:>"^%@sdZddlmZdZGdddeZGdddeZdd Zd d Zd d Z ddZ e dkrddl m Z e dS)z:Tools to manipulate data from nmrview .xpk peaklist files.)print_functionc@s"eZdZdZddZdS)XpkEntryaProvide dictonary access to single entry from nmrview .xpk file. This class is suited for handling single lines of non-header data from an nmrview .xpk file. This class provides methods for extracting data by the field name which is listed in the last line of the peaklist header. Parameters ---------- xpkentry : str The line from an nmrview .xpk file. xpkheadline : str The line from the header file that gives the names of the entries. This is typically the sixth line of the header, 1-origin. Attributes ---------- fields : dict Dictionary of fields where key is in header line, value is an entry. Variables are accessed by either their name in the header line as in self.field["H1.P"] will return the H1.P entry for example. self.field["entrynum"] returns the line number (1st field of line) cCsi|_|j}|j}d}x7tt|dD]}||d|j||W|d}y|d|jd>> from Bio.NMR.xpktools import Peaklist >>> peaklist = Peaklist('../Doc/examples/nmr/noed.xpk') >>> peaklist.firstline 'label dataset sw sf ' >>> peaklist.dataset 'test.nv' >>> peaklist.sf '{599.8230 } { 60.7860 } { 60.7860 }' >>> peaklist.datalabels ' H1.L H1.P H1.W H1.B H1.E H1.J 15N2.L 15N2.P 15N2.W 15N2.B 15N2.E 15N2.J N15.L N15.P N15.W N15.B N15.E N15.J vol int stat ' c Cst|d}|jjdd|_|jjdd|_|jjdd|_|jjdd|_|jjdd|_|jjdd|_dd|D|_ WdQRXdS)zInitialize the class.r rcSs#g|]}|jddqS)rr)r).0linerrr ss z%Peaklist.__init__..N) openreadliner firstline axislabelsdatasetswsf datalabelsdata)r ZinfninfilerrrrfszPeaklist.__init__c CsHd}d}i|_xtt|jD]}|j|}t||jj|d}|jdd}t|}|d kr|}|d kr|}t ||g}t ||g}t ||jkr |jt |} | j || |jt |>> from Bio.NMR.xpktools import Peaklist >>> peaklist = Peaklist('../Doc/examples/nmr/noed.xpk') >>> residue_d = peaklist.residue_dict('H1') >>> sorted(residue_d.keys()) ['10', '3', '4', '5', '6', '7', '8', '9', 'maxres', 'minres'] >>> residue_d['10'] ['8 10.hn 7.663 0.021 0.010 ++ 0.000 10.n 118.341 0.324 0.010 +E 0.000 10.n 118.476 0.324 0.010 +E 0.000 0.49840 0.49840 0'] rz.L.rmaxresminresr)r)r)) dictrr r$rr#rrintmaxminstrappend) r indexr'r(r rindkeyresZtemplstrrr residue_dictus,        zPeaklist.residue_dictc Cst|d}|j|j|jd|j|j|jd|j|j|jd|j|j|jd|j|j|jd|j|j|jdWdQRXdS)z7Write header lines from input file to handle ``outfn``.wrN)rwriterrr r!r"r#)r Zoutfnoutfilerrr write_headers     zPeaklist.write_headerN)rrrrrr4r8rrrrr;s )  >rcCs_t||}t||djd}|d|t||||d}|S)zReplace an entry in a string by the field number. No padding is implemented currently. Spacing will change if the original field entry and the new field entry are of different lengths. Nr)_find_start_entryr rr.)rZfieldnZnewentrystartlengnewlinerrr replace_entrys  ,r=cCsd}|dkrdSd}t|}|ddkrGd}d}n d}d}xz||kr||kr|r||dkr||ddk rd}n ||dksd}|d}|d}qVW|dS)a"Find the starting character for entry ``n`` in a space delimited ``line`` (PRIVATE). n is counted starting with 1. The n=1 field by definition begins at the first character. Returns ------- starting character : str The starting character for entry ``n``. rr )r )rnZinfieldcr;fieldrrrr9s&   %  r9c Cs@g}t||\}}|dd}|dd}xB|D]:}||dkr^|d}||dkr>|d}q>W|} x| |kr;d} t| } xq|D]i}|| } t| |kr| dt|t| d| j|} n| dd} | d} qW| d} |j| | d} qW|S)azGenerate a data table from a list of input xpk files. Parameters ---------- fn_list : list List of .xpk file names. datalabel : str The data element reported. keyatom : str The name of the nucleus used as an index for the data table. Returns ------- outlist : list List of table rows indexed by ``keyatom``. rr(r' *rr) _read_dictsr.rrr/) fn_listZ datalabelkeyatomZoutlist dict_listZlabel_line_listZminrZmaxr dictionaryr3countrlabelrrr data_tables.     /  rKcCs_g}g}xF|D]>}t|}|j|}|j||j|jqW||gS)zBRead multiple files into a list of residue dictionaries (PRIVATE).)rr4r/r#)rErFrGZdatalabel_listfnZpeaklistr*rrrrD8s   rD__main__) run_doctestN)r __future__rZ HEADERLENobjectrrr=r9rKrDrZ Bio._utilsrNrrrrs.  . 7