o Rŀg8@sdZddlmZddlmZddlmZddlmZddlmZddlm Z dd lm Z d d Z d d Z Gddde Z Gddde ZGddde ZGdddeZddZddZedkrmddlmZedddSdS)zBio.SeqIO support for the "fasta" (aka FastA or Pearson) file format. You are expected to use this module via the Bio.SeqIO functions. )Seq) SeqRecord)_clean)_get_seq_string) _TextIOSource)SequenceIterator)SequenceWriterccs|D]}|ddkr|dd}nqdSg}|D]*}|ddkr?|d|ddddfVg}|dd}q||q|d|ddddfVdS)aIterate over Fasta records as string tuples. Arguments: - handle - input stream opened in text mode For each record a tuple of two strings is returned, the FASTA title line (without the leading '>' character), and the sequence (with any whitespace removed). The title line is not divided up into an identifier (the first word) and comment or description. >>> with open("Fasta/dups.fasta") as handle: ... for values in SimpleFastaParser(handle): ... print(values) ... ('alpha', 'ACGTA') ('beta', 'CGTC') ('gamma', 'CCGCC') ('alpha (again - this is a duplicate entry to test the indexing code)', 'ACGTA') ('delta', 'CGCGC') r>rN  )rstripjoinreplaceappend)handlelinetitlelinesrE/var/www/html/myenv/lib/python3.10/site-packages/Bio/SeqIO/FastaIO.pySimpleFastaParsers    $rccsd}t|D]9\}}|ddkr(|ddkrtd|d|dd}q|ddkr9td |d |d||fVq|dkrGdS|ddkrUtd |d|ddks_Jd dS) aIterate over no-wrapping Fasta records as string tuples. Arguments: - handle - input stream opened in text mode Functionally the same as SimpleFastaParser but with a strict interpretation of the FASTA format as exactly two lines per record, the greater-than-sign identifier with description, and the sequence with no line wrapping. Any line wrapping will raise an exception, as will excess blank lines (other than the special case of a zero-length sequence as the second line of a record). Examples -------- This file uses two lines per FASTA record: >>> with open("Fasta/aster_no_wrap.pro") as handle: ... for title, seq in FastaTwoLineParser(handle): ... print("%s = %s..." % (title, seq[:3])) ... gi|3298468|dbj|BAA31520.1| SAMIPF = GGH... This equivalent file uses line wrapping: >>> with open("Fasta/aster.pro") as handle: ... for title, seq in FastaTwoLineParser(handle): ... print("%s = %s..." % (title, seq[:3])) ... Traceback (most recent call last): ... ValueError: Expected FASTA record starting with '>' character. Perhaps this file is using FASTA line wrapping? Got: 'MTFGLVYTVYATAIDPKKGSLGTIAPIAIGFIVGANI' rr ziExpected FASTA record starting with '>' character. Perhaps this file is using FASTA line wrapping? Got: ''rNzoTwo '>' FASTA lines in a row. Missing sequence line if this is strict two-line-per-record FASTA format. Have '>z' and 'zjMissing sequence line at end of file if this is strict two-line-per-record FASTA format. Have title line 'z+line[0] == '>' ; this should be impossible!) enumerate ValueErrorrstrip)ridxrrrrrFastaTwoLineParserIs:$    r csBeZdZdZ d deddddffdd Zdd Zd d ZZS) FastaIteratorzParser for Fasta files.Nsourcealphabetreturncs&|durtdtj|ddddS)a|Iterate over Fasta records as SeqRecord objects. Arguments: - source - input stream opened in text mode, or a path to a file - alphabet - optional alphabet, not used. Leave as None. By default this will act like calling Bio.SeqIO.parse(handle, "fasta") with no custom handling of the title lines: >>> with open("Fasta/dups.fasta") as handle: ... for record in FastaIterator(handle): ... print(record.id) ... alpha beta gamma alpha delta If you want to modify the records before writing, for example to change the ID of each record, you can use a generator function as follows: >>> def modify_records(records): ... for record in records: ... record.id = record.id.upper() ... yield record ... >>> with open('Fasta/dups.fasta') as handle: ... for record in modify_records(FastaIterator(handle)): ... print(record.id) ... ALPHA BETA GAMMA ALPHA DELTA Nz,The alphabet argument is no longer supportedtFastamodefmt)rsuper__init__)selfr"r# __class__rrr+s+zFastaIterator.__init__cC||}|Sz9Start parsing the file, and return a SeqRecord generator.iterater,rrecordsrrrparse zFastaIterator.parsec cjt|D]-\}}z |ddd}Wnty&|r"Jt|d}Ynwtt||||dVqdSz.Parse the file and generate SeqRecord objects.Nrrr )idname description)rsplit IndexErrorreprrrr,rrsequence first_wordrrrr2   zFastaIterator.iterateN) __name__ __module__ __qualname____doc__rr+r5r2 __classcell__rrr-rr!s/r!cs0eZdZdZfddZddZddZZS)FastaTwoLineIteratorz9Parser for Fasta files with exactly two lines per record.cstj|ddddS)aIterate over two-line Fasta records (as SeqRecord objects). Arguments: - source - input stream opened in text mode, or a path to a file This uses a strict interpretation of the FASTA as requiring exactly two lines per record (no line wrapping). Only the default title to ID/name/description parsing offered by the relaxed FASTA parser is offered. r%FASTAr'Nr*r+)r,r"r-rrr+s zFastaTwoLineIterator.__init__cCr/r0r1r3rrrr5r6zFastaTwoLineIterator.parsec cr7r8)r r<r=r>rrr?rrrr2rBzFastaTwoLineIterator.iterate)rDrErFrGr+r5r2rHrrr-rrIs  rIcs*eZdZdZdfdd ZddZZS) FastaWriterzClass to write Fasta format files (OBSOLETE). Please use the ``as_fasta`` function instead, or the top level ``Bio.SeqIO.write()`` function instead using ``format="fasta"``. <Ncs,t||r|dkrt||_||_dS)aCreate a Fasta writer (OBSOLETE). Arguments: - target - Output stream opened in text mode, or a path to a file. - wrap - Optional line length used to wrap sequence lines. Defaults to wrapping the sequence at 60 characters Use zero (or None) for no wrapping, giving a single long line for the sequence. - record2title - Optional function to return the text to be used for the title line of each record. By default a combination of the record.id and record.description is used. If the record.description starts with the record.id, then just the record.description is used. You can either use:: handle = open(filename, "w") writer = FastaWriter(handle) writer.write_file(myRecords) handle.close() Or, follow the sequential file writer system, for example:: handle = open(filename, "w") writer = FastaWriter(handle) writer.write_header() # does nothing for Fasta files ... Multiple writer.write_record() and/or writer.write_records() calls ... writer.write_footer() # does nothing for Fasta files handle.close() rN)r*r+rwrap record2title)r,targetrNrOr-rrr+s " zFastaWriter.__init__cCs|jr |||}n'||j}||j}|r'|ddd|kr'|}n |r1|d|}n|}d|vs9Jd|vs?J|jd|dt|}d|vsSJd|vsYJ|jryt dt ||jD]}|j||||jdqedS|j|ddS)z(Write a single Fasta record to the file.Nrrr  r r ) rOcleanr9r;r<rwriterrNrangelen)r,recordrr9r;datairrr write_record$s(       zFastaWriter.write_record)rMN)rDrErFrGr+rYrHrrr-rrLs)rLcs"eZdZdZdfdd ZZS)FastaTwoLineWritera_Class to write 2-line per record Fasta format files (OBSOLETE). This means we write the sequence information without line wrapping, and will always write a blank line for an empty sequence. Please use the ``as_fasta_2line`` function instead, or the top level ``Bio.SeqIO.write()`` function instead using ``format="fasta"``. Ncstj|d|ddS)aOCreate a 2-line per record Fasta writer (OBSOLETE). Arguments: - handle - Handle to an output file, e.g. as returned by open(filename, "w") - record2title - Optional function to return the text to be used for the title line of each record. By default a combination of the record.id and record.description is used. If the record.description starts with the record.id, then just the record.description is used. You can either use:: handle = open(filename, "w") writer = FastaWriter(handle) writer.write_file(myRecords) handle.close() Or, follow the sequential file writer system, for example:: handle = open(filename, "w") writer = FastaWriter(handle) writer.write_header() # does nothing for Fasta files ... Multiple writer.write_record() and/or writer.write_records() calls ... writer.write_footer() # does nothing for Fasta files handle.close() N)rNrOrK)r,rrOr-rrr+NszFastaTwoLineWriter.__init__rC)rDrErFrGr+rHrrr-rrZCs rZcCst|j}t|j}|r|ddd|kr|}n |r#|d|}n|}d|vs+Jd|vs1Jd|dg}t|}d|vsBJd|vsHJtdt|dD]}||||ddqPd |S) zTurn a SeqRecord into a FASTA formatted string. This is used internally by the SeqRecord's .format("fasta") method and by the SeqIO.write(..., ..., "fasta") function. Nrrr rQr r rMr ) rr9r;r<rrTrUrr)rVr9r;rrrWrXrrras_fastaps       r[cCst|j}t|j}|r|ddd|kr|}n |r#|d|}n|}d|vs+Jd|vs1Jt|}d|vs;Jd|vsAJd|d|dS)zTurn a SeqRecord into a two-line FASTA formatted string. This is used internally by the SeqRecord's .format("fasta-2line") method and by the SeqIO.write(..., ..., "fasta-2line") function. Nrrr rQr r )rr9r;r<r)rVr9r;rrWrrras_fasta_2lines      r\__main__) run_doctest)verboseN)rGBio.Seqr Bio.SeqRecordr Interfacesrrrrr rr r!rIrLrZr[r\rD Bio._utilsr^rrrrs(       /BE$O-