def run_print():
"""This is called from test_read* tests as script. Prints & logs unicode"""
from oletools.common.io_encoding import ensure_stdout_handles_unicode
from oletools.common.log_helper import log_helper
ensure_stdout_handles_unicode()
print(u'Check: \u2713') # print check mark
# check logging as well
logger = log_helper.get_or_create_silent_logger('test_encoding_handler')
log_helper.enable_logging(False, 'debug', stream=sys.stdout)
logger.info(u'Check: \u2713')
return 0
def preread_file(args):
"""helper for TestOleObj.test_non_streamed: preread + call process_file"""
ensure_stdout_handles_unicode() # usually, main() call this
ignore_arg, output_dir, filename = args
if ignore_arg != '-d':
raise ValueError('ignore_arg not as expected!')
with open(filename, 'rb') as file_handle:
data = file_handle.read()
err_stream, err_dumping, did_dump = \
oleobj.process_file(filename, data, output_dir=output_dir)
if did_dump and not err_stream and not err_dumping:
return oleobj.RETURN_DID_DUMP
else:
return oleobj.RETURN_NO_DUMP # just anything else
def process_ole(ole):
# parse and display metadata:
meta = ole.get_metadata()
# console output with UTF8 encoding:
ensure_stdout_handles_unicode()
# TODO: move similar code to a function
print('Properties from the SummaryInformation stream:')
t = tablestream.TableStream([21, 30], header_row=['Property', 'Value'])
for prop in meta.SUMMARY_ATTRIBS:
value = getattr(meta, prop)
if value is not None:
# TODO: pretty printing for strings, dates, numbers
# TODO: better unicode handling
# print('- %s: %s' % (prop, value))
# if isinstance(value, unicode):
# # encode to UTF8, avoiding errors
# value = value.encode('utf-8', errors='replace')
# else:
# value = str(value)
t.write_row([prop, value], colors=[None, 'yellow'])
t.close()
print('')
print('Properties from the DocumentSummaryInformation stream:')
t = tablestream.TableStream([21, 30], header_row=['Property', 'Value'])
for prop in meta.DOCSUM_ATTRIBS:
value = getattr(meta, prop)
if value is not None:
# TODO: pretty printing for strings, dates, numbers
# TODO: better unicode handling
# print('- %s: %s' % (prop, value))
# if isinstance(value, unicode):
# # encode to UTF8, avoiding errors
# value = value.encode('utf-8', errors='replace')
# else:
# value = str(value)
t.write_row([prop, value], colors=[None, 'yellow'])
t.close()
def main(cmd_line_args=None):
""" main function, called when running this as script
Per default (cmd_line_args=None) uses sys.argv. For testing, however, can
provide other arguments.
"""
# print banner with version
ensure_stdout_handles_unicode()
print('oleobj %s - http://decalage.info/oletools' % __version__)
print('THIS IS WORK IN PROGRESS - Check updates regularly!')
print('Please report any issue at '
'https://github.com/decalage2/oletools/issues')
print('')
usage = 'usage: %(prog)s [options] <filename> [filename2 ...]'
parser = argparse.ArgumentParser(usage=usage)
# parser.add_argument('-o', '--outfile', dest='outfile',
# help='output file')
# parser.add_argument('-c', '--csv', dest='csv',
# help='export results to a CSV file')
parser.add_argument("-r",
action="store_true",
dest="recursive",
help='find files recursively in subdirectories.')
parser.add_argument("-d",
type=str,
dest="output_dir",
default=None,
help='use specified directory to output files.')
parser.add_argument("-z",
"--zip",
dest='zip_password',
type=str,
default=None,
help='if the file is a zip archive, open first file '
'from it, using the provided password (requires '
'Python 2.6+)')
parser.add_argument("-f",
"--zipfname",
dest='zip_fname',
type=str,
default='*',
help='if the file is a zip archive, file(s) to be '
'opened within the zip. Wildcards * and ? are '
'supported. (default:*)')
parser.add_argument('-l',
'--loglevel',
dest="loglevel",
action="store",
default=DEFAULT_LOG_LEVEL,
help='logging level debug/info/warning/error/critical '
'(default=%(default)s)')
parser.add_argument('input',
nargs='*',
type=existing_file,
metavar='FILE',
help='Office files to parse (same as -i)')
# options for compatibility with ripOLE
parser.add_argument('-i',
'--more-input',
type=str,
metavar='FILE',
help='Additional file to parse (same as positional '
'arguments)')
parser.add_argument('-v',
'--verbose',
action='store_true',
help='verbose mode, set logging to DEBUG '
'(overwrites -l)')
options = parser.parse_args(cmd_line_args)
if options.more_input:
options.input += [
options.more_input,
]
if options.verbose:
options.loglevel = 'debug'
# Print help if no arguments are passed
if not options.input:
parser.print_help()
return RETURN_ERR_ARGS
# Setup logging to the console:
# here we use stdout instead of stderr by default, so that the output
# can be redirected properly.
logging.basicConfig(level=LOG_LEVELS[options.loglevel],
stream=sys.stdout,
format='%(levelname)-8s %(message)s')
# enable logging in the modules:
log.setLevel(logging.NOTSET)
if options.loglevel == 'debug-olefile':
olefile.enable_logging()
# remember if there was a problem and continue with other data
any_err_stream = False
any_err_dumping = False
any_did_dump = False
for container, filename, data in \
xglob.iter_files(options.input, recursive=options.recursive,
zip_password=options.zip_password,
zip_fname=options.zip_fname):
# ignore directory names stored in zip files:
if container and filename.endswith('/'):
continue
err_stream, err_dumping, did_dump = \
process_file(filename, data, options.output_dir)
any_err_stream |= err_stream
any_err_dumping |= err_dumping
any_did_dump |= did_dump
# assemble return value
return_val = RETURN_NO_DUMP
if any_did_dump:
return_val += RETURN_DID_DUMP
if any_err_stream:
return_val += RETURN_ERR_STREAM
if any_err_dumping:
return_val += RETURN_ERR_DUMP
return return_val
def process_output(meta, output):
# console output with UTF8 encoding:
ensure_stdout_handles_unicode()
# TODO: move similar code to a function
if output == 'table':
print('Properties from the SummaryInformation stream:')
t = tablestream.TableStream([21, 30], header_row=['Property', 'Value'])
for prop in meta.SUMMARY_ATTRIBS:
value = getattr(meta, prop)
if value is not None:
# TODO: pretty printing for strings, dates, numbers
# TODO: better unicode handling
# print('- %s: %s' % (prop, value))
# if isinstance(value, unicode):
# # encode to UTF8, avoiding errors
# value = value.encode('utf-8', errors='replace')
# else:
# value = str(value)
t.write_row([prop, value], colors=[None, 'yellow'])
t.close()
print('')
print('Properties from the DocumentSummaryInformation stream:')
t = tablestream.TableStream([21, 30], header_row=['Property', 'Value'])
for prop in meta.DOCSUM_ATTRIBS:
value = getattr(meta, prop)
if value is not None:
# TODO: pretty printing for strings, dates, numbers
# TODO: better unicode handling
# print('- %s: %s' % (prop, value))
# if isinstance(value, unicode):
# # encode to UTF8, avoiding errors
# value = value.encode('utf-8', errors='replace')
# else:
# value = str(value)
t.write_row([prop, value], colors=[None, 'yellow'])
t.close()
else:
# initalize a dictionary with keys for each type of attribute
# update props/values like the table would
output_dict = {"SUMMARY_ATTRIBS": {}, "DOCSUM_ATTRIBS": {}}
for prop in meta.SUMMARY_ATTRIBS:
value = getattr(meta, prop)
if value:
value = clean_output(value)
output_dict['SUMMARY_ATTRIBS'][prop] = value
else:
# pass for now, when logging is enabled log as warning
# logger.warning("Unable to log {}: {}".format(prop, value))
pass
for prop in meta.DOCSUM_ATTRIBS:
value = getattr(meta, prop)
if value:
value = clean_output(value)
output_dict['DOCSUM_ATTRIBS'][prop] = value
else:
# pass for now, when logging is enabled log as warning
# logger.warning("Unable to log {}: {}".format(prop, value))
pass
return output_dict
