rdt 1.19.1.dev0__tar.gz → 1.20.1.dev0__tar.gz

{rdt-1.19.1.dev0/rdt.egg-info → rdt-1.20.1.dev0}/PKG-INFO

@@ -1,18 +1,17 @@
 Metadata-Version: 2.4
 Name: rdt
-Version: 1.19.1.dev0
+Version: 1.20.1.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
-License: BSL-1.1
+License-Expression: BUSL-1.1
 Project-URL: Source Code, https://github.com/sdv-dev/RDT/
 Project-URL: Issue Tracker, https://github.com/sdv-dev/RDT/issues
 Project-URL: Changes, https://github.com/sdv-dev/RDT/blob/main/HISTORY.md
 Project-URL: Twitter, https://twitter.com/sdv_dev
-Project-URL: Chat, https://bit.ly/sdv-slack-invite
+Project-URL: Chat, https://forum.datacebo.com/
 Keywords: machine learning,synthetic data generation,benchmark,generative models
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
-Classifier: License :: Free for non-commercial use
 Classifier: Natural Language :: English
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
@@ -89,7 +88,7 @@ Dynamic: license-file
 [![Unit Tests](https://github.com/sdv-dev/RDT/actions/workflows/unit.yml/badge.svg)](https://github.com/sdv-dev/RDT/actions/workflows/unit.yml)
 [![Downloads](https://pepy.tech/badge/rdt)](https://pepy.tech/project/rdt)
 [![Coverage Status](https://codecov.io/gh/sdv-dev/RDT/branch/main/graph/badge.svg)](https://codecov.io/gh/sdv-dev/RDT)
-[![Slack](https://img.shields.io/badge/Community-Slack-blue?style=plastic&logo=slack)](https://bit.ly/sdv-slack-invite)
+[![Forum](https://img.shields.io/badge/Forum-Join%20now!-36C5F0)](https://forum.datacebo.com)
 
 <div align="left">
 <br/>

{rdt-1.19.1.dev0 → rdt-1.20.1.dev0}/README.md

@@ -9,7 +9,7 @@
 [![Unit Tests](https://github.com/sdv-dev/RDT/actions/workflows/unit.yml/badge.svg)](https://github.com/sdv-dev/RDT/actions/workflows/unit.yml)
 [![Downloads](https://pepy.tech/badge/rdt)](https://pepy.tech/project/rdt)
 [![Coverage Status](https://codecov.io/gh/sdv-dev/RDT/branch/main/graph/badge.svg)](https://codecov.io/gh/sdv-dev/RDT)
-[![Slack](https://img.shields.io/badge/Community-Slack-blue?style=plastic&logo=slack)](https://bit.ly/sdv-slack-invite)
+[![Forum](https://img.shields.io/badge/Forum-Join%20now!-36C5F0)](https://forum.datacebo.com)
 
 <div align="left">
 <br/>

{rdt-1.19.1.dev0 → rdt-1.20.1.dev0}/pyproject.toml

@@ -5,7 +5,6 @@ authors = [{ name = 'DataCebo, Inc.', email = 'info@sdv.dev' }]
 classifiers = [
     'Development Status :: 5 - Production/Stable',
     'Intended Audience :: Developers',
-    'License :: Free for non-commercial use',
     'Natural Language :: English',
     'Programming Language :: Python :: 3',
     'Programming Language :: Python :: 3.9',
@@ -18,7 +17,8 @@ classifiers = [
 ]
 keywords = ['machine learning', 'synthetic data generation', 'benchmark', 'generative models']
 dynamic = ['version']
-license = { text = 'BSL-1.1' }
+license = 'BUSL-1.1'
+license-files = ['LICENSE']
 requires-python = '>=3.9,<3.15'
 readme = 'README.md'
 dependencies = [
@@ -52,7 +52,7 @@ dependencies = [
 "Issue Tracker" = "https://github.com/sdv-dev/RDT/issues"
 "Changes" = "https://github.com/sdv-dev/RDT/blob/main/HISTORY.md"
 "Twitter" = "https://twitter.com/sdv_dev"
-"Chat" = "https://bit.ly/sdv-slack-invite"
+"Chat" = "https://forum.datacebo.com/"
 
 [project.entry-points]
 rdt = { main = 'rdt.cli.__main__:main' }
@@ -101,7 +101,6 @@ readme = ['rundoc>=0.4.3,<0.5',]
 
 [tool.setuptools]
 include-package-data = true
-license-files = ['LICENSE']
 
 [tool.setuptools.packages.find]
 include = ['rdt', 'rdt.*']
@@ -151,7 +150,7 @@ collect_ignore = ['pyproject.toml']
 exclude_lines = ['NotImplementedError()']
 
 [tool.bumpversion]
-current_version = "1.19.1.dev0"
+current_version = "1.20.1.dev0"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',

{rdt-1.19.1.dev0 → rdt-1.20.1.dev0}/rdt/__init__.py

@@ -4,7 +4,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
-__version__ = '1.19.1.dev0'
+__version__ = '1.20.1.dev0'
 
 
 import sys

{rdt-1.19.1.dev0 → rdt-1.20.1.dev0}/rdt/transformers/utils.py

@@ -15,7 +15,10 @@ from dateutil import parser
 from dateutil.parser import ParserError, UnknownTimezoneWarning
 from dateutil.tz import UTC
 
-import sre_parse  # isort:skip
+if sys.version_info >= (3, 11):  # isort:skip  # pragma: no cover
+    from re import _parser
+else:  # pragma: no cover
+    import sre_parse as _parser
 
 LOGGER = logging.getLogger(__name__)
 
@@ -54,7 +57,7 @@ def _any(options, max_repeat):
 
 def _max_repeat(options, max_repeat):
     min_, max_, options = options
-    if max_ == sre_parse.MAXREPEAT:
+    if max_ == _parser.MAXREPEAT:
         max_ = max_repeat
 
     option, args = options[0]
@@ -80,12 +83,12 @@ def _category_chars(regex):
 
 
 _CATEGORIES = {
-    sre_parse.CATEGORY_SPACE: _category_chars(re.compile(r'\s')),
-    sre_parse.CATEGORY_NOT_SPACE: _category_chars(re.compile(r'\S')),
-    sre_parse.CATEGORY_DIGIT: _category_chars(re.compile(r'\d')),
-    sre_parse.CATEGORY_NOT_DIGIT: _category_chars(re.compile(r'\D')),
-    sre_parse.CATEGORY_WORD: _category_chars(re.compile(r'\w')),
-    sre_parse.CATEGORY_NOT_WORD: _category_chars(re.compile(r'\W')),
+    _parser.CATEGORY_SPACE: _category_chars(re.compile(r'\s')),
+    _parser.CATEGORY_NOT_SPACE: _category_chars(re.compile(r'\S')),
+    _parser.CATEGORY_DIGIT: _category_chars(re.compile(r'\d')),
+    _parser.CATEGORY_NOT_DIGIT: _category_chars(re.compile(r'\D')),
+    _parser.CATEGORY_WORD: _category_chars(re.compile(r'\w')),
+    _parser.CATEGORY_NOT_WORD: _category_chars(re.compile(r'\W')),
 }
 
 
@@ -95,13 +98,31 @@ def _category(category, max_repeat):
     return iter(characters), len(characters)
 
 
+def _parse_pattern(pattern, max_repeat):
+    generators = []
+    sizes = []
+    for option, args in reversed(pattern):
+        if option != _parser.AT:
+            generator, size = _GENERATORS[option](args, max_repeat)
+            generators.append((generator, option, args))
+            sizes.append(size)
+
+    return _from_generators(generators, max_repeat), np.prod(sizes, dtype=np.complex128).real
+
+
+def _subpattern(args, max_repeat):
+    # args is (group_id, add_flags, del_flags, pattern)
+    return _parse_pattern(args[3], max_repeat)
+
+
 _GENERATORS = {
-    sre_parse.LITERAL: _literal,
-    sre_parse.IN: _in,
-    sre_parse.RANGE: _range,
-    sre_parse.ANY: _any,
-    sre_parse.MAX_REPEAT: _max_repeat,
-    sre_parse.CATEGORY: _category,
+    _parser.LITERAL: _literal,
+    _parser.IN: _in,
+    _parser.RANGE: _range,
+    _parser.ANY: _any,
+    _parser.MAX_REPEAT: _max_repeat,
+    _parser.CATEGORY: _category,
+    _parser.SUBPATTERN: _subpattern,
 }
 
 
@@ -149,8 +170,6 @@ def strings_from_regex(regex, max_repeat=16):
     the indicated regular expressions alongside an integer indicating the
     total length of the generator.
 
-    WARNING: Subpatterns are currently not supported.
-
     Args:
         regex (str):
             String representing a valid python regular expression.
@@ -163,16 +182,8 @@ def strings_from_regex(regex, max_repeat=16):
             * Generator that produces strings that match the given regex.
             * Total length of the generator.
     """
-    parsed = sre_parse.parse(regex, flags=sre_parse.SRE_FLAG_UNICODE)
-    generators = []
-    sizes = []
-    for option, args in reversed(parsed):
-        if option != sre_parse.AT:
-            generator, size = _GENERATORS[option](args, max_repeat)
-            generators.append((generator, option, args))
-            sizes.append(size)
-
-    return _from_generators(generators, max_repeat), np.prod(sizes, dtype=np.complex128).real
+    parsed = _parser.parse(regex, flags=_parser.SRE_FLAG_UNICODE)
+    return _parse_pattern(parsed, max_repeat)
 
 
 def _fill_nan_with_none_series(data):

{rdt-1.19.1.dev0 → rdt-1.20.1.dev0/rdt.egg-info}/PKG-INFO

@@ -1,18 +1,17 @@
 Metadata-Version: 2.4
 Name: rdt
-Version: 1.19.1.dev0
+Version: 1.20.1.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
-License: BSL-1.1
+License-Expression: BUSL-1.1
 Project-URL: Source Code, https://github.com/sdv-dev/RDT/
 Project-URL: Issue Tracker, https://github.com/sdv-dev/RDT/issues
 Project-URL: Changes, https://github.com/sdv-dev/RDT/blob/main/HISTORY.md
 Project-URL: Twitter, https://twitter.com/sdv_dev
-Project-URL: Chat, https://bit.ly/sdv-slack-invite
+Project-URL: Chat, https://forum.datacebo.com/
 Keywords: machine learning,synthetic data generation,benchmark,generative models
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
-Classifier: License :: Free for non-commercial use
 Classifier: Natural Language :: English
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
@@ -89,7 +88,7 @@ Dynamic: license-file
 [![Unit Tests](https://github.com/sdv-dev/RDT/actions/workflows/unit.yml/badge.svg)](https://github.com/sdv-dev/RDT/actions/workflows/unit.yml)
 [![Downloads](https://pepy.tech/badge/rdt)](https://pepy.tech/project/rdt)
 [![Coverage Status](https://codecov.io/gh/sdv-dev/RDT/branch/main/graph/badge.svg)](https://codecov.io/gh/sdv-dev/RDT)
-[![Slack](https://img.shields.io/badge/Community-Slack-blue?style=plastic&logo=slack)](https://bit.ly/sdv-slack-invite)
+[![Forum](https://img.shields.io/badge/Forum-Join%20now!-36C5F0)](https://forum.datacebo.com)
 
 <div align="left">
 <br/>

{rdt-1.19.1.dev0 → rdt-1.20.1.dev0}/rdt/transformers/__init__.py

@@ -75,13 +75,13 @@ def get_transformer_name(transformer):
         transformer:
             A transformer class.
 
-    Raises:
-        ValueError:
-            Crashes when the transformer is not passed as a class.
-
     Returns:
         string:
             The path of the transformer.
+
+    Raises:
+        ValueError:
+            Crashes when the transformer is not passed as a class.
     """
     if inspect.isclass(transformer):
         return transformer.__module__ + '.' + transformer.get_name()