Merge remote-tracking branch 'origin/releases/0.21.0rc2' into 0.21.latest

* Avoid infinite recursion in macro state check

* Add test case for infinite macro recursion

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.21.0b2
+current_version = 0.21.0rc2
 parse = (?P<major>\d+)
 	\.(?P<minor>\d+)
 	\.(?P<patch>\d+)

CHANGELOG.md

@@ -1,8 +1,17 @@
 ## dbt 0.21.0 (Release TBD)
 
-## dbt 0.21.0b2 (August 19, 2021)
+## dbt 0.21.0rc2 (September 27, 2021)
 
 
+### Fixes
+- Fix batching for large seeds on Snowflake ([#3941](https://github.com/dbt-labs/dbt/issues/3941), [#3942](https://github.com/dbt-labs/dbt/pull/3942))
+- Avoid infinite recursion in `state:modified.macros` check ([#3904](https://github.com/dbt-labs/dbt/issues/3904), [#3957](https://github.com/dbt-labs/dbt/pull/3957))
+
+### Under the hood
+- Bump artifact schema versions for 0.21.0 ([#3945](https://github.com/dbt-labs/dbt/pull/3945))
+
+## dbt 0.21.0rc1 (September 20, 2021)
+
 ### Features
 
 - Experimental parser now detects macro overrides of ref, source, and config builtins. ([#3581](https://github.com/dbt-labs/dbt/issues/3866), [#3582](https://github.com/dbt-labs/dbt/pull/3877))
@@ -16,6 +25,7 @@
 - Added default field in the `selectors.yml` to allow user to define default selector ([#3448](https://github.com/dbt-labs/dbt/issues/3448), [#3875](https://github.com/dbt-labs/dbt/issues/3875), [#3892](https://github.com/dbt-labs/dbt/issues/3892))
 - Added timing and thread information to sources.json artifact ([#3804](https://github.com/dbt-labs/dbt/issues/3804), [#3894](https://github.com/dbt-labs/dbt/pull/3894))
 - Update cli and rpc flags for the `build` task to align with other commands (`--resource-type`, `--store-failures`) ([#3596](https://github.com/dbt-labs/dbt/issues/3596), [#3884](https://github.com/dbt-labs/dbt/pull/3884))
+- Log tests that are not indirectly selected. Add `--greedy` flag to `test`, `list`, `build` and `greedy` property in yaml selectors ([#3723](https://github.com/dbt-labs/dbt/pull/3723), [#3833](https://github.com/dbt-labs/dbt/pull/3833))
 
 ### Fixes
 
@@ -44,7 +54,7 @@ Contributors:
 - [@dbrtly](https://github.com/dbrtly) ([#3834](https://github.com/dbt-labs/dbt/pull/3834))
 - [@swanderz](https://github.com/swanderz) [#3623](https://github.com/dbt-labs/dbt/pull/3623)
 - [@JasonGluck](https://github.com/JasonGluck) ([#3582](https://github.com/dbt-labs/dbt/pull/3582))
-- [@joellabes](https://github.com/joellabes) ([#3669](https://github.com/dbt-labs/dbt/pull/3669))
+- [@joellabes](https://github.com/joellabes) ([#3669](https://github.com/dbt-labs/dbt/pull/3669), [#3833](https://github.com/dbt-labs/dbt/pull/3833))
 - [@juma-adoreme](https://github.com/juma-adoreme) ([#3838](https://github.com/dbt-labs/dbt/pull/3838))
 - [@annafil](https://github.com/annafil) ([#3825](https://github.com/dbt-labs/dbt/pull/3825))
 - [@AndreasTA-AW](https://github.com/AndreasTA-AW) ([#3691](https://github.com/dbt-labs/dbt/pull/3691))
@@ -52,6 +62,7 @@ Contributors:
 - [@TeddyCr](https://github.com/TeddyCr) ([#3448](https://github.com/dbt-labs/dbt/pull/3865))
 - [@sdebruyn](https://github.com/sdebruyn) ([#3906](https://github.com/dbt-labs/dbt/pull/3906))
 
+
 ## dbt 0.21.0b2 (August 19, 2021)
 
 ### Features

core/dbt/contracts/graph/manifest.py

@@ -1071,7 +1071,7 @@ AnyManifest = Union[Manifest, MacroManifest]
 
 
 @dataclass
-@schema_version('manifest', 2)
+@schema_version('manifest', 3)
 class WritableManifest(ArtifactMixin):
     nodes: Mapping[UniqueID, ManifestNode] = field(
         metadata=dict(description=(

core/dbt/contracts/results.py

@@ -185,7 +185,7 @@ class RunExecutionResult(
 
 
 @dataclass
-@schema_version('run-results', 2)
+@schema_version('run-results', 3)
 class RunResultsArtifact(ExecutionResult, ArtifactMixin):
     results: Sequence[RunResultOutput]
     args: Dict[str, Any] = field(default_factory=dict)
@@ -369,7 +369,7 @@ class FreshnessResult(ExecutionResult):
 
 
 @dataclass
-@schema_version('sources', 1)
+@schema_version('sources', 2)
 class FreshnessExecutionResultArtifact(
     ArtifactMixin,
     VersionedSchema,

core/dbt/flags.py

@@ -18,6 +18,7 @@ WRITE_JSON = None
 PARTIAL_PARSE = None
 USE_COLORS = None
 STORE_FAILURES = None
+GREEDY = None
 
 
 def env_set_truthy(key: str) -> Optional[str]:
@@ -56,7 +57,7 @@ MP_CONTEXT = _get_context()
 def reset():
     global STRICT_MODE, FULL_REFRESH, USE_CACHE, WARN_ERROR, TEST_NEW_PARSER, \
         USE_EXPERIMENTAL_PARSER, WRITE_JSON, PARTIAL_PARSE, MP_CONTEXT, USE_COLORS, \
-        STORE_FAILURES
+        STORE_FAILURES, GREEDY
 
     STRICT_MODE = False
     FULL_REFRESH = False
@@ -69,12 +70,13 @@ def reset():
     MP_CONTEXT = _get_context()
     USE_COLORS = True
     STORE_FAILURES = False
+    GREEDY = False
 
 
 def set_from_args(args):
     global STRICT_MODE, FULL_REFRESH, USE_CACHE, WARN_ERROR, TEST_NEW_PARSER, \
         USE_EXPERIMENTAL_PARSER, WRITE_JSON, PARTIAL_PARSE, MP_CONTEXT, USE_COLORS, \
-        STORE_FAILURES
+        STORE_FAILURES, GREEDY
 
     USE_CACHE = getattr(args, 'use_cache', USE_CACHE)
 
@@ -99,6 +101,7 @@ def set_from_args(args):
         USE_COLORS = use_colors_override
 
     STORE_FAILURES = getattr(args, 'store_failures', STORE_FAILURES)
+    GREEDY = getattr(args, 'greedy', GREEDY)
 
 
 # initialize everything to the defaults on module load

core/dbt/graph/cli.py

@@ -1,4 +1,5 @@
 # special support for CLI argument parsing.
+from dbt import flags
 import itertools
 from dbt.clients.yaml_helper import yaml, Loader, Dumper  # noqa: F401
 
@@ -66,7 +67,7 @@ def parse_union_from_default(
 def parse_difference(
     include: Optional[List[str]], exclude: Optional[List[str]]
 ) -> SelectionDifference:
-    included = parse_union_from_default(include, DEFAULT_INCLUDES)
+    included = parse_union_from_default(include, DEFAULT_INCLUDES, greedy=bool(flags.GREEDY))
     excluded = parse_union_from_default(exclude, DEFAULT_EXCLUDES, greedy=True)
     return SelectionDifference(components=[included, excluded])
 
@@ -180,7 +181,7 @@ def parse_union_definition(definition: Dict[str, Any]) -> SelectionSpec:
     union_def_parts = _get_list_dicts(definition, 'union')
     include, exclude = _parse_include_exclude_subdefs(union_def_parts)
 
-    union = SelectionUnion(components=include)
+    union = SelectionUnion(components=include, greedy_warning=False)
 
     if exclude is None:
         union.raw = definition
@@ -188,7 +189,8 @@ def parse_union_definition(definition: Dict[str, Any]) -> SelectionSpec:
     else:
         return SelectionDifference(
             components=[union, exclude],
-            raw=definition
+            raw=definition,
+            greedy_warning=False
         )
 
 
@@ -197,7 +199,7 @@ def parse_intersection_definition(
 ) -> SelectionSpec:
     intersection_def_parts = _get_list_dicts(definition, 'intersection')
     include, exclude = _parse_include_exclude_subdefs(intersection_def_parts)
-    intersection = SelectionIntersection(components=include)
+    intersection = SelectionIntersection(components=include, greedy_warning=False)
 
     if exclude is None:
         intersection.raw = definition
@@ -205,7 +207,8 @@ def parse_intersection_definition(
     else:
         return SelectionDifference(
             components=[intersection, exclude],
-            raw=definition
+            raw=definition,
+            greedy_warning=False
         )
 
 
@@ -239,7 +242,7 @@ def parse_dict_definition(definition: Dict[str, Any]) -> SelectionSpec:
     if diff_arg is None:
         return base
     else:
-        return SelectionDifference(components=[base, diff_arg])
+        return SelectionDifference(components=[base, diff_arg], greedy_warning=False)
 
 
 def parse_from_definition(

core/dbt/graph/selector.py

@@ -1,4 +1,3 @@
-
 from typing import Set, List, Optional, Tuple
 
 from .graph import Graph, UniqueId
@@ -30,6 +29,24 @@ def alert_non_existence(raw_spec, nodes):
         )
 
 
+def alert_unused_nodes(raw_spec, node_names):
+    summary_nodes_str = ("\n  - ").join(node_names[:3])
+    debug_nodes_str = ("\n  - ").join(node_names)
+    and_more_str = f"\n  - and {len(node_names) - 3} more" if len(node_names) > 4 else ""
+    summary_msg = (
+        f"\nSome tests were excluded because at least one parent is not selected. "
+        f"Use the --greedy flag to include them."
+        f"\n  - {summary_nodes_str}{and_more_str}"
+    )
+    logger.info(summary_msg)
+    if len(node_names) > 4:
+        debug_msg = (
+            f"Full list of tests that were excluded:"
+            f"\n  - {debug_nodes_str}"
+        )
+        logger.debug(debug_msg)
+
+
 def can_select_indirectly(node):
     """If a node is not selected itself, but its parent(s) are, it may qualify
     for indirect selection.
@@ -151,16 +168,16 @@ class NodeSelector(MethodManager):
 
         return direct_nodes, indirect_nodes
 
-    def select_nodes(self, spec: SelectionSpec) -> Set[UniqueId]:
+    def select_nodes(self, spec: SelectionSpec) -> Tuple[Set[UniqueId], Set[UniqueId]]:
         """Select the nodes in the graph according to the spec.
 
         This is the main point of entry for turning a spec into a set of nodes:
         - Recurse through spec, select by criteria, combine by set operation
         - Return final (unfiltered) selection set
         """
-
         direct_nodes, indirect_nodes = self.select_nodes_recursively(spec)
-        return direct_nodes
+        indirect_only = indirect_nodes.difference(direct_nodes)
+        return direct_nodes, indirect_only
 
     def _is_graph_member(self, unique_id: UniqueId) -> bool:
         if unique_id in self.manifest.sources:
@@ -213,6 +230,8 @@ class NodeSelector(MethodManager):
         #  - If ANY parent is missing, return it separately. We'll keep it around
         #    for later and see if its other parents show up.
         # We use this for INCLUSION.
+        # Users can also opt in to inclusive GREEDY mode by passing --greedy flag,
+        # or by specifying `greedy: true` in a yaml selector
 
         direct_nodes = set(selected)
         indirect_nodes = set()
@@ -251,15 +270,24 @@ class NodeSelector(MethodManager):
 
             - node selection. Based on the include/exclude sets, the set
                 of matched unique IDs is returned
-                - expand the graph at each leaf node, before combination
-                    - selectors might override this. for example, this is where
-                        tests are added
+                - includes direct + indirect selection (for tests)
             - filtering:
                 - selectors can filter the nodes after all of them have been
                   selected
         """
-        selected_nodes = self.select_nodes(spec)
+        selected_nodes, indirect_only = self.select_nodes(spec)
         filtered_nodes = self.filter_selection(selected_nodes)
+
+        if indirect_only:
+            filtered_unused_nodes = self.filter_selection(indirect_only)
+            if filtered_unused_nodes and spec.greedy_warning:
+                # log anything that didn't make the cut
+                unused_node_names = []
+                for unique_id in filtered_unused_nodes:
+                    name = self.manifest.nodes[unique_id].name
+                    unused_node_names.append(name)
+                alert_unused_nodes(spec, unused_node_names)
+
         return filtered_nodes
 
     def get_graph_queue(self, spec: SelectionSpec) -> GraphQueue:

core/dbt/graph/selector_methods.py

@@ -405,27 +405,38 @@ class StateSelectorMethod(SelectorMethod):
 
         return modified
 
-    def recursively_check_macros_modified(self, node):
-        # check if there are any changes in macros the first time
-        if self.modified_macros is None:
-            self.modified_macros = self._macros_modified()
-
+    def recursively_check_macros_modified(self, node, previous_macros):
         # loop through all macros that this node depends on
         for macro_uid in node.depends_on.macros:
+            # avoid infinite recursion if we've already seen this macro
+            if macro_uid in previous_macros:
+                continue
+            previous_macros.append(macro_uid)
             # is this macro one of the modified macros?
             if macro_uid in self.modified_macros:
                 return True
             # if not, and this macro depends on other macros, keep looping
-            macro = self.manifest.macros[macro_uid]
-            if len(macro.depends_on.macros) > 0:
-                return self.recursively_check_macros_modified(macro)
+            macro_node = self.manifest.macros[macro_uid]
+            if len(macro_node.depends_on.macros) > 0:
+                return self.recursively_check_macros_modified(macro_node, previous_macros)
             else:
                 return False
-        return False
+
+    def check_macros_modified(self, node):
+        # check if there are any changes in macros the first time
+        if self.modified_macros is None:
+            self.modified_macros = self._macros_modified()
+        # no macros have been modified, skip looping entirely
+        if not self.modified_macros:
+            return False
+        # recursively loop through upstream macros to see if any is modified
+        else:
+            previous_macros = []
+            return self.recursively_check_macros_modified(node, previous_macros)
 
     def check_modified(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
         different_contents = not new.same_contents(old)  # type: ignore
-        upstream_macro_change = self.recursively_check_macros_modified(new)
+        upstream_macro_change = self.check_macros_modified(new)
         return different_contents or upstream_macro_change
 
     def check_modified_body(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
@@ -457,7 +468,7 @@ class StateSelectorMethod(SelectorMethod):
             return False
 
     def check_modified_macros(self, _, new: SelectorTarget) -> bool:
-        return self.recursively_check_macros_modified(new)
+        return self.check_macros_modified(new)
 
     def check_new(self, old: Optional[SelectorTarget], new: SelectorTarget) -> bool:
         return old is None

core/dbt/graph/selector_spec.py

@@ -67,6 +67,7 @@ class SelectionCriteria:
     children: bool
     children_depth: Optional[int]
     greedy: bool = False
+    greedy_warning: bool = False  # do not raise warning for yaml selectors
 
     def __post_init__(self):
         if self.children and self.childrens_parents:
@@ -124,11 +125,11 @@ class SelectionCriteria:
             parents_depth=parents_depth,
             children=bool(dct.get('children')),
             children_depth=children_depth,
-            greedy=greedy
+            greedy=(greedy or bool(dct.get('greedy'))),
         )
 
     @classmethod
-    def dict_from_single_spec(cls, raw: str, greedy: bool = False):
+    def dict_from_single_spec(cls, raw: str):
         result = RAW_SELECTOR_PATTERN.match(raw)
         if result is None:
             return {'error': 'Invalid selector spec'}
@@ -145,6 +146,8 @@ class SelectionCriteria:
             dct['parents'] = bool(dct.get('parents'))
         if 'children' in dct:
             dct['children'] = bool(dct.get('children'))
+        if 'greedy' in dct:
+            dct['greedy'] = bool(dct.get('greedy'))
         return dct
 
     @classmethod
@@ -162,10 +165,12 @@ class BaseSelectionGroup(Iterable[SelectionSpec], metaclass=ABCMeta):
         self,
         components: Iterable[SelectionSpec],
         expect_exists: bool = False,
+        greedy_warning: bool = True,
         raw: Any = None,
     ):
         self.components: List[SelectionSpec] = list(components)
         self.expect_exists = expect_exists
+        self.greedy_warning = greedy_warning
         self.raw = raw
 
     def __iter__(self) -> Iterator[SelectionSpec]:

core/dbt/include/global_project/macros/materializations/seed/seed.sql

@@ -51,7 +51,7 @@
 {% endmacro %}
 
 {% macro get_batch_size() -%}
-  {{ adapter.dispatch('get_batch_size', 'dbt')() }}
+  {{ return(adapter.dispatch('get_batch_size', 'dbt')()) }}
 {%- endmacro %}
 
 {% macro default__get_batch_size() %}

core/dbt/main.py

@@ -406,6 +406,14 @@ def _build_build_subparser(subparsers, base_subparser):
         Store test results (failing rows) in the database
         '''
     )
+    sub.add_argument(
+        '--greedy',
+        action='store_true',
+        help='''
+        Select all tests that touch the selected resources,
+        even if they also depend on unselected resources
+        '''
+    )
     resource_values: List[str] = [
         str(s) for s in build_task.BuildTask.ALL_RESOURCE_VALUES
     ] + ['all']
@@ -637,7 +645,7 @@ def _add_table_mutability_arguments(*subparsers):
             '--full-refresh',
             action='store_true',
             help='''
-            If specified, DBT will drop incremental models and
+            If specified, dbt will drop incremental models and
             fully-recalculate the incremental table from the model definition.
             '''
         )
@@ -753,6 +761,14 @@ def _build_test_subparser(subparsers, base_subparser):
         Store test results (failing rows) in the database
         '''
     )
+    sub.add_argument(
+        '--greedy',
+        action='store_true',
+        help='''
+        Select all tests that touch the selected resources,
+        even if they also depend on unselected resources
+        '''
+    )
 
     sub.set_defaults(cls=test_task.TestTask, which='test', rpc_method='test')
     return sub
@@ -878,6 +894,14 @@ def _build_list_subparser(subparsers, base_subparser):
         metavar='SELECTOR',
         required=False,
     )
+    sub.add_argument(
+        '--greedy',
+        action='store_true',
+        help='''
+        Select all tests that touch the selected resources,
+        even if they also depend on unselected resources
+        '''
+    )
     _add_common_selector_arguments(sub)
 
     return sub

core/dbt/task/runnable.py

@@ -438,7 +438,7 @@ class GraphRunnableTask(ManifestTask):
             )
 
         if len(self._flattened_nodes) == 0:
-            logger.warning("WARNING: Nothing to do. Try checking your model "
+            logger.warning("\nWARNING: Nothing to do. Try checking your model "
                            "configs and model specification args")
             result = self.get_result(
                 results=[],

core/dbt/version.py

@@ -96,5 +96,5 @@ def _get_dbt_plugins_info():
         yield plugin_name, mod.version
 
 
-__version__ = '0.21.0b2'
+__version__ = '0.21.0rc2'
 installed = get_installed_version()

core/scripts/create_adapter_plugins.py

@@ -284,12 +284,12 @@ def parse_args(argv=None):
     parser.add_argument('adapter')
     parser.add_argument('--title-case', '-t', default=None)
     parser.add_argument('--dependency', action='append')
-    parser.add_argument('--dbt-core-version', default='0.21.0b2')
+    parser.add_argument('--dbt-core-version', default='0.21.0rc2')
     parser.add_argument('--email')
     parser.add_argument('--author')
     parser.add_argument('--url')
     parser.add_argument('--sql', action='store_true')
-    parser.add_argument('--package-version', default='0.21.0b2')
+    parser.add_argument('--package-version', default='0.21.0rc2')
     parser.add_argument('--project-version', default='1.0')
     parser.add_argument(
         '--no-dependency', action='store_false', dest='set_dependency'

core/setup.py

@@ -24,7 +24,7 @@ def read(fname):
 
 
 package_name = "dbt-core"
-package_version = "0.21.0b2"
+package_version = "0.21.0rc2"
 description = """dbt (data build tool) is a command line tool that helps \
 analysts and engineers transform data in their warehouse more effectively"""
 

docker/requirements/requirements.0.21.0rc1.txt

@@ -0,0 +1,75 @@
+agate==1.6.1
+asn1crypto==1.4.0
+attrs==21.2.0
+azure-common==1.1.27
+azure-core==1.18.0
+azure-storage-blob==12.8.1
+Babel==2.9.1
+boto3==1.18.44
+botocore==1.21.44
+cachetools==4.2.2
+certifi==2021.5.30
+cffi==1.14.6
+chardet==4.0.0
+charset-normalizer==2.0.6
+colorama==0.4.4
+cryptography==3.4.8
+google-api-core==1.31.2
+google-auth==1.35.0
+google-cloud-bigquery==2.26.0
+google-cloud-core==1.7.2
+google-crc32c==1.1.2
+google-resumable-media==2.0.2
+googleapis-common-protos==1.53.0
+grpcio==1.40.0
+hologram==0.0.14
+idna==3.2
+importlib-metadata==4.8.1
+isodate==0.6.0
+jeepney==0.7.1
+Jinja2==2.11.3
+jmespath==0.10.0
+json-rpc==1.13.0
+jsonschema==3.1.1
+keyring==21.8.0
+leather==0.3.3
+Logbook==1.5.3
+MarkupSafe==2.0.1
+mashumaro==2.5
+minimal-snowplow-tracker==0.0.2
+msgpack==1.0.2
+msrest==0.6.21
+networkx==2.6.3
+oauthlib==3.1.1
+oscrypto==1.2.1
+packaging==20.9
+parsedatetime==2.6
+proto-plus==1.19.0
+protobuf==3.18.0
+psycopg2-binary==2.9.1
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pycparser==2.20
+pycryptodomex==3.10.1
+PyJWT==2.1.0
+pyOpenSSL==20.0.1
+pyparsing==2.4.7
+pyrsistent==0.18.0
+python-dateutil==2.8.2
+python-slugify==5.0.2
+pytimeparse==1.1.8
+pytz==2021.1
+PyYAML==5.4.1
+requests==2.26.0
+requests-oauthlib==1.3.0
+rsa==4.7.2
+s3transfer==0.5.0
+SecretStorage==3.3.1
+six==1.16.0
+snowflake-connector-python==2.5.1
+sqlparse==0.4.2
+text-unidecode==1.3
+typing-extensions==3.10.0.2
+urllib3==1.26.6
+Werkzeug==2.0.1
+zipp==3.5.0

docker/requirements/requirements.0.21.0rc2.txt

@@ -0,0 +1,75 @@
+agate==1.6.1
+asn1crypto==1.4.0
+attrs==21.2.0
+azure-common==1.1.27
+azure-core==1.18.0
+azure-storage-blob==12.9.0
+Babel==2.9.1
+boto3==1.18.48
+botocore==1.21.48
+cachetools==4.2.2
+certifi==2021.5.30
+cffi==1.14.6
+chardet==4.0.0
+charset-normalizer==2.0.6
+colorama==0.4.4
+cryptography==3.4.8
+google-api-core==1.31.3
+google-auth==1.35.0
+google-cloud-bigquery==2.27.0
+google-cloud-core==1.7.2
+google-crc32c==1.2.0
+google-resumable-media==2.0.3
+googleapis-common-protos==1.53.0
+grpcio==1.40.0
+hologram==0.0.14
+idna==3.2
+importlib-metadata==4.8.1
+isodate==0.6.0
+jeepney==0.7.1
+Jinja2==2.11.3
+jmespath==0.10.0
+json-rpc==1.13.0
+jsonschema==3.1.1
+keyring==21.8.0
+leather==0.3.3
+Logbook==1.5.3
+MarkupSafe==2.0.1
+mashumaro==2.5
+minimal-snowplow-tracker==0.0.2
+msgpack==1.0.2
+msrest==0.6.21
+networkx==2.6.3
+oauthlib==3.1.1
+oscrypto==1.2.1
+packaging==20.9
+parsedatetime==2.6
+proto-plus==1.19.0
+protobuf==3.17.3
+psycopg2-binary==2.9.1
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pycparser==2.20
+pycryptodomex==3.10.4
+PyJWT==2.1.0
+pyOpenSSL==20.0.1
+pyparsing==2.4.7
+pyrsistent==0.18.0
+python-dateutil==2.8.2
+python-slugify==5.0.2
+pytimeparse==1.1.8
+pytz==2021.1
+PyYAML==5.4.1
+requests==2.26.0
+requests-oauthlib==1.3.0
+rsa==4.7.2
+s3transfer==0.5.0
+SecretStorage==3.3.1
+six==1.16.0
+snowflake-connector-python==2.5.1
+sqlparse==0.4.2
+text-unidecode==1.3
+typing-extensions==3.10.0.2
+urllib3==1.26.7
+Werkzeug==2.0.1
+zipp==3.5.0

plugins/bigquery/dbt/adapters/bigquery/__version__.py

@@ -1 +1 @@
-version = '0.21.0b2'
+version = '0.21.0rc2'

plugins/bigquery/setup.py

@@ -20,7 +20,7 @@ except ImportError:
 
 
 package_name = "dbt-bigquery"
-package_version = "0.21.0b2"
+package_version = "0.21.0rc2"
 description = """The bigquery adapter plugin for dbt (data build tool)"""
 
 this_directory = os.path.abspath(os.path.dirname(__file__))

plugins/postgres/dbt/adapters/postgres/__version__.py

@@ -1 +1 @@
-version = '0.21.0b2'
+version = '0.21.0rc2'

plugins/postgres/setup.py

@@ -41,7 +41,7 @@ def _dbt_psycopg2_name():
 
 
 package_name = "dbt-postgres"
-package_version = "0.21.0b2"
+package_version = "0.21.0rc2"
 description = """The postgres adpter plugin for dbt (data build tool)"""
 
 this_directory = os.path.abspath(os.path.dirname(__file__))

plugins/redshift/dbt/adapters/redshift/__version__.py

@@ -1 +1 @@
-version = '0.21.0b2'
+version = '0.21.0rc2'

plugins/redshift/setup.py

@@ -20,7 +20,7 @@ except ImportError:
 
 
 package_name = "dbt-redshift"
-package_version = "0.21.0b2"
+package_version = "0.21.0rc2"
 description = """The redshift adapter plugin for dbt (data build tool)"""
 
 this_directory = os.path.abspath(os.path.dirname(__file__))

plugins/snowflake/dbt/adapters/snowflake/__version__.py

@@ -1 +1 @@
-version = '0.21.0b2'
+version = '0.21.0rc2'

plugins/snowflake/dbt/include/snowflake/macros/materializations/seed.sql

@@ -1,4 +1,5 @@
 {% macro snowflake__load_csv_rows(model, agate_table) %}
+    {% set batch_size = get_batch_size() %}
     {% set cols_sql = get_seed_column_quoted_csv(model, agate_table.column_names) %}
     {% set bindings = [] %}
 

plugins/snowflake/setup.py

@@ -20,7 +20,7 @@ except ImportError:
 
 
 package_name = "dbt-snowflake"
-package_version = "0.21.0b2"
+package_version = "0.21.0rc2"
 description = """The snowflake adapter plugin for dbt (data build tool)"""
 
 this_directory = os.path.abspath(os.path.dirname(__file__))

setup.py

@@ -24,7 +24,7 @@ with open(os.path.join(this_directory, 'README.md')) as f:
 
 
 package_name = "dbt"
-package_version = "0.21.0b2"
+package_version = "0.21.0rc2"
 description = """With dbt, data analysts and engineers can build analytics \
 the way engineers build applications."""
 

test/integration/005_simple_seed_test/data-big/.gitignore

@@ -0,0 +1 @@
+*.csv

test/integration/005_simple_seed_test/test_simple_seed.py

@@ -1,5 +1,5 @@
 import os
-
+import csv
 from test.integration.base import DBTIntegrationTest, use_profile
 
 
@@ -311,4 +311,43 @@ class TestSimpleSeedWithDots(DBTIntegrationTest):
     @use_profile('postgres')
     def test_postgres_simple_seed(self):
         results = self.run_dbt(["seed"])
-        self.assertEqual(len(results),  1)
+        self.assertEqual(len(results),  1)
+        
+class TestSimpleBigSeedBatched(DBTIntegrationTest):
+    @property
+    def schema(self):
+        return "simple_seed_005"
+
+    @property
+    def models(self):
+        return "models"
+
+    @property
+    def project_config(self):
+        return {
+            'config-version': 2,
+            "data-paths": ['data-big'],
+            'seeds': {
+                'quote_columns': False,
+            }
+        }
+
+    def test_big_batched_seed(self):
+        with open('data-big/my_seed.csv', 'w') as f:
+            writer = csv.writer(f)
+            writer.writerow(['id'])
+            for i in range(0, 20000):
+                writer.writerow([i])
+            
+        results = self.run_dbt(["seed"])
+        self.assertEqual(len(results),  1)
+
+
+    @use_profile('postgres')
+    def test_postgres_big_batched_seed(self):
+        self.test_big_batched_seed()
+    
+    @use_profile('snowflake')
+    def test_snowflake_big_batched_seed(self):
+        self.test_big_batched_seed()
+    

test/integration/029_docs_generate_tests/test_docs_generate.py

@@ -1093,7 +1093,7 @@ class TestDocsGenerate(DBTIntegrationTest):
         )
 
         return {
-            'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v2.json',
+            'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v3.json',
             'dbt_version': dbt.version.__version__,
             'nodes': {
                 'model.test.model': {
@@ -1680,7 +1680,7 @@ class TestDocsGenerate(DBTIntegrationTest):
         snapshot_path = self.dir('snapshot/snapshot_seed.sql')
 
         return {
-            'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v2.json',
+            'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v3.json',
             'dbt_version': dbt.version.__version__,
             'nodes': {
                 'model.test.ephemeral_copy': {
@@ -2203,7 +2203,7 @@ class TestDocsGenerate(DBTIntegrationTest):
         my_schema_name = self.unique_schema()
 
         return {
-            'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v2.json',
+            'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v3.json',
             'dbt_version': dbt.version.__version__,
             'nodes': {
                 'model.test.clustered': {
@@ -2695,7 +2695,7 @@ class TestDocsGenerate(DBTIntegrationTest):
         snapshot_path = self.dir('snapshot/snapshot_seed.sql')
 
         return {
-            'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v2.json',
+            'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v3.json',
             'dbt_version': dbt.version.__version__,
             'nodes': {
                 'model.test.model': {
@@ -2959,7 +2959,7 @@ class TestDocsGenerate(DBTIntegrationTest):
             elif key == 'metadata':
                 metadata = manifest['metadata']
                 self.verify_metadata(
-                    metadata, 'https://schemas.getdbt.com/dbt/manifest/v2.json')
+                    metadata, 'https://schemas.getdbt.com/dbt/manifest/v3.json')
                 assert 'project_id' in metadata and metadata[
                     'project_id'] == '098f6bcd4621d373cade4e832627b4f6'
                 assert 'send_anonymous_usage_stats' in metadata and metadata[
@@ -3100,7 +3100,7 @@ class TestDocsGenerate(DBTIntegrationTest):
         run_results = _read_json('./target/run_results.json')
         assert 'metadata' in run_results
         self.verify_metadata(
-            run_results['metadata'], 'https://schemas.getdbt.com/dbt/run-results/v2.json')
+            run_results['metadata'], 'https://schemas.getdbt.com/dbt/run-results/v3.json')
         self.assertIn('elapsed_time', run_results)
         self.assertGreater(run_results['elapsed_time'], 0)
         self.assertTrue(

test/integration/042_sources_test/test_sources.py

@@ -248,7 +248,7 @@ class TestSourceFreshness(SuccessfulSourcesTest):
         assert isinstance(data['elapsed_time'], float)
         self.assertBetween(data['metadata']['generated_at'],
                            self.freshness_start_time)
-        assert data['metadata']['dbt_schema_version'] == 'https://schemas.getdbt.com/dbt/sources/v1.json'
+        assert data['metadata']['dbt_schema_version'] == 'https://schemas.getdbt.com/dbt/sources/v2.json'
         assert data['metadata']['dbt_version'] == dbt.version.__version__
         assert data['metadata']['invocation_id'] == dbt.tracking.active_user.invocation_id
         key = 'key'

test/integration/062_defer_state_test/macros/infinite_macros.sql

@@ -0,0 +1,13 @@
+{# trigger infinite recursion if not handled #}
+
+{% macro my_infinitely_recursive_macro() %}
+  {{ return(adapter.dispatch('my_infinitely_recursive_macro')()) }}
+{% endmacro %}
+
+{% macro default__my_infinitely_recursive_macro() %}
+    {% if unmet_condition %}
+        {{ my_infinitely_recursive_macro() }}
+    {% else %}
+        {{ return('') }}
+    {% endif %}
+{% endmacro %}

test/integration/062_defer_state_test/models/view_model.sql

@@ -1 +1,4 @@
 select * from {{ ref('seed') }}
+
+-- establish a macro dependency that trips infinite recursion if not handled
+-- depends on: {{ my_infinitely_recursive_macro() }}

test/integration/066_test_selection_tests/test_selection_expansion.py

@@ -1,4 +1,5 @@
 from test.integration.base import DBTIntegrationTest, FakeArgs, use_profile
+import yaml
 
 from dbt.task.test import TestTask
 from dbt.task.list import ListTask
@@ -20,12 +21,18 @@ class TestSelectionExpansion(DBTIntegrationTest):
             "test-paths": ["tests"]
         }
 
-    def list_tests_and_assert(self, include, exclude, expected_tests):
+    def list_tests_and_assert(self, include, exclude, expected_tests, greedy=False, selector_name=None):
         list_args = [ 'ls', '--resource-type', 'test']
         if include:
             list_args.extend(('--select', include))
         if exclude:
             list_args.extend(('--exclude', exclude))
+        if exclude:
+            list_args.extend(('--exclude', exclude))
+        if greedy:
+            list_args.append('--greedy')
+        if selector_name:
+            list_args.extend(('--selector', selector_name))
         
         listed = self.run_dbt(list_args)
         assert len(listed) == len(expected_tests)
@@ -34,7 +41,7 @@ class TestSelectionExpansion(DBTIntegrationTest):
         assert sorted(test_names) == sorted(expected_tests)
 
     def run_tests_and_assert(
-        self, include, exclude, expected_tests, schema = False, data = False
+        self, include, exclude, expected_tests, schema=False, data=False, greedy=False, selector_name=None
     ):
         results = self.run_dbt(['run'])
         self.assertEqual(len(results), 2)
@@ -48,6 +55,10 @@ class TestSelectionExpansion(DBTIntegrationTest):
             test_args.append('--schema')
         if data:
             test_args.append('--data')
+        if greedy:
+            test_args.append('--greedy')
+        if selector_name:
+            test_args.extend(('--selector', selector_name))
         
         results = self.run_dbt(test_args)
         tests_run = [r.node.name for r in results]
@@ -228,3 +239,80 @@ class TestSelectionExpansion(DBTIntegrationTest):
         
         self.list_tests_and_assert(select, exclude, expected)
         self.run_tests_and_assert(select, exclude, expected)
+
+    @use_profile('postgres')
+    def test__postgres__model_a_greedy(self):
+        select = 'model_a'
+        exclude = None
+        greedy = True
+        expected = [
+            'cf_a_b', 'cf_a_src', 'just_a',
+            'relationships_model_a_fun__fun__ref_model_b_',
+            'relationships_model_a_fun__fun__source_my_src_my_tbl_',
+            'unique_model_a_fun'
+        ]
+            
+        self.list_tests_and_assert(select, exclude, expected, greedy)
+        self.run_tests_and_assert(select, exclude, expected, greedy=greedy)
+
+    @use_profile('postgres')
+    def test__postgres__model_a_greedy_exclude_unique_tests(self):
+        select = 'model_a'
+        exclude = 'test_name:unique'
+        greedy = True
+        expected = [
+            'cf_a_b', 'cf_a_src', 'just_a',
+            'relationships_model_a_fun__fun__ref_model_b_',
+            'relationships_model_a_fun__fun__source_my_src_my_tbl_',
+        ]
+            
+        self.list_tests_and_assert(select, exclude, expected, greedy)
+        self.run_tests_and_assert(select, exclude, expected, greedy=greedy)
+
+class TestExpansionWithSelectors(TestSelectionExpansion):
+
+    @property
+    def selectors_config(self):
+        return yaml.safe_load('''
+            selectors:
+            - name: model_a_greedy_none
+              definition:
+                method: fqn
+                value: model_a
+            - name: model_a_greedy_false
+              definition:
+                method: fqn
+                value: model_a
+                greedy: false
+            - name: model_a_greedy_true
+              definition:
+                method: fqn
+                value: model_a
+                greedy: true
+        ''')
+
+    @use_profile('postgres')
+    def test__postgres__selector_model_a_not_greedy(self):
+        expected = ['just_a','unique_model_a_fun']
+        
+        # when greedy is not specified, so implicitly False
+        self.list_tests_and_assert(include=None, exclude=None, expected_tests=expected, selector_name='model_a_greedy_none')
+        self.run_tests_and_assert(include=None, exclude=None, expected_tests=expected, selector_name='model_a_greedy_none')
+
+        # when greedy is explicitly False
+        self.list_tests_and_assert(include=None, exclude=None, expected_tests=expected, selector_name='model_a_greedy_false')
+        self.run_tests_and_assert(include=None, exclude=None, expected_tests=expected, selector_name='model_a_greedy_false')
+
+
+    @use_profile('postgres')
+    def test__postgres__selector_model_a_yes_greedy(self):
+        expected = [
+            'cf_a_b', 'cf_a_src', 'just_a',
+            'relationships_model_a_fun__fun__ref_model_b_',
+            'relationships_model_a_fun__fun__source_my_src_my_tbl_',
+            'unique_model_a_fun'
+        ]
+
+        # when greedy is explicitly False
+        self.list_tests_and_assert(include=None, exclude=None, expected_tests=expected, selector_name='model_a_greedy_true')
+        self.run_tests_and_assert(include=None, exclude=None, expected_tests=expected, selector_name='model_a_greedy_true')

test/unit/test_graph_selection.py

@@ -120,7 +120,7 @@ def test_run_specs(include, exclude, expected):
     manifest = _get_manifest(graph)
     selector = graph_selector.NodeSelector(graph, manifest)
     spec = graph_cli.parse_difference(include, exclude)
-    selected = selector.select_nodes(spec)
+    selected, _ = selector.select_nodes(spec)
 
     assert selected == expected
 

test/unit/test_manifest.py

@@ -273,7 +273,7 @@ class ManifestTest(unittest.TestCase):
                 'child_map': {},
                 'metadata': {
                     'generated_at': '2018-02-14T09:15:13Z',
-                    'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v2.json',
+                    'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v3.json',
                     'dbt_version': dbt.version.__version__,
                     'env': {ENV_KEY_NAME: 'value'},
                     # invocation_id is None, so it will not be present
@@ -419,7 +419,7 @@ class ManifestTest(unittest.TestCase):
                 'docs': {},
                 'metadata': {
                     'generated_at': '2018-02-14T09:15:13Z',
-                    'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v2.json',
+                    'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v3.json',
                     'dbt_version': dbt.version.__version__,
                     'project_id': '098f6bcd4621d373cade4e832627b4f6',
                     'user_id': 'cfc9500f-dc7f-4c83-9ea7-2c581c1b38cf',
@@ -662,7 +662,7 @@ class MixedManifestTest(unittest.TestCase):
                 'child_map': {},
                 'metadata': {
                     'generated_at': '2018-02-14T09:15:13Z',
-                    'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v2.json',
+                    'dbt_schema_version': 'https://schemas.getdbt.com/dbt/manifest/v3.json',
                     'dbt_version': dbt.version.__version__,
                     'invocation_id': '01234567-0123-0123-0123-0123456789ab',
                     'env': {ENV_KEY_NAME: 'value'},