Skip to content

Add preserve_missing_values parameter to set_types and dump #119

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

Add preserve_missing_values parameter to set_types and dump #119

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions dataflows/base/schema_validator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,8 +30,10 @@ def drop(res_name, row, i, e):
return False


def schema_validator(resource, iterator,
field_names=None, on_error=None):
def schema_validator(
resource, iterator, field_names=None,
on_error=None, preserve_missing_values=False,
):
if on_error is None:
on_error = raise_exception
if isinstance(resource, Resource):
Expand All @@ -46,7 +48,7 @@ def schema_validator(resource, iterator,
for i, row in enumerate(iterator):
try:
for f in schema_fields:
row[f.name] = f.cast_value(row.get(f.name))
row[f.name] = f.cast_value(row.get(f.name), preserve_missing_values=preserve_missing_values)
except CastError as e:
if not on_error(resource['name'], row, i, e):
continue
Expand Down
9 changes: 7 additions & 2 deletions dataflows/processors/set_type.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,10 @@

class set_type(DataStreamProcessor):

def __init__(self, name, resources=-1, regex=True, on_error=None, **options):
def __init__(
self, name, resources=-1, regex=True,
on_error=None, preserve_missing_values=False, **options
):
super(set_type, self).__init__()
if not regex:
name = re.escape(name)
Expand All @@ -15,14 +18,16 @@ def __init__(self, name, resources=-1, regex=True, on_error=None, **options):
self.resources = resources
self.field_names = []
self.on_error = on_error
self.preserve_missing_values = preserve_missing_values

def process_resources(self, resources):
for res in resources:
if self.matcher.match(res.res.name):
if len(self.field_names) > 0:
yield schema_validator(res.res, res,
field_names=self.field_names,
on_error=self.on_error)
on_error=self.on_error,
preserve_missing_values=self.preserve_missing_values)
else:
yield res
else:
Expand Down