Example #1
0
def filetype(filename):
    """Try to guess the type of the file."""
    if os.path.isdir(filename):
        # Potentially a BundleTrajectory
        if BundleTrajectory.is_bundle(filename):
            return 'bundle'
        elif os.path.normpath(filename) == 'states':
            return 'eon'
        else:
            raise IOError('Directory: ' + filename)

    if filename.startswith('pg://'):
        return 'postgresql'

    fileobj = open(filename, 'rU')
    s3 = fileobj.read(3)
    if len(s3) == 0:
        raise IOError('Empty file: ' + filename)

    if s3.startswith('{"'):
        return 'json'

    if filename.endswith('.db'):
        return 'db'

    if filename.lower().endswith('.cmr'):
        return 'cmr'

    if is_tarfile(filename):
        return 'gpw'

    if s3 == 'CDF':
        from ase.io.pupynere import NetCDFFile
        nc = NetCDFFile(filename)
        if 'number_of_dynamic_atoms' in nc.dimensions:
            return 'dacapo'

        history = nc.history
        if history == 'GPAW restart file':
            return 'gpw-nc'
        if history == 'ASE trajectory':
            return 'nc'
        if history == 'Dacapo':
            return 'dacapo'
        if hasattr(nc, 'file_format') and nc.file_format.startswith('ETSF'):
            return 'etsf'
        raise IOError('Unknown netCDF file!')

    if is_zipfile(filename):
        return 'vnl'

    fileobj.seek(0)
    lines = fileobj.readlines(1000)

    if lines[0].startswith('PickleTrajectory'):
        return 'traj'

    if (lines[1].startswith('OUTER LOOP:')
            or filename.lower().endswith('.cube')):
        return 'cube'

    if '  ___ ___ ___ _ _ _  \n' in lines:
        return 'gpaw-text'

    if (' &&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&\n'
            in lines[:90]):
        return 'dacapo-text'

    for line in lines:
        if line[0] != '#':
            word = line.strip()
            if word in ['ANIMSTEPS', 'CRYSTAL', 'SLAB', 'POLYMER', 'MOLECULE']:
                return 'xsf'

    filename_v = os.path.basename(filename)
    if 'POSCAR' in filename_v or 'CONTCAR' in filename_v:
        return 'vasp'

    if 'OUTCAR' in filename_v:
        return 'vasp_out'

    if filename.lower().endswith('.exi'):
        return 'exi'

    if filename.lower().endswith('.mol'):
        return 'mol'

    if filename.lower().endswith('.pdb'):
        return 'pdb'

    if filename.lower().endswith('.cif'):
        return 'cif'

    if filename.lower().endswith('.struct'):
        return 'struct'

    if filename.lower().endswith('.struct_out'):
        return 'struct_out'

    fileobj.seek(0)
    while True:
        line = fileobj.readline()
        if not line:
            break
        if 'Invoking FHI-aims ...' in line:
            return 'aims_out'
        if 'atom' in line:
            data = line.split()
            try:
                Atoms(symbols=[data[4]],
                      positions=[[
                          float(data[1]),
                          float(data[2]),
                          float(data[3])
                      ]])
                return 'aims'
            except:
                pass

    if filename.lower().endswith('.in'):
        fileobj.seek(0)
        while True:
            line = fileobj.readline()
            if not line:
                break
            if ('&system' in line) or ('&SYSTEM' in line):
                return 'esp_in'
        return 'aims'

    if filename.lower().endswith('.cfg'):
        return 'cfg'

    if os.path.split(filename)[1] == 'atoms.dat':
        return 'iwm'

    if filename.endswith('I_info'):
        return 'Cmdft'

    if lines[0].startswith('$coord') or os.path.basename(filename) == 'coord':
        return 'tmol'

    if (lines[0].startswith('$grad')
            or os.path.basename(filename) == 'gradient'):
        return 'tmol-gradient'

    if lines[0].startswith('Geometry'):
        return 'dftb'

    if filename.lower().endswith('.geom'):
        return 'castep_geom'

    if filename.lower().endswith('.castep'):
        return 'castep'

    if filename.lower().endswith('.cell'):
        return 'castep_cell'
    if s3 == '<?x':
        from ase.io.vtkxml import probe_vtkxml
        xmltype = probe_vtkxml(filename)
        if xmltype == 'ImageData':
            return 'vti'
        elif xmltype == 'StructuredGrid':
            return 'vts'
        elif xmltype == 'UnstructuredGrid':
            return 'vtu'
        elif xmltype is not None:
            raise IOError('Unknown VTK XML file!')

    if filename.lower().endswith('.sdf'):
        return 'sdf'

    if filename.lower().endswith('.gen'):
        return 'gen'

    if filename.lower().endswith('.con'):
        return 'eon'

    if 'ITEM: TIMESTEP\n' in lines:
        return 'lammps'

    if filename.lower().endswith('.gro'):
        return 'gromacs'

    if filename.lower().endswith('.log'):
        return 'gaussian_out'

    if filename.lower().endswith('.com'):
        return 'gaussian'

    if filename.lower().endswith('.g96'):
        return 'gromos'

    if filename.lower().endswith('.out'):
        return 'esp_out'

    if filename.endswith('.nw'):
        return 'nw'

    return 'xyz'
Example #2
0
def filetype(filename):
    """Try to guess the type of the file."""
    if os.path.isdir(filename):
        # Potentially a BundleTrajectory
        if BundleTrajectory.is_bundle(filename):
            return 'bundle'
        else:
            raise IOError('Directory: ' + filename)

    fileobj = open(filename)
    s3 = fileobj.read(3)
    if len(s3) == 0:
        raise IOError('Empty file: ' + filename)

    if is_tarfile(filename):
        return 'gpw'

    if s3 == 'CDF':
        from ase.io.pupynere import NetCDFFile
        nc = NetCDFFile(filename)
        if 'number_of_dynamic_atoms' in nc.dimensions:
            return 'dacapo'

        history = nc.history
        if history == 'GPAW restart file':
            return 'gpw-nc'
        if history == 'ASE trajectory':
            return 'nc'
        if history == 'Dacapo':
            return 'dacapo'
        if hasattr(nc, 'file_format') and nc.file_format.startswith('ETSF'):
            return 'etsf'
        raise IOError('Unknown netCDF file!')

    if is_zipfile(filename):
        return 'vnl'

    fileobj.seek(0)
    lines = fileobj.readlines(1000)

    if lines[0].startswith('PickleTrajectory'):
        return 'traj'

    if lines[1].startswith('OUTER LOOP:') or filename.lower().endswith(
            '.cube'):
        return 'cube'

    if '  ___ ___ ___ _ _ _  \n' in lines:
        return 'gpaw-text'

    if (' &&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&\n'
            in lines[:90]):
        return 'dacapo-text'

    for line in lines:
        if line[0] != '#':
            word = line.strip()
            if word in ['ANIMSTEPS', 'CRYSTAL', 'SLAB', 'POLYMER', 'MOLECULE']:
                return 'xsf'

    filename_v = basename(filename)
    if 'POSCAR' in filename_v or 'CONTCAR' in filename_v:
        return 'vasp'

    if 'OUTCAR' in filename_v:
        return 'vasp_out'

    if filename.lower().endswith('.exi'):
        return 'exi'

    if filename.lower().endswith('.mol'):
        return 'mol'

    if filename.lower().endswith('.pdb'):
        return 'pdb'

    if filename.lower().endswith('.cif'):
        return 'cif'

    if filename.lower().endswith('.struct'):
        return 'struct'

    if filename.lower().endswith('.in'):
        return 'aims'

    if filename.lower().endswith('.out'):
        return 'aims_out'

    if filename.lower().endswith('.cfg'):
        return 'cfg'

    if os.path.split(filename)[1] == 'atoms.dat':
        return 'iwm'

    if filename.endswith('I_info'):
        return 'Cmdft'

    if lines[0].startswith('$coord'):
        return 'tmol'

    if lines[0].startswith('Geometry'):
        return 'dftb'

    if s3 == '<?x':
        from ase.io.vtkxml import probe_vtkxml
        xmltype = probe_vtkxml(filename)
        if xmltype == 'ImageData':
            return 'vti'
        elif xmltype == 'StructuredGrid':
            return 'vts'
        elif xmltype == 'UnstructuredGrid':
            return 'vtu'
        elif xmltype is not None:
            raise IOError('Unknown VTK XML file!')

    if filename.lower().endswith('.sdf'):
        return 'sdf'

    return 'xyz'
Example #3
0
def filetype(filename):
    """Try to guess the type of the file."""
    if os.path.isdir(filename):
        # Potentially a BundleTrajectory
        if BundleTrajectory.is_bundle(filename):
            return 'bundle'
        elif os.path.normpath(filename) == 'states':
            return 'eon'
        else:
            raise IOError('Directory: ' + filename)

    if filename.startswith('pg://'):
        return 'postgresql'

    fileobj = open(filename, 'rb')
    s3 = fileobj.read(3)
    if len(s3) == 0:
        raise IOError('Empty file: ' + filename)

    if s3.startswith(b'{"'):
        return 'json'

    if filename.endswith('.db'):
        return 'db'

    if filename.lower().endswith('.cmr'):
        return 'cmr'

    if is_tarfile(filename):
        return 'gpw'

    if s3 == 'CDF':
        from ase.io.pupynere import NetCDFFile
        nc = NetCDFFile(filename)
        if 'number_of_dynamic_atoms' in nc.dimensions:
            return 'dacapo'

        history = nc.history
        if history == 'GPAW restart file':
            return 'gpw-nc'
        if history == 'ASE trajectory':
            return 'nc'
        if history == 'Dacapo':
            return 'dacapo'
        if hasattr(nc, 'file_format') and nc.file_format.startswith('ETSF'):
            return 'etsf'
        raise IOError('Unknown netCDF file!')

    if is_zipfile(filename):
        return 'vnl'

    fileobj.seek(0)
    lines = fileobj.readlines(1000)
    if lines[0].startswith(b'AFFormatASE-Trajectory'):
        return 'traj'
    if lines[0].startswith(b'PickleTrajectory'):
        return 'trj'

    if (lines[1].startswith(b'OUTER LOOP:') or
        filename.lower().endswith('.cube')):
        return 'cube'

    if b'  ___ ___ ___ _ _ _  \n' in lines:
        return 'gpaw-text'

    if (b' &&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&\n'
        in lines[:90]):
        return 'dacapo-text'

    for line in lines:
        if line[0] != b'#':
            word = line.strip()
            if word in ['ANIMSTEPS', 'CRYSTAL', 'SLAB', 'POLYMER', 'MOLECULE']:
                return 'xsf'

    filename_v = os.path.basename(filename)
    if 'POSCAR' in filename_v or 'CONTCAR' in filename_v:
        return 'vasp'

    if 'OUTCAR' in filename_v:
        return 'vasp_out'

    if 'XDATCAR' in filename_v:
        return 'vasp_xdatcar'

    if filename.lower().endswith('.exi'):
        return 'exi'

    if filename.lower().endswith('.mol'):
        return 'mol'

    if filename.lower().endswith('.pdb'):
        return 'pdb'

    if filename.lower().endswith('.cif'):
        return 'cif'

    if filename.lower().endswith('.struct'):
        return 'struct'

    if filename.lower().endswith('.struct_out'):
        return 'struct_out'

    fileobj.seek(0)
    while True:
        line = fileobj.readline()
        if not line:
            break
        if b'Invoking FHI-aims ...' in line:
            return 'aims_out'
        if b'atom' in line:
            data = line.split()
            try:
                Atoms(symbols=[data[4]],
                      positions=[[float(data[1]),
                                  float(data[2]),
                                  float(data[3])]])
                return 'aims'
            except:
                pass

    if filename.lower().endswith('.in'):
        fileobj.seek(0)
        while True:
            line = fileobj.readline()
            if not line:
                break
            if ('&system' in line) or ('&SYSTEM' in line):
                return 'esp_in'
        return 'aims'

    if filename.lower().endswith('.cfg'):
        return 'cfg'

    if os.path.split(filename)[1] == 'atoms.dat':
        return 'iwm'

    if filename.endswith('I_info'):
        return 'Cmdft'

    if lines[0].startswith(b'$coord') or os.path.basename(filename) == 'coord':
        return 'tmol'

    if (lines[0].startswith(b'$grad') or
        os.path.basename(filename) == 'gradient'):
        return 'tmol-gradient'

    if lines[0].startswith(b'Geometry'):
        return 'dftb'

    if filename.lower().endswith('.geom'):
        return 'castep_geom'

    if filename.lower().endswith('.castep'):
        return 'castep'

    if filename.lower().endswith('.cell'):
        return 'castep_cell'
    if s3 == '<?x' and not filename.endswith('xsd'):
        from ase.io.vtkxml import probe_vtkxml
        xmltype = probe_vtkxml(filename)
        if xmltype == 'ImageData':
            return 'vti'
        elif xmltype == 'StructuredGrid':
            return 'vts'
        elif xmltype == 'UnstructuredGrid':
            return 'vtu'
        elif xmltype is not None:
            raise IOError('Unknown VTK XML file!')

    if filename.lower().endswith('.sdf'):
        return 'sdf'

    if filename.lower().endswith('.gen'):
        return 'gen'

    if filename.lower().endswith('.con'):
        return 'eon'

    if 'ITEM: TIMESTEP\n' in lines:
        return 'lammps'

    if filename.lower().endswith('.gro'):
        return 'gromacs'

    if filename.lower().endswith('.log'):
        return 'gaussian_out'

    if filename.lower().endswith('.com'):
        return 'gaussian'

    if filename.lower().endswith('.g96'):
        return 'gromos'

    if filename.lower().endswith('.out'):
        return 'esp_out'

    if filename.endswith('.nw'):
        return 'nw'

    if filename.endswith('xsd'):
        return 'xsd'

    return 'xyz'
Example #4
0
def filetype(filename):
    """Try to guess the type of the file."""
    fileobj = open(filename)
    s3 = fileobj.read(3)
    if len(s3) == 0:
        raise IOError('Empty file: ' + filename)
    
    if is_tarfile(filename):
        return 'gpw'

    if s3 == 'CDF':
        from ase.io.pupynere import NetCDFFile
        nc = NetCDFFile(filename)
        if 'number_of_dynamic_atoms' in nc.dimensions:
            return 'dacapo'

        history = nc.history
        if history == 'GPAW restart file':
            return 'gpw-nc'
        if history == 'ASE trajectory':
            return 'nc'
        if history == 'Dacapo':
            return 'dacapo'
        raise IOError('Unknown netCDF file!')

    if s3 == '<?x':
        from ase.io.vtkxml import probe_vtkxml
        xmltype = probe_vtkxml(filename)
        if xmltype == 'ImageData':
            return 'vti'
        elif xmltype == 'StructuredGrid':
            return 'vts'
        elif xmltype == 'UnstructuredGrid':
            return 'vtu'
        elif xmltype is not None:
            raise IOError('Unknown VTK XML file!')

    if is_zipfile(filename):
        return 'vnl'

    fileobj.seek(0)
    lines = fileobj.readlines(1000)

    if lines[0].startswith('PickleTrajectory'):
        return 'traj'

    if lines[1].startswith('OUTER LOOP:') or filename.lower().endswith('.cube'):
        return 'cube'
    
    if '  ___ ___ ___ _ _ _  \n' in lines:
        return 'gpaw-text'

    if (' &&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&\n'
        in lines[:90]):
        return 'dacapo-text'

    for word in ['ANIMSTEPS', 'CRYSTAL', 'SLAB', 'POLYMER', 'MOLECULE']:
        if lines[0].startswith(word):
            return 'xsf'

    filename_v = basename(filename) 
    if 'POSCAR' in filename_v or 'CONTCAR' in filename_v:
        return 'vasp'    

    if filename.lower().endswith('.mol'):
        return 'mol'

    if filename.lower().endswith('.pdb'):
        return 'pdb'

    if filename.lower().endswith('.cif'):
        return 'cif'

    if os.path.split(filename)[1] == 'atoms.dat':
        return 'iwm'

    if filename.endswith('I_info'):
        return 'Cmdft'

    return 'xyz'