Skip to content
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

Jump to bottom

Support configurable delimiter for seed files, default to comma (#3990) #7186

Merged
merged 18 commits into from
Aug 1, 2023
Merged

Support configurable delimiter for seed files, default to comma (#3990) #7186

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
596856b
Support configurable delimiter for seed files, default to comma (#3990)
ramonvermeulen Mar 17, 2023
c6b5b12
Update Features-20230317-144957.yaml
ramonvermeulen Mar 17, 2023
381c3b3
Moved "delimiter" to seed config instead of node config
ramonvermeulen Mar 27, 2023
f44244c
Update core/dbt/clients/agate_helper.py
ramonvermeulen Mar 29, 2023
ca4ff79
Merge commit '050161c78f6d9acc36d0b76bd54ffcd778b7a467'
ramonvermeulen Mar 29, 2023
0322113
Update test_contracts_graph_parsed.py
ramonvermeulen Mar 29, 2023
c2ba7d1
Merge branch 'dbt-labs:main' into configurableDelimiterSeeds
ramonvermeulen May 26, 2023
b258f79
Merge commit '533988233ecc1b2391d2d6139e1d6be095e2d6cd'
ramonvermeulen Jun 23, 2023
20be12b
fixed integration tests
ramonvermeulen Jun 23, 2023
f810942
Added functional tests for seed files with a unique delimiter
ramonvermeulen Jun 23, 2023
10d76f4
Added docstrings
ramonvermeulen Jun 23, 2023
f37e74a
Added a test for an empty string configured delimiter value
ramonvermeulen Jun 23, 2023
d1c8261
whitespace
ramonvermeulen Jun 23, 2023
82f15c4
Merge pull request #1 from dbt-labs/main
ramonvermeulen Jul 14, 2023
2902368
ran black
ramonvermeulen Jul 14, 2023
ff66966
updated changie entry
ramonvermeulen Jul 14, 2023
3083a6d
Update Features-20230317-144957.yaml
ramonvermeulen Jul 14, 2023
847eb2d
Merge branch 'dbt-labs:main' into configurableDelimiterSeeds
ramonvermeulen Aug 1, 2023
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
6 changes: 6 additions & 0 deletions .changes/unreleased/Features-20230317-144957.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
kind: Features
body: Added support to configure a delimiter for a seed file, defaults to comma
time: 2023-03-17T14:49:57.564210866+01:00
custom:
Author: ramonvermeulen
Issue: "3990"
4 changes: 2 additions & 2 deletions core/dbt/clients/agate_helper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,12 +135,12 @@ def as_matrix(table):
return [r.values() for r in table.rows.values()]


def from_csv(abspath, text_columns):
def from_csv(abspath, text_columns, delimiter = ","):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Question: Should we add support for more than just delimiter here? Any/all **kwargs supported by agate.from_csv / Python's stdlib CSV reader?

Thoughts:

  • That can be out of scope for now / for this PR
  • It would risk locking us further into using agate (which I don't love), or at least the Python stdlib csv reader (which I don't mind as much)

ramonvermeulen marked this conversation as resolved.
Show resolved Hide resolved
type_tester = build_type_tester(text_columns=text_columns)
with open(abspath, encoding="utf-8") as fp:
if fp.read(1) != BOM:
fp.seek(0)
return agate.Table.from_csv(fp, column_types=type_tester)
return agate.Table.from_csv(fp, column_types=type_tester, delimiter=delimiter)


class _NullMarker:
Expand Down
3 changes: 2 additions & 1 deletion core/dbt/context/providers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -791,8 +791,9 @@ def load_agate_table(self) -> agate.Table:
assert self.model.root_path
path = os.path.join(self.model.root_path, self.model.original_file_path)
column_types = self.model.config.column_types
delimiter = self.model.config.delimiter
try:
table = agate_helper.from_csv(path, text_columns=column_types)
table = agate_helper.from_csv(path, text_columns=column_types, delimiter=delimiter)
except ValueError as e:
raise LoadAgateTableValueError(e, node=self.model)
table.original_abspath = os.path.abspath(path)
Expand Down
1 change: 1 addition & 0 deletions core/dbt/contracts/graph/model_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -435,6 +435,7 @@ class NodeConfig(NodeAndTestConfig):
default_factory=dict,
metadata=MergeBehavior.Update.meta(),
)
delimiter: str = ","
ramonvermeulen marked this conversation as resolved.
Show resolved Hide resolved
full_refresh: Optional[bool] = None
# 'unique_key' doesn't use 'Optional' because typing.get_type_hints was
# sometimes getting the Union order wrong, causing serialization failures.
Expand Down
2 changes: 2 additions & 0 deletions test/unit/test_contracts_graph_compiled.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,7 @@ def basic_uncompiled_dict():
'tags': [],
'config': {
'column_types': {},
'delimiter': ',',
'enabled': True,
'materialized': 'view',
'persist_docs': {},
Expand Down Expand Up @@ -182,6 +183,7 @@ def basic_compiled_dict():
'tags': [],
'config': {
'column_types': {},
'delimiter': ',',
'enabled': True,
'materialized': 'view',
'persist_docs': {},
Expand Down
26 changes: 24 additions & 2 deletions test/unit/test_contracts_graph_parsed.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,7 @@ def populated_node_config_object():
def populated_node_config_dict():
return {
'column_types': {'a': 'text'},
'delimiter': ',',
'enabled': True,
'materialized': 'table',
'persist_docs': {},
Expand All @@ -91,6 +92,7 @@ def test_config_populated(populated_node_config_object, populated_node_config_di
def unrendered_node_config_dict():
return {
'column_types': {'a': 'text'},
'delimiter': ',',
'materialized': 'table',
'post_hook': 'insert into blah(a, b) select "1", 1',
}
Expand Down Expand Up @@ -150,6 +152,7 @@ def base_parsed_model_dict():
'tags': [],
'config': {
'column_types': {},
'delimiter': ',',
'enabled': True,
'materialized': 'view',
'persist_docs': {},
Expand Down Expand Up @@ -251,6 +254,7 @@ def complex_parsed_model_dict():
'meta': {},
'config': {
'column_types': {'a': 'text'},
'delimiter': ',',
'enabled': True,
'materialized': 'ephemeral',
'persist_docs': {},
Expand Down Expand Up @@ -278,6 +282,7 @@ def complex_parsed_model_dict():
'checksum': {'name': 'sha256', 'checksum': 'e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855'},
'unrendered_config': {
'column_types': {'a': 'text'},
'delimiter': ',',
'materialized': 'ephemeral',
'post_hook': ['insert into blah(a, b) select "1", 1'],
},
Expand Down Expand Up @@ -311,22 +316,24 @@ def complex_parsed_model_object():
meta={},
config=NodeConfig(
column_types={'a': 'text'},
delimiter=',',
materialized='ephemeral',
post_hook=[Hook(sql='insert into blah(a, b) select "1", 1')],
),
columns={'a': ColumnInfo('a', 'a text field', {})},
checksum=FileHash.from_contents(''),
unrendered_config={
'column_types': {'a': 'text'},
'delimiter': ',',
'materialized': 'ephemeral',
'post_hook': ['insert into blah(a, b) select "1", 1'],
},
)


{'enabled': True, 'tags': [], 'meta': {}, 'materialized': 'ephemeral', 'persist_docs': {}, 'quoting': {}, 'column_types': {'a': 'text'}, 'on_schema_change': 'ignore', 'grants': {}, 'packages': [], 'docs': {'show': True}, 'contract': False, 'post-hook': [{'sql': 'insert into blah(a, b) select "1", 1', 'transaction': True}], 'pre-hook': []}
{'enabled': True, 'tags': [], 'meta': {}, 'materialized': 'ephemeral', 'persist_docs': {}, 'quoting': {}, 'column_types': {'a': 'text'}, 'delimiter': ',', 'on_schema_change': 'ignore', 'grants': {}, 'packages': [], 'docs': {'show': True}, 'contract': False, 'post-hook': [{'sql': 'insert into blah(a, b) select "1", 1', 'transaction': True}], 'pre-hook': []}

{'column_types': {'a': 'text'}, 'enabled': True, 'materialized': 'ephemeral', 'persist_docs': {}, 'post-hook': [{'sql': 'insert into blah(a, b) select "1", 1', 'transaction': True}], 'pre-hook': [], 'quoting': {}, 'tags': [], 'on_schema_change': 'ignore', 'meta': {}, 'grants': {}, 'docs': {'show': True}, 'packages': []}
{'column_types': {'a': 'text'}, 'delimiter': ',', 'enabled': True, 'materialized': 'ephemeral', 'persist_docs': {}, 'post-hook': [{'sql': 'insert into blah(a, b) select "1", 1', 'transaction': True}], 'pre-hook': [], 'quoting': {}, 'tags': [], 'on_schema_change': 'ignore', 'meta': {}, 'grants': {}, 'docs': {'show': True}, 'packages': []}

def test_model_basic(basic_parsed_model_object, base_parsed_model_dict, minimal_parsed_model_dict):
node = basic_parsed_model_object
Expand Down Expand Up @@ -452,6 +459,7 @@ def basic_parsed_seed_dict():
'alias': 'foo',
'config': {
'column_types': {},
'delimiter': ',',
'enabled': True,
'materialized': 'seed',
'persist_docs': {},
Expand Down Expand Up @@ -542,6 +550,7 @@ def complex_parsed_seed_dict():
'alias': 'foo',
'config': {
'column_types': {},
'delimiter': ',',
'enabled': True,
'materialized': 'seed',
'persist_docs': {'relation': True, 'columns': True},
Expand Down Expand Up @@ -803,6 +812,7 @@ def base_parsed_hook_dict():
'tags': [],
'config': {
'column_types': {},
'delimiter': ',',
'enabled': True,
'materialized': 'view',
'persist_docs': {},
Expand Down Expand Up @@ -882,6 +892,7 @@ def complex_parsed_hook_dict():
'meta': {},
'config': {
'column_types': {'a': 'text'},
'delimiter': ',',
'enabled': True,
'materialized': 'table',
'persist_docs': {},
Expand Down Expand Up @@ -910,6 +921,7 @@ def complex_parsed_hook_dict():
'checksum': {'name': 'sha256', 'checksum': 'e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855'},
'unrendered_config': {
'column_types': {'a': 'text'},
'delimiter': ',',
'materialized': 'table',
},
'config_call_dict': {},
Expand Down Expand Up @@ -941,6 +953,7 @@ def complex_parsed_hook_object():
meta={},
config=NodeConfig(
column_types={'a': 'text'},
delimiter=',',
materialized='table',
post_hook=[]
),
Expand All @@ -949,6 +962,7 @@ def complex_parsed_hook_object():
checksum=FileHash.from_contents(''),
unrendered_config={
'column_types': {'a': 'text'},
'delimiter': ',',
'materialized': 'table',
},
)
Expand Down Expand Up @@ -1226,6 +1240,7 @@ def test_invalid_severity(complex_parsed_schema_test_dict):
def basic_timestamp_snapshot_config_dict():
return {
'column_types': {},
'delimiter': ',',
'enabled': True,
'materialized': 'snapshot',
'persist_docs': {},
Expand Down Expand Up @@ -1262,6 +1277,7 @@ def basic_timestamp_snapshot_config_object():
def complex_timestamp_snapshot_config_dict():
return {
'column_types': {'a': 'text'},
'delimiter': ',',
'enabled': True,
'materialized': 'snapshot',
'persist_docs': {},
Expand All @@ -1288,6 +1304,7 @@ def complex_timestamp_snapshot_config_dict():
def complex_timestamp_snapshot_config_object():
cfg = SnapshotConfig(
column_types={'a': 'text'},
delimiter=',',
materialized='snapshot',
post_hook=[Hook(sql='insert into blah(a, b) select "1", 1')],
strategy='timestamp',
Expand Down Expand Up @@ -1324,6 +1341,7 @@ def test_invalid_missing_updated_at(basic_timestamp_snapshot_config_dict):
def basic_check_snapshot_config_dict():
return {
'column_types': {},
'delimiter': ',',
'enabled': True,
'materialized': 'snapshot',
'persist_docs': {},
Expand Down Expand Up @@ -1360,6 +1378,7 @@ def basic_check_snapshot_config_object():
def complex_set_snapshot_config_dict():
return {
'column_types': {'a': 'text'},
'delimiter': ',',
'enabled': True,
'materialized': 'snapshot',
'persist_docs': {},
Expand All @@ -1386,6 +1405,7 @@ def complex_set_snapshot_config_dict():
def complex_set_snapshot_config_object():
cfg = SnapshotConfig(
column_types={'a': 'text'},
delimiter=',',
materialized='snapshot',
post_hook=[Hook(sql='insert into blah(a, b) select "1", 1')],
strategy='check',
Expand Down Expand Up @@ -1472,6 +1492,7 @@ def basic_timestamp_snapshot_dict():
'tags': [],
'config': {
'column_types': {},
'delimiter': ',',
'enabled': True,
'materialized': 'snapshot',
'persist_docs': {},
Expand Down Expand Up @@ -1614,6 +1635,7 @@ def basic_check_snapshot_dict():
'tags': [],
'config': {
'column_types': {},
'delimiter': ',',
'enabled': True,
'materialized': 'snapshot',
'persist_docs': {},
Expand Down