Add a path: selector to the node selector (#454)

CHANGELOG.md

@@ -6,6 +6,7 @@
 - Support adapter-specific aliases (like `project` and `dataset` on BigQuery) in source definitions. ([#2133](https://github.com/fishtown-analytics/dbt/issues/2133), [#2244](https://github.com/fishtown-analytics/dbt/pull/2244))
 - Users can now use jinja as arguments to tests. Test arguments are rendered in the native context and injected into the test execution context directly. ([#2149](https://github.com/fishtown-analytics/dbt/issues/2149), [#2220](https://github.com/fishtown-analytics/dbt/pull/2220))
 - Added support for `db_groups` and `autocreate` flags in Redshift configurations.  ([#1995](https://github.com/fishtown-analytics/dbt/issues/1995, [#2262]https://github.com/fishtown-analytics/dbt/pull/2262))
+- Users can supply paths as arguments to `--models` and `--select`, either explicitily by prefixing with `path:` or implicitly with no prefix. ([#454](https://github.com/fishtown-analytics/dbt/issues/454), [#2258](https://github.com/fishtown-analytics/dbt/pull/2258))
 
 ### Fixes
 - When a jinja value is undefined, give a helpful error instead of failing with cryptic "cannot pickle ParserMacroCapture" errors ([#2110](https://github.com/fishtown-analytics/dbt/issues/2110), [#2184](https://github.com/fishtown-analytics/dbt/pull/2184))

core/dbt/graph/selector.py

@@ -1,5 +1,7 @@
+import os
 from enum import Enum
 from itertools import chain
+from pathlib import Path
 from typing import Set, Iterable, Union, List, Container, Tuple, Optional
 
 import networkx as nx  # type: ignore
@@ -16,13 +18,24 @@
 SELECTOR_DELIMITER = ':'
 
 
+def _probably_path(value: str):
+    """Decide if value is probably a path. Windows has two path separators, so
+    we should check both sep ('\\') and altsep ('/') there.
+    """
+    if os.path.sep in value:
+        return True
+    elif os.path.altsep is not None and os.path.altsep in value:
+        return True
+    else:
+        return False
+
+
 class SelectionCriteria:
     def __init__(self, node_spec: str):
         self.raw = node_spec
         self.select_children = False
         self.select_parents = False
         self.select_childrens_parents = False
-        self.selector_type = SELECTOR_FILTERS.FQN
 
         if node_spec.startswith(SELECTOR_CHILDREN_AND_ANCESTORS):
             self.select_childrens_parents = True
@@ -48,12 +61,19 @@ def __init__(self, node_spec: str):
             self.selector_type = SELECTOR_FILTERS(selector_type)
         else:
             self.selector_value = node_spec
+            # if the selector type has an OS path separator in it, it can't
+            # really be a valid file name, so assume it's a path.
+            if _probably_path(node_spec):
+                self.selector_type = SELECTOR_FILTERS.PATH
+            else:
+                self.selector_type = SELECTOR_FILTERS.FQN
 
 
 class SELECTOR_FILTERS(str, Enum):
     FQN = 'fqn'
     TAG = 'tag'
     SOURCE = 'source'
+    PATH = 'path'
 
     def __str__(self):
         return self._value_
@@ -219,6 +239,29 @@ def search(self, included_nodes, selector):
                 yield node
 
 
+class PathSelector(ManifestSelector):
+    FILTER = SELECTOR_FILTERS.PATH
+
+    def search(self, included_nodes, selector):
+        """Yield all nodes in the graph that match the given path.
+
+        :param str selector: The path selector
+        """
+        # use '.' and not 'root' for easy comparison
+        root = Path.cwd()
+        paths = set(p.relative_to(root) for p in root.glob(selector))
+        search = chain(self.parsed_nodes(included_nodes),
+                       self.source_nodes(included_nodes))
+        for node, real_node in search:
+            if Path(real_node.root_path) != root:
+                continue
+            ofp = Path(real_node.original_file_path)
+            if ofp in paths:
+                yield node
+            elif any(parent in paths for parent in ofp.parents):
+                yield node
+
+
 class InvalidSelectorError(Exception):
     pass
 
@@ -231,7 +274,12 @@ class MultiSelector:
     selector types, including the glob operator, but does not handle any graph
     related behavior.
     """
-    SELECTORS = [QualifiedNameSelector, TagSelector, SourceSelector]
+    SELECTORS = [
+        QualifiedNameSelector,
+        TagSelector,
+        SourceSelector,
+        PathSelector,
+    ]
 
     def __init__(self, manifest):
         self.manifest = manifest

test/integration/006_simple_dependency_test/test_local_dependency.py

@@ -65,6 +65,26 @@ def test_postgres_local_dependency(self):
             2
         )
 
+    @use_profile('postgres')
+    def test_postgres_no_dependency_paths(self):
+        self.run_dbt(['deps'])
+        self.run_dbt(['seed'])
+        # this should work
+        local_path = os.path.join('local_models', 'my_model.sql')
+        results = self.run_dbt(
+            ['run', '--models',  f'+{local_path}']
+        )
+        # should run the dependency and my_model
+        self.assertEqual(len(results), 2)
+
+        # this should not work
+        dep_path = os.path.join('models', 'model_to_import.sql')
+        results = self.run_dbt(
+            ['run', '--models', f'+{dep_path}'],
+        )
+        # should not run the dependency, because it "doesn't exist".
+        self.assertEqual(len(results), 0)
+
 
 class TestMissingDependency(DBTIntegrationTest):
     @property

test/integration/007_graph_selection_tests/test_graph_selection.py

@@ -112,7 +112,6 @@ def test__snowflake__specific_model_and_children(self):
         self.assertFalse('BASE_USERS' in created_models)
         self.assertFalse('EMAILS' in created_models)
 
-
     @use_profile('postgres')
     def test__postgres__specific_model_and_parents(self):
         self.run_sql_file("seed.sql")
@@ -143,13 +142,12 @@ def test__snowflake__specific_model_and_parents(self):
         self.assertFalse('BASE_USERS' in created_models)
         self.assertFalse('EMAILS' in created_models)
 
-
     @use_profile('postgres')
     def test__postgres__specific_model_with_exclusion(self):
         self.run_sql_file("seed.sql")
 
         results = self.run_dbt(
-            ['run', '--models', '+users_rollup', '--exclude', 'users_rollup']
+            ['run', '--models', '+users_rollup', '--exclude', 'models/users_rollup.sql']
         )
         self.assertEqual(len(results),  1)
 
@@ -188,6 +186,17 @@ def test__postgres__locally_qualified_name(self):
         self.assertIn('nested_users', created_models)
         self.assert_correct_schemas()
 
+        results = self.run_dbt(['run', '--models', 'models/test/subdir*'])
+        self.assertEqual(len(results), 2)
+
+        created_models = self.get_models_in_schema()
+        self.assertNotIn('users_rollup', created_models)
+        self.assertNotIn('base_users', created_models)
+        self.assertNotIn('emails', created_models)
+        self.assertIn('subdir', created_models)
+        self.assertIn('nested_users', created_models)
+        self.assert_correct_schemas()
+
     @use_profile('postgres')
     def test__postgres__childrens_parents(self):
         self.run_sql_file("seed.sql")
@@ -218,7 +227,7 @@ def test__postgres__more_childrens_parents(self):
     @use_profile('snowflake')
     def test__snowflake__skip_intermediate(self):
         self.run_sql_file("seed.sql")
-        results = self.run_dbt(['run', '--models', '@users'])
+        results = self.run_dbt(['run', '--models', '@models/users.sql'])
         # base_users, emails, users_rollup, users_rollup_dependency
         self.assertEqual(len(results), 4)