def get_file_infos(location):
"""
Return a list of dictionaries of informations collected from the file or
directory at location.
"""
from commoncode import fileutils
from commoncode import filetype
from commoncode.hash import sha1, md5
from typecode import contenttype
T = contenttype.get_type(location)
is_file = T.is_file
is_dir = T.is_dir
infos = OrderedDict()
infos['type'] = filetype.get_type(location, short=False)
infos['name'] = fileutils.file_name(location)
infos['extension'] = is_file and fileutils.file_extension(location) or ''
infos['date'] = is_file and filetype.get_last_modified_date(
location) or None
infos['size'] = T.size
infos['sha1'] = is_file and sha1(location) or None
infos['md5'] = is_file and md5(location) or None
infos['files_count'] = is_dir and filetype.get_file_count(location) or None
infos['mime_type'] = is_file and T.mimetype_file or None
infos['file_type'] = is_file and T.filetype_file or None
infos['programming_language'] = is_file and T.programming_language or None
infos['is_binary'] = is_file and T.is_binary or None
infos['is_text'] = is_file and T.is_text or None
infos['is_archive'] = is_file and T.is_archive or None
infos['is_media'] = is_file and T.is_media or None
infos['is_source'] = is_file and T.is_source or None
infos['is_script'] = is_file and T.is_script or None
return [infos]
def get_file_info(location, **kwargs):
"""
Return a mapping of file information collected for the file at `location`.
"""
result = OrderedDict()
# TODO: move date and size these to the inventory collection step???
result['date'] = get_last_modified_date(location) or None
result['size'] = getsize(location) or 0
sha1, md5, sha256 = multi_checksums(location, ('sha1', 'md5', 'sha256')).values()
result['sha1'] = sha1
result['md5'] = md5
result['sha256'] = sha256
collector = get_type(location)
result['mime_type'] = collector.mimetype_file or None
result['file_type'] = collector.filetype_file or None
result['programming_language'] = collector.programming_language or None
result['is_binary'] = bool(collector.is_binary)
result['is_text'] = bool(collector.is_text)
result['is_archive'] = bool(collector.is_archive)
result['is_media'] = bool(collector.is_media)
result['is_source'] = bool(collector.is_source)
result['is_script'] = bool(collector.is_script)
return result
def get_file_infos(location):
"""
Return a list of dictionaries of informations collected from the file or
directory at location.
"""
from commoncode import fileutils
from commoncode import filetype
from commoncode.hash import sha1, md5
from typecode import contenttype
T = contenttype.get_type(location)
is_file = T.is_file
is_dir = T.is_dir
infos = OrderedDict()
infos['type'] = filetype.get_type(location, short=False)
infos['name'] = fileutils.file_name(location)
infos['extension'] = is_file and fileutils.file_extension(location) or ''
infos['date'] = is_file and filetype.get_last_modified_date(location) or None
infos['size'] = T.size
infos['sha1'] = is_file and sha1(location) or None
infos['md5'] = is_file and md5(location) or None
infos['files_count'] = is_dir and filetype.get_file_count(location) or None
infos['mime_type'] = is_file and T.mimetype_file or None
infos['file_type'] = is_file and T.filetype_file or None
infos['programming_language'] = is_file and T.programming_language or None
infos['is_binary'] = is_file and T.is_binary or None
infos['is_text'] = is_file and T.is_text or None
infos['is_archive'] = is_file and T.is_archive or None
infos['is_media'] = is_file and T.is_media or None
infos['is_source'] = is_file and T.is_source or None
infos['is_script'] = is_file and T.is_script or None
return [infos]
def __init__(self, location):
if (not location
or (not os.path.exists(location)
and not filetype.is_broken_link(location))):
raise IOError("[Errno 2] No such file or directory: "
"'%(location)r'" % locals())
self.location = location
# flags and values
self.is_file = filetype.is_file(location)
self.is_dir = filetype.is_dir(location)
self.is_regular = filetype.is_regular(location)
self.is_special = filetype.is_special(location)
self.date = filetype.get_last_modified_date(location)
self.is_link = filetype.is_link(location)
self.is_broken_link = filetype.is_broken_link(location)
# FIXME: the way the True and False values are checked in properties is verbose and contrived at best
# and is due to use None/True/False as different values
# computed on demand
self._size = None
self._link_target = None
self._mimetype_python = None
self._filetype_file = None
self._mimetype_file = None
self._filetype_pygments = None
self._is_pdf_with_text = None
self._is_text = None
self._is_binary = None
self._contains_text = None
def __init__(self, location):
if not location or (not os.path.exists(location) and not filetype.is_broken_link(location)):
raise IOError("[Errno 2] No such file or directory: " "'%(location)r'" % locals())
self.location = location
# flags and values
self.is_file = filetype.is_file(location)
self.is_dir = filetype.is_dir(location)
self.is_regular = filetype.is_regular(location)
self.is_special = filetype.is_special(location)
self.date = filetype.get_last_modified_date(location)
self.is_link = filetype.is_link(location)
self.is_broken_link = filetype.is_broken_link(location)
# FIXME: the way the True and False values are checked in properties is verbose and contrived at best
# and is due to use None/True/False as different values
# computed on demand
self._size = None
self._link_target = None
self._mimetype_python = None
self._filetype_file = None
self._mimetype_file = None
self._filetype_pygments = None
self._is_pdf_with_text = None
self._is_text = None
self._is_binary = None
def __init__(self, location):
if (not location
or (not os.path.exists(location)
and not filetype.is_broken_link(location))):
raise IOError("[Errno 2] No such file or directory: "
"'%(location)r'" % locals())
self.location = location
# flags and values
self.is_file = filetype.is_file(location)
self.is_dir = filetype.is_dir(location)
self.is_regular = filetype.is_regular(location)
self.is_special = filetype.is_special(location)
self.date = filetype.get_last_modified_date(location)
self.is_link = filetype.is_link(location)
self.is_broken_link = filetype.is_broken_link(location)
# computed on demand
self._size = None
self._link_target = None
self._mimetype_python = None
self._filetype_file = None
self._mimetype_file = None
self._filetype_pygments = None
self._is_pdf_with_text = None
self._is_text = None
self._is_binary = None
def get_file_infos(location):
"""
Return a mapping of file information collected from the file or
directory at `location`.
"""
from commoncode import fileutils
from commoncode import filetype
from commoncode.hash import multi_checksums
from typecode import contenttype
if on_linux:
location = path_to_bytes(location)
else:
location = path_to_unicode(location)
infos = OrderedDict()
is_file = filetype.is_file(location)
is_dir = filetype.is_dir(location)
T = contenttype.get_type(location)
infos['type'] = filetype.get_type(location, short=False)
name = fileutils.file_name(location)
if is_file:
base_name, extension = fileutils.splitext(location)
else:
base_name = name
extension = ''
if on_linux:
infos['name'] = path_to_unicode(name)
infos['base_name'] = path_to_unicode(base_name)
infos['extension'] = path_to_unicode(extension)
else:
infos['name'] = name
infos['base_name'] = base_name
infos['extension'] = extension
infos['date'] = is_file and filetype.get_last_modified_date(
location) or None
infos['size'] = T.size
infos.update(multi_checksums(location, (
'sha1',
'md5',
)))
infos['files_count'] = is_dir and filetype.get_file_count(location) or None
infos['mime_type'] = is_file and T.mimetype_file or None
infos['file_type'] = is_file and T.filetype_file or None
infos['programming_language'] = is_file and T.programming_language or None
infos['is_binary'] = bool(is_file and T.is_binary)
infos['is_text'] = bool(is_file and T.is_text)
infos['is_archive'] = bool(is_file and T.is_archive)
infos['is_media'] = bool(is_file and T.is_media)
infos['is_source'] = bool(is_file and T.is_source)
infos['is_script'] = bool(is_file and T.is_script)
return infos
def get_file_infos(location):
"""
Return a mapping of file information collected from the file or
directory at `location`.
"""
from commoncode import fileutils
from commoncode import filetype
from commoncode.hash import multi_checksums
from typecode import contenttype
if on_linux:
location = path_to_bytes(location)
else:
location = path_to_unicode(location)
infos = OrderedDict()
is_file = filetype.is_file(location)
is_dir = filetype.is_dir(location)
T = contenttype.get_type(location)
infos['type'] = filetype.get_type(location, short=False)
name = fileutils.file_name(location)
if is_file:
base_name, extension = fileutils.splitext(location)
else:
base_name = name
extension = ''
if on_linux:
infos['name'] = path_to_unicode(name)
infos['base_name'] = path_to_unicode(base_name)
infos['extension'] = path_to_unicode(extension)
else:
infos['name'] = name
infos['base_name'] = base_name
infos['extension'] = extension
infos['date'] = is_file and filetype.get_last_modified_date(location) or None
infos['size'] = T.size
infos.update(multi_checksums(location, ('sha1', 'md5',)))
infos['files_count'] = is_dir and filetype.get_file_count(location) or None
infos['mime_type'] = is_file and T.mimetype_file or None
infos['file_type'] = is_file and T.filetype_file or None
infos['programming_language'] = is_file and T.programming_language or None
infos['is_binary'] = bool(is_file and T.is_binary)
infos['is_text'] = bool(is_file and T.is_text)
infos['is_archive'] = bool(is_file and T.is_archive)
infos['is_media'] = bool(is_file and T.is_media)
infos['is_source'] = bool(is_file and T.is_source)
infos['is_script'] = bool(is_file and T.is_script)
return infos
def get_file_infos(location, as_list=True):
"""
Return a list of dictionaries of informations collected from the file or
directory at location.
"""
from commoncode import fileutils
from commoncode import filetype
from commoncode.hash import multi_checksums
from scancode import utils
from typecode import contenttype
infos = OrderedDict()
is_file = filetype.is_file(location)
is_dir = filetype.is_dir(location)
T = contenttype.get_type(location)
infos['type'] = filetype.get_type(location, short=False)
infos['name'] = fileutils.file_name(location)
infos['extension'] = is_file and fileutils.file_extension(location) or ''
infos['date'] = is_file and filetype.get_last_modified_date(
location) or None
infos['size'] = T.size
infos.update(multi_checksums(location, (
'sha1',
'md5',
)))
infos['files_count'] = is_dir and filetype.get_file_count(location) or None
infos['mime_type'] = is_file and T.mimetype_file or None
infos['file_type'] = is_file and T.filetype_file or None
infos['programming_language'] = is_file and T.programming_language or None
infos['is_binary'] = bool(is_file and T.is_binary)
infos['is_text'] = bool(is_file and T.is_text)
infos['is_archive'] = bool(is_file and T.is_archive)
infos['is_media'] = bool(is_file and T.is_media)
infos['is_source'] = bool(is_file and T.is_source)
infos['is_script'] = bool(is_file and T.is_script)
if as_list:
return [infos]
else:
return infos
