diff --git a/CHANGELOG.md b/CHANGELOG.md --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -76,3 +76,9 @@ ## 0.6.0.1 -- 2023-09-04 * Fixed documentation for readSAM_V1_6. + +## 0.7.0.0 -- 2023-10-16 + +* Fixed broken parsing of SAM_V1_6(..). +* Strengthened parsing of SAM_V1_6(..) by accurately emulating the sam v1.6 specification through use of permutable parsers. +* Added initial test suite. diff --git a/hs-samtools.cabal b/hs-samtools.cabal --- a/hs-samtools.cabal +++ b/hs-samtools.cabal @@ -20,7 +20,7 @@ -- PVP summary: +-+------- breaking API changes -- | | +----- non-breaking API additions -- | | | +--- code changes with no API change -version: 0.6.0.1 +version: 0.7.0.0 -- A short (one-line) description of the package. synopsis: Read and write SAM, BAM, and CRAM files. @@ -131,7 +131,7 @@ -- other-extensions: -- Other library packages from which modules are imported. - build-depends: base ^>=4.17.1.0, + build-depends: base ^>=4.17.1.0, ascii >= 1.7.0 && < 1.8, attoparsec >= 0.14.4 && < 0.15, bitvec >= 1.1.4 && < 1.2, @@ -139,6 +139,7 @@ containers >= 0.6.7 && < 0.7, crypton >= 0.33 && < 0.34, generic-deriving >= 1.14.5 && < 1.15, + parser-combinators >= 1.3.0 && < 1.4, pcre-heavy >= 1.0.0 && < 1.1, regex-tdfa >= 1.3.2 && < 1.4, streamly >= 0.9.0 && < 0.10, @@ -174,7 +175,8 @@ main-is: Main.hs -- Test dependencies. - build-depends: - base ^>=4.17.1.0, - hspec == 2.11.4, - hs-samtools + build-depends: base ^>=4.17.1.0, + bytestring, + containers, + hspec, + hs-samtools diff --git a/src/Data/SAM/Version1_6/Alignment/BOPT.hs b/src/Data/SAM/Version1_6/Alignment/BOPT.hs --- a/src/Data/SAM/Version1_6/Alignment/BOPT.hs +++ b/src/Data/SAM/Version1_6/Alignment/BOPT.hs @@ -69,6 +69,27 @@ } deriving (Generic,Typeable) +instance Eq SAM_V1_6_Alignment_BOPT where + SAM_V1_6_Alignment_BOPT sam_v1_6_alignment_bopt_int81 + sam_v1_6_alignment_bopt_word81 + sam_v1_6_alignment_bopt_int161 + sam_v1_6_alignment_bopt_word161 + sam_v1_6_alignment_bopt_int321 + sam_v1_6_alignment_bopt_word321 + sam_v1_6_alignment_bopt_float1 == SAM_V1_6_Alignment_BOPT sam_v1_6_alignment_bopt_int82 + sam_v1_6_alignment_bopt_word82 + sam_v1_6_alignment_bopt_int162 + sam_v1_6_alignment_bopt_word162 + sam_v1_6_alignment_bopt_int322 + sam_v1_6_alignment_bopt_word322 + sam_v1_6_alignment_bopt_float2 = sam_v1_6_alignment_bopt_int81 == sam_v1_6_alignment_bopt_int82 && + sam_v1_6_alignment_bopt_word81 == sam_v1_6_alignment_bopt_word82 && + sam_v1_6_alignment_bopt_int161 == sam_v1_6_alignment_bopt_int162 && + sam_v1_6_alignment_bopt_word161 == sam_v1_6_alignment_bopt_word162 && + sam_v1_6_alignment_bopt_int321 == sam_v1_6_alignment_bopt_int322 && + sam_v1_6_alignment_bopt_word321 == sam_v1_6_alignment_bopt_word322 && + sam_v1_6_alignment_bopt_float1 == sam_v1_6_alignment_bopt_float2 + instance Show SAM_V1_6_Alignment_BOPT where show (SAM_V1_6_Alignment_BOPT int8 word8 diff --git a/src/Data/SAM/Version1_6/Alignment/Base.hs b/src/Data/SAM/Version1_6/Alignment/Base.hs --- a/src/Data/SAM/Version1_6/Alignment/Base.hs +++ b/src/Data/SAM/Version1_6/Alignment/Base.hs @@ -111,6 +111,57 @@ } deriving (Generic,Typeable) +instance Eq SAM_V1_6_Alignment where + SAM_V1_6_Alignment sam_v1_6_alignment_qname1 + sam_v1_6_alignment_flag1 + sam_v1_6_alignment_rname1 + sam_v1_6_alignment_pos1 + sam_v1_6_alignment_mapq1 + sam_v1_6_alignment_cigar1 + sam_v1_6_alignment_rnext1 + sam_v1_6_alignment_pnext1 + sam_v1_6_alignment_tlen1 + sam_v1_6_alignment_seq1 + sam_v1_6_alignment_qual1 + sam_v1_6_alignment_aopt1 + sam_v1_6_alignment_iopt1 + sam_v1_6_alignment_fopt1 + sam_v1_6_alignment_zopt1 + sam_v1_6_alignment_hopt1 + sam_v1_6_alignment_bopt1 == SAM_V1_6_Alignment sam_v1_6_alignment_qname2 + sam_v1_6_alignment_flag2 + sam_v1_6_alignment_rname2 + sam_v1_6_alignment_pos2 + sam_v1_6_alignment_mapq2 + sam_v1_6_alignment_cigar2 + sam_v1_6_alignment_rnext2 + sam_v1_6_alignment_pnext2 + sam_v1_6_alignment_tlen2 + sam_v1_6_alignment_seq2 + sam_v1_6_alignment_qual2 + sam_v1_6_alignment_aopt2 + sam_v1_6_alignment_iopt2 + sam_v1_6_alignment_fopt2 + sam_v1_6_alignment_zopt2 + sam_v1_6_alignment_hopt2 + sam_v1_6_alignment_bopt2 = sam_v1_6_alignment_qname1 == sam_v1_6_alignment_qname2 && + sam_v1_6_alignment_flag1 == sam_v1_6_alignment_flag2 && + sam_v1_6_alignment_rname1 == sam_v1_6_alignment_rname2 && + sam_v1_6_alignment_pos1 == sam_v1_6_alignment_pos2 && + sam_v1_6_alignment_mapq1 == sam_v1_6_alignment_mapq2 && + sam_v1_6_alignment_cigar1 == sam_v1_6_alignment_cigar2 && + sam_v1_6_alignment_rnext1 == sam_v1_6_alignment_rnext2 && + sam_v1_6_alignment_pnext1 == sam_v1_6_alignment_pnext2 && + sam_v1_6_alignment_tlen1 == sam_v1_6_alignment_tlen2 && + sam_v1_6_alignment_seq1 == sam_v1_6_alignment_seq2 && + sam_v1_6_alignment_qual1 == sam_v1_6_alignment_qual2 && + sam_v1_6_alignment_aopt1 == sam_v1_6_alignment_aopt2 && + sam_v1_6_alignment_iopt1 == sam_v1_6_alignment_iopt2 && + sam_v1_6_alignment_fopt1 == sam_v1_6_alignment_fopt2 && + sam_v1_6_alignment_zopt1 == sam_v1_6_alignment_zopt2 && + sam_v1_6_alignment_hopt1 == sam_v1_6_alignment_hopt2 && + sam_v1_6_alignment_bopt1 == sam_v1_6_alignment_bopt2 + instance Show SAM_V1_6_Alignment where show (SAM_V1_6_Alignment qname flag rname pos mapq cigar rnext pnext tlen seq qual aopt iopt fopt zopt hopt bopt) = "SAM_V1_6_Alignment { " ++ diff --git a/src/Data/SAM/Version1_6/Base.hs b/src/Data/SAM/Version1_6/Base.hs --- a/src/Data/SAM/Version1_6/Base.hs +++ b/src/Data/SAM/Version1_6/Base.hs @@ -57,6 +57,24 @@ } deriving (Generic,Typeable) +instance Eq SAM_V1_6 where + SAM_V1_6 sam_v1_6_file_level_metadata1 + sam_v1_6_reference_sequence_dictionary1 + sam_v1_6_read_group1 + sam_v1_6_program1 + sam_v1_6_one_line_comment1 + sam_v1_6_alignment1 == SAM_V1_6 sam_v1_6_file_level_metadata2 + sam_v1_6_reference_sequence_dictionary2 + sam_v1_6_read_group2 + sam_v1_6_program2 + sam_v1_6_one_line_comment2 + sam_v1_6_alignment2 = sam_v1_6_file_level_metadata1 == sam_v1_6_file_level_metadata2 && + sam_v1_6_reference_sequence_dictionary1 == sam_v1_6_reference_sequence_dictionary2 && + sam_v1_6_read_group1 == sam_v1_6_read_group2 && + sam_v1_6_program1 == sam_v1_6_program2 && + sam_v1_6_one_line_comment1 == sam_v1_6_one_line_comment2 && + sam_v1_6_alignment1 == sam_v1_6_alignment2 + instance Show SAM_V1_6 where show (SAM_V1_6 file_level_metadata reference_sequence_dictionary diff --git a/src/Data/SAM/Version1_6/Header/HD.hs b/src/Data/SAM/Version1_6/Header/HD.hs --- a/src/Data/SAM/Version1_6/Header/HD.hs +++ b/src/Data/SAM/Version1_6/Header/HD.hs @@ -45,6 +45,18 @@ } deriving (Generic,Typeable) +instance Eq SAM_V1_6_File_Level_Metadata where + SAM_V1_6_File_Level_Metadata sam_v1_6_file_level_metadata_format_version1 + sam_v1_6_file_level_metadata_sorting_order1 + sam_v1_6_file_level_metadata_alignment_grouping1 + sam_v1_6_file_level_metadata_subsorting_order1 == SAM_V1_6_File_Level_Metadata sam_v1_6_file_level_metadata_format_version2 + sam_v1_6_file_level_metadata_sorting_order2 + sam_v1_6_file_level_metadata_alignment_grouping2 + sam_v1_6_file_level_metadata_subsorting_order2 = sam_v1_6_file_level_metadata_format_version1 == sam_v1_6_file_level_metadata_format_version2 && + sam_v1_6_file_level_metadata_sorting_order1 == sam_v1_6_file_level_metadata_sorting_order2 && + sam_v1_6_file_level_metadata_alignment_grouping1 == sam_v1_6_file_level_metadata_alignment_grouping2 && + sam_v1_6_file_level_metadata_subsorting_order1 == sam_v1_6_file_level_metadata_subsorting_order2 + instance Show SAM_V1_6_File_Level_Metadata where show (SAM_V1_6_File_Level_Metadata version sorting_order alignment_grouping subsorting_order) = "SAM_V1_6_File_Level_Metadata { " ++ diff --git a/src/Data/SAM/Version1_6/Header/PG.hs b/src/Data/SAM/Version1_6/Header/PG.hs --- a/src/Data/SAM/Version1_6/Header/PG.hs +++ b/src/Data/SAM/Version1_6/Header/PG.hs @@ -49,6 +49,24 @@ } deriving (Generic,Typeable) +instance Eq SAM_V1_6_Program where + SAM_V1_6_Program sam_v1_6_program_record_identifier1 + sam_v1_6_program_name1 + sam_v1_6_program_command_line1 + sam_v1_6_program_previous_pg_id1 + sam_v1_6_program_description1 + sam_v1_6_program_version1 == SAM_V1_6_Program sam_v1_6_program_record_identifier2 + sam_v1_6_program_name2 + sam_v1_6_program_command_line2 + sam_v1_6_program_previous_pg_id2 + sam_v1_6_program_description2 + sam_v1_6_program_version2 = sam_v1_6_program_record_identifier1 == sam_v1_6_program_record_identifier2 && + sam_v1_6_program_name1 == sam_v1_6_program_name2 && + sam_v1_6_program_command_line1 == sam_v1_6_program_command_line2 && + sam_v1_6_program_previous_pg_id1 == sam_v1_6_program_previous_pg_id2 && + sam_v1_6_program_description1 == sam_v1_6_program_description2 && + sam_v1_6_program_version1 == sam_v1_6_program_version2 + instance Show SAM_V1_6_Program where show (SAM_V1_6_Program record_identifier name command_line previous_pg_id description version) = "SAM_V1_6_Program { " ++ diff --git a/src/Data/SAM/Version1_6/Header/RG.hs b/src/Data/SAM/Version1_6/Header/RG.hs --- a/src/Data/SAM/Version1_6/Header/RG.hs +++ b/src/Data/SAM/Version1_6/Header/RG.hs @@ -64,6 +64,48 @@ , sam_v1_6_read_group_sample :: Maybe SAM_V1_6_Read_Group_Sample } +instance Eq SAM_V1_6_Read_Group where + SAM_V1_6_Read_Group sam_v1_6_read_group_identifier1 + sam_v1_6_read_group_barcode_sequence1 + sam_v1_6_read_group_sequencing_center1 + sam_v1_6_read_group_description1 + sam_v1_6_read_group_run_date1 + sam_v1_6_read_group_flow_order1 + sam_v1_6_read_group_key_sequence1 + sam_v1_6_read_group_library1 + sam_v1_6_read_group_programs1 + sam_v1_6_read_group_predicted_median_insert_size1 + sam_v1_6_read_group_platform1 + sam_v1_6_read_group_platform_model1 + sam_v1_6_read_group_platform_unit1 + sam_v1_6_read_group_sample1 == SAM_V1_6_Read_Group sam_v1_6_read_group_identifier2 + sam_v1_6_read_group_barcode_sequence2 + sam_v1_6_read_group_sequencing_center2 + sam_v1_6_read_group_description2 + sam_v1_6_read_group_run_date2 + sam_v1_6_read_group_flow_order2 + sam_v1_6_read_group_key_sequence2 + sam_v1_6_read_group_library2 + sam_v1_6_read_group_programs2 + sam_v1_6_read_group_predicted_median_insert_size2 + sam_v1_6_read_group_platform2 + sam_v1_6_read_group_platform_model2 + sam_v1_6_read_group_platform_unit2 + sam_v1_6_read_group_sample2 = sam_v1_6_read_group_identifier1 == sam_v1_6_read_group_identifier2 && + sam_v1_6_read_group_barcode_sequence1 == sam_v1_6_read_group_barcode_sequence2 && + sam_v1_6_read_group_sequencing_center1 == sam_v1_6_read_group_sequencing_center2 && + sam_v1_6_read_group_description1 == sam_v1_6_read_group_description2 && + sam_v1_6_read_group_run_date1 == sam_v1_6_read_group_run_date2 && + sam_v1_6_read_group_flow_order1 == sam_v1_6_read_group_flow_order2 && + sam_v1_6_read_group_key_sequence1 == sam_v1_6_read_group_key_sequence2 && + sam_v1_6_read_group_library1 == sam_v1_6_read_group_library2 && + sam_v1_6_read_group_programs1 == sam_v1_6_read_group_programs2 && + sam_v1_6_read_group_predicted_median_insert_size1 == sam_v1_6_read_group_predicted_median_insert_size2 && + sam_v1_6_read_group_platform1 == sam_v1_6_read_group_platform2 && + sam_v1_6_read_group_platform_model1 == sam_v1_6_read_group_platform_model2 && + sam_v1_6_read_group_platform_unit1 == sam_v1_6_read_group_platform_unit2 && + sam_v1_6_read_group_sample1 == sam_v1_6_read_group_sample2 + instance Show SAM_V1_6_Read_Group where show (SAM_V1_6_Read_Group group_identifier barcode_sequence diff --git a/src/Data/SAM/Version1_6/Header/SQ.hs b/src/Data/SAM/Version1_6/Header/SQ.hs --- a/src/Data/SAM/Version1_6/Header/SQ.hs +++ b/src/Data/SAM/Version1_6/Header/SQ.hs @@ -57,6 +57,36 @@ } deriving (Generic,Typeable) +instance Eq SAM_V1_6_Reference_Sequence_Dictionary where + SAM_V1_6_Reference_Sequence_Dictionary sam_v1_6_reference_sequence_dictionary_reference_sequence_name1 + sam_v1_6_reference_sequence_dictionary_reference_sequence_length1 + sam_v1_6_reference_sequence_dictionary_reference_alternative_locus1 + sam_v1_6_reference_sequence_dictionary_reference_alternative_reference_sequence_names1 + sam_v1_6_reference_sequence_dictionary_genome_assembly_identifier1 + sam_v1_6_reference_sequence_dictionary_description1 + sam_v1_6_reference_sequence_dictionary_md5_checksum1 + sam_v1_6_reference_sequence_dictionary_species1 + sam_v1_6_reference_sequence_dictionary_molecule_topology1 + sam_v1_6_reference_sequence_dictionary_uri1 == SAM_V1_6_Reference_Sequence_Dictionary sam_v1_6_reference_sequence_dictionary_reference_sequence_name2 + sam_v1_6_reference_sequence_dictionary_reference_sequence_length2 + sam_v1_6_reference_sequence_dictionary_reference_alternative_locus2 + sam_v1_6_reference_sequence_dictionary_reference_alternative_reference_sequence_names2 + sam_v1_6_reference_sequence_dictionary_genome_assembly_identifier2 + sam_v1_6_reference_sequence_dictionary_description2 + sam_v1_6_reference_sequence_dictionary_md5_checksum2 + sam_v1_6_reference_sequence_dictionary_species2 + sam_v1_6_reference_sequence_dictionary_molecule_topology2 + sam_v1_6_reference_sequence_dictionary_uri2 = sam_v1_6_reference_sequence_dictionary_reference_sequence_name1 == sam_v1_6_reference_sequence_dictionary_reference_sequence_name2 && + sam_v1_6_reference_sequence_dictionary_reference_sequence_length1 == sam_v1_6_reference_sequence_dictionary_reference_sequence_length2 && + sam_v1_6_reference_sequence_dictionary_reference_alternative_locus1 == sam_v1_6_reference_sequence_dictionary_reference_alternative_locus2 && + sam_v1_6_reference_sequence_dictionary_reference_alternative_reference_sequence_names1 == sam_v1_6_reference_sequence_dictionary_reference_alternative_reference_sequence_names2 && + sam_v1_6_reference_sequence_dictionary_genome_assembly_identifier1 == sam_v1_6_reference_sequence_dictionary_genome_assembly_identifier2 && + sam_v1_6_reference_sequence_dictionary_description1 == sam_v1_6_reference_sequence_dictionary_description2 && + sam_v1_6_reference_sequence_dictionary_md5_checksum1 == sam_v1_6_reference_sequence_dictionary_md5_checksum2 && + sam_v1_6_reference_sequence_dictionary_species1 == sam_v1_6_reference_sequence_dictionary_species2 && + sam_v1_6_reference_sequence_dictionary_molecule_topology1 == sam_v1_6_reference_sequence_dictionary_molecule_topology2 && + sam_v1_6_reference_sequence_dictionary_uri1 == sam_v1_6_reference_sequence_dictionary_uri2 + instance Show SAM_V1_6_Reference_Sequence_Dictionary where show (SAM_V1_6_Reference_Sequence_Dictionary reference_sequence_name reference_sequence_length diff --git a/src/Data/SAM/Version1_6/Read/Base.hs b/src/Data/SAM/Version1_6/Read/Base.hs --- a/src/Data/SAM/Version1_6/Read/Base.hs +++ b/src/Data/SAM/Version1_6/Read/Base.hs @@ -1,16 +1,7 @@ -{-# LANGUAGE DeriveDataTypeable #-} -{-# LANGUAGE DeriveGeneric #-} {-# LANGUAGE FlexibleContexts #-} {-# LANGUAGE FlexibleInstances #-} {-# LANGUAGE MultiParamTypeClasses #-} -{-# LANGUAGE OverloadedLists #-} -{-# LANGUAGE OverloadedStrings #-} -{-# LANGUAGE MultiWayIf #-} -{-# LANGUAGE PackageImports #-} -{-# LANGUAGE RecordWildCards #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} -{-# Language QuasiQuotes #-} -- | -- Module : Data.SAM.Version1_6.Read.Base @@ -35,12 +26,13 @@ import Data.SAM.Version1_6.Read.Parser.Header.CO.Base import Data.SAM.Version1_6.Read.Parser.Alignment.Base -import Data.Attoparsec.ByteString.Char8 as DABC8 +import Control.Applicative.Permutations (intercalateEffect,toPermutationWithDefault) +import Data.Attoparsec.ByteString.Char8 as DABC8 (endOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import Data.ByteString.Lazy as DBL import Data.Sequence as DSeq import qualified Streamly.Data.Stream as S -import Streamly.External.ByteString.Lazy as StreamlyLByteString (fromChunksIO) +import Streamly.External.ByteString.Lazy as StreamlyLByteString (fromChunksIO) import Streamly.Internal.FileSystem.File as StreamlyInternalFile (chunkReader) -- | Make a parser optional, return Nothing if there is no match. @@ -51,36 +43,68 @@ -- | Define the @"SAM_V1_6"@ parser. parse_SAM_V1_6 :: Parser SAM_V1_6 parse_SAM_V1_6 = do - filelevelmetadata <- maybeOption $ parse_SAM_V1_6_File_Level_Metadata <* endOfLine - _ <- word8 10 - referencesequencedictionary <- maybeOption $ DABL.many' $ parse_SAM_V1_6_Reference_Sequence_Dictionary <* endOfLine - _ <- word8 10 - readgroup <- maybeOption $ DABL.many' $ parse_SAM_V1_6_Read_Group <* endOfLine - _ <- word8 10 - program <- maybeOption $ parse_SAM_V1_6_Program <* endOfLine - _ <- word8 10 - onelinecomment <- maybeOption $ DABL.many' $ parse_SAM_V1_6_One_Line_Comment <* endOfLine - _ <- word8 10 - alignment <- DABL.many' $ parse_SAM_V1_6_Alignment <* endOfLine - return SAM_V1_6 { sam_v1_6_file_level_metadata = filelevelmetadata - , sam_v1_6_reference_sequence_dictionary = case referencesequencedictionary of - Nothing -> Nothing - Just referencesequencedictionaryf -> Just $ DSeq.fromList referencesequencedictionaryf - , sam_v1_6_read_group = case readgroup of - Nothing -> Nothing - Just readgroupf -> Just $ DSeq.fromList readgroupf - , sam_v1_6_program = program - , sam_v1_6_one_line_comment = case onelinecomment of - Nothing -> Nothing - Just onelinecommentf -> Just $ DSeq.fromList onelinecommentf - , sam_v1_6_alignment = DSeq.fromList alignment - } + filelevelmetadata <- maybeOption parse_SAM_V1_6_File_Level_Metadata + case filelevelmetadata of + Nothing -> do samwoalignment <- intercalateEffect endOfLine $ + (,,,) + <$> toPermutationWithDefault Nothing + (Just <$> DABL.many1' parse_SAM_V1_6_Reference_Sequence_Dictionary) + <*> toPermutationWithDefault Nothing + (Just <$> DABL.many1' parse_SAM_V1_6_Read_Group) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Program) + <*> toPermutationWithDefault Nothing + (Just <$> DABL.many1' parse_SAM_V1_6_One_Line_Comment) + alignment <- DABL.many1' parse_SAM_V1_6_Alignment + return SAM_V1_6 { sam_v1_6_file_level_metadata = Nothing + , sam_v1_6_reference_sequence_dictionary = (\(a,_,_,_) -> case a of + Nothing -> Nothing + Just finala -> Just $ DSeq.fromList finala + ) samwoalignment + , sam_v1_6_read_group = (\(_,b,_,_) -> case b of + Nothing -> Nothing + Just finalb -> Just $ DSeq.fromList finalb + ) samwoalignment + , sam_v1_6_program = (\(_,_,c,_) -> c) samwoalignment + , sam_v1_6_one_line_comment = (\(_,_,_,d) -> case d of + Nothing -> Nothing + Just finald -> Just $ DSeq.fromList finald + ) samwoalignment + , sam_v1_6_alignment = DSeq.fromList alignment + } + Just flm -> do samwoalignment <- intercalateEffect endOfLine $ + (,,,) + <$> toPermutationWithDefault Nothing + (Just <$> DABL.many1' parse_SAM_V1_6_Reference_Sequence_Dictionary) + <*> toPermutationWithDefault Nothing + (Just <$> DABL.many1' parse_SAM_V1_6_Read_Group) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Program) + <*> toPermutationWithDefault Nothing + (Just <$> DABL.many1' parse_SAM_V1_6_One_Line_Comment) + alignment <- DABL.many1' parse_SAM_V1_6_Alignment + return SAM_V1_6 { sam_v1_6_file_level_metadata = Just flm + , sam_v1_6_reference_sequence_dictionary = (\(a,_,_,_) -> case a of + Nothing -> Nothing + Just finala -> Just $ DSeq.fromList finala + ) samwoalignment + , sam_v1_6_read_group = (\(_,b,_,_) -> case b of + Nothing -> Nothing + Just finalb -> Just $ DSeq.fromList finalb + ) samwoalignment + , sam_v1_6_program = (\(_,_,c,_) -> c) samwoalignment + , sam_v1_6_one_line_comment = (\(_,_,_,d) -> case d of + Nothing -> Nothing + Just finald -> Just $ DSeq.fromList finald + ) samwoalignment + , sam_v1_6_alignment = DSeq.fromList alignment + } -- | Run the @"SAM_V1_6"@ parser. readSAM_V1_6_LBS :: DBL.ByteString -> IO SAM_V1_6 readSAM_V1_6_LBS lbs = - case (DABL.parseOnly parse_SAM_V1_6 lbs) of + case (DABL.parseOnly parse_SAM_V1_6 lbs) of Left samparseerror -> error samparseerror Right sam -> return sam diff --git a/src/Data/SAM/Version1_6/Read/Parser/Alignment/AOPT.hs b/src/Data/SAM/Version1_6/Read/Parser/Alignment/AOPT.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Alignment/AOPT.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Alignment/AOPT.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# Language QuasiQuotes #-} @@ -46,6 +45,7 @@ import Data.SAM.Version1_6.Read.Error +import Data.Attoparsec.ByteString.Char8 as DABC8 (isEndOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import qualified Data.ByteString as DB import Text.Regex.PCRE.Heavy @@ -57,19 +57,19 @@ parse_SAM_V1_6_Alignment_AOPT = do _ <- do alignmentaoptfieldtagp <- DABL.takeTill (== 58) -- Parse AOPT tag of the alignment section. - case (alignmentaoptfieldtagp =~ [re|/[A-Za-z][A-Za-z0-9]/|]) of + case (alignmentaoptfieldtagp =~ [re|[A-Za-z][A-Za-z0-9]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_AOPT_Tag_Incorrect_Format True -> -- AOPT tag is in the accepted format. - return alignmentaoptfieldtagp + return () _ <- word8 58 _ <- do alignmentaoptfieldtypep <- DABL.takeTill (== 58) -- Parse AOPT type of the alignment section. case (alignmentaoptfieldtypep =~ [re|[A]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_AOPT_Type_Incorrect_Format True -> -- AOPT type is in the accepted format. - return alignmentaoptfieldtypep + return () _ <- word8 58 - alignmentaoptfieldvalue <- do alignmentaoptfieldvaluep <- DABL.takeTill (== 09) + alignmentaoptfieldvalue <- do alignmentaoptfieldvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse AOPT value of the alignment section. case (alignmentaoptfieldvaluep =~ [re|[!-~]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_AOPT_Value_Incorrect_Format diff --git a/src/Data/SAM/Version1_6/Read/Parser/Alignment/BOPT.hs b/src/Data/SAM/Version1_6/Read/Parser/Alignment/BOPT.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Alignment/BOPT.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Alignment/BOPT.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# Language QuasiQuotes #-} @@ -47,6 +46,7 @@ import Data.SAM.Version1_6.Alignment.BOPT import Data.SAM.Version1_6.Read.Error +import Data.Attoparsec.ByteString.Char8 as DABC8 (isEndOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import qualified Data.ByteString as DB (head,unpack) import qualified Data.ByteString.Char8 as DBC8 @@ -60,7 +60,7 @@ parse_SAM_V1_6_Alignment_BOPT = do alignmentboptfieldtag <- do alignmentboptfieldtagp <- DABL.takeTill (== 58) -- Parse BOPT tag of the alignment section. - case (alignmentboptfieldtagp =~ [re|/[A-Za-z][A-Za-z0-9]/|]) of + case (alignmentboptfieldtagp =~ [re|[A-Za-z][A-Za-z0-9]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_BOPT_Tag_Incorrect_Format True -> -- BOPT tag is in the accepted format. return alignmentboptfieldtagp @@ -70,7 +70,7 @@ case (alignmentboptfieldtypep =~ [re|[B]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_BOPT_Type_Incorrect_Format True -> -- BOPT type is in the accepted format. - return alignmentboptfieldtypep + return () _ <- word8 58 alignmentboptfieldvaluetype <- do alignmentboptfieldvaluetypep <- DABL.take 1 -- Parse BOPT value type of the alignment section. @@ -78,9 +78,10 @@ False -> fail $ show SAM_V1_6_Error_Alignment_BOPT_Value_Type_Incorrect_Format True -> -- BOPT value type is in the accepted format. return alignmentboptfieldvaluetypep - alignmentboptfieldvaluedata <- do alignmentboptfieldvaluedatap <- DABL.takeTill (\x -> x == 09 || x == 0x0D || x == 0x0A) + _ <- word8 44 + alignmentboptfieldvaluedata <- do alignmentboptfieldvaluedatap <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse BOPT value data of the alignment section. - case (alignmentboptfieldvaluedatap =~ [re|(,[-+]?[0-9]*\.?[0-9]+([eE][-+]?[0-9]+)?)*|]) of + case (alignmentboptfieldvaluedatap =~ [re|([-+]?[0-9]*\.?[0-9]+([eE][-+]?[0-9]+)?)*|]) of False -> fail $ show SAM_V1_6_Error_Alignment_BOPT_Value_Data_Incorrect_Format True -> -- BOPT value data is in the accepted format. return alignmentboptfieldvaluedatap @@ -169,4 +170,4 @@ , sam_v1_6_alignment_bopt_int32 = Nothing , sam_v1_6_alignment_bopt_word32 = Nothing , sam_v1_6_alignment_bopt_float = Nothing - } + } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Alignment/Base.hs b/src/Data/SAM/Version1_6/Read/Parser/Alignment/Base.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Alignment/Base.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Alignment/Base.hs @@ -8,7 +8,6 @@ {-# LANGUAGE MultiWayIf #-} {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# Language QuasiQuotes #-} {-# OPTIONS_GHC -fno-warn-name-shadowing #-} @@ -53,15 +52,12 @@ import Data.SAM.Version1_6.Read.Parser.Alignment.HOPT import Data.SAM.Version1_6.Read.Parser.Alignment.BOPT +import Control.Applicative.Permutations (intercalateEffect,toPermutationWithDefault) +import Data.Attoparsec.ByteString.Char8 as DABC8 (endOfLine,isEndOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import qualified Data.ByteString.Char8 as DBC8 import Text.Regex.PCRE.Heavy --- | Make a parser optional, return Nothing if there is no match. -maybeOption :: Parser a - -> Parser (Maybe a) -maybeOption p = option Nothing (Just <$> p) - -- | @"SAM_V1_6_Alignment"@ parser. -- -- Defines a parser for the alignment section of the SAM v1.6 file format. @@ -78,28 +74,28 @@ _ <- word8 09 flag <- do flagp <- DABL.takeTill (== 09) -- Parse FLAG field of alignment section. - case (flagp =~ [re|[0-9]*|]) of + case (flagp =~ [re|[0-9]+|]) of False -> fail $ show SAM_V1_6_Error_Alignment_FLAG_Incorrect_Format True -> -- FLAG is in the accepted format. return flagp _ <- word8 09 rname <- do rnamep <- DABL.takeTill (== 09) -- Parse RNAME field of alignment section. - case (rnamep =~ [re|\*|[0-9A-Za-z!#$%&+./:;?@^_|~-][0-9A-Za-z!#$%&*+./:;=?@^_|~-]*|]) of + case (rnamep =~ [re|\*|[0-9A-Za-z!#$%&+.:;?@^_|~-][0-9A-Za-z!#$%&*+.:;=?@^_|~-]*|]) of False -> fail $ show SAM_V1_6_Error_Alignment_RNAME_Incorrect_Format True -> -- RNAME is in the accepted format. return rnamep _ <- word8 09 pos <- do posp <- DABL.takeTill (== 09) -- Parse POS field of the alignment section. - case (posp =~ [re|[0-9]*|]) of + case (posp =~ [re|[0-9]+|]) of False -> fail $ show SAM_V1_6_Error_Alignment_POS_Incorrect_Format True -> -- POS is in the accepted format. return posp _ <- word8 09 mapq <- do mapqp <- DABL.takeTill (== 09) -- Parse MAPQ field of the alignment section. - case (mapqp =~ [re|[0-9]*|]) of + case (mapqp =~ [re|[0-9]+|]) of False -> fail $ show SAM_V1_6_Error_Alignment_MAPQ_Incorrect_Format True -> -- MAPQ is in the accepted format. return mapqp @@ -113,21 +109,21 @@ _ <- word8 09 rnext <- do rnextp <- DABL.takeTill (== 09) -- Parse RNEXT field of the alignment section. - case (rnextp =~ [re|\*|=|[0-9A-Za-z!#$%&+./:;?@^_|~-][0-9A-Za-z!#$%&*+./:;=?@^_|~-]*|]) of + case (rnextp =~ [re|\*|=|[0-9A-Za-z!#$%&+.:;?@^_|~-][0-9A-Za-z!#$%&*+.:;=?@^_|~-]*|]) of False -> fail $ show SAM_V1_6_Error_Alignment_RNEXT_Incorrect_Format True -> -- RNEXT is in the accepted format. return rnextp _ <- word8 09 pnext <- do pnextp <- DABL.takeTill (== 09) -- Parse PNEXT field of the alignment section. - case (pnextp =~ [re|[0-9]*|]) of + case (pnextp =~ [re|[0-9]+|]) of False -> fail $ show SAM_V1_6_Error_Alignment_PNEXT_Incorrect_Format True -> -- PNEXT is in the accepted format. return pnextp _ <- word8 09 tlen <- do tlenp <- DABL.takeTill (== 09) -- Parse TLEN field of the alignment section. - case (tlenp =~ [re|[-]?[0-9]*|]) of + case (tlenp =~ [re|[-]?[0-9]+|]) of False -> fail $ show SAM_V1_6_Error_Alignment_TLEN_Incorrect_Format True -> -- TLEN is in the accepted format. return tlenp @@ -139,53 +135,89 @@ True -> -- SEQ is in the accepted format. return seqp _ <- word8 09 - qual <- do qualp <- DABL.takeTill (== 09) + qual <- do qualp <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse QUAL field of the alignment section. case (qualp =~ [re|[!-~?]+|\*|]) of False -> fail $ show SAM_V1_6_Error_Alignment_QUAL_Incorrect_Format True -> -- QUAL is in the accepted format. - return qualp - _ <- word8 09 - -- This parser assumes that the AOPT tag always appears first, - -- followed by IOPT, FOPT, ZOPT, HOPT, and BOPT, if they exist, - -- in that order. - aopt <- maybeOption parse_SAM_V1_6_Alignment_AOPT - _ <- word8 09 - iopt <- maybeOption parse_SAM_V1_6_Alignment_IOPT - _ <- word8 09 - fopt <- maybeOption parse_SAM_V1_6_Alignment_FOPT - _ <- word8 09 - zopt <- maybeOption parse_SAM_V1_6_Alignment_ZOPT - _ <- word8 09 - hopt <- maybeOption parse_SAM_V1_6_Alignment_HOPT - _ <- word8 09 - bopt <- maybeOption parse_SAM_V1_6_Alignment_BOPT - -- Return the parsed SAM_V1_6. - return SAM_V1_6_Alignment { sam_v1_6_alignment_qname = qname - , sam_v1_6_alignment_flag = case (DBC8.readInt flag) of - Nothing -> (-1) - Just (flagint,_) -> flagint - , sam_v1_6_alignment_rname = rname - , sam_v1_6_alignment_pos = case (DBC8.readInteger pos) of - Nothing -> 0 - Just (posinteger,_) -> posinteger - , sam_v1_6_alignment_mapq = case (DBC8.readInt mapq) of - Nothing -> 255 - Just (mapqint,_) -> mapqint - , sam_v1_6_alignment_cigar = cigar - , sam_v1_6_alignment_rnext = rnext - , sam_v1_6_alignment_pnext = case (DBC8.readInteger pnext) of - Nothing -> 0 - Just (pnextinteger,_) -> pnextinteger - , sam_v1_6_alignment_tlen = case (DBC8.readInteger tlen) of - Nothing -> 0 - Just (tleninteger,_) -> tleninteger - , sam_v1_6_alignment_seq = seq - , sam_v1_6_alignment_qual = qual - , sam_v1_6_alignment_aopt = aopt - , sam_v1_6_alignment_iopt = iopt - , sam_v1_6_alignment_fopt = fopt - , sam_v1_6_alignment_zopt = zopt - , sam_v1_6_alignment_hopt = hopt - , sam_v1_6_alignment_bopt = bopt - } + return qualp + optfields <- peekWord8 + case optfields of + Just 10 -> do -- Return the parsed SAM_V1_6. + _ <- endOfLine + return SAM_V1_6_Alignment { sam_v1_6_alignment_qname = qname + , sam_v1_6_alignment_flag = case (DBC8.readInt flag) of + Nothing -> (-1) + Just (flagint,_) -> flagint + , sam_v1_6_alignment_rname = rname + , sam_v1_6_alignment_pos = case (DBC8.readInteger pos) of + Nothing -> 0 + Just (posinteger,_) -> posinteger + , sam_v1_6_alignment_mapq = case (DBC8.readInt mapq) of + Nothing -> 255 + Just (mapqint,_) -> mapqint + , sam_v1_6_alignment_cigar = cigar + , sam_v1_6_alignment_rnext = rnext + , sam_v1_6_alignment_pnext = case (DBC8.readInteger pnext) of + Nothing -> 0 + Just (pnextinteger,_) -> pnextinteger + , sam_v1_6_alignment_tlen = case (DBC8.readInteger tlen) of + Nothing -> 0 + Just (tleninteger,_) -> tleninteger + , sam_v1_6_alignment_seq = seq + , sam_v1_6_alignment_qual = qual + , sam_v1_6_alignment_aopt = Nothing + , sam_v1_6_alignment_iopt = Nothing + , sam_v1_6_alignment_fopt = Nothing + , sam_v1_6_alignment_zopt = Nothing + , sam_v1_6_alignment_hopt = Nothing + , sam_v1_6_alignment_bopt = Nothing + } + _ -> do -- This parser assumes that + -- the AOPT, IOPT, FOPT, ZOPT, HOPT, and BOPT + -- tags can appear in any order. + _ <- word8 09 + optionalfields <- intercalateEffect (word8 09) $ + (,,,,,) + <$> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Alignment_AOPT) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Alignment_IOPT) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Alignment_FOPT) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Alignment_ZOPT) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Alignment_HOPT) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Alignment_BOPT) + _ <- endOfLine + -- Return the parsed SAM_V1_6. + return SAM_V1_6_Alignment { sam_v1_6_alignment_qname = qname + , sam_v1_6_alignment_flag = case (DBC8.readInt flag) of + Nothing -> (-1) + Just (flagint,_) -> flagint + , sam_v1_6_alignment_rname = rname + , sam_v1_6_alignment_pos = case (DBC8.readInteger pos) of + Nothing -> 0 + Just (posinteger,_) -> posinteger + , sam_v1_6_alignment_mapq = case (DBC8.readInt mapq) of + Nothing -> 255 + Just (mapqint,_) -> mapqint + , sam_v1_6_alignment_cigar = cigar + , sam_v1_6_alignment_rnext = rnext + , sam_v1_6_alignment_pnext = case (DBC8.readInteger pnext) of + Nothing -> 0 + Just (pnextinteger,_) -> pnextinteger + , sam_v1_6_alignment_tlen = case (DBC8.readInteger tlen) of + Nothing -> 0 + Just (tleninteger,_) -> tleninteger + , sam_v1_6_alignment_seq = seq + , sam_v1_6_alignment_qual = qual + , sam_v1_6_alignment_aopt = (\(a,_,_,_,_,_) -> a) optionalfields + , sam_v1_6_alignment_iopt = (\(_,i,_,_,_,_) -> i) optionalfields + , sam_v1_6_alignment_fopt = (\(_,_,f,_,_,_) -> f) optionalfields + , sam_v1_6_alignment_zopt = (\(_,_,_,z,_,_) -> z) optionalfields + , sam_v1_6_alignment_hopt = (\(_,_,_,_,h,_) -> h) optionalfields + , sam_v1_6_alignment_bopt = (\(_,_,_,_,_,b) -> b) optionalfields + } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Alignment/FOPT.hs b/src/Data/SAM/Version1_6/Read/Parser/Alignment/FOPT.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Alignment/FOPT.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Alignment/FOPT.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# Language QuasiQuotes #-} @@ -46,6 +45,7 @@ import Data.SAM.Version1_6.Read.Error +import Data.Attoparsec.ByteString.Char8 as DABC8 (isEndOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import qualified Data.ByteString.Char8 as DBC8 import Text.Regex.PCRE.Heavy @@ -57,19 +57,19 @@ parse_SAM_V1_6_Alignment_FOPT = do _ <- do alignmentfoptfieldtagp <- DABL.takeTill (== 58) -- Parse FOPT tag of the alignment section. - case (alignmentfoptfieldtagp =~ [re|/[A-Za-z][A-Za-z0-9]/|]) of + case (alignmentfoptfieldtagp =~ [re|[A-Za-z][A-Za-z0-9]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_FOPT_Tag_Incorrect_Format True -> -- FOPT tag is in the accepted format. - return alignmentfoptfieldtagp + return () _ <- word8 58 _ <- do alignmentfoptfieldtypep <- DABL.takeTill (== 58) -- Parse FOPT type of the alignment section. case (alignmentfoptfieldtypep =~ [re|[f]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_FOPT_Type_Incorrect_Format True -> -- FOPT type is in the accepted format. - return alignmentfoptfieldtypep + return () _ <- word8 58 - alignmentfoptfieldvalue <- do alignmentfoptfieldvaluep <- DABL.takeTill (== 09) + alignmentfoptfieldvalue <- do alignmentfoptfieldvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse FOPT value of the alignment section. case (alignmentfoptfieldvaluep =~ [re|[-+]?[0-9]*\.?[0-9]+([eE][-+]?[0-9]+)?|]) of False -> fail $ show SAM_V1_6_Error_Alignment_FOPT_Value_Incorrect_Format diff --git a/src/Data/SAM/Version1_6/Read/Parser/Alignment/HOPT.hs b/src/Data/SAM/Version1_6/Read/Parser/Alignment/HOPT.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Alignment/HOPT.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Alignment/HOPT.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# Language QuasiQuotes #-} @@ -46,6 +45,7 @@ import Data.SAM.Version1_6.Read.Error +import Data.Attoparsec.ByteString.Char8 as DABC8 (isEndOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import qualified Data.ByteString as DB import Data.Sequence as DSeq @@ -59,19 +59,19 @@ parse_SAM_V1_6_Alignment_HOPT = do _ <- do alignmenthoptfieldtagp <- DABL.takeTill (== 58) -- Parse HOPT tag of the alignment section. - case (alignmenthoptfieldtagp =~ [re|/[A-Za-z][A-Za-z0-9]/|]) of + case (alignmenthoptfieldtagp =~ [re|[A-Za-z][A-Za-z0-9]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_HOPT_Tag_Incorrect_Format True -> -- HOPT tag is in the accepted format. - return alignmenthoptfieldtagp + return () _ <- word8 58 _ <- do alignmenthoptfieldtypep <- DABL.takeTill (== 58) -- Parse HOPT type of the alignment section. case (alignmenthoptfieldtypep =~ [re|[H]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_HOPT_Type_Incorrect_Format True -> -- HOPT type is in the accepted format. - return alignmenthoptfieldtypep + return () _ <- word8 58 - alignmenthoptfieldvalue <- do alignmenthoptfieldvaluep <- DABL.takeTill (== 09) + alignmenthoptfieldvalue <- do alignmenthoptfieldvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse HOPT value of the alignment section. case (alignmenthoptfieldvaluep =~ [re|([0-9A-F][0-9A-F])*|]) of False -> fail $ show SAM_V1_6_Error_Alignment_HOPT_Value_Incorrect_Format diff --git a/src/Data/SAM/Version1_6/Read/Parser/Alignment/IOPT.hs b/src/Data/SAM/Version1_6/Read/Parser/Alignment/IOPT.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Alignment/IOPT.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Alignment/IOPT.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# Language QuasiQuotes #-} @@ -46,6 +45,7 @@ import Data.SAM.Version1_6.Read.Error +import Data.Attoparsec.ByteString.Char8 as DABC8 (isEndOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import qualified Data.ByteString.Char8 as DBC8 import Text.Regex.PCRE.Heavy @@ -57,19 +57,19 @@ parse_SAM_V1_6_Alignment_IOPT = do _ <- do alignmentioptfieldtagp <- DABL.takeTill (== 58) -- Parse IOPT tag of the alignment section. - case (alignmentioptfieldtagp =~ [re|/[A-Za-z][A-Za-z0-9]/|]) of + case (alignmentioptfieldtagp =~ [re|[A-Za-z][A-Za-z0-9]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_IOPT_Tag_Incorrect_Format True -> -- IOPT tag is in the accepted format. - return alignmentioptfieldtagp + return () _ <- word8 58 _ <- do alignmentioptfieldtypep <- DABL.takeTill (== 58) -- Parse IOPT type of the alignment section. case (alignmentioptfieldtypep =~ [re|[i]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_IOPT_Type_Incorrect_Format True -> -- IOPT type is in the accepted format. - return alignmentioptfieldtypep + return () _ <- word8 58 - alignmentioptfieldvalue <- do alignmentioptfieldvaluep <- DABL.takeTill (== 09) + alignmentioptfieldvalue <- do alignmentioptfieldvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse IOPT value of the alignment section. case (alignmentioptfieldvaluep =~ [re|[-+]?[0-9]+|]) of False -> fail $ show SAM_V1_6_Error_Alignment_IOPT_Value_Incorrect_Format diff --git a/src/Data/SAM/Version1_6/Read/Parser/Alignment/ZOPT.hs b/src/Data/SAM/Version1_6/Read/Parser/Alignment/ZOPT.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Alignment/ZOPT.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Alignment/ZOPT.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# Language QuasiQuotes #-} @@ -46,6 +45,7 @@ import Data.SAM.Version1_6.Read.Error +import Data.Attoparsec.ByteString.Char8 as DABC8 (isEndOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import qualified Data.ByteString as DB import Text.Regex.PCRE.Heavy @@ -57,19 +57,19 @@ parse_SAM_V1_6_Alignment_ZOPT = do _ <- do alignmentzoptfieldtagp <- DABL.takeTill (== 58) -- Parse ZOPT tag of the alignment section. - case (alignmentzoptfieldtagp =~ [re|/[A-Za-z][A-Za-z0-9]/|]) of + case (alignmentzoptfieldtagp =~ [re|[A-Za-z][A-Za-z0-9]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_ZOPT_Tag_Incorrect_Format True -> -- ZOPT tag is in the accepted format. - return alignmentzoptfieldtagp + return () _ <- word8 58 _ <- do alignmentzoptfieldtypep <- DABL.takeTill (== 58) -- Parse ZOPT type of the alignment section. case (alignmentzoptfieldtypep =~ [re|[Z]|]) of False -> fail $ show SAM_V1_6_Error_Alignment_ZOPT_Type_Incorrect_Format True -> -- ZOPT type is in the accepted format. - return alignmentzoptfieldtypep + return () _ <- word8 58 - alignmentzoptfieldvalue <- do alignmentzoptfieldvaluep <- DABL.takeTill (== 09) + alignmentzoptfieldvalue <- do alignmentzoptfieldvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse ZOPT value of the alignment section. case (alignmentzoptfieldvaluep =~ [re|[ !-~]*|]) of False -> fail $ show SAM_V1_6_Error_Alignment_ZOPT_Value_Incorrect_Format diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/CO/Base.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/CO/Base.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/CO/Base.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/CO/Base.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} {-# OPTIONS_GHC -fno-warn-name-shadowing #-} @@ -48,7 +47,7 @@ import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Char8 as DABC8 +import Data.Attoparsec.ByteString.Char8 as DABC8 (endOfLine,isEndOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import Text.Regex.PCRE.Heavy @@ -64,8 +63,9 @@ case (coheaderp =~ [re|[@][C][O]|]) of False -> fail $ show SAM_V1_6_Error_One_Line_Comment_Tag_Incorrect_Format True -> -- @CO tag is in the accepted format. - return coheaderp + return () _ <- word8 09 - value <- DABL.takeTill (\x -> x == 13 || x == 10) + value <- DABL.takeTill isEndOfLine + _ <- endOfLine return SAM_V1_6_One_Line_Comment { sam_v1_6_one_line_comment_value = value } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/HD/Base.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/HD/Base.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/HD/Base.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/HD/Base.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -51,14 +50,11 @@ import Data.SAM.Version1_6.Read.Parser.Header.HD.GO import Data.SAM.Version1_6.Read.Parser.Header.HD.SS +import Control.Applicative.Permutations (intercalateEffect,toPermutation,toPermutationWithDefault) +import Data.Attoparsec.ByteString.Char8 as DABC8 (endOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import Text.Regex.PCRE.Heavy --- | Make a parser optional, return Nothing if there is no match. -maybeOption :: Parser a - -> Parser (Maybe a) -maybeOption p = option Nothing (Just <$> p) - -- | @"SAM_V1_6_File_Level_Metadata"@ parser. -- -- Defines a parser for @HD tag section of the SAM v1.6 file format. @@ -71,19 +67,18 @@ case (hdheaderp =~ [re|[@][H][D]|]) of False -> fail $ show SAM_V1_6_Error_File_Level_Metadata_Tag_Incorrect_Format True -> -- @HD tag is in the accepted format. - return hdheaderp + return () _ <- word8 09 - -- This parser assumes that the VN tag always appears first, followed by - -- SO, GO and SS tags, if they exist, in that order. - vn <- parse_SAM_V1_6_File_Level_Metadata_VN - _ <- word8 09 - so <- maybeOption parse_SAM_V1_6_File_Level_Metadata_SO - _ <- word8 09 - go <- maybeOption parse_SAM_V1_6_File_Level_Metadata_GO - _ <- word8 09 - ss <- maybeOption parse_SAM_V1_6_File_Level_Metadata_SS - return SAM_V1_6_File_Level_Metadata { sam_v1_6_file_level_metadata_format_version = vn - , sam_v1_6_file_level_metadata_sorting_order = so - , sam_v1_6_file_level_metadata_alignment_grouping = go - , sam_v1_6_file_level_metadata_subsorting_order = ss - } + -- This parser assumes that the + -- VN, SO, GO and SS tags can appear in any order. + hd <- intercalateEffect (word8 09) $ + SAM_V1_6_File_Level_Metadata + <$> toPermutation parse_SAM_V1_6_File_Level_Metadata_VN + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_File_Level_Metadata_SO) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_File_Level_Metadata_GO) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_File_Level_Metadata_SS) + _ <- endOfLine + return hd diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/HD/GO.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/HD/GO.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/HD/GO.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/HD/GO.hs @@ -47,8 +47,9 @@ import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the GO tag of the @HD tag section of the SAM v1.6 file format. -- @@ -60,9 +61,9 @@ case (hdheaderalignmentgroupingtagp =~ [re|[G][O]|]) of False -> fail $ show SAM_V1_6_Error_File_Level_Metadata_Grouping_Of_Alignments_Tag_Incorrect_Format True -> -- GO tag is in the accepted format. - return hdheaderalignmentgroupingtagp + return () _ <- word8 58 - hdheaderalignmentgroupingvalue <- do hdheaderalignmentgroupingvaluep <- DABL.takeTill (== 09) + hdheaderalignmentgroupingvalue <- do hdheaderalignmentgroupingvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse GO value of the header section. case (hdheaderalignmentgroupingvaluep =~ [re|[n][o][n][e]|[q][u][e][r][y]|[r][e][f][e][r][e][n][c][e]|]) of False -> fail $ show SAM_V1_6_Error_File_Level_Metadata_Grouping_Of_Alignments_Invalid_Value diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/HD/SO.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/HD/SO.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/HD/SO.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/HD/SO.hs @@ -47,8 +47,9 @@ import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the SO tag of the @HD tag section of the SAM v1.6 file format. -- @@ -60,9 +61,9 @@ case (hdheadersortingordertagp =~ [re|[S][O]|]) of False -> fail $ show SAM_V1_6_Error_File_Level_Metadata_Sorting_Order_Tag_Incorrect_Format True -> -- SO tag is in the accepted format. - return hdheadersortingordertagp + return () _ <- word8 58 - hdheadersortingordervalue <- do hdheadersortingordervaluep <- DABL.takeTill (== 09) + hdheadersortingordervalue <- do hdheadersortingordervaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse SO value of the header section. case (hdheadersortingordervaluep =~ [re|[u][n][k][n][o][w][n]|[u][n][s][o][r][t][e][d]|[q][u][e][r][y][n][a][m][e]|[c][o][o][r][d][i][n][a][t][e]|]) of False -> fail $ show SAM_V1_6_Error_File_Level_Metadata_Sorting_Order_Invalid_Value diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/HD/SS.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/HD/SS.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/HD/SS.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/HD/SS.hs @@ -47,8 +47,9 @@ import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the SS tag of the @HD tag section of the SAM v1.6 file format. -- @@ -60,9 +61,9 @@ case (hdheadersubsortingordertagp =~ [re|[S][S]|]) of False -> fail $ show SAM_V1_6_Error_File_Level_Metadata_Subsorting_Order_Tag_Incorrect_Format True -> -- SS tag is in the accepted format. - return hdheadersubsortingordertagp + return () _ <- word8 58 - hdheadersubsortingordervalue <- do hdheadersubsortingordervaluep <- DABL.takeTill (== 09) + hdheadersubsortingordervalue <- do hdheadersubsortingordervaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse SS value of the header section. case (hdheadersubsortingordervaluep =~ [re|(coordinate|queryname|unsorted)(:[A-Za-z0-9_-]+)+|]) of False -> fail $ show SAM_V1_6_Error_File_Level_Metadata_Subsorting_Order_Incorrect_Format diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/HD/VN.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/HD/VN.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/HD/VN.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/HD/VN.hs @@ -47,8 +47,9 @@ import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the VN tag of the @HD tag section of the SAM v1.6 file format. -- @@ -60,11 +61,11 @@ case (hdheaderversiontagp =~ [re|[V][N]|]) of False -> fail $ show SAM_V1_6_Error_File_Level_Metadata_Format_Version_Tag_Incorrect_Format True -> -- VN tag is in the accepted format. - return hdheaderversiontagp + return () _ <- word8 58 - hdheaderversionvalue <- do hdheaderversionvaluep <- DABL.takeTill (== 09) + hdheaderversionvalue <- do hdheaderversionvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse VN value of the header section. - case (hdheaderversionvaluep =~ [re|/^[0-9]+\.[0-9]+$/.|]) of + case (hdheaderversionvaluep =~ [re|^[0-9]+\.[0-9]+$|]) of False -> fail $ show SAM_V1_6_Error_File_Level_Metadata_Format_Version_Value_Incorrect_Format True -> -- VN value is in the accepted format. return hdheaderversionvaluep diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/Base.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/Base.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/Base.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/Base.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} {-# OPTIONS_GHC -fno-warn-name-shadowing #-} @@ -54,14 +53,11 @@ import Data.SAM.Version1_6.Read.Parser.Header.PG.DS import Data.SAM.Version1_6.Read.Parser.Header.PG.VN +import Control.Applicative.Permutations (intercalateEffect,toPermutation,toPermutationWithDefault) +import Data.Attoparsec.ByteString.Char8 as DABC8 (endOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import Text.Regex.PCRE.Heavy --- | Make a parser optional, return Nothing if there is no match. -maybeOption :: Parser a - -> Parser (Maybe a) -maybeOption p = option Nothing (Just <$> p) - -- | @"SAM_V1_6_Program"@ parser. -- -- Defines a parser for @PG tag section of the SAM v1.6 file format. @@ -74,26 +70,22 @@ case (pgheaderp =~ [re|[@][P][G]|]) of False -> fail $ show SAM_V1_6_Error_Program_Tag_Incorrect_Format True -> -- @PG tag is in the accepted format. - return pgheaderp + return () _ <- word8 09 - -- This parser assumes that the ID tag always appears first, followed by - -- the PN, CL, PP, - -- DS and VN tags if they exist, in that order. - id <- parse_SAM_V1_6_SAM_V1_6_Program_ID - _ <- word8 09 - pn <- maybeOption parse_SAM_V1_6_SAM_V1_6_Program_PN - _ <- word8 09 - cl <- maybeOption parse_SAM_V1_6_SAM_V1_6_Program_CL - _ <- word8 09 - pp <- maybeOption parse_SAM_V1_6_SAM_V1_6_Program_PP - _ <- word8 09 - ds <- maybeOption parse_SAM_V1_6_SAM_V1_6_Program_DS - _ <- word8 09 - vn <- maybeOption parse_SAM_V1_6_SAM_V1_6_Program_VN - return SAM_V1_6_Program { sam_v1_6_program_record_identifier = id - , sam_v1_6_program_name = pn - , sam_v1_6_program_command_line = cl - , sam_v1_6_program_previous_pg_id = pp - , sam_v1_6_program_description = ds - , sam_v1_6_program_version = vn - } + -- This parser assumes that the + -- ID, PN, CL, PP, DS, and VN tags can appear in any order. + pg <- intercalateEffect (word8 09) $ + SAM_V1_6_Program + <$> toPermutation parse_SAM_V1_6_Program_ID + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Program_PN) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Program_CL) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Program_PP) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Program_DS) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Program_VN) + _ <- endOfLine + return pg diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/CL.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/CL.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/CL.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/CL.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.PG.CL ( -- * SAM_V1_6 parser - header section (Program) - CL tag - parse_SAM_V1_6_SAM_V1_6_Program_CL + parse_SAM_V1_6_Program_CL ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the CL tag of the @PG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Program_CL :: Parser SAM_V1_6_Program_Command_Line -parse_SAM_V1_6_SAM_V1_6_Program_CL = do +parse_SAM_V1_6_Program_CL :: Parser SAM_V1_6_Program_Command_Line +parse_SAM_V1_6_Program_CL = do _ <- do pgheadercommandlinetagp <- DABL.takeTill (== 58) -- Parse CL tag of the header section. case (pgheadercommandlinetagp =~ [re|[C][L]|]) of False -> fail $ show SAM_V1_6_Error_Program_Command_Line_Incorrect_Format True -> -- CL tag is in the accepted format. - return pgheadercommandlinetagp + return () _ <- word8 58 - pgheadercommandlinevalue <- DABL.takeTill (== 09) + pgheadercommandlinevalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Program_Command_Line { sam_v1_6_program_command_line_value = pgheadercommandlinevalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/DS.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/DS.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/DS.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/DS.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.PG.DS ( -- * SAM_V1_6 parser - header section (Program) - DS tag - parse_SAM_V1_6_SAM_V1_6_Program_DS + parse_SAM_V1_6_Program_DS ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the DS tag of the @PG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Program_DS :: Parser SAM_V1_6_Program_Description -parse_SAM_V1_6_SAM_V1_6_Program_DS = do +parse_SAM_V1_6_Program_DS :: Parser SAM_V1_6_Program_Description +parse_SAM_V1_6_Program_DS = do _ <- do pgheaderdescriptiontagp <- DABL.takeTill (== 58) -- Parse DS tag of the header section. case (pgheaderdescriptiontagp =~ [re|[D][S]|]) of False -> fail $ show SAM_V1_6_Error_Program_Description_Incorrect_Format True -> -- DS tag is in the accepted format. - return pgheaderdescriptiontagp + return () _ <- word8 58 - pgheaderdescriptionvalue <- DABL.takeTill (== 09) + pgheaderdescriptionvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Program_Description { sam_v1_6_program_description_value = pgheaderdescriptionvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/ID.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/ID.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/ID.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/ID.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.PG.ID ( -- * SAM_V1_6 parser - header section (Program) - ID tag - parse_SAM_V1_6_SAM_V1_6_Program_ID + parse_SAM_V1_6_Program_ID ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the ID tag of the @PG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Program_ID :: Parser SAM_V1_6_Program_Record_Identifier -parse_SAM_V1_6_SAM_V1_6_Program_ID = do +parse_SAM_V1_6_Program_ID :: Parser SAM_V1_6_Program_Record_Identifier +parse_SAM_V1_6_Program_ID = do _ <- do pgheaderidentifiertagp <- DABL.takeTill (== 58) -- Parse ID tag of the header section. case (pgheaderidentifiertagp =~ [re|[I][D]|]) of False -> fail $ show SAM_V1_6_Error_Program_Identifier_Incorrect_Format True -> -- ID tag is in the accepted format. - return pgheaderidentifiertagp + return () _ <- word8 58 - pgheaderidentifiervalue <- DABL.takeTill (== 09) + pgheaderidentifiervalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Program_Record_Identifier { sam_v1_6_program_record_identifier_value = pgheaderidentifiervalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/PN.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/PN.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/PN.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/PN.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.PG.PN ( -- * SAM_V1_6 parser - header section (Program) - PN tag - parse_SAM_V1_6_SAM_V1_6_Program_PN + parse_SAM_V1_6_Program_PN ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the PN tag of the @PG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Program_PN :: Parser SAM_V1_6_Program_Name -parse_SAM_V1_6_SAM_V1_6_Program_PN = do +parse_SAM_V1_6_Program_PN :: Parser SAM_V1_6_Program_Name +parse_SAM_V1_6_Program_PN = do _ <- do pgheadernametagp <- DABL.takeTill (== 58) -- Parse PN tag of the header section. case (pgheadernametagp =~ [re|[P][N]|]) of False -> fail $ show SAM_V1_6_Error_Program_Name_Incorrect_Format True -> -- PN tag is in the accepted format. - return pgheadernametagp + return () _ <- word8 58 - pgheadernamevalue <- DABL.takeTill (== 09) + pgheadernamevalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Program_Name { sam_v1_6_program_name_value = pgheadernamevalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/PP.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/PP.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/PP.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/PP.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.PG.PP ( -- * SAM_V1_6 parser - header section (Program) - PP tag - parse_SAM_V1_6_SAM_V1_6_Program_PP + parse_SAM_V1_6_Program_PP ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the PP tag of the @PG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Program_PP :: Parser SAM_V1_6_Program_Previous_PG_ID -parse_SAM_V1_6_SAM_V1_6_Program_PP = do +parse_SAM_V1_6_Program_PP :: Parser SAM_V1_6_Program_Previous_PG_ID +parse_SAM_V1_6_Program_PP = do _ <- do pgheaderpreviouspgidtagp <- DABL.takeTill (== 58) -- Parse PP tag of the header section. case (pgheaderpreviouspgidtagp =~ [re|[P][P]|]) of False -> fail $ show SAM_V1_6_Error_Program_Previous_PG_ID_Incorrect_Format True -> -- PP tag is in the accepted format. - return pgheaderpreviouspgidtagp + return () _ <- word8 58 - pgheaderpreviouspgidvalue <- DABL.takeTill (== 09) + pgheaderpreviouspgidvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Program_Previous_PG_ID { sam_v1_6_program_previous_pg_id_value = pgheaderpreviouspgidvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/VN.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/VN.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/PG/VN.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/PG/VN.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.PG.VN ( -- * SAM_V1_6 parser - header section (Program) - VN tag - parse_SAM_V1_6_SAM_V1_6_Program_VN + parse_SAM_V1_6_Program_VN ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the VN tag of the @PG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Program_VN :: Parser SAM_V1_6_Program_Version -parse_SAM_V1_6_SAM_V1_6_Program_VN = do +parse_SAM_V1_6_Program_VN :: Parser SAM_V1_6_Program_Version +parse_SAM_V1_6_Program_VN = do _ <- do pgheaderversiontagp <- DABL.takeTill (== 58) -- Parse VN tag of the header section. case (pgheaderversiontagp =~ [re|[V][N]|]) of False -> fail $ show SAM_V1_6_Error_Program_Version_Incorrect_Format True -> -- VN tag is in the accepted format. - return pgheaderversiontagp + return () _ <- word8 58 - pgheaderversionvalue <- DABL.takeTill (== 09) + pgheaderversionvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Program_Version { sam_v1_6_program_version_value = pgheaderversionvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/BC.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/BC.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/BC.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/BC.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.BC ( -- * SAM_V1_6 parser - header section (Read group) - BC tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_BC + parse_SAM_V1_6_Read_Group_BC ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the BC tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_BC :: Parser SAM_V1_6_Read_Group_Barcode_Sequence -parse_SAM_V1_6_SAM_V1_6_Read_Group_BC = do +parse_SAM_V1_6_Read_Group_BC :: Parser SAM_V1_6_Read_Group_Barcode_Sequence +parse_SAM_V1_6_Read_Group_BC = do _ <- do rgheaderbarcodesequencetagp <- DABL.takeTill (== 58) -- Parse BC tag of the header section. case (rgheaderbarcodesequencetagp =~ [re|[B][C]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Barcode_Sequence_Incorrect_Format True -> -- BC tag is in the accepted format. - return rgheaderbarcodesequencetagp + return () _ <- word8 58 - rgheaderbarcodesequencevalue <- DABL.takeTill (== 09) + rgheaderbarcodesequencevalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Barcode_Sequence { sam_v1_6_read_group_barcode_sequence_value = rgheaderbarcodesequencevalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/Base.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/Base.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/Base.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/Base.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} {-# OPTIONS_GHC -fno-warn-name-shadowing #-} @@ -62,14 +61,11 @@ import Data.SAM.Version1_6.Read.Parser.Header.RG.PU import Data.SAM.Version1_6.Read.Parser.Header.RG.SM +import Control.Applicative.Permutations (intercalateEffect,toPermutation,toPermutationWithDefault) +import Data.Attoparsec.ByteString.Char8 as DABC8 (endOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import Text.Regex.PCRE.Heavy --- | Make a parser optional, return Nothing if there is no match. -maybeOption :: Parser a - -> Parser (Maybe a) -maybeOption p = option Nothing (Just <$> p) - -- | @"SAM_V1_6_Read_Group"@ parser. -- -- Defines a parser for @RG tag section of the SAM v1.6 file format. @@ -82,50 +78,39 @@ case (rgheaderp =~ [re|[@][R][G]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Tag_Incorrect_Format True -> -- @RG tag is in the accepted format. - return rgheaderp + return () _ <- word8 09 - -- This parser assumes that the ID tag always appears first, followed by - -- the BC, CN, DS, DT, FO, KS, LB, PG, PI, PL, - -- PM, PU and SM tags if they exist, in that order. - id <- parse_SAM_V1_6_SAM_V1_6_Read_Group_ID - _ <- word8 09 - bc <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_BC - _ <- word8 09 - cn <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_CN - _ <- word8 09 - ds <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_DS - _ <- word8 09 - dt <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_DT - _ <- word8 09 - fo <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_FO - _ <- word8 09 - ks <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_KS - _ <- word8 09 - lb <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_LB - _ <- word8 09 - pg <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_PG - _ <- word8 09 - pi <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_PI - _ <- word8 09 - pl <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_PL - _ <- word8 09 - pm <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_PM - _ <- word8 09 - pu <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_PU - _ <- word8 09 - sm <- maybeOption parse_SAM_V1_6_SAM_V1_6_Read_Group_SM - return SAM_V1_6_Read_Group { sam_v1_6_read_group_identifer = id - , sam_v1_6_read_group_barcode_sequence = bc - , sam_v1_6_read_group_sequencing_center = cn - , sam_v1_6_read_group_description = ds - , sam_v1_6_read_group_run_date = dt - , sam_v1_6_read_group_flow_order = fo - , sam_v1_6_read_group_key_sequence = ks - , sam_v1_6_read_group_library = lb - , sam_v1_6_read_group_programs = pg - , sam_v1_6_read_group_predicted_median_insert_size = pi - , sam_v1_6_read_group_platform = pl - , sam_v1_6_read_group_platform_model = pm - , sam_v1_6_read_group_platform_unit = pu - , sam_v1_6_read_group_sample = sm - } + -- This parser assumes that the + -- ID, BC, CN, DS, DT, FO, KS, LB, PG, PI, PL, + -- PM, PU and SM tags can appear in any order. + rg <- intercalateEffect (word8 09) $ + SAM_V1_6_Read_Group + <$> toPermutation parse_SAM_V1_6_Read_Group_ID + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_BC) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_CN) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_DS) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_DT) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_FO) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_KS) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_LB) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_PG) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_PI) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_PL) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_PM) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_PU) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Read_Group_SM) + _ <- endOfLine + return rg diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/CN.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/CN.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/CN.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/CN.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.CN ( -- * SAM_V1_6 parser - header section (Read group) - CN tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_CN + parse_SAM_V1_6_Read_Group_CN ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the CN tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_CN :: Parser SAM_V1_6_Read_Group_Sequencing_Center -parse_SAM_V1_6_SAM_V1_6_Read_Group_CN = do +parse_SAM_V1_6_Read_Group_CN :: Parser SAM_V1_6_Read_Group_Sequencing_Center +parse_SAM_V1_6_Read_Group_CN = do _ <- do rgheadersequencingcentertagp <- DABL.takeTill (== 58) -- Parse CN tag of the header section. case (rgheadersequencingcentertagp =~ [re|[C][N]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Sequencing_Center_Incorrect_Format True -> -- CN tag is in the accepted format. - return rgheadersequencingcentertagp + return () _ <- word8 58 - rgheadersequencingcentervalue <- DABL.takeTill (== 09) + rgheadersequencingcentervalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Sequencing_Center { sam_v1_6_read_group_sequencing_center_value = rgheadersequencingcentervalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/DS.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/DS.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/DS.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/DS.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.DS ( -- * SAM_V1_6 parser - header section (Read group) - DS tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_DS + parse_SAM_V1_6_Read_Group_DS ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the DS tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_DS :: Parser SAM_V1_6_Read_Group_Description -parse_SAM_V1_6_SAM_V1_6_Read_Group_DS = do +parse_SAM_V1_6_Read_Group_DS :: Parser SAM_V1_6_Read_Group_Description +parse_SAM_V1_6_Read_Group_DS = do _ <- do rgheaderdescriptiontagp <- DABL.takeTill (== 58) -- Parse DS tag of the header section. case (rgheaderdescriptiontagp =~ [re|[D][S]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Description_Incorrect_Format True -> -- DS tag is in the accepted format. - return rgheaderdescriptiontagp + return () _ <- word8 58 - rgheaderdescriptionvalue <- DABL.takeTill (== 09) + rgheaderdescriptionvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Description { sam_v1_6_read_group_description_value = rgheaderdescriptionvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/DT.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/DT.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/DT.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/DT.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.DT ( -- * SAM_V1_6 parser - header section (Read group) - DT tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_DT + parse_SAM_V1_6_Read_Group_DT ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the DT tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_DT :: Parser SAM_V1_6_Read_Group_Run_Date -parse_SAM_V1_6_SAM_V1_6_Read_Group_DT = do +parse_SAM_V1_6_Read_Group_DT :: Parser SAM_V1_6_Read_Group_Run_Date +parse_SAM_V1_6_Read_Group_DT = do _ <- do rgheaderrundatetagp <- DABL.takeTill (== 58) -- Parse DT tag of the header section. case (rgheaderrundatetagp =~ [re|[D][T]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Date_Run_Produced_Incorrect_Format True -> -- DT tag is in the accepted format. - return rgheaderrundatetagp + return () _ <- word8 58 - rgheaderrundatevalue <- DABL.takeTill (== 09) + rgheaderrundatevalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Run_Date { sam_v1_6_read_group_run_date_value = rgheaderrundatevalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/FO.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/FO.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/FO.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/FO.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,30 +40,31 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.FO ( -- * SAM_V1_6 parser - header section (Read group) - FO tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_FO + parse_SAM_V1_6_Read_Group_FO ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the FO tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_FO :: Parser SAM_V1_6_Read_Group_Flow_Order -parse_SAM_V1_6_SAM_V1_6_Read_Group_FO = do +parse_SAM_V1_6_Read_Group_FO :: Parser SAM_V1_6_Read_Group_Flow_Order +parse_SAM_V1_6_Read_Group_FO = do _ <- do rgheaderflowordertagp <- DABL.takeTill (== 58) -- Parse FO tag of the header section. case (rgheaderflowordertagp =~ [re|[F][O]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Flow_Order_Incorrect_Format True -> -- FO tag is in the accepted format. - return rgheaderflowordertagp + return () _ <- word8 58 - rgheaderflowordervalue <- do rgheaderflowordervaluep <- DABL.takeTill (== 09) + rgheaderflowordervalue <- do rgheaderflowordervaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse FO value of the header section. - case (rgheaderflowordervaluep =~ [re|/\*|[ACMGRSVTWYHKDBN]+/|]) of + case (rgheaderflowordervaluep =~ [re|\*|[ACMGRSVTWYHKDBN]+|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Flow_Order_Incorrect_Format True -> -- FO value is in the accepted format. return rgheaderflowordervaluep diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/ID.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/ID.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/ID.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/ID.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.ID ( -- * SAM_V1_6 parser - header section (Read group) - ID tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_ID + parse_SAM_V1_6_Read_Group_ID ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the ID tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_ID :: Parser SAM_V1_6_Read_Group_Identifier -parse_SAM_V1_6_SAM_V1_6_Read_Group_ID = do +parse_SAM_V1_6_Read_Group_ID :: Parser SAM_V1_6_Read_Group_Identifier +parse_SAM_V1_6_Read_Group_ID = do _ <- do rgheaderreadgroupidentifiertagp <- DABL.takeTill (== 58) -- Parse ID tag of the header section. case (rgheaderreadgroupidentifiertagp =~ [re|[I][D]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Read_Group_Identifier_Incorrect_Format True -> -- ID tag is in the accepted format. - return rgheaderreadgroupidentifiertagp + return () _ <- word8 58 - rgheaderreadgroupidentifiervalue <- DABL.takeTill (== 09) + rgheaderreadgroupidentifiervalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Identifier { sam_v1_6_read_group_identifier_value = rgheaderreadgroupidentifiervalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/KS.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/KS.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/KS.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/KS.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.KS ( -- * SAM_V1_6 parser - header section (Read group) - KS tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_KS + parse_SAM_V1_6_Read_Group_KS ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the KS tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_KS :: Parser SAM_V1_6_Read_Group_Key_Sequence -parse_SAM_V1_6_SAM_V1_6_Read_Group_KS = do +parse_SAM_V1_6_Read_Group_KS :: Parser SAM_V1_6_Read_Group_Key_Sequence +parse_SAM_V1_6_Read_Group_KS = do _ <- do rgheaderkeysequencetagp <- DABL.takeTill (== 58) -- Parse KS tag of the header section. case (rgheaderkeysequencetagp =~ [re|[K][S]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Key_Sequence_Incorrect_Format True -> -- KS tag is in the accepted format. - return rgheaderkeysequencetagp + return () _ <- word8 58 - rgheaderkeysequencevalue <- DABL.takeTill (== 09) + rgheaderkeysequencevalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Key_Sequence { sam_v1_6_read_group_key_sequence_value = rgheaderkeysequencevalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/LB.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/LB.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/LB.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/LB.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.LB ( -- * SAM_V1_6 parser - header section (Read group) - LB tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_LB + parse_SAM_V1_6_Read_Group_LB ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the LB tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_LB :: Parser SAM_V1_6_Read_Group_Library -parse_SAM_V1_6_SAM_V1_6_Read_Group_LB = do +parse_SAM_V1_6_Read_Group_LB :: Parser SAM_V1_6_Read_Group_Library +parse_SAM_V1_6_Read_Group_LB = do _ <- do rgheaderlibrarytagp <- DABL.takeTill (== 58) -- Parse LB tag of the header section. case (rgheaderlibrarytagp =~ [re|[L][B]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Library_Incorrect_Format True -> -- LB tag is in the accepted format. - return rgheaderlibrarytagp + return () _ <- word8 58 - rgheaderlibraryvalue <- DABL.takeTill (== 09) + rgheaderlibraryvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Library { sam_v1_6_read_group_library_value = rgheaderlibraryvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PG.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PG.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PG.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PG.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.PG ( -- * SAM_V1_6 parser - header section (Read group) - PG tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_PG + parse_SAM_V1_6_Read_Group_PG ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the PG tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_PG :: Parser SAM_V1_6_Read_Group_Programs -parse_SAM_V1_6_SAM_V1_6_Read_Group_PG = do +parse_SAM_V1_6_Read_Group_PG :: Parser SAM_V1_6_Read_Group_Programs +parse_SAM_V1_6_Read_Group_PG = do _ <- do rgheaderprogramstagp <- DABL.takeTill (== 58) -- Parse PG tag of the header section. case (rgheaderprogramstagp =~ [re|[P][G]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Programs_Incorrect_Format True -> -- PG tag is in the accepted format. - return rgheaderprogramstagp + return () _ <- word8 58 - rgheaderprogramsvalue <- DABL.takeTill (== 09) + rgheaderprogramsvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Programs { sam_v1_6_read_group_programs_value = rgheaderprogramsvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PI.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PI.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PI.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PI.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.PI ( -- * SAM_V1_6 parser - header section (Read group) - PI tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_PI + parse_SAM_V1_6_Read_Group_PI ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the PI tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_PI :: Parser SAM_V1_6_Read_Group_Predicted_Median_Insert_Size -parse_SAM_V1_6_SAM_V1_6_Read_Group_PI = do +parse_SAM_V1_6_Read_Group_PI :: Parser SAM_V1_6_Read_Group_Predicted_Median_Insert_Size +parse_SAM_V1_6_Read_Group_PI = do _ <- do rgheaderpredictedmedianinsertsizetagp <- DABL.takeTill (== 58) -- Parse PI tag of the header section. case (rgheaderpredictedmedianinsertsizetagp =~ [re|[P][I]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Predicted_Median_Insert_Size_Incorrect_Format True -> -- PI tag is in the accepted format. - return rgheaderpredictedmedianinsertsizetagp + return () _ <- word8 58 - rgheaderpredictedmedianinsertsizevalue <- DABL.takeTill (== 09) + rgheaderpredictedmedianinsertsizevalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Predicted_Median_Insert_Size { sam_v1_6_read_group_predicted_median_insert_size_value = rgheaderpredictedmedianinsertsizevalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PL.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PL.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PL.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PL.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,28 +40,29 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.PL ( -- * SAM_V1_6 parser - header section (Read group) - PL tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_PL + parse_SAM_V1_6_Read_Group_PL ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the PL tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_PL :: Parser SAM_V1_6_Read_Group_Platform -parse_SAM_V1_6_SAM_V1_6_Read_Group_PL = do +parse_SAM_V1_6_Read_Group_PL :: Parser SAM_V1_6_Read_Group_Platform +parse_SAM_V1_6_Read_Group_PL = do _ <- do rgheaderplatformtagp <- DABL.takeTill (== 58) -- Parse PL tag of the header section. case (rgheaderplatformtagp =~ [re|[P][L]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Platform_Incorrect_Format True -> -- PL tag is in the accepted format. - return rgheaderplatformtagp + return () _ <- word8 58 - rgheaderplatformvalue <- do rgheaderplatformvaluep <- DABL.takeTill (== 09) + rgheaderplatformvalue <- do rgheaderplatformvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse PL value of the header section. case (rgheaderplatformvaluep =~ [re|[C][A][P][I][L][L][A][R][Y]|[D][N][B][S][E][Q]|[E][L][E][M][E][N][T]|[H][E][L][I][C][O][S]|[I][L][L][U][M][I][N][A]|[I][O][N][T][O][R][R][E][N][T]|[L][S][4][5][4]|[O][N][T]|[P][A][C][B][I][O]|[S][O][L][I][D]|[U][L][T][I][M][A]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Platform_Incorrect_Format diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PM.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PM.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PM.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PM.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.PM ( -- * SAM_V1_6 parser - header section (Read group) - PM tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_PM + parse_SAM_V1_6_Read_Group_PM ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the PM tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_PM :: Parser SAM_V1_6_Read_Group_Platform_Model -parse_SAM_V1_6_SAM_V1_6_Read_Group_PM = do +parse_SAM_V1_6_Read_Group_PM :: Parser SAM_V1_6_Read_Group_Platform_Model +parse_SAM_V1_6_Read_Group_PM = do _ <- do rgheaderplatformmodeltagp <- DABL.takeTill (== 58) -- Parse PM tag of the header section. case (rgheaderplatformmodeltagp =~ [re|[P][M]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Platform_Model_Incorrect_Format True -> -- PM tag is in the accepted format. - return rgheaderplatformmodeltagp + return () _ <- word8 58 - rgheaderplatformmodelvalue <- DABL.takeTill (== 09) + rgheaderplatformmodelvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Platform_Model { sam_v1_6_read_group_platform_model_value = rgheaderplatformmodelvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PU.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PU.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PU.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/PU.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.PU ( -- * SAM_V1_6 parser - header section (Read group) - PU tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_PU + parse_SAM_V1_6_Read_Group_PU ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the PU tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_PU :: Parser SAM_V1_6_Read_Group_Platform_Unit -parse_SAM_V1_6_SAM_V1_6_Read_Group_PU = do +parse_SAM_V1_6_Read_Group_PU :: Parser SAM_V1_6_Read_Group_Platform_Unit +parse_SAM_V1_6_Read_Group_PU = do _ <- do rgheaderplatformunittagp <- DABL.takeTill (== 58) -- Parse PU tag of the header section. case (rgheaderplatformunittagp =~ [re|[P][U]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Platform_Unit_Incorrect_Format True -> -- PU tag is in the accepted format. - return rgheaderplatformunittagp + return () _ <- word8 58 - rgheaderplatformunitvalue <- DABL.takeTill (== 09) + rgheaderplatformunitvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Platform_Unit { sam_v1_6_read_group_platform_unit_value = rgheaderplatformunitvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/SM.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/SM.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/RG/SM.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/RG/SM.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.RG.SM ( -- * SAM_V1_6 parser - header section (Read group) - SM tag - parse_SAM_V1_6_SAM_V1_6_Read_Group_SM + parse_SAM_V1_6_Read_Group_SM ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the SM tag of the @RG tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Read_Group_SM :: Parser SAM_V1_6_Read_Group_Sample -parse_SAM_V1_6_SAM_V1_6_Read_Group_SM = do +parse_SAM_V1_6_Read_Group_SM :: Parser SAM_V1_6_Read_Group_Sample +parse_SAM_V1_6_Read_Group_SM = do _ <- do rgheadersampletagp <- DABL.takeTill (== 58) -- Parse SM tag of the header section. case (rgheadersampletagp =~ [re|[S][M]|]) of False -> fail $ show SAM_V1_6_Error_Read_Group_Sample_Incorrect_Format True -> -- SM tag is in the accepted format. - return rgheadersampletagp + return () _ <- word8 58 - rgheadersamplevalue <- DABL.takeTill (== 09) + rgheadersamplevalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Read_Group_Sample { sam_v1_6_read_group_sample_value = rgheadersamplevalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AH.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AH.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AH.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AH.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.SQ.AH ( -- * SAM_V1_6 parser - header section (Reference sequence dictionary) - AH tag - parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AH + parse_SAM_V1_6_Reference_Sequence_Dictionary_AH ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the AH tag of the @SQ tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AH :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Alternative_Locus -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AH = do +parse_SAM_V1_6_Reference_Sequence_Dictionary_AH :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Alternative_Locus +parse_SAM_V1_6_Reference_Sequence_Dictionary_AH = do _ <- do sqheaderalternativelocustagp <- DABL.takeTill (== 58) -- Parse AH tag of the header section. case (sqheaderalternativelocustagp =~ [re|[A][H]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Alternative_Locus_Incorrect_Format True -> -- AH tag is in the accepted format. - return sqheaderalternativelocustagp + return () _ <- word8 58 - sqheaderalternativelocusvalue <- DABL.takeTill (== 09) + sqheaderalternativelocusvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Reference_Sequence_Dictionary_Alternative_Locus { sam_v1_6_reference_sequence_dictionary_alternative_locus_value = sqheaderalternativelocusvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AN.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AN.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AN.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AN.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,30 +40,31 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.SQ.AN ( -- * SAM_V1_6 parser - header section (Reference sequence dictionary) - AN tag - parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AN + parse_SAM_V1_6_Reference_Sequence_Dictionary_AN ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the AN tag of the @SQ tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AN :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Alternative_Reference_Sequence_Names -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AN = do +parse_SAM_V1_6_Reference_Sequence_Dictionary_AN :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Alternative_Reference_Sequence_Names +parse_SAM_V1_6_Reference_Sequence_Dictionary_AN = do _ <- do sqheaderalternativereferencesequencenamestagp <- DABL.takeTill (== 58) -- Parse AN tag of the header section. case (sqheaderalternativereferencesequencenamestagp =~ [re|[A][N]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Alternative_Reference_Sequence_Names_Incorrect_Format True -> -- AN tag is in the accepted format. - return sqheaderalternativereferencesequencenamestagp + return () _ <- word8 58 - sqheaderalternativereferencesequencenamesvalue <- do sqheaderalternativereferencesequencenamesvaluep <- DABL.takeTill (== 09) + sqheaderalternativereferencesequencenamesvalue <- do sqheaderalternativereferencesequencenamesvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse AN value of the header section. - case (sqheaderalternativereferencesequencenamesvaluep =~ [re|[0-9A-Za-z!#$%&+./:;?@^_|~-][0-9A-Za-z!#$%&*+./:;=?@^_|~-]*(,[0-9A-Za-z!#$%&+./:;?@^_|~-][0-9A-Za-z!#$%&*+./:;=?@^_|~-]*)*|]) of + case (sqheaderalternativereferencesequencenamesvaluep =~ [re|[0-9A-Za-z!#$%&+.:;?@^_|~-][0-9A-Za-z!#$%&*+.:;=?@^_|~-]*(,[0-9A-Za-z!#$%&+.:;?@^_|~-][0-9A-Za-z!#$%&*+.:;=?@^_|~-]*)*|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Alternative_Reference_Sequence_Names_Invalid_Value True -> -- AN value is in the accepted format. return sqheaderalternativereferencesequencenamesvaluep diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AS.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AS.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AS.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/AS.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.SQ.AS ( -- * SAM_V1_6 parser - header section (Reference sequence dictionary) - AS tag - parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AS + parse_SAM_V1_6_Reference_Sequence_Dictionary_AS ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the AS tag of the @SQ tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AS :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Genome_Assembly_Identifier -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AS = do +parse_SAM_V1_6_Reference_Sequence_Dictionary_AS :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Genome_Assembly_Identifier +parse_SAM_V1_6_Reference_Sequence_Dictionary_AS = do _ <- do sqheadergenomeassemblyidentifiertagp <- DABL.takeTill (== 58) -- Parse AS tag of the header section. case (sqheadergenomeassemblyidentifiertagp =~ [re|[A][S]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Genome_Assembly_Identifier_Incorrect_Format True -> -- AS tag is in the accepted format. - return sqheadergenomeassemblyidentifiertagp + return () _ <- word8 58 - sqheadergenomeassemblyidentifiervalue <- DABL.takeTill (== 09) + sqheadergenomeassemblyidentifiervalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Reference_Sequence_Dictionary_Genome_Assembly_Identifier { sam_v1_6_reference_sequence_dictionary_genome_assembly_identifier_value = sqheadergenomeassemblyidentifiervalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/Base.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/Base.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/Base.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/Base.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -57,14 +56,11 @@ import Data.SAM.Version1_6.Read.Parser.Header.SQ.TP import Data.SAM.Version1_6.Read.Parser.Header.SQ.UR +import Control.Applicative.Permutations (intercalateEffect,toPermutation,toPermutationWithDefault) +import Data.Attoparsec.ByteString.Char8 as DABC8 (endOfLine) import Data.Attoparsec.ByteString.Lazy as DABL import Text.Regex.PCRE.Heavy --- | Make a parser optional, return Nothing if there is no match. -maybeOption :: Parser a - -> Parser (Maybe a) -maybeOption p = option Nothing (Just <$> p) - -- | @"SAM_V1_6_Reference_Sequence_Dictionary"@ parser. -- -- Defines a parser for @SQ tag section of the SAM v1.6 file format. @@ -77,38 +73,30 @@ case (sqheaderp =~ [re|[@][S][Q]|]) of False -> fail $ show SAM_V1_6_Error_File_Level_Metadata_Tag_Incorrect_Format True -> -- @SQ tag is in the accepted format. - return sqheaderp + return () _ <- word8 09 - -- This parser assumes that the SN tag always appears first, followed by - -- the LN tag, followed by the AH, AN, AS, DS, M5, - -- SP, TP and UR tags if they exist, in that order. - sn <- parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_SN - _ <- word8 09 - ln <- parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_LN - _ <- word8 09 - ah <- maybeOption parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AH - _ <- word8 09 - an <- maybeOption parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AN - _ <- word8 09 - as <- maybeOption parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_AS - _ <- word8 09 - ds <- maybeOption parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_DS - _ <- word8 09 - m5 <- maybeOption parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_M5 - _ <- word8 09 - sp <- maybeOption parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_SP - _ <- word8 09 - tp <- maybeOption parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_TP - _ <- word8 09 - ur <- maybeOption parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_UR - return SAM_V1_6_Reference_Sequence_Dictionary { sam_v1_6_reference_sequence_dictionary_reference_sequence_name = sn - , sam_v1_6_reference_sequence_dictionary_reference_sequence_length = ln - , sam_v1_6_reference_sequence_dictionary_reference_alternative_locus = ah - , sam_v1_6_reference_sequence_dictionary_reference_alternative_reference_sequence_names = an - , sam_v1_6_reference_sequence_dictionary_genome_assembly_identifier = as - , sam_v1_6_reference_sequence_dictionary_description = ds - , sam_v1_6_reference_sequence_dictionary_md5_checksum = m5 - , sam_v1_6_reference_sequence_dictionary_species = sp - , sam_v1_6_reference_sequence_dictionary_molecule_topology = tp - , sam_v1_6_reference_sequence_dictionary_uri = ur - } + -- This parser assumes that the + -- SN, LN, AH, AN, AS, DS, M5, + -- SP, TP and UR tags can appear in any order. + sq <- intercalateEffect (word8 09) $ + SAM_V1_6_Reference_Sequence_Dictionary + <$> toPermutation parse_SAM_V1_6_Reference_Sequence_Dictionary_SN + <*> toPermutation parse_SAM_V1_6_Reference_Sequence_Dictionary_LN + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Reference_Sequence_Dictionary_AH) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Reference_Sequence_Dictionary_AN) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Reference_Sequence_Dictionary_AS) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Reference_Sequence_Dictionary_DS) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Reference_Sequence_Dictionary_M5) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Reference_Sequence_Dictionary_SP) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Reference_Sequence_Dictionary_TP) + <*> toPermutationWithDefault Nothing + (Just <$> parse_SAM_V1_6_Reference_Sequence_Dictionary_UR) + _ <- endOfLine + return sq diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/DS.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/DS.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/DS.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/DS.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.SQ.DS ( -- * SAM_V1_6 parser - header section (Reference sequence dictionary) - DS tag - parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_DS + parse_SAM_V1_6_Reference_Sequence_Dictionary_DS ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the DS tag of the @SQ tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_DS :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Description -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_DS = do +parse_SAM_V1_6_Reference_Sequence_Dictionary_DS :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Description +parse_SAM_V1_6_Reference_Sequence_Dictionary_DS = do _ <- do sqheaderdescriptiontagp <- DABL.takeTill (== 58) -- Parse DS tag of the header section. case (sqheaderdescriptiontagp =~ [re|[D][S]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Description_Incorrect_Format True -> -- DS tag is in the accepted format. - return sqheaderdescriptiontagp + return () _ <- word8 58 - sqheaderdescriptionvalue <- DABL.takeTill (== 09) + sqheaderdescriptionvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Reference_Sequence_Dictionary_Description { sam_v1_6_reference_sequence_dictionary_description_value = sqheaderdescriptionvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/LN.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/LN.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/LN.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/LN.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,28 +40,29 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.SQ.LN ( -- * SAM_V1_6 parser - header section (Reference sequence dictionary) - LN tag - parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_LN + parse_SAM_V1_6_Reference_Sequence_Dictionary_LN ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the LN tag of the @SQ tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_LN :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Length -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_LN = do +parse_SAM_V1_6_Reference_Sequence_Dictionary_LN :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Length +parse_SAM_V1_6_Reference_Sequence_Dictionary_LN = do _ <- do sqheadersequencelengthtagp <- DABL.takeTill (== 58) -- Parse LN tag of the header section. case (sqheadersequencelengthtagp =~ [re|[L][N]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Reference_Sequence_Length_Incorrect_Format True -> -- LN tag is in the accepted format. - return sqheadersequencelengthtagp + return () _ <- word8 58 - sqheadersequencelengthvalue <- do sqheadersequencelengthvaluep <- DABL.takeTill (== 09) + sqheadersequencelengthvalue <- do sqheadersequencelengthvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse LN value of the header section. case (sqheadersequencelengthvaluep =~ [re|[0-9]*|]) of -- Make this regex actually check the range of [1,2^31 - 1]? False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Reference_Sequence_Length_Invalid_Value diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/M5.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/M5.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/M5.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/M5.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.SQ.M5 ( -- * SAM_V1_6 parser - header section (Reference sequence dictionary) - M5 tag - parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_M5 + parse_SAM_V1_6_Reference_Sequence_Dictionary_M5 ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the M5 tag of the @SQ tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_M5 :: Parser SAM_V1_6_Reference_Sequence_Dictionary_MD5_Checksum -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_M5 = do +parse_SAM_V1_6_Reference_Sequence_Dictionary_M5 :: Parser SAM_V1_6_Reference_Sequence_Dictionary_MD5_Checksum +parse_SAM_V1_6_Reference_Sequence_Dictionary_M5 = do _ <- do sqheadermd5checksumtagp <- DABL.takeTill (== 58) -- Parse M5 tag of the header section. case (sqheadermd5checksumtagp =~ [re|[M][5]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_MD5_Checksum_Incorrect_Format True -> -- M5 tag is in the accepted format. - return sqheadermd5checksumtagp + return () _ <- word8 58 - sqheadermd5checksumvalue <- DABL.takeTill (== 09) + sqheadermd5checksumvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Reference_Sequence_Dictionary_MD5_Checksum { sam_v1_6_reference_sequence_dictionary_md5_checksum_value = sqheadermd5checksumvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/SN.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/SN.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/SN.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/SN.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,32 +40,33 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.SQ.SN ( -- * SAM_V1_6 parser - header section (Reference sequence dictionary) - SN tag - parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_SN + parse_SAM_V1_6_Reference_Sequence_Dictionary_SN ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the SN tag of the @SQ tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_SN :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Name -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_SN = do +parse_SAM_V1_6_Reference_Sequence_Dictionary_SN :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Name +parse_SAM_V1_6_Reference_Sequence_Dictionary_SN = do _ <- do sqheadersequencenametagp <- DABL.takeTill (== 58) -- Parse SN tag of the header section. case (sqheadersequencenametagp =~ [re|[S][N]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Reference_Sequence_Name_Incorrect_Format True -> -- SN tag is in the accepted format. - return sqheadersequencenametagp + return () _ <- word8 58 - sqheadersequencenamevalue <- do sqheadersequencenamevaluep <- DABL.takeTill (== 09) + sqheadersequencenamevalue <- do sqheadersequencenamevaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse SN value of the header section. case (sqheadersequencenamevaluep =~ [re|[0-9A-Za-z!#$%&+./:;?@^_|~-][0-9A-Za-z!#$%&*+./:;=?@^_|~-]*|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Reference_Sequence_Name_Invalid_Value True -> -- SN value is in the accepted format. - return sqheadersequencenamevaluep + return sqheadersequencenamevaluep return SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Name { sam_v1_6_reference_sequence_dictionary_reference_sequence_name_value = sqheadersequencenamevalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/SP.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/SP.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/SP.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/SP.hs @@ -41,27 +41,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.SQ.SP ( -- * SAM_V1_6 parser - header section (Reference sequence dictionary) - SP tag - parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_SP + parse_SAM_V1_6_Reference_Sequence_Dictionary_SP ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the SP tag of the @SQ tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_SP :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Species -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_SP = do +parse_SAM_V1_6_Reference_Sequence_Dictionary_SP :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Species +parse_SAM_V1_6_Reference_Sequence_Dictionary_SP = do _ <- do sqheaderspeciestagp <- DABL.takeTill (== 58) -- Parse SP tag of the header section. case (sqheaderspeciestagp =~ [re|[S][P]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Species_Incorrect_Format True -> -- SP tag is in the accepted format. - return sqheaderspeciestagp + return () _ <- word8 58 - sqheaderspeciesvalue <- DABL.takeTill (== 09) + sqheaderspeciesvalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Reference_Sequence_Dictionary_Species { sam_v1_6_reference_sequence_dictionary_species_value = sqheaderspeciesvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/TP.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/TP.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/TP.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/TP.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,32 +40,33 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.SQ.TP ( -- * SAM_V1_6 parser - header section (Reference sequence dictionary) - TP tag - parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_TP + parse_SAM_V1_6_Reference_Sequence_Dictionary_TP ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the TP tag of the @SQ tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_TP :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Molecule_Topology -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_TP = do +parse_SAM_V1_6_Reference_Sequence_Dictionary_TP :: Parser SAM_V1_6_Reference_Sequence_Dictionary_Molecule_Topology +parse_SAM_V1_6_Reference_Sequence_Dictionary_TP = do _ <- do sqheadermoleculetopologytagp <- DABL.takeTill (== 58) -- Parse TP tag of the header section. case (sqheadermoleculetopologytagp =~ [re|[T][P]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Molecule_Topology_Incorrect_Format True -> -- TP tag is in the accepted format. - return sqheadermoleculetopologytagp + return () _ <- word8 58 - sqheadermoleculetopologyvalue <- do sqheadermoleculetopologyvaluep <- DABL.takeTill (== 09) + sqheadermoleculetopologyvalue <- do sqheadermoleculetopologyvaluep <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) -- Parse TP value of the header section. case (sqheadermoleculetopologyvaluep =~ [re|[l][i][n][e][a][r]|[c][i][r][c][u][l][a][r]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_Molecule_Topology_Invalid_Value True -> -- TP value is in the accepted format. - return sqheadermoleculetopologyvaluep + return sqheadermoleculetopologyvaluep return SAM_V1_6_Reference_Sequence_Dictionary_Molecule_Topology { sam_v1_6_reference_sequence_dictionary_molecule_topology_value = sqheadermoleculetopologyvalue } diff --git a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/UR.hs b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/UR.hs --- a/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/UR.hs +++ b/src/Data/SAM/Version1_6/Read/Parser/Header/SQ/UR.hs @@ -9,7 +9,6 @@ {-# LANGUAGE PackageImports #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE TypeFamilies #-} {-# LANGUAGE QuasiQuotes #-} @@ -41,27 +40,28 @@ -- This library enables the decoding/encoding of SAM, BAM and CRAM file formats. module Data.SAM.Version1_6.Read.Parser.Header.SQ.UR ( -- * SAM_V1_6 parser - header section (Reference sequence dictionary) - UR tag - parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_UR + parse_SAM_V1_6_Reference_Sequence_Dictionary_UR ) where import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Error -import Data.Attoparsec.ByteString.Lazy as DABL -import Text.Regex.PCRE.Heavy +import Data.Attoparsec.ByteString.Char8 (isEndOfLine) +import Data.Attoparsec.ByteString.Lazy as DABL +import Text.Regex.PCRE.Heavy -- | Defines a parser for the UR tag of the @SQ tag section of the SAM v1.6 file format. -- -- See the [SAM v1.6](http://samtools.github.io/hts-specs/SAMv1.pdf) specification documentation. -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_UR :: Parser SAM_V1_6_Reference_Sequence_Dictionary_URI -parse_SAM_V1_6_SAM_V1_6_Reference_Sequence_Dictionary_UR = do +parse_SAM_V1_6_Reference_Sequence_Dictionary_UR :: Parser SAM_V1_6_Reference_Sequence_Dictionary_URI +parse_SAM_V1_6_Reference_Sequence_Dictionary_UR = do _ <- do sqheaderuritagp <- DABL.takeTill (== 58) -- Parse UR tag of the header section. case (sqheaderuritagp =~ [re|[U][R]|]) of False -> fail $ show SAM_V1_6_Error_Reference_Sequence_Dictionary_URI_Incorrect_Format True -> -- UR tag is in the accepted format. - return sqheaderuritagp + return () _ <- word8 58 - sqheaderurivalue <- DABL.takeTill (== 09) + sqheaderurivalue <- DABL.takeTill (\x -> x == 09 || isEndOfLine x) return SAM_V1_6_Reference_Sequence_Dictionary_URI { sam_v1_6_reference_sequence_dictionary_uri_value = sqheaderurivalue } diff --git a/test/Main.hs b/test/Main.hs --- a/test/Main.hs +++ b/test/Main.hs @@ -1,14 +1,65 @@ module Main (main) where +import Data.SAM.Version1_6.Base +import Data.SAM.Version1_6.Alignment +import Data.SAM.Version1_6.Alignment.BOPT +import Data.SAM.Version1_6.Header import Data.SAM.Version1_6.Read.Base +import Data.Sequence (fromList) +import Data.String (fromString) import Test.Hspec main :: IO () -main = do --hspec $ do - -- describe "Data.SAM.Version1_6.Read.Base" $ do - -- describe "readSAM_V1_6" $ do - -- describe "toy1.sam" $ do - -- it "Ensures that readSAM_V1_6 can read and parse: toy1.sam" $ do - toy1sam <- readSAM_V1_6 "test/examples/toy4.sam" - print toy1sam +main = hspec $ do + describe "Data.SAM.Version1_6.Read.Base" $ do + describe "readSAM_V1_6" $ do + describe "toy5.sam" $ do + it "Ensures that readSAM_V1_6 can read and parse a SAM file with only alignment fields." $ do + readSAM_V1_6 "test/examples/toy5.sam" `shouldReturn` toy5sam + describe "toy4.sam" $ do + it "Ensures that readSAM_V1_6 can read and parse a SAM file with an optional alignment field." $ do + readSAM_V1_6 "test/examples/toy4.sam" `shouldReturn` toy4sam + describe "toy2.sam" $ do + it "Ensures that readSAM_V1_6 can read and parse a SAM file with file-level metadata (@HD) and reference sequence dictionary (@SQ) optional header fields." $ do + readSAM_V1_6 "test/examples/toy2.sam" `shouldReturn` toy2sam + describe "toy1.sam" $ do + it "Ensures that readSAM_V1_6 can read and parse a SAM file with multiple reference sequence dictionary (@SQ) optional header fields." $ do + readSAM_V1_6 "test/examples/toy1.sam" `shouldReturn` toy1sam + where + toy1sam = SAM_V1_6 { sam_v1_6_file_level_metadata = Nothing + , sam_v1_6_reference_sequence_dictionary = Just (fromList [SAM_V1_6_Reference_Sequence_Dictionary { sam_v1_6_reference_sequence_dictionary_reference_sequence_name = SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Name { sam_v1_6_reference_sequence_dictionary_reference_sequence_name_value = fromString "ref" } , sam_v1_6_reference_sequence_dictionary_reference_sequence_length = SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Length { sam_v1_6_reference_sequence_dictionary_reference_sequence_length_value = fromString "45" } , sam_v1_6_reference_sequence_dictionary_reference_alternative_locus = Nothing , sam_v1_6_reference_sequence_dictionary_reference_alternative_reference_sequence_names = Nothing , sam_v1_6_reference_sequence_dictionary_genome_assembly_identifier = Nothing , sam_v1_6_reference_sequence_dictionary_description = Nothing , sam_v1_6_reference_sequence_dictionary_md5_checksum = Nothing , sam_v1_6_reference_sequence_dictionary_species = Nothing , sam_v1_6_reference_sequence_dictionary_molecule_topology = Nothing , sam_v1_6_reference_sequence_dictionary_uri = Nothing },SAM_V1_6_Reference_Sequence_Dictionary { sam_v1_6_reference_sequence_dictionary_reference_sequence_name = SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Name { sam_v1_6_reference_sequence_dictionary_reference_sequence_name_value = fromString "ref2" } , sam_v1_6_reference_sequence_dictionary_reference_sequence_length = SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Length { sam_v1_6_reference_sequence_dictionary_reference_sequence_length_value = fromString "40" } , sam_v1_6_reference_sequence_dictionary_reference_alternative_locus = Nothing , sam_v1_6_reference_sequence_dictionary_reference_alternative_reference_sequence_names = Nothing , sam_v1_6_reference_sequence_dictionary_genome_assembly_identifier = Nothing , sam_v1_6_reference_sequence_dictionary_description = Nothing , sam_v1_6_reference_sequence_dictionary_md5_checksum = Nothing , sam_v1_6_reference_sequence_dictionary_species = Nothing , sam_v1_6_reference_sequence_dictionary_molecule_topology = Nothing , sam_v1_6_reference_sequence_dictionary_uri = Nothing }]) + , sam_v1_6_read_group = Nothing + , sam_v1_6_program = Nothing + , sam_v1_6_one_line_comment = Nothing + , sam_v1_6_alignment = fromList [ SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r001" , sam_v1_6_alignment_flag = 163 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 7 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "8M4I4M1D3M" , sam_v1_6_alignment_rnext = fromString "=" , sam_v1_6_alignment_pnext = 37 , sam_v1_6_alignment_tlen = 39 , sam_v1_6_alignment_seq = fromString "TTAGATAAAGAGGATACTG" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Just SAM_V1_6_Alignment_BOPT { sam_v1_6_alignment_bopt_int8 = Nothing , sam_v1_6_alignment_bopt_word8 = Nothing , sam_v1_6_alignment_bopt_int16 = Nothing , sam_v1_6_alignment_bopt_word16 = Just SAM_V1_6_Alignment_BOPT_Word16 { sam_v1_6_alignment_bopt_word16_tag = fromList [88,88] , sam_v1_6_alignment_bopt_word16_type = 83 , sam_v1_6_alignment_bopt_word16_value = fromList [49,50,53,54,49,44,50,44,50,48,44,49,49,50] } , sam_v1_6_alignment_bopt_int32 = Nothing , sam_v1_6_alignment_bopt_word32 = Nothing , sam_v1_6_alignment_bopt_float = Nothing } },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r002" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 9 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "1S2I6M1P1I1P1I4M2I" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "AAAAGATAAGGGATAAA" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r003" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 9 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "5H6M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "AGCTAA" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r004" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 16 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "6M14N1I5M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "ATAGCTCTCAGC" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r003" , sam_v1_6_alignment_flag = 16 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 29 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "6H5M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "TAGGC" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r001" , sam_v1_6_alignment_flag = 83 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 37 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "9M" , sam_v1_6_alignment_rnext = fromString "=" , sam_v1_6_alignment_pnext = 7 , sam_v1_6_alignment_tlen = -39 , sam_v1_6_alignment_seq = fromString "CAGCGCCAT" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x1" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 1 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "20M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "aggttttataaaacaaataa" , sam_v1_6_alignment_qual = fromString "????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x2" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 2 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "21M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "ggttttataaaacaaataatt" , sam_v1_6_alignment_qual = fromString "?????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x3" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 6 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "9M4I13M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "ttataaaacAAATaattaagtctaca" , sam_v1_6_alignment_qual = fromString "??????????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x4" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 10 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "25M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "CaaaTaattaagtctacagagcaac" , sam_v1_6_alignment_qual = fromString "?????????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x5" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 12 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "24M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "aaTaattaagtctacagagcaact" , sam_v1_6_alignment_qual = fromString "????????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x6" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 14 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "23M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "Taattaagtctacagagcaacta" , sam_v1_6_alignment_qual = fromString "???????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing + } + ] + } + toy2sam = SAM_V1_6 { sam_v1_6_file_level_metadata = Just SAM_V1_6_File_Level_Metadata { sam_v1_6_file_level_metadata_format_version = SAM_V1_6_File_Level_Metadata_Format_Version { sam_v1_6_file_level_metadata_format_version_value = fromString "1.6" } , sam_v1_6_file_level_metadata_sorting_order = Just SAM_V1_6_File_Level_Metadata_Sorting_Order { sam_v1_6_file_level_metadata_sorting_order_value = fromString "coordinate" } , sam_v1_6_file_level_metadata_alignment_grouping = Nothing , sam_v1_6_file_level_metadata_subsorting_order = Nothing } + , sam_v1_6_reference_sequence_dictionary = Just (fromList [SAM_V1_6_Reference_Sequence_Dictionary { sam_v1_6_reference_sequence_dictionary_reference_sequence_name = SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Name { sam_v1_6_reference_sequence_dictionary_reference_sequence_name_value = fromString "ref" } , sam_v1_6_reference_sequence_dictionary_reference_sequence_length = SAM_V1_6_Reference_Sequence_Dictionary_Reference_Sequence_Length { sam_v1_6_reference_sequence_dictionary_reference_sequence_length_value = fromString "45" } , sam_v1_6_reference_sequence_dictionary_reference_alternative_locus = Nothing , sam_v1_6_reference_sequence_dictionary_reference_alternative_reference_sequence_names = Nothing , sam_v1_6_reference_sequence_dictionary_genome_assembly_identifier = Nothing , sam_v1_6_reference_sequence_dictionary_description = Nothing , sam_v1_6_reference_sequence_dictionary_md5_checksum = Nothing , sam_v1_6_reference_sequence_dictionary_species = Nothing , sam_v1_6_reference_sequence_dictionary_molecule_topology = Nothing , sam_v1_6_reference_sequence_dictionary_uri = Nothing }]) + , sam_v1_6_read_group = Nothing + , sam_v1_6_program = Nothing + , sam_v1_6_one_line_comment = Nothing + , sam_v1_6_alignment = fromList [ SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r001" , sam_v1_6_alignment_flag = 99 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 7 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "8M2I4M1D3M" , sam_v1_6_alignment_rnext = fromString "=" , sam_v1_6_alignment_pnext = 37 , sam_v1_6_alignment_tlen = 39 , sam_v1_6_alignment_seq = fromString "TTAGATAAAGGATACTG" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r002" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 9 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "3S6M1P1I4M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "AAAAGATAAGGATA" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r003" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 9 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "5S6M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "GCCTAAGCTAA" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Just (fromString "ref,29,-,6H5M,17,0;") , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r004" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 16 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "6M14N5M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "ATAGCTTCAGC" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r003" , sam_v1_6_alignment_flag = 2064 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 29 , sam_v1_6_alignment_mapq = 17 , sam_v1_6_alignment_cigar = fromString "6H5M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "TAGGC" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Just (fromString "ref,9,+,5S6M,30,1;") , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r001" , sam_v1_6_alignment_flag = 147 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 37 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "9M" , sam_v1_6_alignment_rnext = fromString "=" , sam_v1_6_alignment_pnext = 7 , sam_v1_6_alignment_tlen = -39 , sam_v1_6_alignment_seq = fromString "CAGCGGCAT" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Just 1 , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing + } + ] + } + toy4sam = SAM_V1_6 { sam_v1_6_file_level_metadata = Nothing + , sam_v1_6_reference_sequence_dictionary = Nothing + , sam_v1_6_read_group = Nothing + , sam_v1_6_program = Nothing + , sam_v1_6_one_line_comment = Nothing + , sam_v1_6_alignment = fromList [ SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r001" , sam_v1_6_alignment_flag = 163 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 7 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "8M4I4M1D3M" , sam_v1_6_alignment_rnext = fromString "=" , sam_v1_6_alignment_pnext = 37 , sam_v1_6_alignment_tlen = 39 , sam_v1_6_alignment_seq = fromString "TTAGATAAAGAGGATACTG" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Just SAM_V1_6_Alignment_BOPT { sam_v1_6_alignment_bopt_int8 = Nothing , sam_v1_6_alignment_bopt_word8 = Nothing , sam_v1_6_alignment_bopt_int16 = Nothing , sam_v1_6_alignment_bopt_word16 = Just SAM_V1_6_Alignment_BOPT_Word16 { sam_v1_6_alignment_bopt_word16_tag = fromList [88,88] , sam_v1_6_alignment_bopt_word16_type = 83 , sam_v1_6_alignment_bopt_word16_value = fromList [49,50,53,54,49,44,50,44,50,48,44,49,49,50] } , sam_v1_6_alignment_bopt_int32 = Nothing , sam_v1_6_alignment_bopt_word32 = Nothing , sam_v1_6_alignment_bopt_float = Nothing } },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r002" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 9 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "1S2I6M1P1I1P1I4M2I" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "AAAAGATAAGGGATAAA" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r003" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 9 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "5H6M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "AGCTAA" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r004" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 16 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "6M14N1I5M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "ATAGCTCTCAGC" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r003" , sam_v1_6_alignment_flag = 16 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 29 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "6H5M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "TAGGC" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r001" , sam_v1_6_alignment_flag = 83 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 37 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "9M" , sam_v1_6_alignment_rnext = fromString "=" , sam_v1_6_alignment_pnext = 7 , sam_v1_6_alignment_tlen = -39 , sam_v1_6_alignment_seq = fromString "CAGCGCCAT" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x1" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 1 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "20M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "aggttttataaaacaaataa" , sam_v1_6_alignment_qual = fromString "????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x2" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 2 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "21M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "ggttttataaaacaaataatt" , sam_v1_6_alignment_qual = fromString "?????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x3" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 6 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "9M4I13M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "ttataaaacAAATaattaagtctaca" , sam_v1_6_alignment_qual = fromString "??????????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x4" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 10 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "25M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "CaaaTaattaagtctacagagcaac" , sam_v1_6_alignment_qual = fromString "?????????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x5" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 12 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "24M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "aaTaattaagtctacagagcaact" , sam_v1_6_alignment_qual = fromString "????????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x6" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 14 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "23M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "Taattaagtctacagagcaacta" , sam_v1_6_alignment_qual = fromString "???????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing + } + ] + } + toy5sam = SAM_V1_6 { sam_v1_6_file_level_metadata = Nothing + , sam_v1_6_reference_sequence_dictionary = Nothing + , sam_v1_6_read_group = Nothing + , sam_v1_6_program = Nothing + , sam_v1_6_one_line_comment = Nothing + , sam_v1_6_alignment = fromList [ SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r001" , sam_v1_6_alignment_flag = 163 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 7 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "8M4I4M1D3M" , sam_v1_6_alignment_rnext = fromString "=" , sam_v1_6_alignment_pnext = 37 , sam_v1_6_alignment_tlen = 39 , sam_v1_6_alignment_seq = fromString "TTAGATAAAGAGGATACTG" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r002" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 9 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "1S2I6M1P1I1P1I4M2I" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "AAAAGATAAGGGATAAA" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r003" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 9 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "5H6M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "AGCTAA" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r004" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 16 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "6M14N1I5M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "ATAGCTCTCAGC" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r003" , sam_v1_6_alignment_flag = 16 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 29 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "6H5M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "TAGGC" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "r001" , sam_v1_6_alignment_flag = 83 , sam_v1_6_alignment_rname = fromString "ref" , sam_v1_6_alignment_pos = 37 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "9M" , sam_v1_6_alignment_rnext = fromString "=" , sam_v1_6_alignment_pnext = 7 , sam_v1_6_alignment_tlen = -39 , sam_v1_6_alignment_seq = fromString "CAGCGCCAT" , sam_v1_6_alignment_qual = fromString "*" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x1" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 1 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "20M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "aggttttataaaacaaataa" , sam_v1_6_alignment_qual = fromString "????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x2" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 2 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "21M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "ggttttataaaacaaataatt" , sam_v1_6_alignment_qual = fromString "?????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x3" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 6 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "9M4I13M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "ttataaaacAAATaattaagtctaca" , sam_v1_6_alignment_qual = fromString "??????????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x4" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 10 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "25M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "CaaaTaattaagtctacagagcaac" , sam_v1_6_alignment_qual = fromString "?????????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x5" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 12 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "24M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "aaTaattaagtctacagagcaact" , sam_v1_6_alignment_qual = fromString "????????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing },SAM_V1_6_Alignment { sam_v1_6_alignment_qname = fromString "x6" , sam_v1_6_alignment_flag = 0 , sam_v1_6_alignment_rname = fromString "ref2" , sam_v1_6_alignment_pos = 14 , sam_v1_6_alignment_mapq = 30 , sam_v1_6_alignment_cigar = fromString "23M" , sam_v1_6_alignment_rnext = fromString "*" , sam_v1_6_alignment_pnext = 0 , sam_v1_6_alignment_tlen = 0 , sam_v1_6_alignment_seq = fromString "Taattaagtctacagagcaacta" , sam_v1_6_alignment_qual = fromString "???????????????????????" , sam_v1_6_alignment_aopt = Nothing , sam_v1_6_alignment_iopt = Nothing , sam_v1_6_alignment_fopt = Nothing , sam_v1_6_alignment_zopt = Nothing , sam_v1_6_alignment_hopt = Nothing , sam_v1_6_alignment_bopt = Nothing + } + ] + }