Note this means the serialization of e.g. IntegerRangeField now has
strings for lower and upper, so use to_python when they came back in
(same behaviour as ArrayField, hopefully, from where I also got the
set_attributes_from_name function).
Provide `contained_by` lookups for the equivalent single valued fields
related to the range field types. This acts as the opposite direction to
rangefield__contains.
With thanks to schinckel for the idea and initial tests.
Field.rel is now deprecated. Rel objects have now also remote_field
attribute. This means that self == self.remote_field.remote_field.
In addition, made the Rel objects a bit more like Field objects. Still,
marked ManyToManyFields as null=True.
Several issues resolved here, following from a report that a base_field
of GenericIpAddressField was failing.
We were using get_prep_value instead of get_db_prep_value in ArrayField
which was bypassing any extra modifications to the value being made in
the base field's get_db_prep_value. Changing this broke datetime
support, so the postgres backend has gained the relevant operation
methods to send dates/times/datetimes directly to the db backend instead
of casting them to strings. Similarly, a new database feature has been
added allowing the uuid to be passed directly to the backend, as we do
with timedeltas.
On the other side, psycopg2 expects an Inet() instance for IP address
fields, so we add a value_to_db_ipaddress method to wrap the strings on
postgres. We also have to manually add a database adapter to psycopg2,
as we do not wish to use the built in adapter which would turn
everything into Inet() instances.
Thanks to smclenithan for the report.
Added support for PostgreSQL range types to contrib.postgres.
- 5 new model fields
- 4 new form fields
- New validators
- Uses psycopg2's range type implementation in python
These refactorings making overriding some text based lookup names on
other fields (specifically `contains`) much cleaner. It also removes a
bunch of duplication in the contrib.postgres lookups.
Made deconstruct path overwriting for ArrayField conditional,
so it only occurs when the deconstructed field is an instance
of ArrayField itself and not a subclass.
This reverts commit f36151ed16.
Adding kwargs to deconstructed objects does not achieve useful
forward-compatibility in general, since additional arguments are silently
dropped rather than having their intended effect. In fact, it can make the
failure more difficult to diagnose. Thanks Shai Berger for discussion.
Fields normally try to force the default value to a string. As
translatable strings are not valid default values for ArrayField, we can
remove this behaviour which was causing issues with some migrations.
Thanks to @schinckel for the report.
The first part of django.contrib.postgres, including model and two form
fields for arrays of other data types.
This commit is formed of the following work:
Add shell of postgres app and test handling.
First draft of array fields.
Use recursive deconstruction.
Stop creating classes at lookup time.
Add validation and size parameter.
Add contained_by lookup.
Add SimpleArrayField for forms.
Add SplitArrayField (mainly for admin).
Fix prepare_value for SimpleArrayField.
Stop using MultiValueField and MultiWidget.
They don't play nice with flexible sizes.
Add basics of admin integration.
Missing:
- Tests
- Fully working js
Add reference document for django.contrib.postgres.fields.ArrayField.
Various performance and style tweaks.
Fix internal docs link, formalise code snippets.
Remove the admin code for now.
It needs a better way of handing JS widgets in the admin as a whole
before it is easy to write. In particular there are serious issues
involving DateTimePicker when used in an array.
Add a test for nested array fields with different delimiters.
This will be a documented pattern so having a test for it is useful.
Add docs for SimpleArrayField.
Add docs for SplitArrayField.
Remove admin related code for now.
definition -> description
Fix typo.
Py3 errors.
Avoid using regexes where they're not needed.
Allow passing tuples by the programmer.
Add some more tests for multidimensional arrays.
Also fix slicing as much as it can be fixed.
Simplify SplitArrayWidget's data loading.
If we aren't including the variable size one, we don't need to search
like this.
Adam Chainz
Matthew Somerville
Marc Tamlyn
Villiers Strauss
Andrea Grandi
Piotr Jakimiak
Tim Graham
Claude Paroz
Andriy Sokolovskiy
Anssi Kääriäinen
foresmac
Ng Zhi An
Jernej Kos
Jon Dufresne
Thomas Chaumeny
Markus Holtermann
Carl Meyer
Josh Smeaton
Daan Vielen