ClustalParser 1.1.2 → 1.1.3

raw patch · 4 files changed

+33/−6 lines, 4 filesPVP ok

version bump matches the API change (PVP)

API changes (from Hackage documentation)

Files

• ClustalParser.cabal +3/−3
• ClustalParserTest.hs +1/−1
• changelog +3/−0
• src/Bio/ClustalParser.hs +26/−2

@@ -5,7 +5,7 @@ -- PVP summary:      +-+------- breaking API changes --                   | | +----- non-breaking API additions --                   | | | +--- code changes with no API change-version:             1.1.2+version:             1.1.3 synopsis:            Libary for parsing Clustal tools output description:         Currently contains parsers and datatypes for: clustalw2, clustalo, mlocarna, cmalign                      .@@ -36,8 +36,8 @@  source-repository this   type:     git-  location: https://github.com/eggzilla/ClustalParser/tree/1.1.2-  tag:      1.1.2+  location: https://github.com/eggzilla/ClustalParser/tree/1.1.3+  tag:      1.1.3  library   -- Modules exported by the library.

@@ -9,7 +9,7 @@   args <- getArgs   let input_file = (head args)                                        -- read Clustal outputfile-  parsedinput <- readStructuralClustalAlignment input_file+  parsedinput <- readClustalAlignment input_file   --parsedinput <- readStructuralClustalAlignment input_file   --print (entrySequenceIdentifier (head (structuralAlignmentEntries(fromRight parsedinput))))   print (fromRight parsedinput)

@@ -1,4 +1,7 @@ -*-change-log-*-+1.1.3 Florian Eggenhofer <florian.eggenhofer@univie.ac.at> 4. July 2015+        * Nucleotide sequences are now parsed by a unified function in line+	with IUPAC nucleotide code 1.1.2 Florian Eggenhofer <florian.eggenhofer@univie.ac.at> 3. July 2015         * Included parsing of optional field in mlocarna clustal output 1.1.1 Florian Eggenhofer <florian.eggenhofer@univie.ac.at> 2. July 2015

@@ -150,7 +150,7 @@ genParserClustalEntrySlice = do   sliceIdentifier <- many1 (noneOf " ")   spacer <- many1 (char ' ')-  sliceSequence <- many1 (oneOf ".SNYRUAGCT-uagct")+  sliceSequence <- parseNucleotideAlignmentEntry   newline   return $ ClustalAlignmentEntrySlice sliceIdentifier sliceSequence (length spacer) @@ -225,7 +225,7 @@ genParserStructuralClustalEntrySlice = do   sliceIdentifier <- many1 (noneOf " ")   many1 (char ' ')-  sliceSequence <- many1 (oneOf ".SNYRUAGCT-uagtc")+  sliceSequence <- parseNucleotideAlignmentEntry   newline   return $ StructuralClustalAlignmentEntrySlice (filter (/='\n') sliceIdentifier) sliceSequence @@ -254,3 +254,27 @@ -- | Parse Clustal summary (printed to STDOUT) from file readClustalSummary :: String -> IO (Either ParseError ClustalSummary)        readClustalSummary = parseFromFile genParserClustalSummary++-- | Parse nucleotide sequence. Allowed letters according to IUPAC+parseNucleotideSequence :: GenParser Char st String+parseNucleotideSequence = do+  nucleotideSequence <- many1 (oneOf "RYSWKMBDHVNATUGCryswkmbdhvnatugc") +  return $ nucleotideSequence++-- | Parse nucleotide alignment entry. Allowed letters according to IUPAC and commonly used gap characters+parseNucleotideAlignmentEntry :: GenParser Char st String+parseNucleotideAlignmentEntry = do+  entry <- many1 (oneOf "~_-.RYSWKMBDHVNATUGCryswkmbdhvnatugc") +  return $ entry++-- | Parse protein amino acid code sequence. Allowed letters according to IUPAC+parseProteinSequence :: GenParser Char st String+parseProteinSequence = do+  proteinSequence <- many1 (oneOf "ABCDEFGHIKLMNPQRSTVWXYZabcdefghiklmnpqrstvwxyz") +  return $ proteinSequence++-- | Parse protein amino acid code alignment entry. Allowed letters according to IUPAC and commonly used gap characters+parseProteinAlignmentEntry :: GenParser Char st String+parseProteinAlignmentEntry = do+  entry <- many1 (oneOf "~_-.ABCDEFGHIKLMNPQRSTVWXYZabcdefghiklmnpqrstvwxyz") +  return $ entry