,h]pdZddlZddlZddlZddlZddlZddlZddlmZGdde Z Gdde Z y) zmThis module includes a bunch of convenient base classes that are reused in many of the other parser modules. N) exceptionsc,eZdZdZdZdZddZddZy) BaseParserzThe :class:`.BaseParser` abstracts out some common functionality that is used across all document Parsers. In particular, it has the responsibility of handling all unicode and byte-encoding. c td)zThis method must be overwritten by child classes to extract raw text from a filename. This method can return either a byte-encoded string or unicode. z$must be overwritten by child classes)NotImplementedError)selffilenamekwargss X/var/www/html/Resume-Scraper/venv/lib/python3.12/site-packages/textract/parsers/utils.pyextractzBaseParser.extracts ""HIIc&|j|dS)zEncode the ``text`` in ``encoding`` byte-encoding. This ignores code points that can't be encoded in byte-strings. ignore)encode)r textencodings r rzBaseParser.encodes{{8X..rc p|j|fi|}|j||}|j||S)aProcess ``filename`` and encode byte-string with ``encoding``. This method is called by :func:`textract.parsers.process` and wraps the :meth:`.BaseParser.extract` method in `a delicious unicode sandwich `_. )r decoder)r r input_encodingoutput_encodingr byte_stringunicode_strings r processzBaseParser.process#s:#dll86v6 [.A{{>?;;rNct|tjr|S|sy|r|j|St j |}|ddkDr|dnd}|j|dS)zcDecode ``text`` using the `chardet `_ package. confidenceg?rutf8replace)errors) isinstancesix text_typerchardetdetect)r rrresultrs r rzBaseParser.decode2sn dCMM *K ;;~. .%)/ )=)D6*%&{{8I{66r)r)N)__name__ __module__ __qualname____doc__r rrrrr rrs J/ <7rrceZdZdZdZdZy) ShellParserzThe :class:`.ShellParser` extends the :class:`.BaseParser` to make it easy to run external programs from the command line with `Fabric `_-like behavior. c tj|tjtj}|j\}}|jdk7r1t jdj||j||||fS#t$rJ}|jtj k(r't jdj|dddd}~wwxYw)zRun ``command`` and return the subsequent ``stdout`` and ``stderr`` as a tuple. If the command is not successful, this raises a :exc:`textract.exceptions.ShellError`. )stdoutstderr rNr) subprocessPopenPIPEOSErrorerrnoENOENTr ShellErrorjoin communicate returncode)r argspipeer/r0s r runzShellParser.runOs ##!zD))+ ??a '' v~' ww%,,&!++HHTNCR s4B C ACC c^tj\}}tj||S)z'Return a unique tempfile name. )tempfilemkstemposclose)r handler s r temp_filenamezShellParser.temp_filenameps($++- rN)r'r(r)r*r@rGr+rr r-r-Is B rr-) r*r3rBrDr7r"r$rrobjectrr-r+rr rIs: 6767r0*0r