support complex types unit testing

.changes/unreleased/Features-20230802-145011.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Initial implementation of unit testing
+time: 2023-08-02T14:50:11.391992-04:00
+custom:
+  Author: gshank
+  Issue: "8287"

.changes/unreleased/Features-20230828-101825.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Unit test manifest artifacts and selection
+time: 2023-08-28T10:18:25.958929-04:00
+custom:
+  Author: gshank
+  Issue: "8295"

.changes/unreleased/Features-20230906-234741.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Support config with tags & meta for unit tests
+time: 2023-09-06T23:47:41.059915-04:00
+custom:
+  Author: michelleark
+  Issue: "8294"

.changes/unreleased/Features-20230928-163205.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Enable inline csv fixtures in unit tests
+time: 2023-09-28T16:32:05.573776-04:00
+custom:
+  Author: gshank
+  Issue: "8626"

.changes/unreleased/Features-20231101-101845.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Support unit testing incremental models
+time: 2023-11-01T10:18:45.341781-04:00
+custom:
+  Author: michelleark
+  Issue: "8422"

.changes/unreleased/Features-20231106-194752.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Add support of csv file fixtures to unit testing
+time: 2023-11-06T19:47:52.501495-06:00
+custom:
+  Author: emmyoop
+  Issue: "8290"

.changes/unreleased/Features-20231107-231006.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Unit tests support --defer and state:modified
+time: 2023-11-07T23:10:06.376588-05:00
+custom:
+  Author: jtcohen6
+  Issue: "8517"

.changes/unreleased/Features-20231111-191150.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Support source inputs in unit tests
+time: 2023-11-11T19:11:50.870494-05:00
+custom:
+  Author: gshank
+  Issue: "8507"

.changes/unreleased/Features-20231114-101555.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Use daff to render diff displayed in stdout when unit test fails
+time: 2023-11-14T10:15:55.689307-05:00
+custom:
+  Author: michelleark
+  Issue: "8558"

.changes/unreleased/Features-20231116-144006.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Move unit testing to test command
+time: 2023-11-16T14:40:06.121336-05:00
+custom:
+  Author: gshank
+  Issue: "8979"

.changes/unreleased/Features-20231130-130948.yaml

@@ -0,0 +1,6 @@
+kind: Features
+body: Support unit tests in non-root packages
+time: 2023-11-30T13:09:48.206007-05:00
+custom:
+  Author: gshank
+  Issue: "8285"

.changes/unreleased/Fixes-20231113-154535.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Use seed file from disk for unit testing if rows not specified in YAML config
+time: 2023-11-13T15:45:35.008565Z
+custom:
+  Author: aranke
+  Issue: "8652"

.changes/unreleased/Under the Hood-20230912-190506.yaml

@@ -0,0 +1,6 @@
+kind: Under the Hood
+body: Add unit testing functional tests
+time: 2023-09-12T19:05:06.023126-04:00
+custom:
+  Author: gshank
+  Issue: "8512"

core/dbt/adapters/base/relation.py

@@ -2,7 +2,13 @@
 from dataclasses import dataclass, field
 from typing import Optional, TypeVar, Any, Type, Dict, Iterator, Tuple, Set, Union, FrozenSet
 
-from dbt.contracts.graph.nodes import SourceDefinition, ManifestNode, ResultNode, ParsedNode
+from dbt.contracts.graph.nodes import (
+    SourceDefinition,
+    ManifestNode,
+    ResultNode,
+    ParsedNode,
+    UnitTestSourceDefinition,
+)
 from dbt.contracts.relation import (
     RelationType,
     ComponentName,
@@ -211,7 +217,9 @@ def quoted(self, identifier):
         )
 
     @classmethod
-    def create_from_source(cls: Type[Self], source: SourceDefinition, **kwargs: Any) -> Self:
+    def create_from_source(
+        cls: Type[Self], source: Union[SourceDefinition, UnitTestSourceDefinition], **kwargs: Any
+    ) -> Self:
         source_quoting = source.quoting.to_dict(omit_none=True)
         source_quoting.pop("column", None)
         quote_policy = deep_merge(
@@ -237,7 +245,7 @@ def create_ephemeral_from_node(
         cls: Type[Self],
         config: HasQuoting,
         node: ManifestNode,
-        limit: Optional[int],
+        limit: Optional[int] = None,
     ) -> Self:
         # Note that ephemeral models are based on the name.
         identifier = cls.add_ephemeral_prefix(node.name)
@@ -271,8 +279,10 @@ def create_from(
         node: ResultNode,
         **kwargs: Any,
     ) -> Self:
-        if node.resource_type == NodeType.Source:
-            if not isinstance(node, SourceDefinition):
+        if node.resource_type == NodeType.Source or isinstance(node, UnitTestSourceDefinition):
+            if not (
+                isinstance(node, SourceDefinition) or isinstance(node, UnitTestSourceDefinition)
+            ):
                 raise DbtInternalError(
                     "type mismatch, expected SourceDefinition but got {}".format(type(node))
                 )

core/dbt/adapters/relation_configs/config_change.py

@@ -12,7 +12,7 @@ class RelationConfigChangeAction(StrEnum):
     drop = "drop"
 
 
-@dataclass(frozen=True, eq=True, unsafe_hash=True)
+@dataclass(frozen=True, eq=True, unsafe_hash=True)  # type: ignore
 class RelationConfigChange(RelationConfigBase, ABC):
     action: RelationConfigChangeAction
     context: Hashable  # this is usually a RelationConfig, e.g. IndexConfig, but shouldn't be limited

core/dbt/clients/agate_helper.py

@@ -3,6 +3,7 @@
 import agate
 import datetime
 import isodate
+import io
 import json
 import dbt.utils
 from typing import Iterable, List, Dict, Union, Optional, Any
@@ -137,6 +138,23 @@ def table_from_data_flat(data, column_names: Iterable[str]) -> agate.Table:
     )
 
 
+def json_rows_from_table(table: agate.Table) -> List[Dict[str, Any]]:
+    "Convert a table to a list of row dict objects"
+    output = io.StringIO()
+    table.to_json(path=output)  # type: ignore
+
+    return json.loads(output.getvalue())
+
+
+def list_rows_from_table(table: agate.Table) -> List[Any]:
+    "Convert a table to a list of lists, where the first element represents the header"
+    rows = [[col.name for col in table.columns]]
+    for row in table.rows:
+        rows.append(list(row.values()))
+
+    return rows
+
+
 def empty_table():
     "Returns an empty Agate table. To be used in place of None"
 

core/dbt/clients/jinja.py

@@ -330,6 +330,26 @@ def __call__(self, *args, **kwargs):
             return self.call_macro(*args, **kwargs)
 
 
+class UnitTestMacroGenerator(MacroGenerator):
+    # this makes UnitTestMacroGenerator objects callable like functions
+    def __init__(
+        self,
+        macro_generator: MacroGenerator,
+        call_return_value: Any,
+    ) -> None:
+        super().__init__(
+            macro_generator.macro,
+            macro_generator.context,
+            macro_generator.node,
+            macro_generator.stack,
+        )
+        self.call_return_value = call_return_value
+
+    def __call__(self, *args, **kwargs):
+        with self.track_call():
+            return self.call_return_value
+
+
 class QueryStringGenerator(BaseMacroGenerator):
     def __init__(self, template_str: str, context: Dict[str, Any]) -> None:
         super().__init__(context)

core/dbt/compilation.py

@@ -12,7 +12,10 @@
 from dbt.adapters.factory import get_adapter
 from dbt.clients import jinja
 from dbt.clients.system import make_directory
-from dbt.context.providers import generate_runtime_model_context
+from dbt.context.providers import (
+    generate_runtime_model_context,
+    generate_runtime_unit_test_context,
+)
 from dbt.contracts.graph.manifest import Manifest, UniqueID
 from dbt.contracts.graph.nodes import (
     ManifestNode,
@@ -21,6 +24,8 @@
     GraphMemberNode,
     InjectedCTE,
     SeedNode,
+    UnitTestNode,
+    UnitTestDefinition,
 )
 from dbt.exceptions import (
     GraphDependencyNotFoundError,
@@ -44,6 +49,7 @@ def print_compile_stats(stats):
     names = {
         NodeType.Model: "model",
         NodeType.Test: "test",
+        NodeType.Unit: "unit test",
         NodeType.Snapshot: "snapshot",
         NodeType.Analysis: "analysis",
         NodeType.Macro: "macro",
@@ -91,6 +97,7 @@ def _generate_stats(manifest: Manifest):
     stats[NodeType.Macro] += len(manifest.macros)
     stats[NodeType.Group] += len(manifest.groups)
     stats[NodeType.SemanticModel] += len(manifest.semantic_models)
+    stats[NodeType.Unit] += len(manifest.unit_tests)
 
     # TODO: should we be counting dimensions + entities?
 
@@ -191,6 +198,8 @@ def link_graph(self, manifest: Manifest):
             self.link_node(exposure, manifest)
         for metric in manifest.metrics.values():
             self.link_node(metric, manifest)
+        for unit_test in manifest.unit_tests.values():
+            self.link_node(unit_test, manifest)
         for saved_query in manifest.saved_queries.values():
             self.link_node(saved_query, manifest)
 
@@ -291,8 +300,10 @@ def _create_node_context(
         manifest: Manifest,
         extra_context: Dict[str, Any],
     ) -> Dict[str, Any]:
-
-        context = generate_runtime_model_context(node, self.config, manifest)
+        if isinstance(node, UnitTestNode):
+            context = generate_runtime_unit_test_context(node, self.config, manifest)
+        else:
+            context = generate_runtime_model_context(node, self.config, manifest)
         context.update(extra_context)
 
         if isinstance(node, GenericTestNode):
@@ -529,6 +540,9 @@ def compile_node(
         the node's raw_code into compiled_code, and then calls the
         recursive method to "prepend" the ctes.
         """
+        if isinstance(node, UnitTestDefinition):
+            return node
+
         # Make sure Lexer for sqlparse 0.4.4 is initialized
         from sqlparse.lexer import Lexer  # type: ignore
 

core/dbt/config/project.py

@@ -441,6 +441,7 @@ def create_project(self, rendered: RenderComponents) -> "Project":
         snapshots: Dict[str, Any]
         sources: Dict[str, Any]
         tests: Dict[str, Any]
+        unit_tests: Dict[str, Any]
         metrics: Dict[str, Any]
         semantic_models: Dict[str, Any]
         saved_queries: Dict[str, Any]
@@ -454,6 +455,7 @@ def create_project(self, rendered: RenderComponents) -> "Project":
         snapshots = cfg.snapshots
         sources = cfg.sources
         tests = cfg.tests
+        unit_tests = cfg.unit_tests
         metrics = cfg.metrics
         semantic_models = cfg.semantic_models
         saved_queries = cfg.saved_queries
@@ -515,6 +517,7 @@ def create_project(self, rendered: RenderComponents) -> "Project":
             query_comment=query_comment,
             sources=sources,
             tests=tests,
+            unit_tests=unit_tests,
             metrics=metrics,
             semantic_models=semantic_models,
             saved_queries=saved_queries,
@@ -625,6 +628,7 @@ class Project:
     snapshots: Dict[str, Any]
     sources: Dict[str, Any]
     tests: Dict[str, Any]
+    unit_tests: Dict[str, Any]
     metrics: Dict[str, Any]
     semantic_models: Dict[str, Any]
     saved_queries: Dict[str, Any]
@@ -658,6 +662,13 @@ def generic_test_paths(self):
             generic_test_paths.append(os.path.join(test_path, "generic"))
         return generic_test_paths
 
+    @property
+    def fixture_paths(self):
+        fixture_paths = []
+        for test_path in self.test_paths:
+            fixture_paths.append(os.path.join(test_path, "fixtures"))
+        return fixture_paths
+
     def __str__(self):
         cfg = self.to_project_config(with_packages=True)
         return str(cfg)
@@ -703,6 +714,7 @@ def to_project_config(self, with_packages=False):
                 "snapshots": self.snapshots,
                 "sources": self.sources,
                 "tests": self.tests,
+                "unit-tests": self.unit_tests,
                 "metrics": self.metrics,
                 "semantic-models": self.semantic_models,
                 "saved-queries": self.saved_queries,

core/dbt/config/runtime.py

@@ -166,6 +166,7 @@ def from_parts(
             query_comment=project.query_comment,
             sources=project.sources,
             tests=project.tests,
+            unit_tests=project.unit_tests,
             metrics=project.metrics,
             semantic_models=project.semantic_models,
             saved_queries=project.saved_queries,
@@ -324,6 +325,7 @@ def get_resource_config_paths(self) -> Dict[str, PathSet]:
             "snapshots": self._get_config_paths(self.snapshots),
             "sources": self._get_config_paths(self.sources),
             "tests": self._get_config_paths(self.tests),
+            "unit_tests": self._get_config_paths(self.unit_tests),
             "metrics": self._get_config_paths(self.metrics),
             "semantic_models": self._get_config_paths(self.semantic_models),
             "saved_queries": self._get_config_paths(self.saved_queries),

core/dbt/context/context_config.py

@@ -51,6 +51,8 @@ def get_config_dict(self, resource_type: NodeType) -> Dict[str, Any]:
             model_configs = unrendered.get("saved_queries")
         elif resource_type == NodeType.Exposure:
             model_configs = unrendered.get("exposures")
+        elif resource_type == NodeType.Unit:
+            model_configs = unrendered.get("unit_tests")
         else:
             model_configs = unrendered.get("models")
         if model_configs is None:
@@ -80,6 +82,8 @@ def get_config_dict(self, resource_type: NodeType) -> Dict[str, Any]:
             model_configs = self.project.saved_queries
         elif resource_type == NodeType.Exposure:
             model_configs = self.project.exposures
+        elif resource_type == NodeType.Unit:
+            model_configs = self.project.unit_tests
         else:
             model_configs = self.project.models
         return model_configs