cumulusci 4.0.1.dev0__tar.gz → 4.0.1.dev1__tar.gz

{cumulusci-4.0.1.dev0 → cumulusci-4.0.1.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cumulusci
-Version: 4.0.1.dev0
+Version: 4.0.1.dev1
 Summary: Build and release tools for Salesforce developers
 Project-URL: Homepage, https://github.com/SFDO-Tooling/CumulusCI
 Project-URL: Changelog, https://cumulusci.readthedocs.io/en/stable/history.html
@@ -19,7 +19,6 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Python: >=3.11
-Requires-Dist: annoy
 Requires-Dist: click>=8.1
 Requires-Dist: cryptography
 Requires-Dist: defusedxml
@@ -31,8 +30,6 @@ Requires-Dist: jinja2
 Requires-Dist: keyring<=23.0.1
 Requires-Dist: lxml
 Requires-Dist: markupsafe
-Requires-Dist: numpy
-Requires-Dist: pandas
 Requires-Dist: psutil
 Requires-Dist: pydantic<2
 Requires-Dist: pyjwt
@@ -49,12 +46,16 @@ Requires-Dist: robotframework-seleniumlibrary<6
 Requires-Dist: rst2ansi>=0.1.5
 Requires-Dist: salesforce-bulk
 Requires-Dist: sarge
-Requires-Dist: scikit-learn
 Requires-Dist: selenium<4
 Requires-Dist: simple-salesforce==1.11.4
 Requires-Dist: snowfakery>=4.0.0
 Requires-Dist: sqlalchemy<2
 Requires-Dist: xmltodict
+Provides-Extra: select
+Requires-Dist: annoy; extra == 'select'
+Requires-Dist: numpy; extra == 'select'
+Requires-Dist: pandas; extra == 'select'
+Requires-Dist: scikit-learn; extra == 'select'
 Description-Content-Type: text/markdown
 
 # CumulusCI
@@ -125,7 +126,7 @@ license](https://github.com/SFDO-Tooling/CumulusCI/blob/main/LICENSE)
 and is not covered by the Salesforce Master Subscription Agreement.
 
 <!-- Changelog -->
-## v4.0.1.dev0 (2024-12-16)
+## v4.0.1.dev1 (2025-01-01)
 
 <!-- Release notes generated using configuration in .github/release.yml at main -->
 
@@ -133,11 +134,7 @@ and is not covered by the Salesforce Master Subscription Agreement.
 
 ### Changes 🎉
 
--   @W-16485311: Core Logic for Selecting Records from Target Org by [@aditya-balachander](https://github.com/aditya-balachander) in [#3818](https://github.com/SFDO-Tooling/CumulusCI/pull/3818)
--   Add integration tests for all selection strategies by [@mjawadtp](https://github.com/mjawadtp) in [#3851](https://github.com/SFDO-Tooling/CumulusCI/pull/3851)
--   @W-17357226: Fix for issue where zero threshold defaulted to select by [@aditya-balachander](https://github.com/aditya-balachander) in [#3853](https://github.com/SFDO-Tooling/CumulusCI/pull/3853)
--   @W-17366392: Fix Omnistudio issues for the sf command format by [@lakshmi2506](https://github.com/lakshmi2506) in [#3855](https://github.com/SFDO-Tooling/CumulusCI/pull/3855)
--   fix: restore task and flow reference docs by [@jstvz](https://github.com/jstvz) in [#3856](https://github.com/SFDO-Tooling/CumulusCI/pull/3856)
--   @W-17412267: Fix for records not being inserted when threshold 0 by [@aditya-balachander](https://github.com/aditya-balachander) in [#3857](https://github.com/SFDO-Tooling/CumulusCI/pull/3857)
+-   @W-17427085: Set ANNOY related dependencies to be optional by [@aditya-balachander](https://github.com/aditya-balachander) in [#3858](https://github.com/SFDO-Tooling/CumulusCI/pull/3858)
+-   Update on the documentation for SFDX_ORG_CREATE_ARGS environment variable by [@lakshmi2506](https://github.com/lakshmi2506) in [#3861](https://github.com/SFDO-Tooling/CumulusCI/pull/3861)
 
-**Full Changelog**: https://github.com/SFDO-Tooling/CumulusCI/compare/v4.0.1...v4.0.1.dev0
+**Full Changelog**: https://github.com/SFDO-Tooling/CumulusCI/compare/v4.0.1.dev0...v4.0.1.dev1

cumulusci-4.0.1.dev1/cumulusci/__about__.py

@@ -0,0 +1 @@
+__version__ = "4.0.1.dev1"

{cumulusci-4.0.1.dev0 → cumulusci-4.0.1.dev1}/cumulusci/tasks/bulkdata/select_utils.py

@@ -1,22 +1,37 @@
+import logging
 import random
 import re
 import typing as T
 from enum import Enum
 
-import numpy as np
-import pandas as pd
-from annoy import AnnoyIndex
 from pydantic import Field, root_validator, validator
-from sklearn.feature_extraction.text import HashingVectorizer
-from sklearn.preprocessing import StandardScaler
 
 from cumulusci.core.enums import StrEnum
 from cumulusci.tasks.bulkdata.extract_dataset_utils.hardcoded_default_declarations import (
     DEFAULT_DECLARATIONS,
 )
 from cumulusci.tasks.bulkdata.utils import CaseInsensitiveDict
+from cumulusci.utils import get_cci_upgrade_command
 from cumulusci.utils.yaml.model_parser import CCIDictModel
 
+logger = logging.getLogger(__name__)
+try:
+    import numpy as np
+    import pandas as pd
+    from annoy import AnnoyIndex
+    from sklearn.feature_extraction.text import HashingVectorizer
+    from sklearn.preprocessing import StandardScaler
+
+    OPTIONAL_DEPENDENCIES_AVAILABLE = True
+except ImportError:
+    logger.warning(
+        f"Optional dependencies are missing. "
+        "Handling high volumes of records for the 'select' functionality will be significantly slower, "
+        "as optimizations for this feature are currently disabled. "
+        f"To enable optimized performance, install all required dependencies using: {get_cci_upgrade_command()}[select]\n"
+    )
+    OPTIONAL_DEPENDENCIES_AVAILABLE = False
+
 
 class SelectStrategy(StrEnum):
     """Enum defining the different selection strategies requested."""
@@ -308,7 +323,7 @@ def similarity_post_process(
     select_records = []
     insert_records = []
 
-    if complexity_constant < 1000:
+    if complexity_constant < 1000 or not OPTIONAL_DEPENDENCIES_AVAILABLE:
         select_records, insert_records = levenshtein_post_process(
             load_records, query_records, fields, weights, threshold
         )
@@ -328,6 +343,12 @@ def annoy_post_process(
     threshold: T.Union[float, None],
 ) -> T.Tuple[T.List[dict], list]:
     """Processes the query results for the similarity selection strategy using Annoy algorithm for large number of records"""
+    # Add warning when threshold is 0
+    if threshold is not None and threshold == 0:
+        logger.warning(
+            "Warning: A threshold of 0 may miss exact matches in high volumes. Use a small value like 0.1 for better accuracy."
+        )
+
     selected_records = []
     insertion_candidates = []
 

{cumulusci-4.0.1.dev0 → cumulusci-4.0.1.dev1}/cumulusci/tasks/bulkdata/tests/test_select_utils.py

@@ -1,7 +1,7 @@
-import pandas as pd
 import pytest
 
 from cumulusci.tasks.bulkdata.select_utils import (
+    OPTIONAL_DEPENDENCIES_AVAILABLE,
     SelectOperationExecutor,
     SelectStrategy,
     add_limit_offset_to_user_filter,
@@ -15,6 +15,14 @@ from cumulusci.tasks.bulkdata.select_utils import (
     vectorize_records,
 )
 
+# Check for pandas availability
+try:
+    import pandas as pd
+
+    PANDAS_AVAILABLE = True
+except ImportError:
+    PANDAS_AVAILABLE = False
+
 
 # Test Cases for standard_generate_query
 def test_standard_generate_query_with_default_record_declaration():
@@ -511,6 +519,10 @@ def test_calculate_levenshtein_distance_weights_length_doesnt_match():
     assert "Records must be same size as fields (weights)." in str(e.value)
 
 
+@pytest.mark.skipif(
+    not PANDAS_AVAILABLE or not OPTIONAL_DEPENDENCIES_AVAILABLE,
+    reason="requires optional dependencies for annoy",
+)
 def test_all_numeric_columns():
     df_db = pd.DataFrame({"A": ["1", "2", "3"], "B": ["4.5", " 5.5", "6.5"]})
     df_query = pd.DataFrame({"A": ["4", "5", ""], "B": ["4.5", "5.5", "6.5"]})
@@ -526,6 +538,10 @@ def test_all_numeric_columns():
     assert determine_field_types(df_db, df_query, weights) == expected_output
 
 
+@pytest.mark.skipif(
+    not PANDAS_AVAILABLE or not OPTIONAL_DEPENDENCIES_AVAILABLE,
+    reason="requires optional dependencies for annoy",
+)
 def test_numeric_columns__one_non_numeric():
     df_db = pd.DataFrame({"A": ["1", "2", "3"], "B": ["4.5", "5.5", "6.5"]})
     df_query = pd.DataFrame({"A": ["4", "5", "6"], "B": ["abcd", "5.5", "6.5"]})
@@ -541,6 +557,10 @@ def test_numeric_columns__one_non_numeric():
     assert determine_field_types(df_db, df_query, weights) == expected_output
 
 
+@pytest.mark.skipif(
+    not PANDAS_AVAILABLE or not OPTIONAL_DEPENDENCIES_AVAILABLE,
+    reason="requires optional dependencies for annoy",
+)
 def test_all_boolean_columns():
     df_db = pd.DataFrame(
         {"A": ["true", "false", "true"], "B": ["false", "true", "false"]}
@@ -560,6 +580,10 @@ def test_all_boolean_columns():
     assert determine_field_types(df_db, df_query, weights) == expected_output
 
 
+@pytest.mark.skipif(
+    not PANDAS_AVAILABLE or not OPTIONAL_DEPENDENCIES_AVAILABLE,
+    reason="requires optional dependencies for annoy",
+)
 def test_all_categorical_columns():
     df_db = pd.DataFrame(
         {"A": ["apple", "banana", "cherry"], "B": ["dog", "cat", "mouse"]}
@@ -579,6 +603,10 @@ def test_all_categorical_columns():
     assert determine_field_types(df_db, df_query, weights) == expected_output
 
 
+@pytest.mark.skipif(
+    not PANDAS_AVAILABLE or not OPTIONAL_DEPENDENCIES_AVAILABLE,
+    reason="requires optional dependencies for annoy",
+)
 def test_mixed_types():
     df_db = pd.DataFrame(
         {
@@ -606,6 +634,10 @@ def test_mixed_types():
     assert determine_field_types(df_db, df_query, weights) == expected_output
 
 
+@pytest.mark.skipif(
+    not PANDAS_AVAILABLE or not OPTIONAL_DEPENDENCIES_AVAILABLE,
+    reason="requires optional dependencies for annoy",
+)
 def test_vectorize_records_mixed_numerical_boolean_categorical():
     # Test data with mixed types: numerical and categorical only
     db_records = [["1.0", "true", "apple"], ["2.0", "false", "banana"]]
@@ -633,6 +665,10 @@ def test_vectorize_records_mixed_numerical_boolean_categorical():
     ), "Query vectors column count mismatch"
 
 
+@pytest.mark.skipif(
+    not PANDAS_AVAILABLE or not OPTIONAL_DEPENDENCIES_AVAILABLE,
+    reason="requires optional dependencies for annoy",
+)
 def test_annoy_post_process():
     # Test data
     load_records = [["Alice", "Engineer"], ["Bob", "Doctor"]]
@@ -659,6 +695,10 @@ def test_annoy_post_process():
     assert not insert_records
 
 
+@pytest.mark.skipif(
+    not PANDAS_AVAILABLE or not OPTIONAL_DEPENDENCIES_AVAILABLE,
+    reason="requires optional dependencies for annoy",
+)
 def test_annoy_post_process__insert_records():
     # Test data
     load_records = [["Alice", "Engineer"], ["Bob", "Doctor"]]
@@ -714,6 +754,10 @@ def test_annoy_post_process__no_query_records():
     ]  # The first insert record should match the second load record
 
 
+@pytest.mark.skipif(
+    not PANDAS_AVAILABLE or not OPTIONAL_DEPENDENCIES_AVAILABLE,
+    reason="requires optional dependencies for annoy",
+)
 def test_annoy_post_process__insert_records_with_polymorphic_fields():
     # Test data
     load_records = [
@@ -749,6 +793,10 @@ def test_annoy_post_process__insert_records_with_polymorphic_fields():
     ]  # The first insert record should match the second load record
 
 
+@pytest.mark.skipif(
+    not PANDAS_AVAILABLE or not OPTIONAL_DEPENDENCIES_AVAILABLE,
+    reason="requires optional dependencies for annoy",
+)
 def test_single_record_match_annoy_post_process():
     # Mock data where only the first query record matches the first load record
     load_records = [["Alice", "Engineer"], ["Bob", "Doctor"]]

{cumulusci-4.0.1.dev0 → cumulusci-4.0.1.dev1}/docs/history.md

@@ -2,6 +2,21 @@
 
 <!-- latest-start -->
 
+## v4.0.1.dev1 (2025-01-01)
+
+<!-- Release notes generated using configuration in .github/release.yml at main -->
+
+## What's Changed
+
+### Changes 🎉
+
+-   @W-17427085: Set ANNOY related dependencies to be optional by [@aditya-balachander](https://github.com/aditya-balachander) in [#3858](https://github.com/SFDO-Tooling/CumulusCI/pull/3858)
+-   Update on the documentation for SFDX_ORG_CREATE_ARGS environment variable by [@lakshmi2506](https://github.com/lakshmi2506) in [#3861](https://github.com/SFDO-Tooling/CumulusCI/pull/3861)
+
+**Full Changelog**: https://github.com/SFDO-Tooling/CumulusCI/compare/v4.0.1.dev0...v4.0.1.dev1
+
+<!-- latest-stop -->
+
 ## v4.0.1.dev0 (2024-12-16)
 
 <!-- Release notes generated using configuration in .github/release.yml at main -->
@@ -19,8 +34,6 @@
 
 **Full Changelog**: https://github.com/SFDO-Tooling/CumulusCI/compare/v4.0.1...v4.0.1.dev0
 
-<!-- latest-stop -->
-
 ## v4.0.1 (2024-11-18)
 
 ### Issues Fixed 🩴
@@ -1711,9 +1724,9 @@ Critical Changes:
         subfolders will see a change in resolution behavior. Previously,
         a dependency specified like this:
 
-                  dependencies:
-                      - github: https://github.com/SalesforceFoundation/NPSP
-                        subfolder: unpackaged/config/trial
+                    dependencies:
+                        - github: https://github.com/SalesforceFoundation/NPSP
+                          subfolder: unpackaged/config/trial
 
         would always deploy from the latest commit on the default
         branch. Now, this dependency will be resolved to a GitHub commit
@@ -1724,12 +1737,12 @@ Critical Changes:
     -   The `project__dependencies` section in `cumulusci.yml` no longer
         supports nested dependencies specified like this:
 
-                  dependencies:
-                      - namespace: "test"
-                        version: "1.0"
-                        dependencies:
-                          - namespace: "parent"
-                            version: "2.2"
+                    dependencies:
+                        - namespace: "test"
+                          version: "1.0"
+                          dependencies:
+                            - namespace: "parent"
+                              version: "2.2"
 
         All dependencies should be listed in install order.
 
@@ -1898,12 +1911,12 @@ Critical changes:
     -   The `project__dependencies` section in `cumulusci.yml` will no
         longer support nested dependencies specified like this :
 
-                  dependencies:
-                    - namespace: "test"
-                      version: "1.0"
-                      dependencies:
-                        - namespace: "parent"
-                          version: "2.2"
+                    dependencies:
+                      - namespace: "test"
+                        version: "1.0"
+                        dependencies:
+                          - namespace: "parent"
+                            version: "2.2"
 
     All dependencies should be listed in install order.
 
@@ -3510,33 +3523,33 @@ New features:
 
     : -
 
-                  Added keywords for generating a collection of sObjects according to a template:
+                    Added keywords for generating a collection of sObjects according to a template:
 
-                  :   -   `Generate Test Data`
-                      -   `Salesforce Collection Insert`
-                      -   `Salesforce Collection Update`
+                    :   -   `Generate Test Data`
+                        -   `Salesforce Collection Insert`
+                        -   `Salesforce Collection Update`
 
-              -
+                -
 
-                  Changes to Page Objects:
+                    Changes to Page Objects:
 
-                  :   -   More than one page object can be loaded at once.
-                          Once loaded, the keywords of a page object remain
-                          visible in the suite. Robot will give priority to
-                          keywords in the reverse order in which they were
-                          imported.
-                      -   There is a new keyword, `Log Current Page Object`,
-                          which can be useful to see information about the
-                          most recently loaded page object.
-                      -   There is a new keyword, `Get Page Object`, which
-                          will return the robot library for a given page
-                          object. This can be used in other keywords to access
-                          keywords from another page object if necessary.
-                      -   The `Go To Page` keyword will now automatically load
-                          the page object for the given page.
+                    :   -   More than one page object can be loaded at once.
+                            Once loaded, the keywords of a page object remain
+                            visible in the suite. Robot will give priority to
+                            keywords in the reverse order in which they were
+                            imported.
+                        -   There is a new keyword, `Log Current Page Object`,
+                            which can be useful to see information about the
+                            most recently loaded page object.
+                        -   There is a new keyword, `Get Page Object`, which
+                            will return the robot library for a given page
+                            object. This can be used in other keywords to access
+                            keywords from another page object if necessary.
+                        -   The `Go To Page` keyword will now automatically load
+                            the page object for the given page.
 
-              -   Added a basic debugger for Robot tests. It can be enabled
-                  using the `-o debug True` option to the robot task.
+                -   Added a basic debugger for Robot tests. It can be enabled
+                    using the `-o debug True` option to the robot task.
 
 -   Added support for deploying new metadata types
     `ProfilePasswordPolicy` and `ProfileSessionSetting`.
@@ -3611,8 +3624,8 @@ New features:
     permanently set this option, add this in
     `~/.cumulusci/cumulusci.yml`:
 
-              cli:
-                  plain_output: True
+                cli:
+                    plain_output: True
 
 -   Added additional info to the `cci version` command, including the
     Python version, an upgrade check, and a warning on Python 2.
@@ -4893,12 +4906,12 @@ Resolving a few issues from beta77:
     below. In flows that need to inject the actual namespace prefix,
     override the [unmanaged]{.title-ref} option .. :
 
-              custom_deploy_task:
-                  class_path: cumulusci.tasks.salesforce.Deploy
-                  options:
-                      path: your/custom/metadata
-                      namespace_inject: $project_config.project__package__namespace
-                      unmanaged: False
+                custom_deploy_task:
+                    class_path: cumulusci.tasks.salesforce.Deploy
+                    options:
+                        path: your/custom/metadata
+                        namespace_inject: $project_config.project__package__namespace
+                        unmanaged: False
 
 ### Enhancements
 
@@ -5613,13 +5626,13 @@ Resolving a few issues from beta77:
 -   **IMPORANT** This release changes the yaml structure for flows. The
     new structure now looks like this:
 
-              flows:
-                  flow_name:
-                      tasks:
-                          1:
-                              task: deploy
-                          2:
-                              task: run_tests
+                flows:
+                    flow_name:
+                        tasks:
+                            1:
+                                task: deploy
+                            2:
+                                task: run_tests
 
 -   See the new flow customization examples in the cookbook for examples
     of why this change was made and how to use it:

{cumulusci-4.0.1.dev0 → cumulusci-4.0.1.dev1}/pyproject.toml

@@ -23,7 +23,6 @@ classifiers = [
     "Programming Language :: Python :: 3.13",
 ]
 dependencies = [
-    "annoy",
     "click>=8.1",
     "cryptography",
     "python-dateutil",
@@ -35,8 +34,6 @@ dependencies = [
     "defusedxml",
     "lxml",
     "MarkupSafe",
-    "numpy",
-    "pandas",
     "psutil",
     "pydantic<2",
     "PyJWT",
@@ -53,7 +50,6 @@ dependencies = [
     "rst2ansi>=0.1.5",
     "salesforce-bulk",
     "sarge",
-    "scikit-learn",
     "selenium<4",
     "simple-salesforce==1.11.4",
     "snowfakery>=4.0.0",
@@ -88,6 +84,14 @@ lint = [
     "pre-commit>=3.5.0",
 ]
 
+[project.optional-dependencies]
+select = [
+    "annoy",
+    "numpy",
+    "pandas",
+    "scikit-learn",
+]
+
 [project.scripts]
 cci = "cumulusci.cli.cci:main"
 snowfakery = "snowfakery.cli:main"

cumulusci-4.0.1.dev0/cumulusci/__about__.py

@@ -1 +0,0 @@
-__version__ = "4.0.1.dev0"