o Rŀg@s|dZddlmZddlZddlmZddlmZddlm Z ddl m Z ddl m Z Gd d d ejZGd d d ejZdS) aBio.Align support for the "nexus" file format. You are expected to use this module via the Bio.Align functions. See also the Bio.Nexus module (which this code calls internally), as this offers more than just accessing the alignment or its sequences as SeqRecord objects. )StringION) Alignment) interfaces)Nexus)Seq) SeqRecordcsVeZdZdZdZdfdd ZfddZddd Zdd d Zd d Z ddZ Z S)AlignmentWriterzNexus alignment writer. Note that Nexus files are only expected to hold ONE alignment matrix. You are expected to call this class via Bio.Align.write(). rNcst|||_dS)a2Create an AlignmentWriter object. Arguments: - target - output stream or file name - interleave - if None (default): interleave if columns > 1000 if True: use interleaved format if False: do not use interleaved format N)super__init__ interleave)selftargetr  __class__C/var/www/html/myenv/lib/python3.10/site-packages/Bio/Align/nexus.pyr 's zAlignmentWriter.__init__cs&t||}|dkrtd||S)zWrite a file with the alignments, and return the number of alignments. alignments - A list or iterator returning Alignment objects z'Expected to write 1 alignment; wrote %d)r write_file ValueError)r stream alignmentscountrrrr4s zAlignmentWriter.write_filecCs&t}|||||d|S)aReturn a string with a single alignment in the Nexus format. Creates an empty Nexus object, adds the sequences and then gets Nexus to prepare the output. - alignment - An Alignment object - interleave - if None (default): interleave if columns > 1000 if True: use interleaved format if False: do not use interleaved format r)rwrite_alignmentseekread)r alignmentr rrrrformat_alignment>s  z AlignmentWriter.format_alignmentc Cs|j\}}|dkr td|dkrtd|j\}}|dkr"td|dkr*td||}d|} t| } t|j|D]-\} } |dkrSd| jvrSt| jd|dkrdd | jvrdt| jd | | j| q>|d urt|d k}| j ||d d S)aCWrite a single alignment to the output file. - alignment - An Alignment object - stream - output stream - interleave - if None (default): interleave if columns > 1000 if True: use interleaved format if False: do not use interleaved format rzMust have at least one sequencez Non-empty sequences are requiredz?begin data; dimensions ntax=0 nchar=0; format datatype=%s; end;dnaUz contains U, but DNA alignmentrnaTz contains T, but RNA alignmentNir ) shaper_classify_mol_type_for_nexusrzip sequencesseqid add_sequencewrite_nexus_data) r rrr nseqslengthrowscolumnsdatatypeminimal_recordnrecordaligned_sequencerrrrNs.    zAlignmentWriter.write_alignmentcCs0d}|j}|D]}|j|||d|d7}q|S)zWrite alignments to the output file, and return the number of alignments. alignments - A list or iterator returning Alignment objects rr!r)r r)r rrrr rrrrwrite_alignmentsts  z AlignmentWriter.write_alignmentscCsZdd|jD}tdd|DrdStdd|DrdStdd|Dr)d Std ) zReturn 'protein', 'dna', or 'rna' based on records' molecule type (PRIVATE). All the records must have a molecule_type annotation, and they must agree. Raises an exception if this is not possible. cSsh|] }|jddqS) molecule_typeN) annotationsget).0sequencerrr s z?AlignmentWriter._classify_mol_type_for_nexus..cs|] }|o d|vVqdS)DNANrr7_rrr z?AlignmentWriter._classify_mol_type_for_nexus..rcsr:)RNANrr<rrrr>r?rcsr:)proteinNrr<rrrr>r?rAz$Need the molecule type to be defined)r%allr)r rvaluesrrrr#sz,AlignmentWriter._classify_mol_type_for_nexus)N) __name__ __module__ __qualname____doc__fmtr rrrr3r# __classcell__rrrrrs & rc@s$eZdZdZdZddZddZdS)AlignmentIteratorzNexus alignment iterator.rcCs>zt|}Wn tytddw|dkrtddS)Nz Empty file.z#NEXUSz&File does not start with NEXUS header.)next StopIterationrstrip)r rlinerrr _read_headers    zAlignmentIterator._read_headerc st|js dStjtjksJjdvr ddinjdkr*ddin jdkr4ddindfddjD}t|\}}fd dt|jD}t |d  d }t |d kd d }t ||d }t||}|S) N)r nucleotider4r;rr@rAcsg|] }tj|qSr)bytesmatrix)r7name)r0rr sz:AlignmentIterator._read_next_alignment..cs"g|] \}}tt||dqS))r'r5)rr)r7r&rS)r5rrrTsrr)rrRlenunaltered_taxlabels taxlabelsr.rparse_printed_alignmentr$npdiffmaxnonzerodelete) r r aligned_seqsseqs coordinatesrecordsstepsindicesrr)r5r0r_read_next_alignments*          z&AlignmentIterator._read_next_alignmentN)rDrErFrGrHrOrdrrrrrJs  rJ)rGiornumpyrY Bio.Alignrr Bio.NexusrBio.Seqr Bio.SeqRecordrrrJrrrrs      z