U Ae<@@sddlZddlZddlZddlZddlmZmZmZm Z m Z m Z ddl m Z ddZdddZdd Zd d Zdd d ZdddZddZddZGdddeZedkredS)N)Fasta wrap_sequence FetchError ucsc_split bed_splitget_valid_filename) defaultdictc stjj\}}|r"|dd}tjj}jrBfdd}t jj t j j j|jj d}t\}}|s|}d}|D]^}||\} } } | dkrqjr| dk r| dk r| | } n t|| } jd| ksjd| krqjr0ddd | | | |fD} t| } t| d }njr@j}ntj}zfjr|spjd krp|d d }|t|| | | n"t|| | | D]}||qWn4t k r}zt t!|dW5d}~XYnXjr|"q|#dS)Ncstj| SN)recompileregexsearch)xargs*lib/python3.8/site-packages/pyfaidx/cli.pyz write_sequence..) default_seqZ key_functionZ strict_bounds split_char filt_functionZread_long_namesZrebuildFr.css|]}|rt|VqdSr )str).0errr 'sz!write_sequence..w nucleotidez name start end A T C G N others Tz Try setting --lazy. )$ospathsplitextfastar r r rZ invert_matchrrevalZheader_functionZlazy delimiterZ long_namesZ no_rebuild split_regionskeysZ size_rangelenZ split_filesjoinropenoutsysstdout transformwritetransform_sequencefetch_sequencerrclose__exit__)r_extrr#regions_to_fetchsplit_functionheaderregionnamestartendZ sequence_lenfilenameZoutfilelinerrrrwrite_sequence sR  .      " r?ccszb|jj|j}|jrP||krP|dk rP|dk rP|||d|d}|jj}n||||}Wn,tk rtj dj ft YdSX|jr|j}|jr|j}|j rdS|j rn8|s|r|jsdd|jdgVndd|jdgVt||jD] }|VqdS)Nr z"warning: {name} not found in file > )faidxindexlenc auto_strandreverse complementKeyErrorr,stderrr/formatlocals no_outputZno_namesZ no_coordsr)Z fancy_namer:rseq)rr#r:r;r<line_lenZsequencer>rrrr1>s, r1c Cst|jd|jd}t|\}}|D]}||\}}}|jr|rL|rL||}n*|sb|sbt||}nt||||}||j||||<q"|jr"||||||||<q"dS)NT)Zmutabler) rr#r%r&mask_with_default_seqr(r mask_by_caseZ lowercase) rr#r6r7r9Zrnamer;r<spanrrr mask_sequence[s  rScCs$|jr|j}t}n |j}t}||fSr )bedrregionsr)rr6r7rrrr&ns r&cs^|jj|j}||||}|jr*|j}|jr6|j}|jr@dS|jdkrddj|j|j d|j dS|jdkrdj|jt |dS|jdkr2t | tt}|fd d tD|d d }|d d } |dd } |dd } |dd } ddd |D} djf|j|j |j dtS|jdkrZdj|j|j |j t |dSdS)NrTz{name} {start} {end} r )r:r;r< chromsizesz{name} {length} )r:lengthrcsg|]}||fqSr)count)rcssrr sz&transform_sequence..ArTCGN|cSs"g|]\}}d|t|fqS):)r)r)rkvrrrr\sz5{sname} {sstart} {send} {A} {T} {C} {G} {N} {others} )ZsnameZsstartsend transposedz{name} {start} {end} {seq} )r:r;r<rN)rCrDrErHrGrMr.rKr:r;r<r(rupperrintupdatesetpopr)itemsrL)rr#r:r;r<rOsZnucsr]r^r_r`raZothersrrZrr0xs2           r0c Csddlm}tjddd}|jdtdd|jd td d d |d }|d}|d}|jddtddd|jddtddd|jddtddd|jdddd d!d"|jd#d$dd d%d"|jd&d'dd d(d"|jd)d*tdd+d,| }|jd-d.dd d/d"|jd0d1dd d2d"|jd3d4dd d5d"|jd6d7dd d8d"|jd9d:dd d;d"|jdd,|jd?d@tddAd,|jdBdCtdDdEd,|jdFdGtdHdIdJdK|dL}|jdMdNtdOdPd,|jdQdRdd dSd"| }|jdTdUdd dVd"|jdWdXdd dYd"|jdZdd d[d"|jd\dd d]d"|jd^d_|d`dat t j dbkrn|sn|t dbn|r||} n|} | jr| jrt jdc| jrt jdd| js| jrt| nt| dS)eNr) __version__zFetch sequences from FASTA. If no regions are specified, all entries in the input file are returned. Input FASTA file must be consistently line-wrapped, and line wrapping of output is based on input line lengths.zPlease cite: Shirley MD, Ma Z, Pedersen BS, Wheelan SJ. (2015) Efficient "pythonic" access to FASTA files using pyfaidx. PeerJ PrePrints 3:e1196 https://dx.doi.org/10.7287/peerj.preprints.970v1) descriptionepilogr#z FASTA file)typehelprU*z=space separated regions of sequence to fetch e.g. chr1:1-1000)rrnargsrsz input optionszoutput optionszheader optionsz-bz--bedrz1bed file of regions (zero-based start coordinate)z-oz--outrz"output file name (default: stdout)z-iz --transform)rTrVrrgzItransform the requested regions into another format. default: %(default)s)rrchoicesrsz-cz --complement store_trueFz-complement the sequence. default: %(default)s)actiondefaultrsz-rz --reversez*reverse the sequence. default: %(default)sz-yz --auto-strandzQreverse complement the sequence when start > end coordinate. default: %(default)sz-az --size-rangezZselected sequences are in the size range [low, high]. example: 1,1000 default: %(default)s)rrrzrsz-nz --no-namesz5omit sequence names from output. default: %(default)sz-fz --long-nameszpoutput full (long) names from the input fasta headers. default: headers are truncated after the first whitespacez-tz --no-coordszOomit coordinates (e.g. chr:start-end) from output headers. default: %(default)sz-xz --split-fileszEwrite each region to a separate file (names are derived from regions)z-lz--lazyz>fill in --default-seq for missing ranges. default: %(default)sz-sz --default-seqzDdefault base for missing positions and masking. default: %(default)sz-dz --delimiterzjdelimiter for splitting names to multiple values (duplicate names will be discarded). default: %(default)sz-ez--header-functionzlambda x: x.split()[0]z]python function to modify header lines e.g: "lambda x: x.split("|")[0]". default: %(default)sz-uz--duplicates-actionstop)r{firstZlastZlongestZshortestzQentry to take when duplicate sequence names are encountered. default: %(default)s)rrrzrwrszmatching argumentsz-gz--regexz.*zNselected sequences are those matching regular expression. default: %(default)sz-vz--invert-matchzRselected sequences are those not matching 'regions' argument. default: %(default)sz-mz--mask-with-default-seqz|||<q>|S)z? Intersection is the minimum of corresponding counts. r)rrrminr(filter __contains__)rrZ_minrrrrrr__and__`s   zCounter.__and__)N)N)N)N)r __module__ __qualname____doc__rrrr classmethodrrjrrrrrrrrrrrrs       r__main__)NN)NN)N)rr,Zos.pathr r r~rrrrrr collectionsrr?r1rSr&r0rrrrrrrrrrs"  5   9