matthias/mayan-edms
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Support ignoring certain rows

Browse Source 
Signed-off-by: Roberto Rosario <roberto.rosario.gonzalez@gmail.com>
This commit is contained in:
Roberto Rosario
2019-06-20 10:12:53 -04:00
parent 5808d3653d
commit 925b55d76d
1 changed files with 70 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

127
mayan/apps/importer/management/commands/import.py
View File

@@ -34,6 +34,11 @@ class Command(management.BaseCommand):
help='Don\'t stop the import process on common errors like ' help='Don\'t stop the import process on common errors like '
'incorrect file paths.', 'incorrect file paths.',
) )
parser.add_argument(
'--ignore_rows',
action='store', dest='ignore_rows', default='',
help='Ignore a set of rows. Row numbers must be separated by commas.'
)
parser.add_argument( parser.add_argument(
'--metadata_pairs_column', '--metadata_pairs_column',
action='store', dest='metadata_pairs_column', action='store', dest='metadata_pairs_column',
@@ -49,6 +54,10 @@ class Command(management.BaseCommand):
document_types = {} document_types = {}
uploaded_count = 0 uploaded_count = 0
row_count = 0 row_count = 0
rows_to_ignore = []
for entry in options['ignore_rows'].split(','):
if entry:
rows_to_ignore.append(int(entry))
DocumentType = apps.get_model( DocumentType = apps.get_model(
app_label='documents', model_name='DocumentType' app_label='documents', model_name='DocumentType'
@@ -64,71 +73,75 @@ class Command(management.BaseCommand):
with open(options['filelist']) as csv_datafile: with open(options['filelist']) as csv_datafile:
csv_reader = csv.reader(csv_datafile) csv_reader = csv.reader(csv_datafile)
for row in csv_reader: for row in csv_reader:
# Increase row count here even though start index is 0
# purpose is to avoid losing row number increments on
# exceptions
row_count = row_count + 1 row_count = row_count + 1
try: if row_count - 1 not in rows_to_ignore:
with open(row[options['document_path_column']]) as file_object: try:
document_type_label = row[options['document_type_column']] with open(row[options['document_path_column']]) as file_object:
document_type_label = row[options['document_type_column']]
if document_type_label not in document_types: if document_type_label not in document_types:
self.stdout.write( self.stdout.write(
'New document type: {}. Creating and caching.'.format( 'New document type: {}. Creating and caching.'.format(
document_type_label document_type_label
)
)
document_type, created = DocumentType.objects.get_or_create(
label=document_type_label
)
document_types[document_type_label] = document_type
else:
document_type = document_types[document_type_label]
shared_uploaded_file = SharedUploadedFile.objects.create(
file=File(file_object)
)
extra_data = {}
if options['metadata_pairs_column']:
extra_data['metadata_pairs'] = []
for pair in options['metadata_pairs_column'].split(','):
name, value = pair.split(':')
extra_data['metadata_pairs'].append(
{
'name': row[int(name)],
'value': row[int(value)]
}
)
task_upload_new_document.apply_async(
kwargs=dict(
document_type_id=document_type.pk,
shared_uploaded_file_id=shared_uploaded_file.pk,
extra_data=extra_data
) )
) )
document_type, created = DocumentType.objects.get_or_create(
label=document_type_label uploaded_count = uploaded_count + 1
)
document_types[document_type_label] = document_type if (time.time() - time_last_display) > 1:
time_last_display = time.time()
self.stdout.write(
'Time: {}s, Files copied and queued: {}, files processed per second: {}'.format(
int(time.time() - time_start),
uploaded_count,
uploaded_count / (time.time() - time_start)
)
)
except (IOError, OSError) as exception:
if not options['ignore_errors']:
raise
else: else:
document_type = document_types[document_type_label] self.stderr.write(
'Error processing row: {}; {}.'.format(
shared_uploaded_file = SharedUploadedFile.objects.create( row_count - 1, exception
file=File(file_object)
)
extra_data = {}
if options['metadata_pairs_column']:
extra_data['metadata_pairs'] = []
for pair in options['metadata_pairs_column'].split(','):
name, value = pair.split(':')
extra_data['metadata_pairs'].append(
{
'name': row[int(name)],
'value': row[int(value)]
}
)
task_upload_new_document.apply_async(
kwargs=dict(
document_type_id=document_type.pk,
shared_uploaded_file_id=shared_uploaded_file.pk,
extra_data=extra_data
)
)
uploaded_count = uploaded_count + 1
if (time.time() - time_last_display) > 1:
time_last_display = time.time()
self.stdout.write(
'Time: {}s, Files copied and queued: {}, files processed per second: {}'.format(
int(time.time() - time_start),
uploaded_count,
uploaded_count / (time.time() - time_start)
) )
) )
except (IOError, OSError) as exception:
if not options['ignore_errors']:
raise
else:
self.stderr.write(
'Error processing row: {}; {}.'.format(
row_count - 1, exception
)
)
self.stdout.write( self.stdout.write(
'Total files copied and queues: {}'.format(uploaded_count) 'Total files copied and queues: {}'.format(uploaded_count)
) )