o Rŀg4@shdZddlmZgdZGdddZddZdd Zd d Zd d Ze dkr2ddl m Z e dSdS)aIParser for PHD files output by PHRED and used by PHRAP and CONSED. This module can be used directly, which will return Record objects containing all the original data in the file. Alternatively, using Bio.SeqIO with the "phd" format will call this module internally. This will give SeqRecord objects for each contig sequence. )Seq) CHROMAT_FILEABI_THUMBPRINT PHRED_VERSION CALL_METHODQUALITY_LEVELSTIMETRACE_ARRAY_MIN_INDEXTRACE_ARRAY_MAX_INDEXTRIMTRACE_PEAK_AREA_RATIOCHEMDYEc@seZdZdZddZdS)Recordz!Hold information from a PHD file.cCs:d|_i|_tD] }d|j|<qg|_d|_d|_dS)zInitialize the class.N) file_namecomments CKEYWORDSlowersitesseq seq_trimmed)selfkwrF/var/www/html/myenv/lib/python3.10/site-packages/Bio/Sequencing/Phd.py__init__(s zRecord.__init__N)__name__ __module__ __qualname____doc__rrrrrr%s rcCsdt|}z#t|}z t|Wtdty'|YW||ur&|SSw||ur1|ww)aWRead one PHD record from the file and return it as a Record object. Argument source is a file-like object opened in text mode, or a path to a file. This function reads PHD file data line by line from the source, and returns a single Record object. A ValueError is raised if more than one record is found in the file. zMore than one PHD record found)_open_readnext StopIterationclose ValueErrorsourcehandlerecordrrrread3s     r+ccsPt|}z t|}|sW||ur|dSdS|Vq||ur'|ww)aLIterate over a file yielding multiple PHD records. Argument source is a file-like object opened in text mode, or a path to a file. The data is read line by line from the source. Typical usage:: records = parse(handle) for record in records: # do something with the record object TN)r!r"r%r'rrrparseKs  r,cCs@zt|}W|Sty|}|ddkrtddY|Sw)Nrrz&PHD files must be opened in text mode.)open TypeErrorr+r&)r(r)rrrr!is   r!c Cs|D]}|drt}|dd|_nqdS|D] }|dr%nqtd|D]Z}|}|s5q,|dkr;nP|dd\}}|}|}|dvrU||j|<q,|d vrat ||j|<q,|d krmt ||j|<q,|d kr|\}}}t |t |t |f|j|<q,td |D] }|d rnqtd|D]}|drn|}t |dvr|j t|qtd|D] }|drnqtdtddd|j D|_|jd dur|jd dd\}}|j|||_|S)NBEGIN_SEQUENCE BEGIN_COMMENTz!Failed to find BEGIN_COMMENT line END_COMMENT:) chromat_file phred_version call_methodchemdyetimebasecaller_versiontrace_processor_version)abi_thumbprintquality_levelstrace_array_min_indextrace_array_max_indextrace_peak_area_ratiotrimzFailed to find END_COMMENT line BEGIN_DNAzFailed to find BEGIN_DNA lineEND_DNA)zODNA line must contain a base and quality score, and optionally a peak location. END_SEQUENCEz Failed to find END_SEQUENCE linercss|]}|dVqdS)rNr).0nrrr sz_read..rE) startswithrrstriprr&stripsplitrrintfloatlenrappendtuplerjoinrr) r)liner*keywordvaluefirstlastprobpartsrrrr"ssp       r"__main__) run_doctestN) r Biorrrr+r,r!r"r Bio._utilsr]rrrrs  V