o Rŀg@sNdZddZddZGdddeZddZed kr%d d lmZed Sd S) aXParser for the cellosaurus.txt file from ExPASy. See https://web.expasy.org/cellosaurus/ Tested with the release of Version 18 (July 2016). Functions: - read Reads a file containing one cell line entry - parse Reads a file containing multiple cell line entries Classes: - Record Holds cell line data. Examples -------- This example downloads the Cellosaurus database and parses it. Note that urlopen returns a stream of bytes, while the parser expects a stream of plain string, so we use TextIOWrapper to convert bytes to string using the UTF-8 encoding. This is not needed if you download the cellosaurus.txt file in advance and open it (see the comment below). >>> from urllib.request import urlopen >>> from io import TextIOWrapper >>> from Bio.ExPASy import cellosaurus >>> url = "ftp://ftp.expasy.org/databases/cellosaurus/cellosaurus.txt" >>> bytestream = urlopen(url) >>> textstream = TextIOWrapper(bytestream, "UTF-8") >>> # alternatively, use >>> # textstream = open("cellosaurus.txt") >>> # if you downloaded the cellosaurus.txt file in advance. >>> records = cellosaurus.parse(textstream) >>> for record in records: ... if 'Homo sapiens' in record['OX'][0]: ... print(record['ID']) # doctest:+ELLIPSIS ... #15310-LN #W7079 (L)PC6 0.5alpha ... ccs t|}|s dS|Vq)zParse cell line records. This function is for parsing cell line files containing multiple records. Arguments: - handle - handle to the file. TN)__read)handlerecordrJ/var/www/html/myenv/lib/python3.10/site-packages/Bio/ExPASy/cellosaurus.pyparse2s rcCs t|}|}|rtd|S)zRead one cell line record. This function is for parsing cell line files containing exactly one record. Arguments: - handle - handle to the file. z$More than one cell line record found)rread ValueError)rr remainderrrrrCs  rc@s(eZdZdZddZddZddZdS) Recorda$Holds information from an ExPASy Cellosaurus record as a Python dictionary. Each record contains the following keys: ========= ============================== ======================= Line code Content Occurrence in an entry ========= ============================== ======================= ID Identifier (cell line name) Once; starts an entry AC Accession (CVCL_xxxx) Once AS Secondary accession number(s) Optional; once SY Synonyms Optional; once DR Cross-references Optional; once or more RX References identifiers Optional: once or more WW Web pages Optional; once or more CC Comments Optional; once or more ST STR profile data Optional; twice or more DI Diseases Optional; once or more OX Species of origin Once or more HI Hierarchy Optional; once or more OI Originate from same individual Optional; once or more SX Sex of cell Optional; once AG Age of donor at sampling Optional; once CA Category Once DT Date (entry history) Once // Terminator Once; ends an entry ========= ============================== ======================= cCst|d|d<d|d<d|d<d|d<g|d<g|d<g|d<g|d <g|d <g|d <g|d <g|d <g|d<d|d<d|d<d|d<d|d<dS)zInitialize the class.IDACASSYDRRXWWCCSTDIOXHIOISXAGCADTN)dict__init__selfrrrrss$  zRecord.__init__cCsX|dr%|dr|jjd|dd|ddS|jjd|ddS|jjdS)z@Return the canonical string representation of the Record object.r r z (z, )z ( )) __class____name__rrrr__repr__s "zRecord.__repr__cCs4d|d}|d|d7}|d|d7}|d|d7}|d t|d 7}|d t|d 7}|d t|d7}|dt|d7}|dt|d7}|dt|d7}|dt|d7}|dt|d7}|dt|d7}|d|d7}|d|d7}|d|d 7}|d!|d"7}|S)#z=Return a readable string representation of the Record object.zID: r z AC: r z AS: rz SY: rz DR: rz RX: rz WW: rz CC: rz ST: rz DI: rz OX: rz HI: rz OI: rz SX: rz AG: rz CA: rz DT: r)repr)r outputrrr__str__s$ zRecord.__str__N)r# __module__ __qualname____doc__rr$r'rrrrr Us  r cCsd}|D]Z}|dd|dd}}|dkr!t}||d<q|dvr.|||7<q|dvr:|||q|dkrS|d\}}|d||fq|dkr^|r]|Sqq|retd dS) Nr )r rrrrrr)rrrrrrrrr;z//zUnexpected end of stream)rstripr appendsplitstripr)rrlinekeyvaluekvrrrrs*  r__main__) run_doctestN) r*rrrr rr# Bio._utilsr9rrrrs,V"