Python internals.find_binary函数代码示例

def config_tadm(bin=None):
    global _tadm_bin
    _tadm_bin = find_binary(
        'tadm', bin,
        env_vars=['TADM'],
        binary_names=['tadm'],
        url='http://tadm.sf.net')

    def _repr_png_(self):
        """Draws and outputs in PNG for ipython.

        PNG is used instead of PDF, since it can be displayed in the qt
        console and has wider browser support.
        """
        with tempfile.NamedTemporaryFile() as f_tmp:
            in_path = '{0:}.ps'.format(f_tmp.name)
            out_path = '{0:}.png'.format(f_tmp.name)
            # generate PostScript using the drawing utils of NLTK
            self.to_ps(in_path)
            # convert to PNG with ghostscript
            subprocess.call(
                [find_binary('gs',
                             binary_names=['gswin32c.exe', 'gswin64c.exe'],
                             env_vars=['PATH'], verbose=False)] +
                '-q -dEPSCrop {2:} -dSAFER -dBATCH -dNOPAUSE -sOutputFile={0:} {1:}'
                .format(out_path, in_path, _GS_PARAMS['png']).split())
            # this function will return the encoded+decoded bytes of the PNG
            # file
            with open(out_path, 'rb') as sr:
                res = sr.read()
            os.remove(in_path)
            os.remove(out_path)
            return base64.b64encode(res).decode()

def config_mallet(mallet_home=None):
    """
    Configure NLTK's interface to the Mallet machine learning package.

    :type mallet_home: str
    :param mallet_home: The full path to the mallet directory. If not
        specified, then NLTK will search the system for a mallet directory;
        and if one is not found, it will raise a ``LookupError`` exception.
    """
    global _mallet_home, _mallet_classpath

    # We don't actually care about this binary -- we just use it to
    # make sure we've found the right directory.
    mallethon_bin = find_binary(
        "mallet",
        mallet_home,
        env_vars=["MALLET", "MALLET_HOME"],
        binary_names=["mallethon"],
        url="http://mallet.cs.umass.edu",
    )
    # Record the location where mallet lives.
    bin_dir = os.path.split(mallethon_bin)[0]
    _mallet_home = os.path.split(bin_dir)[0]
    # Construct a classpath for using mallet.
    lib_dir = os.path.join(_mallet_home, "lib")
    if not os.path.isdir(lib_dir):
        raise ValueError("While configuring mallet: directory %r " "not found." % lib_dir)
    _mallet_classpath = os.path.pathsep.join(
        os.path.join(lib_dir, filename) for filename in sorted(os.listdir(lib_dir)) if filename.endswith(".jar")
    )

 def _find_binary(self, name, bin_dir, verbose=False):
     return find_binary(name,
         path_to_bin=bin_dir,
         env_vars=['CANDC'],
         url='http://svn.ask.it.usyd.edu.au/trac/candc/',
         binary_names=[name, name + '.exe'],
         verbose=verbose)

 def _find_binary(self, name, verbose=False):
     return find_binary(name,
         searchpath=Theorem.BINARY_LOCATIONS,
         env_vars=['PROVER9HOME'],
         url='http://www.cs.unm.edu/~mccune/prover9/',
         binary_names=[name],
         verbose=verbose)

def config_mallet(mallet_home=None):
    """
    Configure NLTK's interface to the C{mallet} machine learning
    package.

    :param mallet_home: The full path to the C{mallet} directory.  If
        not specified, then nltk will search the system for a
        C{mallet} directory; and if one is not found, it will raise a
        C{LookupError} exception.
    :type mallet_home: str
    """
    global _mallet_home, _mallet_classpath
    
    # We don't actually care about this binary -- we just use it to
    # make sure we've found the right directory.
    mallethon_bin = find_binary(
        'mallet', mallet_home,
        env_vars=['MALLET',  'MALLET_HOME'],
        binary_names=['mallethon'],
        url='http://mallet.cs.umass.edu>')
    # Record the location where mallet lives.
    bin_dir = os.path.split(mallethon_bin)[0]
    _mallet_home = os.path.split(bin_dir)[0]
    # Construct a classpath for using mallet.
    lib_dir = os.path.join(_mallet_home, 'lib')
    if not os.path.isdir(lib_dir):
        raise ValueError('While configuring mallet: directory %r '
                         'not found.' % lib_dir)
    _mallet_classpath = ':'.join([os.path.join(lib_dir, filename)
                                  for filename in sorted(os.listdir(lib_dir))
                                  if filename.endswith('.jar')])

    def __init__(self, path_to_model, path_to_bin=None,
                 encoding=_hunpos_charset, verbose=False):
        """
        Starts the hunpos-tag executable and establishes a connection with it.

        :param path_to_model: The model file.
        :param path_to_bin: The hunpos-tag binary.
        :param encoding: The encoding used by the model. Unicode tokens
            passed to the tag() and tag_sents() methods are converted to
            this charset when they are sent to hunpos-tag.
            The default is ISO-8859-1 (Latin-1).

            This parameter is ignored for str tokens, which are sent as-is.
            The caller must ensure that tokens are encoded in the right charset.
        """
        self._closed = True
        hunpos_paths = ['.', '/usr/bin', '/usr/local/bin', '/opt/local/bin',
                        '/Applications/bin', '~/bin', '~/Applications/bin']
        hunpos_paths = list(map(os.path.expanduser, hunpos_paths))

        self._hunpos_bin = find_binary(
            'hunpos-tag', path_to_bin,
            env_vars=('HUNPOS_TAGGER',),
            searchpath=hunpos_paths,
            url=_hunpos_url,
            verbose=verbose
        )

        self._hunpos_model = find_file(
            path_to_model, env_vars=('HUNPOS_TAGGER',), verbose=verbose)
        self._encoding = encoding
        self._hunpos = Popen([self._hunpos_bin, self._hunpos_model],
                             shell=False, stdin=PIPE, stdout=PIPE, stderr=PIPE)
        self._closed = False

    def config_malt(self, bin=None, verbose=False):
        """
        Configure NLTK's interface to the C{malt} package.  This
        searches for a directory containing the malt jar
        
        :param bin: The full path to the C{malt} binary.  If not
            specified, then nltk will search the system for a C{malt}
            binary; and if one is not found, it will raise a
            C{LookupError} exception.
        :type bin: str
        """
        #: A list of directories that should be searched for the malt
        #: executables.  This list is used by L{config_malt} when searching
        #: for the malt executables.
        _malt_path = ['.',
                     '/usr/lib/malt-1*',
                     '/usr/share/malt-1*',
                     '/usr/local/bin',
                     '/usr/local/malt-1*',
                     '/usr/local/bin/malt-1*',
                     '/usr/local/malt-1*',
                     '/usr/local/share/malt-1*']
        
        # Expand wildcards in _malt_path:
        malt_path = reduce(add, map(glob.glob, _malt_path))

        # Find the malt binary.
        self._malt_bin = find_binary('malt.jar', bin,
            searchpath=malt_path, env_vars=['MALTPARSERHOME'],
            url='http://w3.msi.vxu.se/~jha/maltparser/index.html',
            verbose=verbose)

 def _find_binary(self, name, bin_dir, verbose=False):
     return find_binary(
         name,
         path_to_bin=bin_dir,
         env_vars=["CANDCHOME"],
         url="http://svn.ask.it.usyd.edu.au/trac/candc/",
         binary_names=[name, name + ".exe"],
         verbose=verbose,
     )

    def __init__(self, path_to_treetagger=None, language='english',
                 verbose=False, abbreviation_list=None):
        """
        Initialize the TreeTagger.

        :param language: Default language is english.

        The encoding used by the model. Unicode tokens
        passed to the tag() method are converted to
        this charset when they are sent to TreeTagger.
        The default is utf-8.

        This parameter is ignored for str tokens, which are sent as-is.
        The caller must ensure that tokens are encoded in the right charset.
        """
        if path_to_treetagger:
            self._path_to_treetagger = path_to_treetagger
        else:
            self._path_to_treetagger = None

        treetagger_paths = ['.']
        if 'TREETAGGER_HOME' in os.environ:
            if _platform == "win32":
                tt_path = os.path.normpath(os.path.join(os.environ['TREETAGGER_HOME'], 'bin'))
            else:
                tt_path = os.path.normpath(os.path.join(os.environ['TREETAGGER_HOME'], 'cmd'))
            treetagger_paths.append(tt_path)
        elif self._path_to_treetagger:
            if _platform == "win32":
                tt_path = os.path.normpath(os.path.join(self._path_to_treetagger, 'bin'))
            else:
                tt_path = os.path.normpath(os.path.join(self._path_to_treetagger, 'cmd'))
            treetagger_paths.append(tt_path)
        else:
            raise LookupError('Set \'TREETAGGER_HOME\' or use path_to_treetagger!')
        treetagger_paths = list(map(os.path.expanduser, treetagger_paths))

        self._abbr_list = abbreviation_list

        if language in self.get_installed_lang():
            if _platform == "win32":
                treetagger_bin_name = 'tag-' + language + '.bat'
            else:
                treetagger_bin_name = 'tree-tagger-' + language
        else:
            raise LookupError('Language not installed!')

        try:
            self._treetagger_bin = find_binary(
                treetagger_bin_name,
                searchpath=treetagger_paths,
                url=_treetagger_url,
                verbose=verbose)
        except LookupError:
            print('NLTK was unable to find the TreeTagger bin!')

    def __init__(self, path_to_home=None, language="english", encoding="latin-1", verbose=False):
        """
        Initialize the TreeTagger.

        :param path_to_home: The TreeTagger binary.
        :param language: Default language is german.
        :param encoding: The encoding used by the model. Unicode tokens
            passed to the tag() and batch_tag() methods are converted to
            this charset when they are sent to TreeTagger.
            The default is utf8.

            This parameter is ignored for str tokens, which are sent as-is.
            The caller must ensure that tokens are encoded in the right charset.
        """
        treetagger_paths = [
            ".",
            "/usr/bin",
            "/usr/local/bin",
            "/opt/local/bin",
            "/Applications/bin",
            "~/bin",
            "~/Applications/bin",
            "~/work/TreeTagger/cmd",
        ]
        treetagger_paths = map(os.path.expanduser, treetagger_paths)

        try:
            if language in _treetagger_languages[encoding]:
                if encoding == u"latin-1":
                    """the executable has no encoding information for latin-1"""
                    treetagger_bin_name = "tree-tagger-" + language
                    self._encoding = u"latin-1"
                else:
                    treetagger_bin_name = "tree-tagger-" + language + u"-" + encoding
                    self._encoding = encoding

            else:
                raise LookupError("NLTK was unable to find the TreeTagger bin!")
        except KeyError as e:
            raise LookupError("NLTK was unable to find the TreeTagger bin!")

        self._treetagger_bin = find_binary(
            treetagger_bin_name,
            path_to_home,
            env_vars=("TREETAGGER", "TREETAGGER_HOME"),
            searchpath=treetagger_paths,
            url=_treetagger_url,
            verbose=verbose,
        )

        if encoding in _treetagger_charset:
            self._encoding = encoding

 def to_pdf(self, filename):
     """Image representation in PDF.
     """
     # generate PostScript using the drawing utils of NLTK
     root, ext = os.path.splitext(filename)
     in_path = '{0:}.ps'.format(root)
     self.to_ps(in_path)
     # convert to PDF with ghostscript
     subprocess.call(
         [find_binary('gs',
                      binary_names=['gswin32c.exe', 'gswin64c.exe'],
                      env_vars=['PATH'], verbose=False)] +
         '-q -dEPSCrop {2:} -dSAFER -dBATCH -dNOPAUSE -sOutputFile={0:} {1:}'
         .format(filename, in_path, _GS_PARAMS['pdf']).split())
     os.remove(in_path)

    def __init__(self, path_to_home=None, language='german', 
                 encoding='utf8', verbose=False, abbreviation_list=None):
        """
        Initialize the TreeTagger.

        :param path_to_home: The TreeTagger binary.
        :param language: Default language is german.
        :param encoding: The encoding used by the model. Unicode tokens
            passed to the tag() and batch_tag() methods are converted to
            this charset when they are sent to TreeTagger.
            The default is utf8.

            This parameter is ignored for str tokens, which are sent as-is.
            The caller must ensure that tokens are encoded in the right charset.
        """
        treetagger_paths = ['.', '/usr/bin', '/usr/local/bin', '/opt/local/bin',
                        '/Applications/bin', '~/bin', '~/Applications/bin',
                        '~/work/TreeTagger/cmd', '~/tree-tagger/cmd', '/tree-tagger/bin', '/tree-tagger/cmd', '/var/opt/treetagger/bin', '/var/opt/treetagger/cmd']
        treetagger_paths = map(os.path.expanduser, treetagger_paths)
        self._abbr_list = abbreviation_list

        try:
            if language in _treetagger_languages[encoding]:
                if encoding == u'latin-1':
                    """the executable has no encoding information for latin-1"""
                    treetagger_bin_name = 'tree-tagger-' + language
                    self._encoding = u'latin-1'
                else:
                    #treetagger_bin_name = 'tree-tagger-' + language + u'-' + encoding
                    treetagger_bin_name = 'tree-tagger-' + language
                    self._encoding = encoding

            else:
                raise LookupError('NLTK was unable to find the TreeTagger bin!')
        except KeyError as e:
                raise LookupError('NLTK was unable to find the TreeTagger bin!')

        self._treetagger_bin = find_binary(
                treetagger_bin_name, path_to_home,
                env_vars=('TREETAGGER', 'TREETAGGER_HOME'),
                searchpath=treetagger_paths,
                url=_treetagger_url,
                verbose=verbose)
        print(u'### {}'.format(self._treetagger_bin))

        if encoding in _treetagger_charset:
            self._encoding = encoding
        print(u'#### {}'.format(self._encoding))

def config_megam(bin=None):
    """
    Configure NLTK's interface to the ``megam`` maxent optimization
    package.

    :param bin: The full path to the ``megam`` binary.  If not specified,
        then nltk will search the system for a ``megam`` binary; and if
        one is not found, it will raise a ``LookupError`` exception.
    :type bin: str
    """
    global _megam_bin
    _megam_bin = find_binary(
        'megam', bin,
        env_vars=['MEGAM'],
        binary_names=['megam.opt', 'megam', 'megam_686', 'megam_i686.opt'],
        url='http://www.umiacs.umd.edu/~hal/megam/index.html')

def config_megam(bin=None):
    """
    Configure NLTK's interface to the C{megam} maxent optimization
    package.

    @param bin: The full path to the C{megam} binary.  If not specified,
        then nltk will search the system for a C{megam} binary; and if
        one is not found, it will raise a C{LookupError} exception.
    @type bin: C{string}
    """
    global _megam_bin
    _megam_bin = find_binary(
        'megam', bin,
        env_vars=['MEGAM',  'MEGAMHOME'],
        binary_names=['megam.opt', 'megam', 'megam_686', 'megam_i686.opt'],
        url='http://www.cs.utah.edu/~hal/megam/')