,h< hdZddlZddlZddlZddlZddlmZddddddd d Zd Zd Z d Z dedfd Z dZ y)zA Route the request to the appropriate parser based on file type. N) exceptionsz.jpgz.tiffz.htmlz.txtz.tsv)z.jpegz.tffz.tifz.htmz.logz.tabutf_8_parserc tjj|stj||r)|}|j dsd|z}|j }n2tjj|\}}|j }tj||}|tz} tj|d}|j} | j |||fi|S#t$rtj|wxYw)zThis is the core function used for extracting text. It routes the ``filename`` to the appropriate parser and returns the extracted text as a byte-string encoded with ``encoding``. .ztextract.parsers)ospathexistsrMissingFileError startswithlowersplitextEXTENSION_SYNONYMSget_FILENAME_SUFFIX importlib import_module ImportErrorExtensionNotSupportedParserprocess) filenameinput_encodingoutput_encoding extensionkwargsext_ rel_modulefiletype_moduleparsers [/var/www/html/Resume-Scraper/venv/lib/python3.12/site-packages/textract/parsers/__init__.pyrr!s 77>>( #))(33~~c")Ciik!!(+3iik  c *C ''J4#11 *  # # %F 6>>(NO Nv NN 4..s334s 2C--D cg}tjjtjjt}tjj|dt zdz}|j dd}tj|j dd}tj|D]K}|j|}|jd}|j||jd|zMtjD]8}|s|j||j|j ddd :|j|S) zkGet a list of available file extensions to make it easy for tab-completion and exception handling. *z.pyz//z////z (?P\w+)rr r)r r joindirname__file__rreplacerecompileglobmatchgroupsappendrkeyssort) extensions parsers_dir glob_filenameext_rer ext_matchrs r$_get_available_extensionsr9Rs'J'',,rwwx89KGGLLc4D.Du.LMM!))$7M ZZ --c?C DFIIm,%LL*  ###)$ %"&&(7    c "   ckk#r15 67OO ) __doc__r rr.r,rrrDEFAULT_OUTPUT_ENCODINGDEFAULT_ENCODINGrrr9r:r$r?sg       "&*;R^b.Obr: