Python StringIO.StringIO() Examples

def emit(events, stream=None, Dumper=Dumper,
        canonical=None, indent=None, width=None,
        allow_unicode=None, line_break=None):
    """
    Emit YAML parsing events into a stream.
    If stream is None, return the produced string instead.
    """
    getvalue = None
    if stream is None:
        from StringIO import StringIO
        stream = StringIO()
        getvalue = stream.getvalue
    dumper = Dumper(stream, canonical=canonical, indent=indent, width=width,
            allow_unicode=allow_unicode, line_break=line_break)
    try:
        for event in events:
            dumper.emit(event)
    finally:
        dumper.dispose()
    if getvalue:
        return getvalue() 

def add_log_stream(self, stream=sys.stderr, level=logging.INFO):
		"""
		Add a stream where messages are outputted to.

		@param stream: stderr/stdout or a file stream
		@type stream: file | FileIO | StringIO
		@param level: minimum level of messages to be logged
		@type level: int | long

		@return: None
		@rtype: None
		"""
		assert self.is_stream(stream)
		# assert isinstance(stream, (file, io.FileIO))
		assert level in self._levelNames

		err_handler = logging.StreamHandler(stream)
		err_handler.setFormatter(self.message_formatter)
		err_handler.setLevel(level)
		self._logger.addHandler(err_handler) 

def __init__(self, logfile=None, verbose=True, debug=False, seed=None, tmp_dir=None):
		"""
			Anonymize fasta sequences

			@attention: 'shuf' is used which loads everything into memory!

			@param logfile: file handler or file path to a log file
			@type logfile: file | io.FileIO | StringIO.StringIO | str | unicode
			@param verbose: Not verbose means that only warnings and errors will be past to stream
			@type verbose: bool
			@param debug: more output and files are kept, manual clean up required
			@type debug: bool
			@param seed: The seed written to the random_source file used by the 'shuf' command
			@type seed: long | int | float | str | unicode
			@param tmp_dir: directory for temporary files, like the random_source file for 'shuf'
			@type tmp_dir: str | unicode

			@return: None
			@rtype: None
		"""
		assert isinstance(verbose, bool)
		assert isinstance(debug, bool)
		assert seed is None or isinstance(seed, (long, int, float, basestring))
		assert tmp_dir is None or isinstance(tmp_dir, basestring)
		if tmp_dir is not None:
			assert self.validate_dir(tmp_dir)
		else:
			tmp_dir = tempfile.gettempdir()
		self._tmp_dir = tmp_dir
		super(FastaAnonymizer, self).__init__(logfile, verbose, debug, label="FastaAnonymizer")

		if seed is not None:
			random.seed(seed)

		script_dir = os.path.dirname(self.get_full_path(__file__))
		self._anonymizer = os.path.join(script_dir, "anonymizer.py")
		self._fastastreamer = os.path.join(script_dir, "fastastreamer.py")
		assert self.validate_file(self._anonymizer)
		assert self.validate_file(self._fastastreamer) 

def test_str(self):
        """
        Test __str__ method, for full coverage and check that all modules have required attributes.
        """
        atts_list = ['PlanetPopulation', 'PlanetPhysicalModel', 'dMagLim', 'minComp']

        for mod in self.allmods:
            with RedirectStreams(stdout=self.dev_null):
                obj = mod(**copy.deepcopy(self.spec))
            original_stdout = sys.stdout
            sys.stdout = StringIO()
            # call __str__ method
            result = obj.__str__()
            # examine what was printed
            contents = sys.stdout.getvalue()
            self.assertEqual(type(contents), type(''))
            # attributes from ICD
            for att in atts_list:
                self.assertIn(att,contents,'{} missing for {}'.format(att,mod.__name__))
            sys.stdout.close()
            # it also returns a string, which is not necessary
            self.assertEqual(type(result), type(''))
            # put stdout back
            sys.stdout = original_stdout 

def __init__(self, separator="\t", logfile=None, verbose=True):
		"""
			Handle tab separated files

			@attention:

			@param separator: default character assumed to separate values in a file
			@type separator: str | unicode
			@param logfile: file handler or file path to a log file
			@type logfile: file | io.FileIO | StringIO.StringIO | basestring
			@param verbose: Not verbose means that only warnings and errors will be past to stream
			@type verbose: bool

			@return: None
			@rtype: None
		"""
		assert logfile is None or isinstance(logfile, basestring) or self.is_stream(logfile)
		assert isinstance(separator, basestring), "separator must be string"
		assert isinstance(verbose, bool), "verbose must be true or false"
		super(MetadataTable, self).__init__(label="MetadataReader", logfile=logfile, verbose=verbose)

		self._number_of_rows = 0
		self._meta_table = {}
		self._separator = separator
		self._list_of_column_names = [] 

def get_data_from_biodbnet(self, df_hgnc):
        """keys are unique Gene names
        
        input is made of the df based on HGNC data web services

        uniprot accession are duplicated sometimes. If som this is actually the
        iprimary accession entry and all secondary ones.


        e.g. ,
        
        ABHD11 >>>> Q8N723;Q8NFV2;Q8NFV3;Q6PJU0;Q8NFV4;H7BYM8;Q8N722;Q9HBS8 ABHDB_HUMAN Alpha/beta hydrolase domain-containing protein 11
        correspond actually to the primary one : Q8NFV4

        """
        b = biodbnet.BioDBNet()
        res2 = b.db2db("Gene Symbol", ["HGNC ID", "UniProt Accession", "UniProt Entry Name", "UniProt Protein Name", "KEGG Gene ID", "Ensembl Gene ID"], 
                res.keys()[0:2000])

        import pandas as pd
        import StringIO
        c = pd.read_csv(StringIO.StringIO(res2), delimiter="\t", index_col="Gene Symbol")
        return c 

def dummy_open(x, mode="r"):
  if mode == "r":
    known = {
      "/sw/BUILD/27ce49698e818e8efb56b6eff6dd785e503df341/defaults-release/.build_succeeded": (0, StringIO("0")),
      "/sw/BUILD/3e90b4e08bad439fa5f25282480d1adb9efb0c0d/zlib/.build_succeeded": (0, StringIO("0")),
      "/sw/BUILD/%s/ROOT/.build_succeeded" % TEST_ROOT_BUILD_HASH: (0, StringIO("0")),
      "/sw/osx_x86-64/defaults-release/v1-1/.build-hash": (1, StringIO("27ce49698e818e8efb56b6eff6dd785e503df341")),
      "/sw/osx_x86-64/zlib/v1.2.3-1/.build-hash": (1, StringIO("3e90b4e08bad439fa5f25282480d1adb9efb0c0d")),
      "/sw/osx_x86-64/ROOT/v6-08-30-1/.build-hash": (1, StringIO(TEST_ROOT_BUILD_HASH))
    }
    if not x in known:
      return DEFAULT
    threshold, result = known[x]
    if threshold > TIMES_ASKED.get(x, 0):
      result = None
    TIMES_ASKED[x] = TIMES_ASKED.get(x, 0) + 1
    if not result:
      raise IOError
    return result
  return StringIO() 

def _copy_eclipse_settings(p, files=None):
    processors = p.annotation_processors()

    settingsDir = join(p.dir, ".settings")
    mx.ensure_dir_exists(settingsDir)

    for name, sources in p.eclipse_settings_sources().items():
        out = StringIO()
        print('# GENERATED -- DO NOT EDIT', file=out)
        for source in sources:
            print('# Source:', source, file=out)
            with open(source) as f:
                print(f.read(), file=out)
        if p.javaCompliance:
            jc = p.javaCompliance if p.javaCompliance.value < _max_Eclipse_JavaExecutionEnvironment else mx.JavaCompliance(_max_Eclipse_JavaExecutionEnvironment)
            content = out.getvalue().replace('${javaCompliance}', str(jc))
        else:
            content = out.getvalue()
        if processors:
            content = content.replace('org.eclipse.jdt.core.compiler.processAnnotations=disabled', 'org.eclipse.jdt.core.compiler.processAnnotations=enabled')
        mx.update_file(join(settingsDir, name), content)
        if files:
            files.append(join(settingsDir, name)) 

def get_shell_commands(args, jdk, extra_jdks):
    setvar_format = get_setvar_format(args.shell)
    shell_commands = StringIO()
    print(setvar_format % ('JAVA_HOME', jdk), file=shell_commands)
    if extra_jdks:
        print(setvar_format % ('EXTRA_JAVA_HOMES', os.pathsep.join(extra_jdks)), file=shell_commands)
    path = os.environ.get('PATH').split(os.pathsep)
    if path:
        jdk_bin = join(jdk, 'bin')
        old_java_home = os.environ.get('JAVA_HOME')
        replace = join(old_java_home, 'bin') if old_java_home else None
        if replace in path:
            path = [e if e != replace else jdk_bin for e in path]
        else:
            path = [jdk_bin] + path
        print(setvar_format % ('PATH', get_PATH_sep(args.shell).join(path)), file=shell_commands)
    return shell_commands.getvalue().strip() 

def test_str(self):
        """
        Test __str__ method, for full coverage and check that all modules have required attributes.
        """
        atts_list = ['PlanetPhysicalModel', 'arange', 'erange', 'Irange', 'Orange', 'wrange', 'prange',
                     'Rprange', 'Mprange', 'rrange', 'scaleOrbits', 'constrainOrbits', 'eta']
        for mod in self.allmods:
            with RedirectStreams(stdout=self.dev_null):
                obj = mod(**self.spec)
            original_stdout = sys.stdout
            sys.stdout = StringIO()
            # call __str__ method
            result = obj.__str__()
            # examine what was printed
            contents = sys.stdout.getvalue()
            self.assertEqual(type(contents), type(''))
            # attributes from ICD
            for att in atts_list:
                self.assertIn(att,contents,'{} missing for {}'.format(att,mod.__name__))
            sys.stdout.close()
            # it also returns a string, which is not necessary
            self.assertEqual(type(result), type(''))
            # put stdout back
            sys.stdout = original_stdout 

def test_str(self):
        r"""Test __str__ method, for full coverage."""
        tlist = self.fixture
        # replace stdout and keep a reference
        original_stdout = sys.stdout
        sys.stdout = StringIO()
        # call __str__ method
        result = tlist.__str__()
        # examine what was printed
        contents = sys.stdout.getvalue()
        self.assertEqual(type(contents), type(''))
        self.assertIn('PlanetPhysicalModel', contents)
        self.assertIn('PlanetPopulation', contents)
        self.assertIn('Completeness', contents)
        sys.stdout.close()
        # it also returns a string, which is not necessary
        self.assertEqual(type(result), type(''))
        # put stdout back
        sys.stdout = original_stdout

    # @unittest.skip("Skipping populate_target_list.") 

def test_str(self):
        """
        Test __str__ method, for full coverage and check that all modules have required attributes.
        """

        for mod in self.allmods:
            with RedirectStreams(stdout=self.dev_null):
                obj = mod()
            original_stdout = sys.stdout
            sys.stdout = StringIO()
            # call __str__ method
            result = obj.__str__()
            # examine what was printed
            contents = sys.stdout.getvalue()
            self.assertEqual(type(contents), type(''))
            # attributes from ICD
            self.assertIn('_outspec', contents,'_outspec missing for %s'%mod.__name__)
            sys.stdout.close()
            # it also returns a string, which is not necessary
            self.assertEqual(type(result), type(''))
            # put stdout back
            sys.stdout = original_stdout 

def test_shouldCreateAllMigrations(self):
        for f in os.listdir("river/migrations"):
            if f != "__init__.py" and f != "__pycache__" and not f.endswith(".pyc"):
                open(os.path.join("river/tests/volatile/river/", f), 'wb').write(open(os.path.join("river/migrations", f), 'rb').read())

        self.migrations_before = list(filter(lambda f: f.endswith('.py') and f != '__init__.py', os.listdir('river/tests/volatile/river/')))

        out = StringIO()
        sys.stout = out

        call_command('makemigrations', 'river', stdout=out)

        self.migrations_after = list(filter(lambda f: f.endswith('.py') and f != '__init__.py', os.listdir('river/tests/volatile/river/')))

        assert_that(out.getvalue(), equal_to("No changes detected in app 'river'\n"))
        assert_that(self.migrations_after, has_length(len(self.migrations_before))) 

def dumps(obj, protocol=None):
    """Serialize obj as a string of bytes allocated in memory

    protocol defaults to cloudpickle.DEFAULT_PROTOCOL which is an alias to
    pickle.HIGHEST_PROTOCOL. This setting favors maximum communication speed
    between processes running the same Python version.

    Set protocol=pickle.DEFAULT_PROTOCOL instead if you need to ensure
    compatibility with older versions of Python.
    """
    file = StringIO()
    try:
        cp = CloudPickler(file, protocol=protocol)
        cp.dump(obj)
        return file.getvalue()
    finally:
        file.close()


# including pickles unloading functions in this namespace 

def open_local_file(self, req):
        host = req.get_host()
        file = req.get_selector()
        localfile = url2pathname(file)
        stats = os.stat(localfile)
        size = stats[stat.ST_SIZE]
        modified = rfc822.formatdate(stats[stat.ST_MTIME])
        mtype = mimetypes.guess_type(file)[0]
        stats = os.stat(localfile)
        headers = mimetools.Message(StringIO(
            'Content-Type: %s\nContent-Length: %d\nLast-modified: %s\n' %
            (mtype or 'text/plain', size, modified)))
        if host:
            host, port = splitport(host)
        if not host or \
           (not port and socket.gethostbyname(host) in self.get_names()):
            return addinfourl(open(localfile, 'rb'),
                              headers, 'file:'+file)
        raise URLError('file not on local host') 

def test_same_file_as():
    fh = FileHolder('a_fname')
    assert_true(fh.same_file_as(fh))
    fh2 = FileHolder('a_test')
    assert_false(fh.same_file_as(fh2))
    sio0 = StringIO()
    fh3 = FileHolder('a_fname', sio0)
    fh4 = FileHolder('a_fname', sio0)
    assert_true(fh3.same_file_as(fh4))
    assert_false(fh3.same_file_as(fh))
    fh5 = FileHolder(fileobj=sio0)
    fh6 = FileHolder(fileobj=sio0)
    assert_true(fh5.same_file_as(fh6))
    # Not if the filename is the same
    assert_false(fh5.same_file_as(fh3))
    # pos doesn't matter
    fh4_again = FileHolder('a_fname', sio0, pos=4)
    assert_true(fh3.same_file_as(fh4_again)) 

def emit(events, stream=None, Dumper=Dumper,
        canonical=None, indent=None, width=None,
        allow_unicode=None, line_break=None):
    """
    Emit YAML parsing events into a stream.
    If stream is None, return the produced string instead.
    """
    getvalue = None
    if stream is None:
        from StringIO import StringIO
        stream = StringIO()
        getvalue = stream.getvalue
    dumper = Dumper(stream, canonical=canonical, indent=indent, width=width,
            allow_unicode=allow_unicode, line_break=line_break)
    try:
        for event in events:
            dumper.emit(event)
    finally:
        dumper.dispose()
    if getvalue:
        return getvalue() 

def _make_diagram(self):

        class Option(object): #pylint: disable=too-many-instance-attributes,too-few-public-methods
            """Diagram configuration."""

            def __init__(self):
                self.axis = False
                self.batch = None
                self.color = True
                self.encoding = None
                self.function = None
                self.height = None
                self.keys = None
                self.legend = None
                self.palette = 'spectrum-reversed'
                self.reverse = None
                self.sleep = None

        data = self.data

        istream = [str(x) for x in data['ticks']]
        ostream = StringIO.StringIO()
        size = diagram.Point((self.width, self.height))
        option = Option()
        engine = diagram.AxisGraph(size, option)
        engine.consume(istream, ostream)

        meta = data['meta']

        high_line = self._align_label(meta['time_max'], _format_value(meta['max']))
        low_line = self._align_label(meta['time_min'], _format_value(meta['min']))
        lines = [high_line] + ostream.getvalue().splitlines() + [low_line]

        output = ""
        output += "\n".join([u"  │ %s" % x.decode('utf-8') for x in lines])
        output += u"\n  └" + u"─" * 80

        return output 

def __init__(self, response):
		# response doesn't support tell() and read(), required by
		# GzipFile
		if not gzip:
			raise SpeedtestHTTPError('HTTP response body is gzip encoded, '
									 'but gzip support is not available')
		IO = BytesIO or StringIO
		self.io = IO()
		while 1:
			chunk = response.read(1024)
			if len(chunk) == 0:
				break
			self.io.write(chunk)
		self.io.seek(0)
		gzip.GzipFile.__init__(self, mode='rb', fileobj=self.io) 

def ftp_open(self, req):
        host = req.get_host()
        if not host:
            raise IOError('ftp error', 'no host given')
        # XXX handle custom username & password
        try:
            host = socket.gethostbyname(host)
        except socket.error(msg):
            raise URLError(msg)
        host, port = splitport(host)
        if port is None:
            port = ftplib.FTP_PORT
        path, attrs = splitattr(req.get_selector())
        path = unquote(path)
        dirs = path.split('/')
        dirs, file = dirs[:-1], dirs[-1]
        if dirs and not dirs[0]:
            dirs = dirs[1:]
        user = passwd = '' # XXX
        try:
            fw = self.connect_ftp(user, passwd, host, port, dirs)
            type = file and 'I' or 'D'
            for attr in attrs:
                attr, value = splitattr(attr)
                if attr.lower() == 'type' and \
                   value in ('a', 'A', 'i', 'I', 'd', 'D'):
                    type = value.upper()
            fp, retrlen = fw.retrfile(file, type)
            headers = ""
            mtype = mimetypes.guess_type(req.get_full_url())[0]
            if mtype:
                headers += "Content-Type: %s\n" % mtype
            if retrlen is not None and retrlen >= 0:
                headers += "Content-Length: %d\n" % retrlen
            sf = StringIO(headers)
            headers = mimetools.Message(sf)
            return addinfourl(fp, headers, req.get_full_url())
        except ftplib.all_errors(msg):
            raise IOError(('ftp error', msg), sys.exc_info()[2]) 

def save_file(self, obj):
        """Save a file"""
        try:
            import StringIO as pystringIO  # we can't use cStringIO as it lacks the name attribute
        except ImportError:
            import io as pystringIO

        if not hasattr(obj, 'name') or not hasattr(obj, 'mode'):
            raise pickle.PicklingError("Cannot pickle files that do not map to an actual file")
        if obj is sys.stdout:
            return self.save_reduce(getattr, (sys, 'stdout'), obj=obj)
        if obj is sys.stderr:
            return self.save_reduce(getattr, (sys, 'stderr'), obj=obj)
        if obj is sys.stdin:
            raise pickle.PicklingError("Cannot pickle standard input")
        if obj.closed:
            raise pickle.PicklingError("Cannot pickle closed files")
        if hasattr(obj, 'isatty') and obj.isatty():
            raise pickle.PicklingError("Cannot pickle files that map to tty objects")
        if 'r' not in obj.mode and '+' not in obj.mode:
            raise pickle.PicklingError("Cannot pickle files that are not opened for reading: %s" % obj.mode)

        name = obj.name

        retval = pystringIO.StringIO()

        try:
            # Read the whole file
            curloc = obj.tell()
            obj.seek(0)
            contents = obj.read()
            obj.seek(curloc)
        except IOError:
            raise pickle.PicklingError("Cannot pickle file %s as it cannot be read" % name)
        retval.write(contents)
        retval.seek(curloc)

        retval.name = name
        self.save(retval)
        self.memoize(obj) 

def csv(self, delimiter=','):
		"""Return data in CSV format"""

		data = self.dict()
		out = StringIO()
		writer = csv.writer(out, delimiter=delimiter, lineterminator='')
		writer.writerow([data['server']['id'], data['server']['sponsor'],
						 data['server']['name'], data['timestamp'],
						 data['server']['d'], data['ping'], data['download'],
						 data['upload']])
		return out.getvalue() 

def _create_data(self):
		chars = '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ'
		multiplier = int(round(int(self.length) / 36.0))
		IO = BytesIO or StringIO
		self._data = IO(
			('content1=%s' %
			 (chars * multiplier)[0:int(self.length) - 9]
			 ).encode()
		) 

def __init__(self, name, value):
        """Constructor from field name and value."""
        self.name = name
        self.value = value
        # self.file = StringIO(value) 

def read_lines(self):
        """Internal: read lines until EOF or outerboundary."""
        self.file = self.__file = StringIO()
        if self.outerboundary:
            self.read_lines_to_outerboundary()
        else:
            self.read_lines_to_eof() 

def __init__(self, name, value):
        """Constructor from field name and value."""
        self.name = name
        self.value = value
        # self.file = StringIO(value) 

def check_nb_pages(self, data):
        """
        Does this PDF contain enough pages?
        """
        try:
            s_io = StringIO(data)
            reader = PyPDF2.PdfFileReader(s_io)
            num_pages = reader.getNumPages()
            print("num pages: %d" % num_pages)
            return num_pages > 2
        except PyPdfError as e:
            return False 

def open_string(self, s):
        """Open a standard format marker string for sequential reading. 
        
        @param s: string to parse as a standard format marker input file
        @type s: string
        """
        self._file = StringIO(s) 

def load_exclusion_list_from_string(self, string):
    exc_in = StringIO.StringIO(string)
    self.load_exclusion_list(exc_in) 

def load_dictionary_from_string(self, string):
    rid_in = StringIO.StringIO(string)
    self.load_dictionary(rid_in)