def pdf_do_file(afile):
try:
fid = open(afile)
except IOError:
log_error('IOError', afile)
pdf_do_pdf(fid, afile)
fid.close()
def types_data( data ):
try:
mime = magic.from_buffer(data, mime=True)
except IOError:
log_error('IOError', '_data')
return ('other', False)
return types_filter(mime)
def types_file( afile ):
try:
mime = magic.from_file(afile, mime=True)
except IOError:
log_error('IOError', afile)
return ('other', False)
return types_filter(mime)
def gz_do_file(afile):
try:
agz = gzip.GzipFile(afile)
except IOError:
log_error('IOError', afile)
return
gz_do_gz(agz, afile)
agz.close()
def zip_do_file(afile):
try:
azip = zipfile.ZipFile(afile)
except zipfile.BadZipfile:
log_error('zipfile.BadZipFile', afile)
return
zip_do_zip(azip, afile)
azip.close()
def types_file(afile):
"""guess a file's type"""
try:
mime = magic.from_file(afile, mime=True)
except IOError:
log_error('IOError', afile)
return ('other', False)
return types_find(mime, afile)
def tar_do_file(afile):
try:
atar = tarfile.open(afile)
except tarfile.TarError:
log_error('tarfile.TarError', afile)
return
tar_do_tar(atar, afile)
atar.close()
def docx_do_file(afile):
try:
azip = zipfile.ZipFile(afile)
except zipfile.BadZipfile:
log_error("zipfile.BadZipFile", afile)
return
docx_do_docx(azip, afile)
azip.close()
def docx_do_data(data, afile):
filelike = io.BytesIO(data)
try:
azip = zipfile.ZipFile(filelike)
except zipfile.BadZipfile:
log_error("zipfile.BadZipFile", afile)
return
docx_do_docx(azip, afile)
azip.close()
def zip_do_data(data, afile):
filelike = io.BytesIO(data)
try:
azip = zipfile.ZipFile(filelike)
except zipfile.BadZipfile:
log_error('zipfile.BadZipFile', afile)
return
zip_do_zip(azip, afile)
azip.close()
def tar_do_data(data, afile):
filelike = io.BytesIO(data)
try:
atar = tarfile.open(fileobj=filelike)
except tarfile.TarError:
log_error('tarfile.TarError', afile)
return
tar_do_tar(atar, afile)
atar.close()
def text_do_file(afile):
try:
fid = open(afile)
except IOError:
log_error('IOError', afile)
return
data = fid.read()
fid.close()
text_do_data(data, afile)
def gz_do_data(data, afile):
filelike = io.BytesIO(data)
try:
agz = gzip.GzipFile(fileobj=filelike)
except IOError:
log_error('IOError', afile)
return
gz_do_gz(agz, afile)
agz.close()
def rar_do_file(afile):
# fixes problems with default '\' separator
rarfile.PATH_SEP = '/'
try:
arar = rarfile.RarFile(afile)
except rarfile.BadRarFile:
log_error('rarfile.BadRarFile', afile)
return
rar_do_rar(arar, afile)
arar.close()
def types_data(data, afile=''):
"""guess an in-memory file's type
optional file name (as found in archive or decompressed)
"""
try:
mime = magic.from_buffer(data, mime=True)
except IOError:
log_error('IOError', '_data')
return ('other', False)
return types_find(mime, afile)
def gz_do_gz(agz, afile):
"""agz:GzipFile, afile:source file name"""
try:
data = agz.read()
except IOError:
log_error('IOError', afile)
return
(ftype, keep) = types_data(data)
if keep:
# strip any .gz extension
(root, ext) = os.path.splitext(afile)
if ext.lower() == '.gz':
do_data(ftype, data, afile+':'+root)
else:
do_data(ftype, data, afile)
def gz_do_gz(agz, afile):
"""agz:GzipFile, afile:source file name"""
try:
data = agz.read()
except IOError:
log_error('IOError', afile)
return
(ftype, keep) = types_data(data)
if keep:
# strip any .gz extension
(root, ext) = os.path.splitext(afile)
if ext.lower() == '.gz':
do_data(ftype, data, afile + ':' + root)
else:
do_data(ftype, data, afile)
