ') text)              &&                not ("REFERENCE" `BS.isPrefixOf` text)

@@ -75,7 +75,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseREVDAT :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent]-parseREVDAT line line_no = return $ if errs == []+parseREVDAT line line_no = return $ if null errs                                       then [result]                                       else errs   where

@@ -59,7 +59,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseSEQADV :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent]-parseSEQADV line line_no = return $ if errs == []+parseSEQADV line line_no = return $ if null errs                                      then [result]                                      else errs   where@@ -77,7 +77,7 @@                    IFNone       -> Nothing     IFStr  comment   = fComment -    errs      = if fErrs == [] then fgErrs else fErrs+    errs      = if null fErrs then fgErrs else fErrs     fgRes     = maybeFgResidue False "modified residue" 15 fResname fChain fSeqNum fInsCode     fgErrs    = liftFgErrs line_no [fgRes]     Right res = fgRes

@@ -69,7 +69,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseSEQRES :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent]-parseSEQRES line line_no = return $ if errs == []+parseSEQRES line line_no = return $ if null errs                                       then [result]                                       else errs   where

@@ -100,7 +100,7 @@ -- Result is a monad action returning a list of 'PDBEvent's. parseSHEET ::  (Monad m) => String -> Int -> m [PDBEvent] parseSHEET line line_no = --return [Test $ BS.pack $ show $ ((length helixFields)::Int)]-  return $ if errs == []+  return $ if null errs                                       then [result]                                       else errs   where

@@ -94,12 +94,12 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseSITE ::  (Monad m) => String -> Int -> m [PDBEvent]-parseSITE line line_no = return $ if errs == []+parseSITE line line_no = return $ if null errs                                    then [result]                                    else errs   where     -- parse-    errs = if fErrs == [] then fgErrs else fErrs+    errs = if null fErrs then fgErrs else fErrs     (fields, fErrs) = parseFields siteFields line line_no     [fRec, _, fSerial, _, fSiteId, _, fNumRes, _,      fResname1, _, fChain1, fResnum1, fInsCode1, _,

@@ -65,7 +65,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseSLTBRG ::  (Monad m) => String -> Int -> m [PDBEvent]-parseSLTBRG line line_no = return $ if errs == []+parseSLTBRG line line_no = return $ if null errs                                    then [result]                                    else errs   where

@@ -49,7 +49,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseSPLIT :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent]-parseSPLIT line line_no = return $ if errs == []+parseSPLIT line line_no = return $ if null errs                                      then [result]                                      else errs   where

@@ -63,7 +63,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseSSBOND ::  (Monad m) => String -> Int -> m [PDBEvent]-parseSSBOND line line_no = return $ if errs == []+parseSSBOND line line_no = return $ if null errs                                    then [result]                                    else errs   where

@@ -57,7 +57,7 @@     checkEntry :: [String] -> [PDBEvent]     checkEntry [_, _] = []     checkEntry [   _] = []-    checkEntry entry  = [PDBParseError line_no 11 {- column where speclist begins -} $+    checkEntry entry  = [PDBParseError line_no 11 {- column where speclist begins -}                          ("Cannot parse specification list fragment: " `BS.append`                           ( BS.pack . show $ entry))] 

@@ -46,7 +46,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseTER ::  (Monad m) => String -> Int -> m [PDBEvent]-parseTER line line_no = return $ if errs == []+parseTER line line_no = return $ if null errs                                    then [result]                                    else errs   where

@@ -36,7 +36,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseTITLE :: (Monad m) => BS.ByteString -> Int -> m [PDBEvent]-parseTITLE line line_no = return $ if errs == []+parseTITLE line line_no = return $ if null errs                                      then [result]                                      else errs   where

@@ -44,7 +44,7 @@ -- -- Result is a monad action returning a list of 'PDBEvent's. parseTVECT ::  (Monad m) => String -> Int -> m [PDBEvent]-parseTVECT line line_no = return $ if errs == []+parseTVECT line line_no = return $ if null errs                                      then [result]                                      else errs   where

@@ -4,7 +4,7 @@  import qualified Control.Exception(catch) import Control.Exception.Base(SomeException)-import System.IO hiding(writeFile)+import System.IO hiding(writeFile, FilePath) import Prelude hiding(String,writeFile) import Bio.PDB.EventParser.PDBParsingAbstractions import Bio.PDB.Structure.List as L@@ -25,26 +25,30 @@ -- Until I get a newer version of Control.DeepSeq: force x = x `deepseq` x -parse :: String -> IO (Maybe Bio.PDB.Structure.Structure)-parse filename = do input <- Bio.PDB.IO.OpenAnyFile.readFile $ BS.unpack filename-                    (do (structure, errs) <- return $ Bio.PDB.StructureBuilder.parse filename input-                        mapM_ (showError filename) (L.toList errs)-                        structure `deepseq` return $ Just $ structure-                      `Control.Exception.catch`-                     (exceptionHandler filename))+-- | Parse a .pdb file and return `Bio.PDB.Structure.Structure`.+parse :: FilePath -> IO (Maybe Bio.PDB.Structure.Structure)+parse filename = do input <- Bio.PDB.IO.OpenAnyFile.readFile filename+                    do (structure, errs) <- return $ Bio.PDB.StructureBuilder.parse filename input+                       mapM_ (showError filename) (L.toList errs)+                       structure `deepseq` return $ Just structure+                     `Control.Exception.catch`+                     exceptionHandler filename -exceptionHandler :: String -> SomeException -> IO (Maybe a)-exceptionHandler filename e = do printError $ [filename, ":", BS.pack $ show e]+-- | Default exception handler that for `IO (Maybe a)` just prints nice error message to stderr, and returns Nothing+exceptionHandler :: FilePath -> SomeException -> IO (Maybe a)+exceptionHandler filename e = do printError [BS.pack filename, ":", BS.pack $ show e]                                  return Nothing +-- | Prints a catenated list of ByteStrings to stderr. (Convenience function.) printError msg = BS.hPutStrLn System.IO.stderr $ BS.concat msg +-- | Show error message from `PDBParser`. showError filename (PDBParseError line_no col_no msg) =-  printError $ [filename, ":", BS.pack $ show line_no, ":", BS.pack $ show col_no, "\t", msg]+  printError [BS.pack filename, ":", BS.pack $ show line_no, ":", BS.pack $ show col_no, "\t", msg] showError filename (PDBIgnoredLine line)              =-  printError $ [filename, ": IGNORED ", line]+  printError [BS.pack filename, ": IGNORED ", line] --- | Write structure to a .pdb file. (NOT YET IMPLEMENTED)-write :: Bio.PDB.Structure.Structure -> String -> IO ()-write structure fname = writeFile (BS.unpack fname) $ \h -> PDBSP.write h structure+-- | Write structure to a .pdb file.+write :: Bio.PDB.Structure.Structure -> FilePath -> IO ()+write structure fname = writeFile fname $ \h -> PDBSP.write h structure 

@@ -11,6 +11,7 @@ import System.Directory (doesFileExist, getPermissions, Permissions(..)) import System.IO.Error  (userError, IOError) import System.IO        (withFile, IOMode(..))+import Control.Monad    (void) -- if we have zlib: import qualified Codec.Compression.GZip as GZip import qualified Data.ByteString.Lazy   as BSL@@ -21,7 +22,7 @@  -- if we have MMap: #ifdef HAVE_MMAP-import System.IO.Posix.MMap(unsafeMMapFile)+import System.IO.MMap   (mmapFileByteString) #endif  -- otherwise:@@ -35,8 +36,8 @@                         throwNotFound fname  readFile' fname = do content <- simpleRead fname-                     let r = (let codec = getCodec fname content-                              in BS.concat $ BSL.toChunks $ codec $ BSL.fromChunks [content])+                     let r = let codec = getCodec fname content+                             in BS.concat $ BSL.toChunks $ codec $ BSL.fromChunks [content]                      return r  throwNotFound :: String -> IO a@@ -45,7 +46,7 @@ getCodec fname c | (".gz" `BS.isSuffixOf` BS.pack fname) ||                    (".Z"  `BS.isSuffixOf` BS.pack fname) = GZip.decompressWith (gzipParams c) --getCodec fname c | (".bz2" `BS.isSuffixOf` (BS.pack fname)) = BZip.decompressWith (bzipParams c) -- DOESN'T WORK!!!-getCodec fname c | otherwise                             = id+getCodec fname c                                         = id  gzipParams c = GZip.DecompressParams GZip.defaultWindowBits (fromIntegral (BS.length c * 5)) #ifndef OLD_ZLIB@@ -62,13 +63,12 @@                         else return False  #ifndef HAVE_MMAP-simpleRead fname = BS.readFile fname+simpleRead       = BS.readFile  #else-simpleRead fname = unsafeMMapFile fname `Exc.catch` \e -> do reportError (e :: IOError)-                                                             BS.readFile fname+simpleRead fname = mmapFileByteString fname Nothing `Exc.catch` \e -> do reportError (e :: IOError) -- cannot mmap+                                                                         BS.readFile fname   where     reportError e = do putStrLn $ concat [show e, "while trying to mmap('", fname, "')"] #endif -writeFile fname writer = do withFile fname WriteMode $ writer -                            return ()+writeFile fname writer = void $ withFile fname WriteMode writer 

@@ -1,68 +0,0 @@-{-# LANGUAGE TemplateHaskell, MultiParamTypeClasses, FlexibleInstances, FlexibleContexts, NoMonomorphismRestriction #-}-module Bio.PDB.InstantiateIterable(Iterable(..)  ,-                                   gen_iterable  ,-                                   self_iterable ,-                                   trans_iterable) where--import qualified Bio.PDB.Structure.List as L-import Language.Haskell.TH.Syntax-import Control.Monad.Identity(runIdentity,foldM)-import Data.List(foldl')--class Iterable a b where-  imapM   :: (Monad m) => (b -> m b) -> a -> m a-  imap    ::              (b ->   b) -> a ->   a-  imap f e = runIdentity $ imapM (\b -> return $ f b) e-  ifoldM  :: (Monad m) => (c -> b -> m c) -> c -> a -> m c-  ifoldr  ::              (b -> c ->   c) -> c -> a ->   c-  ifoldl  ::              (c -> b ->   c) -> c -> a ->   c-  ifoldl' ::              (c -> b ->   c) -> c -> a ->   c-  ilength :: b -> a -> Int -- NOTE: b is 'dummy' type argument to satisfy Iterable a b constraint---- | Generates a direct instance of iterable between $typA and $typB with---   given names of getter and setter, so that:---   $getter :: $typA -> $typB ---   $setter :: $typB -> $typA -> $typA-gen_iterable typA typB getter setter = -  [d| instance Iterable $(typA) $(typB) where-        imapM f a =-          do b' <- L.mapM f ( $(getter) a)-             return $ $(setter) a b'-        ifoldM  f e a  = do r <- L.foldM f e ( $(getter) a)-                            return r-        ifoldr  f e a = L.foldr  f e ( $(getter) a)-        ifoldl  f e a = L.foldl  f e ( $(getter) a)-        ifoldl' f e a = L.foldl' f e ( $(getter) a) -        ilength   d a = L.length ( $(getter) a)-    |]---- | Generates convenience function for iterating over a single object.-self_iterable typA = -  [d| instance Iterable $(typA) $(typA) where-        imapM f a     = f a -        ifoldM  f e a = f e a-        ifoldr  f e a = f a e-        ifoldl  f e a = f e a -        ifoldl' f e a = f e a-        ilength   d a = 1-    |]---self_iterable typA = gen_iterable typA typA [e| id |] [e| L.singleton |]---- This works:---   ilength     a = L.length     ( $(getter) a)---- | Generates a transitive instance of `Iterable` between $typA and $typC,---   assuming existence of `Iterable` $typA $typB, and `Iterable` $typB $typC.-trans_iterable typA typB typC = -  [d| instance Iterable $(typA) $(typC) where-        imapM   f a   = (imapM   :: (Monad m) => ( $(typB) -> m $(typB) ) -> $(typA)   -> m $(typA) ) (imapM f) a -        imap    f a   = (imap    ::              ( $(typB) ->   $(typB) ) -> $(typA)   ->   $(typA) ) (imap  f) a -        ifoldM  f e a = (ifoldM  :: (Monad m) => (c -> $(typB)   -> m c) -> c   -> $(typA)   -> m c       ) (ifoldM  f) e a -        ifoldr  f e a = (ifoldr  ::              ($(typB) -> c   ->   c) -> c   -> $(typA)   ->   c       ) (\bb cc -> ifoldr  f cc bb) e a-        ifoldl  f e a = (ifoldl  ::              (c -> $(typB)   ->   c) -> c   -> $(typA)   ->   c       ) (ifoldl  f) e a-        ifoldl' f e a = (ifoldl' ::              (c -> $(typB)   ->   c) -> c   -> $(typA)   ->   c       ) (ifoldl' f) e a-        ilength _   a = (ifoldl' ::              (c -> $(typB)   ->   c) -> c   -> $(typA)   ->   c       ) (\a b-> a + ilength (undefined :: $(typC)) b) 0 a-    |]--- How to make this work:---       ilength     a = (ifoldl' ::              (Int -> $(typB) -> Int) -> Int -> $(typA)   ->   Int     ) (\i b -> i+(ilength :: Iterable $(typB) $(typC) => $(typB) -> Int) b) 0 a-

@@ -1,20 +1,23 @@ {-# LANGUAGE MultiParamTypeClasses, FlexibleInstances, UndecidableInstances, OverlappingInstances, TemplateHaskell, FlexibleContexts #-}+-- | Instances of Iterable class. module Bio.PDB.Iterable(Iterable(..)) where +import Data.Iterable+import Data.Iterable.Instantiate+import Data.Iterable.Instantiate.Vector+import Data.Vector import Bio.PDB.Structure.List as L import Bio.PDB.Structure  import Control.Monad.Identity import Control.Monad(foldM) -import Bio.PDB.InstantiateIterable--$(gen_iterable [t| Structure |] [t| Model   |] [e| models   |] [e| (\s m -> s { models   = m }) |] )+$(gen_vector_iterable [t| Structure |] [t| Model   |] [e| models   |] [e| (\s m -> s { models   = m }) |] ) -$(gen_iterable [t| Model     |] [t| Chain   |] [e| chains   |] [e| (\s m -> s { chains   = m }) |] )+$(gen_vector_iterable [t| Model     |] [t| Chain   |] [e| chains   |] [e| (\s m -> s { chains   = m }) |] ) -$(gen_iterable [t| Chain     |] [t| Residue |] [e| residues |] [e| (\s m -> s { residues = m }) |] )+$(gen_vector_iterable [t| Chain     |] [t| Residue |] [e| residues |] [e| (\s m -> s { residues = m }) |] ) -$(gen_iterable [t| Residue   |] [t| Atom    |] [e| atoms    |] [e| (\s m -> s { atoms    = m }) |] )+$(gen_vector_iterable [t| Residue   |] [t| Atom    |] [e| atoms    |] [e| (\s m -> s { atoms    = m }) |] )  $(self_iterable [t| Structure |] ) $(self_iterable [t| Model     |] )

@@ -1,4 +1,4 @@-{-# LANGUAGE BangPatterns, DisambiguateRecordFields #-}+{-# LANGUAGE DisambiguateRecordFields #-} module Bio.PDB.Structure(String,                          vdot, vnorm, vproj, vperpend, vperpends, vdihedral, (*|), (|*),                          Structure(..), Model(..), Chain(..), Residue(..), Atom(..))

@@ -1,4 +1,4 @@-{-# LANGUAGE OverloadedStrings, BangPatterns #-}+{-# LANGUAGE OverloadedStrings #-} module Bio.PDB.Structure.Elements(Element(..),                                   -- Finding element for a given atom                                   assignElement,

@@ -70,7 +70,7 @@                                   when (i < 0) $ fail "Negative STRef"                                   let j = i + 1                                       l = M.length v-                                  v' <- if (j > l)+                                  v' <- if j > l                                           then do nV <- M.grow v j                                                   writeSTRef vs nV                                                   return nV

@@ -1,6 +1,6 @@ {-# LANGUAGE NoMonomorphismRestriction, BangPatterns #-}-module Bio.PDB.Structure.Vector(Vec3D(..),-                                unpackVec3D,+module Bio.PDB.Structure.Vector(Vector3(..),+                                unpackVector3,                                 vnormalise, vdot, (*|), (|*),                                 vzip, vmap,                                 vnorm, vproj, vperpend, vperpends, vdihedral) where@@ -10,54 +10,51 @@ import Data.List(foldl') import Test.QuickCheck --- ^ This module wraps 3D vector operations, and adds missing ones. Also hides a "Vector" class---- | Defines type alias for position and translation vectors in PDB structures.-type Vec3D = Vector3+-- ^ This module wraps 3D vector operations, and adds missing ones.  -- | Unpacks an abstract 3D vector into a triple of Doubles.-unpackVec3D :: Vec3D -> (Double, Double, Double)-unpackVec3D (Vector3 x y z) = (x, y, z)+unpackVector3 :: Vector3 -> (Double, Double, Double)+unpackVector3 (Vector3 x y z) = (x, y, z)  -- | Maps an operation that modifies a Double onto a 3D vector. {-# INLINE vmap #-}-vmap :: (Double -> Double) -> Vec3D -> Vec3D+vmap :: (Double -> Double) -> Vector3 -> Vector3 vmap = C.vmap  -- | Maps an operation on a pair of Doubles onto a pair of 3D vectors --   coordinatewise.-vzip :: (Double -> Double -> Double) -> Vec3D -> Vec3D -> Vec3D+vzip :: (Double -> Double -> Double) -> Vector3 -> Vector3 -> Vector3 vzip = C.vzip  -- | Normalises to a unit vector in the same direction as input. {-# INLINE vnormalise #-}-vnormalise :: Vec3D -> Vec3D+vnormalise :: Vector3 -> Vector3 vnormalise = C.vnormalise   -- | Computes a dot product of two 3D vectors. {-# INLINE vdot #-}-vdot :: Vec3D -> Vec3D -> Double+vdot :: Vector3 -> Vector3 -> Double vdot = C.vdot  {-# INLINE vnorm #-} -- | 2-norm of a vector (also called a magnitude or length.)-vnorm :: Vec3D -> Double+vnorm :: Vector3 -> Double vnorm = C.vmag  {-# INLINE vdihedral #-} -- | Compute dihedral between three bond vectors using spherical angle formula.-vdihedral :: Vec3D -> Vec3D -> Vec3D -> Double-vdihedral !a !b !c = (atan2 (vnorm b * (a `vdot`  (b `vcross` c)))-                            ((a `vcross` b) `vdot` (b `vcross` c)) )+vdihedral :: Vector3 -> Vector3 -> Vector3 -> Double+vdihedral !a !b !c = atan2 (vnorm b * (a `vdot`  (b `vcross` c)))+                           ((a `vcross` b) `vdot` (b `vcross` c))  -- | Scalar product. (`*` indicates side on which one can put a scalar.) {-# INLINE (*|) #-}-(*|) :: Double -> Vec3D  -> Vec3D+(*|) :: Double -> Vector3  -> Vector3 (*|) = (C.*|)  -- | Scalar product. (`*` indicates side on which one can put a scalar.) {-# INLINE (|*) #-}-(|*) :: Vec3D  -> Double -> Vec3D+(|*) :: Vector3  -> Double -> Vector3 (|*) = (C.|*)  {-# INLINE vproj #-}

@@ -1,4 +1,4 @@-{-# LANGUAGE BangPatterns, DisambiguateRecordFields, MultiParamTypeClasses, NamedFieldPuns, FlexibleContexts, OverloadedStrings, PatternGuards, RankNTypes #-}+{-# LANGUAGE BangPatterns, DisambiguateRecordFields, MultiParamTypeClasses, NamedFieldPuns, FlexibleContexts, OverloadedStrings, RankNTypes #-} {-# LANGUAGE RecordWildCards #-} -- for convenient debugging {-# OPTIONS_GHC -fspec-constr-count=2 #-} module Bio.PDB.StructureBuilder(parse)@@ -11,6 +11,7 @@ import Control.Monad.State.Strict      as State  import Control.Monad(when) import Data.STRef                      as STRef+import Data.Maybe(isNothing, isJust)  import Bio.PDB.EventParser.PDBEvents(PDBEvent(..), RESID(..)) import qualified Bio.PDB.EventParser.PDBEventParser(parsePDBRecords)@@ -28,14 +29,14 @@ parsePDBRec :: String -> String -> (() -> PDBEvent -> ParsingMonad t ()) -> () -> ParsingMonad t () parsePDBRec = Bio.PDB.EventParser.PDBEventParser.parsePDBRecords ---parse :: (State.MonadState BState m) => String -> String -> m (Structure, [PDBEvent]) -- | Given filename, and contents, parses a whole PDB file, returning a monadic action -- | with a tuple of (Structure, [PDBEvent]), where the list of events contains all -- | parsing or construction errors.+--parse :: (State.MonadState BState m) => FilePath -> String -> m (Structure, [PDBEvent]) parse fname contents = ST.runST $ do initial <- initializeState                                      (s, e)  <- State.evalStateT parsing initial-                                     return $! (s :: Structure, e :: L.List PDBEvent)-  where parsing = do parsePDBRec fname contents (\() !ev -> parseStep ev) ()+                                     return (s :: Structure, e :: L.List PDBEvent)+  where parsing = do parsePDBRec (BS.pack fname) contents (\() !ev -> parseStep ev) ()                      closeStructure                      s  <- State.gets currentStructure                      e  <- State.gets errors@@ -52,7 +53,7 @@                          modelContents     :: L.TempList  s Chain,                          structureContents :: L.TempList  s Model,                          errors            :: L.TempList  s PDBEvent,-                         line_no           :: STRef.STRef s Int+                         lineNo           :: STRef.STRef s Int                        }  -- | Initial state of the structure record builder.@@ -63,16 +64,16 @@                      s  <- L.initialNew 1                      e  <- L.initialNew 100                      l  <- STRef.newSTRef 1-                     return $ BState { currentResidue    = Nothing,-                                       currentModel      = Nothing,-                                       currentChain      = Nothing,-                                       currentStructure  = Structure { models = L.empty },-                                       residueContents   = r,-                                       chainContents     = c,-                                       modelContents     = m,-                                       structureContents = s,-                                       errors            = e,-                                       line_no           = l }+                     return BState { currentResidue    = Nothing,+                                     currentModel      = Nothing,+                                     currentChain      = Nothing,+                                     currentStructure  = Structure { models = L.empty },+                                     residueContents   = r,+                                     chainContents     = c,+                                     modelContents     = m,+                                     structureContents = s,+                                     errors            = e,+                                     lineNo           = l } -- | Checks that a residue with a given identification tuple is current, -- | or if not, then closes previous residue (if present), -- | and marks a new ,,current'' residue in a state of builder.@@ -109,8 +110,8 @@   where     chainChanged Nothing                               = True     chainChanged (Just (Chain { chainId = oldChain })) = oldChain /= name-    createChain l state = state { currentChain = Just $! Chain { chainId  = name,-                                                                 residues = L.empty },+    createChain l state = state { currentChain = Just Chain { chainId  = name,+                                                              residues = L.empty },                                   chainContents = l }  @@ -120,18 +121,18 @@ --       [Otherwise one needs to report an error!] checkModel :: ParsingMonad t () checkModel = do curModel <- State.gets currentModel-                when (curModel == Nothing) $ openModel 1+                when (isNothing curModel) $ openModel 1 -- | Closes construction of a current residue and appends this residue to a current chain. (Monadic action.) --closeResidue :: State.State BState ()  closeResidue :: ParsingMonad t () closeResidue = do r <- State.gets currentResidue-                  when (r /= Nothing) $ do let Just res = r-                                           rc  <- State.gets residueContents-                                           rf  <- L.finalize rc-                                           cc  <- State.gets chainContents-                                           cc' <- L.add cc $ res { Bio.PDB.Structure.atoms = rf }-                                           State.modify clearResidue+                  when (isJust r) $ do let Just res = r+                                       rc  <- State.gets residueContents+                                       rf  <- L.finalize rc+                                       cc  <- State.gets chainContents+                                       cc' <- L.add cc $ res { Bio.PDB.Structure.atoms = rf }+                                       State.modify clearResidue   where     clearResidue st = st { currentResidue = Nothing } @@ -142,21 +143,21 @@ closeChain = do closeResidue                 c  <- State.gets currentChain                 ac <- State.gets chainContents-                when (c /= Nothing) $ do l   <- State.gets chainContents-                                         l'  <- L.finalize l-                                         let Just ch = c-                                             ch' = ch { Bio.PDB.Structure.residues = l' }-                                         m   <- State.gets currentModel-                                         when (m == Nothing) $ do mli <- State.gets structureContents-                                                                  i <- L.tempLength mli-                                                                  openModel i-                                                                  addError ["Trying to close chain when currentChain is ",-                                                                            BS.pack . show $ ch,-                                                                            " and currentModel is ",-                                                                            BS.pack . show $ m]-                                         ml  <- State.gets modelContents-                                         ml' <- L.add ml ch'-                                         State.modify clearChain+                when (isJust c) $ do l   <- State.gets chainContents+                                     l'  <- L.finalize l+                                     let Just ch = c+                                         ch' = ch { Bio.PDB.Structure.residues = l' }+                                     m   <- State.gets currentModel+                                     when (isNothing m) $ do mli <- State.gets structureContents+                                                             i <- L.tempLength mli+                                                             openModel i+                                                             addError ["Trying to close chain when currentChain is ",+                                                                       BS.pack . show $ ch,+                                                                       " and currentModel is ",+                                                                       BS.pack . show $ m]+                                     ml  <- State.gets modelContents+                                     ml' <- L.add ml ch'+                                     State.modify clearChain   where     clearChain st = st { currentChain = Nothing } @@ -165,11 +166,12 @@ -- TODO: forgot about line/column number passing! addError :: [String] -> ParsingMonad t () addError msg = do e  <- State.gets errors-                  lnref <- State.gets line_no+                  lnref <- State.gets lineNo                   ln <- lift $ STRef.readSTRef lnref                   lift $ STRef.modifySTRef lnref (+1)                   L.add e $ anError ln-  where anError ln = PDBParseError ln 0 $ BS.concat msg+  where+    anError ln = PDBParseError ln 0 $ BS.concat msg  -- | Finalizes construction of current model closeModel :: ParsingMonad t ()@@ -199,14 +201,14 @@                structureContents = undefined }  nextLine :: ParsingMonad t ()-nextLine = do lnref <- State.gets line_no+nextLine = do lnref <- State.gets lineNo               lift $ STRef.modifySTRef lnref (+1)  -- | Performs a match on a single PDBEvent and performs relevant change to a BState of structure builder. --parseStep   :: (State.MonadState BState m) => PDBEvent -> m () parseStep pe@(PDBParseError l _ _) = do e  <- State.gets errors                                         L.add e pe -                                        lnref <- State.gets line_no+                                        lnref <- State.gets lineNo                                         lift $ STRef.writeSTRef lnref l parseStep (ATOM { no        = atSer,      -- :: !Int,                   atomtype  = atType,     -- :: !String,

@@ -1,128 +1,15 @@ {-# LANGUAGE CPP #-} --- | This module contains instances of `NFData` for Data.ByteString---   and `Params` before text-format 0.3.0.8.+-- | This module contains instances of `NFData` for Data.ByteString. module Bio.PDB.Util.MissingInstances() where  import Prelude() import qualified Data.ByteString as BS import Control.DeepSeq -#ifdef DEFINE_PARAMS_INSTANCES-import Data.Text.Buildable-import Data.Text.Format.Types-import Data.Text.Lazy.Builder-import Data.Text.Format.Params(Params(..))-#endif-- #ifdef DEFINE_NFDATA_INSTANCE -- I use strict version of BS.ByteString so default implementation should do -- | Nothing needs to be done in NFData instance for stricty `BS.ByteString`. instance NFData BS.ByteString where #endif -#ifdef DEFINE_PARAMS_INSTANCES---- | Adds instances of Params for tuples of more than ten Buildables.-instance (Buildable a, Buildable b, Buildable c, Buildable d, Buildable e,-          Buildable f, Buildable g, Buildable h, Buildable i, Buildable j,-          Buildable k)-    => Params (a,b,c,d,e,f,g,h,i,j,k) where-    buildParams (a,b,c,d,e,f,g,h,i,j,k) =-        [build a, build b, build c, build d, build e,-         build f, build g, build h, build i, build j,-         build k]--instance (Buildable a, Buildable b, Buildable c, Buildable d, Buildable e,-          Buildable f, Buildable g, Buildable h, Buildable i, Buildable j,-          Buildable k, Buildable l)-    => Params (a,b,c,d,e,f,g,h,i,j,k,l) where-    buildParams (a,b,c,d,e,f,g,h,i,j,k,l) =-        [build a, build b, build c, build d, build e,-         build f, build g, build h, build i, build j,-         build k, build l]--instance (Buildable a, Buildable b, Buildable c, Buildable d, Buildable e,-          Buildable f, Buildable g, Buildable h, Buildable i, Buildable j,-          Buildable k, Buildable l, Buildable m)-    => Params (a,b,c,d,e,f,g,h,i,j,k,l,m) where-    buildParams (a,b,c,d,e,f,g,h,i,j,k,l,m) =-        [build a, build b, build c, build d, build e,-         build f, build g, build h, build i, build j,-         build k, build l, build m]--instance (Buildable a, Buildable b, Buildable c, Buildable d, Buildable e,-          Buildable f, Buildable g, Buildable h, Buildable i, Buildable j,-          Buildable k, Buildable l, Buildable m, Buildable n)-    => Params (a,b,c,d,e,f,g,h,i,j,k,l,m,n) where-    buildParams (a,b,c,d,e,f,g,h,i,j,k,l,m,n) =-        [build a, build b, build c, build d, build e,-         build f, build g, build h, build i, build j,-         build k, build l, build m, build n]--instance (Buildable a, Buildable b, Buildable c, Buildable d, Buildable e,-          Buildable f, Buildable g, Buildable h, Buildable i, Buildable j,-          Buildable k, Buildable l, Buildable m, Buildable n, Buildable o)-    => Params (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o) where-    buildParams (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o) =-        [build a, build b, build c, build d, build e,-         build f, build g, build h, build i, build j,-         build k, build l, build m, build n, build o]--instance (Buildable a, Buildable b, Buildable c, Buildable d, Buildable e,-          Buildable f, Buildable g, Buildable h, Buildable i, Buildable j,-          Buildable k, Buildable l, Buildable m, Buildable n, Buildable o,-          Buildable p)-    => Params (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p) where-    buildParams (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p) =-        [build a, build b, build c, build d, build e,-         build f, build g, build h, build i, build j,-         build k, build l, build m, build n, build o,-         build p]--instance (Buildable a, Buildable b, Buildable c, Buildable d, Buildable e,-          Buildable f, Buildable g, Buildable h, Buildable i, Buildable j,-          Buildable k, Buildable l, Buildable m, Buildable n, Buildable o,-          Buildable p, Buildable r)-    => Params (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p,r) where-    buildParams (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p,r) =-        [build a, build b, build c, build d, build e,-         build f, build g, build h, build i, build j,-         build k, build l, build m, build n, build o,-         build p, build r]--instance (Buildable a, Buildable b, Buildable c, Buildable d, Buildable e,-          Buildable f, Buildable g, Buildable h, Buildable i, Buildable j,-          Buildable k, Buildable l, Buildable m, Buildable n, Buildable o,-          Buildable p, Buildable r, Buildable s)-    => Params (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p,r,s) where-    buildParams (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p,r,s) =-        [build a, build b, build c, build d, build e,-         build f, build g, build h, build i, build j,-         build k, build l, build m, build n, build o,-         build p, build r, build s]--instance (Buildable a, Buildable b, Buildable c, Buildable d, Buildable e,-          Buildable f, Buildable g, Buildable h, Buildable i, Buildable j,-          Buildable k, Buildable l, Buildable m, Buildable n, Buildable o,-          Buildable p, Buildable r, Buildable s, Buildable t)-    => Params (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p,r,s,t) where-    buildParams (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p,r,s,t) =-        [build a, build b, build c, build d, build e,-         build f, build g, build h, build i, build j,-         build k, build l, build m, build n, build o,-         build p, build r, build s, build t]--instance (Buildable a, Buildable b, Buildable c, Buildable d, Buildable e,-          Buildable f, Buildable g, Buildable h, Buildable i, Buildable j,-          Buildable k, Buildable l, Buildable m, Buildable n, Buildable o,-          Buildable p, Buildable r, Buildable s, Buildable t, Buildable u)-    => Params (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p,r,s,t,u) where-    buildParams (a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p,r,s,t,u) =-        [build a, build b, build c, build d, build e,-         build f, build g, build h, build i, build j,-         build k, build l, build m, build n, build o,-         build p, build r, build s, build t, build u]--#endif

@@ -0,0 +1,32 @@+Please use either `cabal install` or `runhaskell Setup configure --user`+to install or configure the package. This is because `runhaskell Setup`+defaults to use global package database, and thus may give spurious error+messages, when the dependencies are installed in user's package database.++For a fresh GHC install on Ubuntu, you may first need to `apt-get install+zlib1g-dev` to get zlib header files.++Troubleshooting:+1. `runhaskell Setup configure` tells that dependencies are missing,+even though I have them installed!++Use `runhaskell Setup configure --user` or see Cabal FAQ:+http://www.haskell.org/cabal/FAQ.html#runghc-setup-complains-of-missing-packages++2. double-conversion dependency breaks the linking process with error:++This is known GHC bug that may appear in FreeBSD and Windows:+http://ghc.haskell.org/trac/ghc/ticket/5289++Workaround is to switch off the flag that makes printing faster:+Append `-f-have-double-conversion` to `cabal install` or `runhaskell Setup+configure` arguments.++3. [Windows] Cannot get `unix` dependency.++Please switch off using bytestring-mmap package by appending flag+`-f-have-mmap` to `cabal install` or `runhaskell Setup configure` arguments.++TODO: try to change *.cabal file so it is done automatically.++4. 

@@ -0,0 +1,13 @@+hPDB+====+Haskell PDB file format parser.++[![Build Status](https://api.travis-ci.org/mgajda/hPDB.png?branch=master)](https://www.travis-ci.org/mgajda/hPDB)++Protein Data Bank file format is a most popular format for holding biomolecule data.++This is a very fast parser: below 7s for the largest entry in PDB - 1HTQ which is over 70MB - as compared with 11s of RASMOL 2.7.5, or 2m15s of BioPython with Python 2.6 interpreter.++It is aimed to not only deliver event-based interface, but also a high-level data structure for manipulating data in spirit of BioPython's PDB parser. ++Details on official releases are on [Hackage](http://hackage.haskell.org/package/hPDB).

@@ -1,4 +1,18 @@ #! /usr/bin/env runhaskell +module Main(main) where+ import Distribution.Simple-main = defaultMain+import System.Environment+import Control.Monad(when)+import Data.List(isPrefixOf)++-- Defaults to installing in --user package database.+isPkgDbOpts arg = ("--package-db" `isPrefixOf` arg  ) || (arg `elem` ["--user", "--global"])+haveNotPkgDbOpts   = not . any isPkgDbOpts++main = do args <- getArgs+          defaultMainArgs $ if (length args > 0 && (head args `elem` ["configure", "install"]) && haveNotPkgDbOpts args)+                              then (head args:"--user":tail args)+                              else args+            

@@ -1,40 +1,46 @@ name:                hPDB-version:             0.99-stability:           beta+version:             0.999+synopsis:            Protein Databank file format library homepage:            https://github.com/mgajda/hpdb+stability:           beta package-url:         http://hackage.haskell.org/package/hPDB-synopsis:            Parser, print and manipulate structures in PDB file format. description:         Protein Data Bank file format is a most popular format for holding biomolecule data.--  This is a very fast parser (below 7s for the largest entry in PDB - 1HTQ which is over 70MB - as compared with 11s of RASMOL 2.7.5, or 2m15s of BioPython with Python 2.6 interpreter.)--  It is aimed to not only deliver event-based interface, but also a high-level data structure for manipulating data in spirit of BioPython's PDB parser. -+                     .+                     This is a very fast parser: below 7s for the largest entry in PDB - 1HTQ which is over 70MB - as compared with 11s of RASMOL 2.7.5, or 2m15s of BioPython with Python 2.6 interpreter.+                     .+                     It is aimed to not only deliver event-based interface, but also a high-level data structure for manipulating data in spirit of BioPython's PDB parser.  category:            Bioinformatics  license:             BSD3 license-file:        LICENSE  author:              Michal J. Gajda-copyright:           Copyright by Michal J. Gajda '2009-'2012+copyright:           Copyright by Michal J. Gajda '2009-'2013 maintainer:          mjgajda@googlemail.com bug-reports:         mailto:mjgajda@googlemail.com  build-type:          Simple cabal-version:       >=1.8-tested-with:         GHC==7.4.1, GHC==7.0.3, GHC==7.4.2---Need to re-test: GHC==6.12.1,  GHC==7.0.4, GHC==7.1.20101026 +tested-with:         GHC==7.0.3, GHC==7.2.2, GHC==7.4.1, GHC==7.4.2, GHC==7.6.1, GHC==7.6.2+extra-source-files:  README.md INSTALL AUTHORS +source-repository head+  type:     git+  location: https://github.com/mgajda/hPDB+ flag have-mmap-  description: Use bytestring-mmap to read input faster.+  description: Use mmap to read input faster.   default: True  flag have-sse2   description: Use -msse2 for faster code.   default: True -flag old-text-format-  description: Use text-format versions before 0.3.0.9 (and define Params instance for 11-tuple to 20-tuple yourself.)-               Disable for (yet unreleased) versions after 0.3.0.8 when change was merged into upstream.+flag have-text-format+  description: Do not use text-format, since it may require double-conversion+               and thus linking of libstdc++ which may break compilation+               due to GHC bug #5289:+               .+               http://ghc.haskell.org/trac/ghc/ticket/5289   default: True  flag old-bytestring@@ -58,17 +64,15 @@  Library   ghc-options:      -fspec-constr-count=4 -O3 -  build-depends:    base>=4.0, base <4.7, ghc-prim, directory, mtl, template-haskell, vector, AC-Vector, containers, deepseq, QuickCheck >= 2.5.0.0, text>=0.11.1.13+  build-depends:    base>=4.0, base <4.7, ghc-prim, directory, mtl, template-haskell, vector, AC-Vector, containers, deepseq, QuickCheck >= 2.5.0.0, text>=0.11.1.13, iterable >= 1.0   if flag(have-mmap)-    build-depends: bytestring-mmap+    build-depends: mmap     cpp-options: -DHAVE_MMAP-  if flag(have-sse2)-    ghc-options: -fspec-constr-count=4 -O3 -  if flag(old-text-format)-    cpp-options: -DDEFINE_PARAMS_INSTANCES-    build-depends: text-format <= 0.3.0.8-  else-    build-depends: text-format >= 0.3.0.9+  -- These optimization options change a lot for GHC >= 7.4.1+  ghc-options: -fspec-constr-count=4 -O3 +  if flag(have-text-format)+    cpp-options: -DHAVE_TEXT_FORMAT+    build-depends: text-format >= 0.3.1.0   if flag(old-bytestring)     cpp-options: -DDEFINE_NFDATA_INSTANCE     build-depends: bytestring <= 0.9.2.1@@ -84,8 +88,8 @@     build-depends: zlib <= 0.5.3.3   else     build-depends: zlib >= 0.5.4.0-  other-extensions:       ScopedTypeVariables OverloadedStrings BangPatterns NoMonomorphismRestriction EmptyDataDecls MagicHash-  other-modules:    Bio.PDB.EventParser.ParseATOM, Bio.PDB.EventParser.ParseCAVEAT, Bio.PDB.EventParser.ParseCISPEP, Bio.PDB.EventParser.ParseCONECT, Bio.PDB.EventParser.ParseCRYST1, Bio.PDB.EventParser.ParseDBREF, Bio.PDB.EventParser.ParseFORMUL, Bio.PDB.EventParser.ParseHEADER, Bio.PDB.EventParser.ParseHELIX, Bio.PDB.EventParser.ParseHET, Bio.PDB.EventParser.ParseHETNAM, Bio.PDB.EventParser.ParseHYDBND, Bio.PDB.EventParser.ParseIntRecord, Bio.PDB.EventParser.ParseJRNL, Bio.PDB.EventParser.ParseLINK, Bio.PDB.EventParser.ParseListRecord, Bio.PDB.EventParser.ParseMASTER, Bio.PDB.EventParser.ParseMatrixRecord, Bio.PDB.EventParser.ParseMODRES, Bio.PDB.EventParser.ParseObsoleting, Bio.PDB.EventParser.ParseREMARK, Bio.PDB.EventParser.ParseREVDAT, Bio.PDB.EventParser.ParseSEQADV, Bio.PDB.EventParser.ParseSEQRES, Bio.PDB.EventParser.ParseSHEET, Bio.PDB.EventParser.ParseSITE, Bio.PDB.EventParser.ParseSLTBRG, Bio.PDB.EventParser.ParseSpecListRecord, Bio.PDB.EventParser.ParseSPLIT, Bio.PDB.EventParser.ParseSSBOND, Bio.PDB.EventParser.ParseTER, Bio.PDB.EventParser.ParseTITLE, Bio.PDB.EventParser.ParseTVECT, Bio.PDB.EventParser.PDBParsingAbstractions, Bio.PDB.EventParser.FastParse, Bio.PDB.Util.MissingInstances, Bio.PDB.Common, Bio.PDB.InstantiateIterable, Bio.PDB.Iterable.Utils+  other-extensions:       ScopedTypeVariables OverloadedStrings BangPatterns NoMonomorphismRestriction EmptyDataDecls MagicHash CPP PatternGuards NamedFieldPuns DisambiguateRecordFields TemplateHaskell MultiParamTypeClasses FlexibleInstances FlexibleContexts+  other-modules:    Bio.PDB.EventParser.ParseATOM, Bio.PDB.EventParser.ParseCAVEAT, Bio.PDB.EventParser.ParseCISPEP, Bio.PDB.EventParser.ParseCONECT, Bio.PDB.EventParser.ParseCRYST1, Bio.PDB.EventParser.ParseDBREF, Bio.PDB.EventParser.ParseFORMUL, Bio.PDB.EventParser.ParseHEADER, Bio.PDB.EventParser.ParseHELIX, Bio.PDB.EventParser.ParseHET, Bio.PDB.EventParser.ParseHETNAM, Bio.PDB.EventParser.ParseHYDBND, Bio.PDB.EventParser.ParseIntRecord, Bio.PDB.EventParser.ParseJRNL, Bio.PDB.EventParser.ParseLINK, Bio.PDB.EventParser.ParseListRecord, Bio.PDB.EventParser.ParseMASTER, Bio.PDB.EventParser.ParseMatrixRecord, Bio.PDB.EventParser.ParseMODRES, Bio.PDB.EventParser.ParseObsoleting, Bio.PDB.EventParser.ParseREMARK, Bio.PDB.EventParser.ParseREVDAT, Bio.PDB.EventParser.ParseSEQADV, Bio.PDB.EventParser.ParseSEQRES, Bio.PDB.EventParser.ParseSHEET, Bio.PDB.EventParser.ParseSITE, Bio.PDB.EventParser.ParseSLTBRG, Bio.PDB.EventParser.ParseSpecListRecord, Bio.PDB.EventParser.ParseSPLIT, Bio.PDB.EventParser.ParseSSBOND, Bio.PDB.EventParser.ParseTER, Bio.PDB.EventParser.ParseTITLE, Bio.PDB.EventParser.ParseTVECT, Bio.PDB.EventParser.PDBParsingAbstractions, Bio.PDB.EventParser.FastParse, Bio.PDB.Util.MissingInstances, Bio.PDB.Common, Bio.PDB.Iterable.Utils   exposed-modules:  Bio.PDB.EventParser.PDBEvents, Bio.PDB.EventParser.PDBEventParser, Bio.PDB.EventParser.ExperimentalMethods, Bio.PDB.EventParser.HelixTypes, Bio.PDB.EventParser.StrandSense, Bio.PDB.Structure, Bio.PDB.StructureBuilder, Bio.PDB.Iterable, Bio.PDB.IO, Bio.PDB.Fasta, Bio.PDB, Bio.PDB.Structure.Vector, Bio.PDB.Structure.Elements, Bio.PDB.Structure.List, Bio.PDB.StructurePrinter, Bio.PDB.EventParser.PDBEventPrinter, Bio.PDB.IO.OpenAnyFile   exposed:          True