def export_to_file(self,
aChunkSize=0,
filename=None,
target_mime=None,
target_extension=None,
ignore_conversion_problems=False,
directory=None):
if self._payload[self._idx['size']] == 0:
return None
if filename is None:
filename = self.get_useful_filename(make_unique=True,
directory=directory)
success = gmPG2.bytea2file(data_query={
'cmd':
u'SELECT substring(data from %(start)s for %(size)s) FROM blobs.doc_obj WHERE pk=%(pk)s',
'args': {
'pk': self.pk_obj
}
},
filename=filename,
chunk_size=aChunkSize,
data_size=self._payload[self._idx['size']])
if not success:
return None
if target_mime is None:
return filename
if target_extension is None:
target_extension = gmMimeLib.guess_ext_by_mimetype(
mimetype=target_mime)
target_path, name = os.path.split(filename)
name, tmp = os.path.splitext(name)
target_fname = gmTools.get_unique_filename(prefix='%s-converted-' %
name,
suffix=target_extension)
_log.debug('attempting conversion: [%s] -> [<%s>:%s]', filename,
target_mime, target_fname)
if gmMimeLib.convert_file(filename=filename,
target_mime=target_mime,
target_filename=target_fname):
return target_fname
_log.warning('conversion failed')
if not ignore_conversion_problems:
return None
_log.warning(
'programmed to ignore conversion problems, hoping receiver can handle [%s]',
filename)
return filename
def save_to_file(self, aChunkSize=0, filename=None, target_mime=None, target_extension=None, ignore_conversion_problems=False, directory=None, adjust_extension=False, conn=None):
if self._payload[self._idx['size']] == 0:
return None
if filename is None:
filename = self.get_useful_filename(make_unique = True, directory = directory)
success = gmPG2.bytea2file (
data_query = {
'cmd': 'SELECT substring(data from %(start)s for %(size)s) FROM blobs.doc_obj WHERE pk=%(pk)s',
'args': {'pk': self.pk_obj}
},
filename = filename,
chunk_size = aChunkSize,
data_size = self._payload[self._idx['size']],
conn = conn
)
if not success:
return None
if target_mime is None:
if filename.endswith('.dat'):
if adjust_extension:
return gmMimeLib.adjust_extension_by_mimetype(filename)
return filename
if target_extension is None:
target_extension = gmMimeLib.guess_ext_by_mimetype(mimetype = target_mime)
target_path, name = os.path.split(filename)
name, tmp = os.path.splitext(name)
target_fname = gmTools.get_unique_filename (
prefix = '%s-conv-' % name,
suffix = target_extension
)
_log.debug('attempting conversion: [%s] -> [<%s>:%s]', filename, target_mime, target_fname)
if gmMimeLib.convert_file (
filename = filename,
target_mime = target_mime,
target_filename = target_fname
):
return target_fname
_log.warning('conversion failed')
if not ignore_conversion_problems:
return None
if filename.endswith('.dat'):
if adjust_extension:
filename = gmMimeLib.adjust_extension_by_mimetype(filename)
_log.warning('programmed to ignore conversion problems, hoping receiver can handle [%s]', filename)
return filename
def save_to_file(self,
aChunkSize=0,
target_mime=None,
target_extension=None,
ignore_conversion_problems=False):
if self._payload[self._idx['is_textual']]:
return None
if self._payload[self._idx['data_size']] == 0:
return None
filename = gmTools.get_unique_filename(prefix='gm-data_snippet-')
success = gmPG2.bytea2file(data_query={
'cmd':
'SELECT substring(binary_data from %(start)s for %(size)s) FROM ref.keyword_expansion WHERE pk = %(pk)s',
'args': {
'pk': self.pk_obj
}
},
filename=filename,
chunk_size=aChunkSize,
data_size=self._payload[
self._idx['data_size']])
if not success:
return None
if target_mime is None:
return filename
if target_extension is None:
target_extension = gmMimeLib.guess_ext_by_mimetype(
mimetype=target_mime)
target_fname = gmTools.get_unique_filename(
prefix='gm-data_snippet-converted-', suffix=target_extension)
_log.debug('attempting conversion: [%s] -> [<%s>:%s]', filename,
target_mime, target_fname)
if gmMimeLib.convert_file(filename=filename,
target_mime=target_mime,
target_filename=target_fname):
return target_fname
_log.warning('conversion failed')
if not ignore_conversion_problems:
return None
_log.warning(
'programmed to ignore conversion problems, hoping receiver can handle [%s]',
filename)
return filename
def export_to_file(
self,
aChunkSize=0,
filename=None,
target_mime=None,
target_extension=None,
ignore_conversion_problems=False,
directory=None,
):
if self._payload[self._idx["size"]] == 0:
return None
if filename is None:
filename = self.get_useful_filename(make_unique=True, directory=directory)
success = gmPG2.bytea2file(
data_query={
"cmd": u"SELECT substring(data from %(start)s for %(size)s) FROM blobs.doc_obj WHERE pk=%(pk)s",
"args": {"pk": self.pk_obj},
},
filename=filename,
chunk_size=aChunkSize,
data_size=self._payload[self._idx["size"]],
)
if not success:
return None
if target_mime is None:
return filename
if target_extension is None:
target_extension = gmMimeLib.guess_ext_by_mimetype(mimetype=target_mime)
target_path, name = os.path.split(filename)
name, tmp = os.path.splitext(name)
target_fname = gmTools.get_unique_filename(prefix="%s-converted-" % name, suffix=target_extension)
_log.debug("attempting conversion: [%s] -> [<%s>:%s]", filename, target_mime, target_fname)
if gmMimeLib.convert_file(filename=filename, target_mime=target_mime, target_filename=target_fname):
return target_fname
_log.warning("conversion failed")
if not ignore_conversion_problems:
return None
_log.warning("programmed to ignore conversion problems, hoping receiver can handle [%s]", filename)
return filename
def export_to_file(self, aChunkSize=0, target_mime=None, target_extension=None, ignore_conversion_problems=False):
if self._payload[self._idx['is_textual']]:
return None
if self._payload[self._idx['data_size']] == 0:
return None
filename = gmTools.get_unique_filename(prefix = 'gm-data_snippet-')
success = gmPG2.bytea2file (
data_query = {
'cmd': u'SELECT substring(binary_data from %(start)s for %(size)s) FROM ref.keyword_expansion WHERE pk = %(pk)s',
'args': {'pk': self.pk_obj}
},
filename = filename,
chunk_size = aChunkSize,
data_size = self._payload[self._idx['data_size']]
)
if not success:
return None
if target_mime is None:
return filename
if target_extension is None:
target_extension = gmMimeLib.guess_ext_by_mimetype(mimetype = target_mime)
target_fname = gmTools.get_unique_filename (
prefix = 'gm-data_snippet-converted-',
suffix = target_extension
)
_log.debug('attempting conversion: [%s] -> [<%s>:%s]', filename, target_mime, target_fname)
if gmMimeLib.convert_file (
filename = filename,
target_mime = target_mime,
target_filename = target_fname
):
return target_fname
_log.warning('conversion failed')
if not ignore_conversion_problems:
return None
_log.warning('programmed to ignore conversion problems, hoping receiver can handle [%s]', filename)
return filename
def save_to_file(self, aChunkSize=0, filename=None, target_mime=None, target_extension=None, ignore_conversion_problems=False, directory=None, adjust_extension=False, conn=None):
if filename is None:
filename = self.get_useful_filename(make_unique = True, directory = directory)
filename = self.__download_to_file(filename = filename)
if filename is None:
return None
if target_mime is None:
if filename.endswith('.dat'):
if adjust_extension:
return gmMimeLib.adjust_extension_by_mimetype(filename)
return filename
if target_extension is None:
target_extension = gmMimeLib.guess_ext_by_mimetype(mimetype = target_mime)
target_path, name = os.path.split(filename)
name, tmp = os.path.splitext(name)
target_fname = gmTools.get_unique_filename (
prefix = '%s-conv-' % name,
suffix = target_extension
)
_log.debug('attempting conversion: [%s] -> [<%s>:%s]', filename, target_mime, target_fname)
converted_fname = gmMimeLib.convert_file (
filename = filename,
target_mime = target_mime,
target_filename = target_fname
)
if converted_fname is not None:
return converted_fname
_log.warning('conversion failed')
if not ignore_conversion_problems:
return None
if filename.endswith('.dat'):
if adjust_extension:
filename = gmMimeLib.adjust_extension_by_mimetype(filename)
_log.warning('programmed to ignore conversion problems, hoping receiver can handle [%s]', filename)
return filename
def check_mimetypes_in_archive():
mimetypes = {}
cmd = 'SELECT pk FROM blobs.doc_med'
doc_pks, idx = gmPG2.run_ro_queries(queries = [{'cmd': cmd}])
print('Detecting mimetypes in document archive ...')
doc_idx = 0
part_count = 0
for pk_row in doc_pks:
doc_idx += 1
print('\n#%s - document %s of %s: ' % (pk_row['pk'], doc_idx, len(doc_pks)), end = '')
doc = cDocument(aPK_obj = pk_row['pk'])
for part in doc.parts:
part_count += 1
print('#%s:%s bytes, ' % (part['pk_obj'], part['size']), end = '')
part_fname = part.save_to_file()
mimetype = gmMimeLib.guess_mimetype(part_fname)
try:
mimetypes[mimetype]['count'] += 1
except KeyError:
mimetypes[mimetype] = {
'count': 1,
'viewer': gmMimeLib.get_viewer_cmd(mimetype),
'editor': gmMimeLib.get_editor_cmd(mimetype),
'extension': gmMimeLib.guess_ext_by_mimetype(mimetype)
}
print('')
print('')
print('Number of documents :', len(doc_pks))
print('Number of parts :', part_count)
print('Number of mime types:', len(mimetypes))
for mimetype in mimetypes:
print('')
print('<%s>' % mimetype)
print(' Extension:', mimetypes[mimetype]['extension'])
print(' Use count:', mimetypes[mimetype]['count'])
print(' Viewer:', mimetypes[mimetype]['viewer'])
print(' Editor:', mimetypes[mimetype]['editor'])
return 0
