o +wi@sXddlmZddlmZddlZddlZddlZddlZddlZddl Z ddl m Z ej ej eZgdZe jddkrHGdddejZd(d d Ze jddkrcdd lmZd)ddZddZddZe jddkrsddZnejZddZddZe jddkreZddZd)ddZ d)ddZ!d)d d!Z"d"d#Z#d$d%Z$Gd&d'd'e Z%dS)*)absolute_import)unicode_literalsN)Thread) )·/)u․r)uㆍr)u･r)u～~)u❑-)u‘')u’r )u“")u”r )u「<)u」>c@seZdZddZdS)UnicodePrintercCs:t|trtjjp d}||ddfStj|||||S)z0Overrided method to enable Unicode pretty print.utf-8TF) isinstanceunicodesysstdoutencodingencodepp PrettyPrinterformat)selfobjectcontext maxlevelslevelrrI/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/konlpy/utils.pyr s  zUnicodePrinter.formatN)__name__ __module__ __qualname__rrrrrrs rFc s\|}fddt|D}|r,|D]}td|d|td|d|dfq|S)uFind concordances of a phrase in a text. The farmost left numbers are indices, that indicate the location of the phrase in the text (by means of tokens). The following string, is part of the text surrounding the phrase for the given index. :param phrase: Phrase to search in the document. :param text: Target document. :param show: If ``True``, shows locations of the phrase on the console. .. code-block:: python >>> from konlpy.corpus import kolaw >>> from konlpy.tag import Mecab >>> from konlpy import utils >>> constitution = kolaw.open('constitution.txt').read() >>> idx = utils.concordance(u'대한민국', constitution, show=True) 0 대한민국헌법 유구한 역사와 9 대한국민은 3·1운동으로 건립된 대한민국임시정부의 법통과 불의에 98 총강 제1조 ① 대한민국은 민주공화국이다. ②대한민국의 100 ① 대한민국은 민주공화국이다. ②대한민국의 주권은 국민에게 110 나온다. 제2조 ① 대한민국의 국민이 되는 126 의무를 진다. 제3조 대한민국의 영토는 한반도와 133 부속도서로 한다. 제4조 대한민국은 통일을 지향하며, 147 추진한다. 제5조 ① 대한민국은 국제평화의 유지에 787 군무원이 아닌 국민은 대한민국의 영역안에서는 중대한 1836 파견 또는 외국군대의 대한민국 영역안에서의 주류에 3620 경제 제119조 ① 대한민국의 경제질서는 개인과 >>> idx [0, 9, 98, 100, 110, 126, 133, 147, 787, 1836, 3620] csg|] \}}|vr|qSrr).0itermphraserr Kzconcordance..z%d %s rr )split enumerateprintjoinmax)r'textshowtermsindexesr$rr&r concordance(s ".r4)csvutilsrcCst|}dd|DS)u,Reads a csv file. :param f: File object. .. code-block:: python >>> from konlpy.utils import csvread >>> with open('some.csv', 'r') as f: print csvread(f) [[u'이 / NR', u'차 / NNB'], [u'나가 / VV', u'네 / EFN']] cSsg|]}|qSrr)r#rowrrrr(bszcsvread..)r5 UnicodeReader)frreaderrrrcsvreadUs r:cCst||S)u:Writes a csv file. :param data: A list of list. .. code-block:: python >>> from konlpy.utils import csvwrite >>> d = [[u'이 / NR', u'차 / NNB'], [u'나가 / VV', u'네 / EFN']] >>> with open('some.csv', 'w') as f: csvwrite(d, f) )r5 UnicodeWriter writerows)datar8rrrcsvwriteds r>cs$fddtdg||dgDS)zPartitions a list to several parts using indices. :param list_: The target list. :param indices: Indices to partition the target list. csg|] \}}||qSrr)r#r$jlist_rrr(yr)zpartition..rN)zip)rAindicesrr@r partitionss$rDcKs,d|vrt|dd|St|S)uUnicode pretty printer. .. code-block:: python >>> import pprint, konlpy >>> pprint.pprint([u"Print", u"유니코드", u"easily"]) [u'Print', u'유니코드', u'easily'] >>> konlpy.utils.pprint([u"Print", u"유니코드", u"easily"]) ['Print', '유니코드', 'easily'] :param stream: Option to stream to a particular destination. Can be either sys.stdout (default) or sys.stderr. See #179 for details. stream)rE)keysrpprint)objkwargsrrrrG|s  rGcCstD] \}}|||}q|S)z:Replaces some ambiguous punctuation marks to simpler ones.) replace_setreplace)r'abrrrselects rNcCs tt|S)utConverts a unicode character to hex. .. code-block:: python >>> char2hex(u'음') '0xc74c' )hexord)crrrchar2hexs rRcCstt|dS)uConverts a hex character to unicode. .. code-block:: python >>> print hex2char('c74c') 음 >>> print hex2char('0xc74c') 음 )unichrint)hrrrhex2char rWcCstj|d|dS)zEText file loader. To read a file, use ``read_txt()``instead. rr)ioopen)filenamerrrrload_txtsr^cCs<tj|d|d }|WdS1swYdS)zText file reader.rYrZN)r[r\readr]rr8rrrread_txts$racCs>tj|d|d }t|WdS1swYdS)zJSON file reader.rYrZN)r[r\jsonloadr`rrr read_jsons$rdcCtdd|S)zDelete links from input string Args: string (str): string to delete links Returns: str: string without links zhttp\S+resubstringrrr delete_linksrXrlcCre)zDelete at marks from input string Args: string (str): string to delete at marks Returns: str: string without at marks. z@\S+rfrgrjrrrdelete_mentionsrXrmcs(eZdZdZddZfddZZS)PropagatingThreadzPropagatingThread is just a fancy wrapper for Thread to manage exceptions. Raises: self.exception: Exception defined in higher-level. Returns: self.ret: Thread target object. c Csvd|_z!t|dr|j|ji|j|_WdS|j|ji|j|_WdSt y:}z ||_WYd}~dSd}~ww)N_Thread__target) exceptionhasattrro _Thread__args_Thread__kwargsret_target_args_kwargs BaseException)rerrrruns zPropagatingThread.runcs tt||jr |j|jS)N)superrnr.rprt)r __class__rrr.szPropagatingThread.join)r r!r"__doc__rzr. __classcell__rrr|rrns  rn)F)r)& __future__rrr[rbosrhrGrr threadingrpathdirnamerealpath__file__ installpathrJ version_inforrr4konlpyr5r:r>rDrNrRchrrTrWr^rardrlrmrnrrrrsB    *