DUf0ddlZddlmZddlZddlZddlZddlZddlm Z ddl m Z m Z  ddlm Z n#e$reejdZ YnwxYwe eZdZd Zd Zd Zd Zd ZdZdZdZdZdZe jejdej dddejdej ddej!dddde"eej!dd dd!e"eej!d"d#dd$e"eej!d%d&dd'e"eej!d(d)d*ej#d+d,gd,d-ej!d.d/dd0d1ej!d2d3d4e"d5d-ej!d6d7d8dd0d1ej!d9d:e$d;d-ej!dd-ej!d?d@e$Aej!dBdCdDEej!dFdGdHe"Aej!dIdJdKe"AdLZ%dS)MN) cmd_exists)cli get_logger)DEVNULLwbz6sort -k{C1},{C1} -k{P1},{P1}n -k{C2},{C2} -k{P2},{P2}nz6sort -k{C1},{C1} -k{C2},{C2} -k{P1},{P1}n -k{P2},{P2}nztabix -f -s{C1} -b{P1} -e{P1}z3pairix -f -s{C1} -d{C2} -b{P1} -e{P1} -u{P2} -v{P2}aimport sys from signal import signal, SIGPIPE, SIG_DFL signal(SIGPIPE, SIG_DFL) instream = getattr(sys.stdin, "buffer", sys.stdin) outstream = getattr(sys.stdout, "buffer", sys.stdout) with open("{chromosomes_path}", "rb") as f: chrIDs = {{}} for i, line in enumerate(f, 1): chrom = line.split(b"\t")[0].strip() if chrom: chrIDs[chrom] = i for line in instream: if line.startswith(b"{comment_char}"): continue parts = line.strip().split(b"{sep}") chrom1, chrom2 = parts[{c1}], parts[{c2}] if chrom1 in chrIDs and chrom2 in chrIDs: cid1, cid2 = chrIDs[chrom1], chrIDs[chrom2] pos1, pos2 = int(parts[{p1}]), int(parts[{p2}]) if (cid1 > cid2) or ((cid1 == cid2) and (pos1 > pos2)): parts[{c1}], parts[{c2}] = parts[{c2}], parts[{c1}] parts[{p1}], parts[{p2}] = parts[{p2}], parts[{p1}] outstream.write(b"\t".join(parts) + b"\n") c\tjddgtttdkS)Nsortz --parallel=1)stdinstdoutstderrr) subprocesscallrM/var/www/html/software/conda/lib/python3.11/site-packages/cooler/cli/csort.py_has_parallel_sortr;s3 ^ $GGG     rc:|dkrtjd|S)NrzField numbers are one-based)click BadParameter)ctxparamvalues r_validate_fieldnumrDs" zz !>??? Lrc|d}|rZtdrdd|g}nItdrdd|g}n4tdtjtjdnd|g}|S) aX If input file appears gzipped based its extension, read using one of pigz or gzip for decompression. Otherwise assume uncompressed and use cat. Note ---- Gzip decompression can't actually be parallelized, but pigz will create three extra threads that may help. See . .gzpigzz-dcgzipzNo gzip decompressor found.filercat)endswithrprintsysrexit)infileingzipread_cmds rmake_read_commandr*Js__U # #F # f   v.HH    v.HH /cj A A A A HQKKKK6? Orc "t|5}tdt|dD]a\}}|dd}|r-t|dzt |zb dddn #1swxYwY|ddz }|ddz } |ddz } |ddz } t||||| | | } tj d | gS) Nz$Enumerating requested chromosomes...r rC1C2P1P2)chromosomes_pathsep comment_charc1c2p1p2-c) openloggerinfo enumeratesplitstripstr FLIP_TEMPLATEformatr% executable) r1r2r3fieldsfilinechromr4r5r6r7 flip_codes rmake_flip_commandrIes\   31 :;;; A 3 3GAtJJt$$Q'--//E 3 EDL3q661222 3333333333333333  B  B  B  B$$) ! %I ND) ,,sB B**B.1B.cdtjd<|dkr$tjt jdi|}n)|dkr#tjt jdi|}||z }|S)NCLC_ALLtabixpairixr)osenvironshlexr=SORT_POSrASORT_BLK)indexrC sort_optionssort_cmds rmake_sort_commandrWssBJx ;x888899 (  ;x888899 H Orc|dkr$tjtjdi|}n)|dkr#tjt jdi|}|r|dgz }g||S)NrMrN-0r)rQr= INDEX_TBXrA INDEX_PX2)rTrC zero_basedoutfile index_cmds rmake_index_commandr_s~ K 0 : :6 : :;; (  K 0 : :6 : :;; dV Y   r pairs_pathT)exists allow_dash PAIRS_PATH)typemetavarr1)raCHROMOSOMES_PATHz--chrom1z-c1z7chrom1 field number in the input file (starting from 1))requiredhelprdcallbackz--chrom2z-c2zchrom2 field numberz--pos1z-p1zpos1 field numberz--pos2z-p2zpos2 field numberz--indexz-iz+Select the preset sort and indexing optionsrMrN)rhrddefault show_defaultz --flip-onlyz9Only flip mates; no sorting or indexing. Write to stdout.F)rhis_flagrjrkz--nprocz-pzNumber of processorsz --zero-basedrYzRead positions are zero-basedz--sepz Data delimiter in the input filez\tz--comment-charz Comment character to skip header#z--sort-optionsz3Quoted list of additional options to `sort` command)rhrdz--outz-ozOutput gzip file)rhz --strand1z-s1z!strand1 field number (deprecated)z --strand2z-s2z!strand2 field number (deprecated)c  tjdkrtjdddlm}m}m}|||dd|fD]D}t|s3td|dtj tj d E|}| |d kr(|s&t d tj|}d}|drtj|d}|drtj|d}d}|dkrd}nd}||z|z}n| }| t#j| } nt'rd|dg} ng} ||||d}t)|}t+|| | |}|r>tdg}td||t5j||d kr tjnd t4jtd||t5j||djtj|d d dD]5}||j dkrtj d 6d StC||| }ddg}tE||| |}td|dtd|d||ksJtG|d5} g}td||t5j||d kr tjnd t4jtd td||t5j||djt4j|dkrtd!ntd"td||t5j||djt4jtd||t5j||dj| |d d dD]g}||j dkrFt d|j$tj d h d d d n #1swxYwYtd#td$|td|t5j|}||j dkrtj d d Sd S)%a Sort and index a contact list. Order the mates of each pair record so that all contacts are upper triangular with respect to the chromosome ordering given by the chromosomes file, sort contacts by genomic location, and index the resulting file. PAIRS_PATH : Contacts (i.e. read pairs) text file, optionally compressed. CHROMOSOMES_PATH : File listing desired chromosomes in the desired order. May be tab-delimited, e.g. a UCSC-style chromsizes file. Contacts mapping to other chromosomes will be discarded. **Notes** - csort can also be used to sort and index a text representation of a contact *matrix* in bedGraph-like format. In this case, substitute `pos1` and `pos2` with `start1` and `start2`, respectively. - Requires Unix tools: sort, bgzip + tabix or pairix. If indexing with Tabix, the output file will have the following properties: - Upper triangular: the read pairs on each row are assigned to side 1 or 2 in such a way that (chrom1, pos1) is always "less than" (chrom2, pos2) - Rows are lexicographically sorted by chrom1, pos1, chrom2, pos2; i.e. "positionally sorted" - Compressed with bgzip [*] - Indexed using Tabix [*] on chrom1 and pos1. If indexing with Pairix, the output file will have the following properties: - Upper triangular: the read pairs on each row are assigned to side 1 or 2 in such a way that (chrom1, pos1) is always "less than" (chrom2, pos2) - Rows are lexicographically sorted by chrom1, chrom2, pos1, pos2; i.e. "block sorted" - Compressed with bgzip [*] - Indexed using Pairix [+] on chrom1, chrom2 and pos1. [*] Tabix manpage: . [+] Pairix on Github: ntzm"cooler csort" does not work on Windows. To ingest unsorted pairs data, see the "cooler cload pairs" command.r)SIG_DFLSIGPIPEsignalr bgzipzCommand z not foundr rN-z(Output name required when input is stdinrz.txtz.txt.gzrNz.blksrtz.possrtz --parallel=z--buffer-size=50%)r-r/r.r0zReordering pair mates... )r r r8zInput: ''z Output: 'r z1Reordering pair mates and sorting pair records...z.Sort order: block (chrom1, chrom2, pos1, pos2)z3Sort order: positional (chrom1, pos1, chrom2, pos2)z Indexing...z Indexer: )%rOnamerAbortrsrqrrrr$r%rr&r:errorr#opsplitextrQr=rr*rIr;debugjoinappendrPopenr PIPEr communicate returncoderWr_r9args)!r`r1rTchrom1chrom2pos1pos2 flip_onlynprocr\r2r3rUoutkwargsrqrrrstoolr'prefixext sort_styler]rCr)flip_cmdpipelineprV write_cmdr^fouts! rcsortrsd w$k :   0///////// F7G%($  -T---CJ ? ? ? ? HQKKKF { S=== LLC D D D+  ??5 ! ! ,[((+F ??6 " " [((+FC H  "JJ"J:%+{<00   -e--/BC  $fD A AF!((H !13 fMMHR ./// SXXh''(((  #)S==ciid!        SXXh''(((  XXb\-@ T T T   $$B$  A MMOOO|q      %UFLAAdO &ufj'JJ   (v((())) ****+++    '4 ) DH LL(++ , , , OO '-}}#))$%?    KKK L L L LL(++ , , , OO HRL$7        LMMMM QRRR KK** + + + OO HRL$7     LL),, - - - OO (2,2EdSSS   ddd^   <1$$LL!&!1!1222HQKKK  I) ) ) ) ) ) ) ) ) ) ) ) ) ) ) X  M""" '''((( CHHY''(((  Y ' '  <1   HQKKKKK  sI8W  W W )&rOos.pathpathr|rQrr%rutilrrrr ImportErrorr9devnull__name__r:rRrSrZr[r@rrr*rIrWr_commandargumentPathoptionintChoicer?rrrrrs   %"""""""%%%d2:t$$GGG% H   D C + A  < 6---4!!! zuz$???ZUZt444>P  B                  6 w) * *   D    t0sATX (    +   +   >  gt"4555 k5'JQTUUU k5'JQTUUUBBVUVU65 nBBBs1A  A