datacompose 0.2.6.1__py3-none-any.whl → 0.2.7.0__py3-none-any.whl

datacompose/cli/__init__.py

@@ -2,4 +2,4 @@
 Datacompose CLI - Command-line interface for generating data cleaning UDFs.
 """
 
-__version__ = "0.2.6.0"
+__version__ = "0.2.7.0"

datacompose/cli/commands/add.py

@@ -111,6 +111,20 @@ def add(ctx, transformer, target, type, output, verbose):
     config = ConfigLoader.load_config()
 
     if target is None:
+        # If no config file exists or is malformed, fail early
+        if config is None:
+            print(
+                error(
+                    "Error: No target specified and no config file found"
+                )
+            )
+            print(
+                info(
+                    "Please specify a target with --target or run 'datacompose init' to set up defaults"
+                )
+            )
+            ctx.exit(1)
+            
         # Try to get default target from config
         target = ConfigLoader.get_default_target(config)
         if target is None:

datacompose/cli/config.py

@@ -46,6 +46,8 @@ class ConfigLoader:
         """
         if config is None:
             config = ConfigLoader.load_config()
+            if not config:
+                return "pyspark"
             
         if not config:
             return None

datacompose/cli/main.py

@@ -19,7 +19,7 @@ from datacompose.cli.commands.list import list_cmd
 
 
 @click.group()
-@click.version_option("0.1.0", prog_name="datacompose")
+@click.version_option("0.2.7.0", prog_name="datacompose")
 @click.pass_context
 def cli(ctx):
     """Generate data cleaning UDFs for various platforms.

datacompose/operators/__init__.py

@@ -18,4 +18,4 @@ __all__ = [
     "PrimitiveRegistry",
 ]
 
-__version__ = "0.2.6.0"
+__version__ = "0.2.7.0"

datacompose/transformers/text/addresses/pyspark/pyspark_primitives.py

@@ -1956,6 +1956,8 @@ def remove_po_box(col: Column) -> Column:
     return F.trim(result)
 
 
+
+
 @addresses.register()
 def standardize_po_box(col: Column) -> Column:
     """Standardize PO Box format to consistent representation.

datacompose/transformers/text/emails/pyspark/pyspark_primitives.py

@@ -749,6 +749,23 @@ def get_email_provider(col: Column) -> Column:
     return result
 
 
+@emails.register()
+def hash_email_sha256(
+    col: Column, salt: str = "", standardize_first: bool = True
+) -> Column:
+    """Hash email with SHA256, with email-specific preprocessing."""
+    if standardize_first:
+        # Critical: hash the CANONICAL form for deduplication
+        email = get_canonical_email(col)
+    else:
+        email = col
+
+    # Only hash valid emails
+    return F.when(
+        is_valid_email(email), F.sha2(F.concat(email, F.lit(salt)), 256)
+    ).otherwise(F.lit(None))
+
+
 @emails.register()
 def mask_email(col: Column, mask_char: str = "*", keep_chars: int = 3) -> Column:
     """

datacompose/transformers/text/phone_numbers/pyspark/pyspark_primitives.py

@@ -922,6 +922,21 @@ def get_region_from_area_code(col: Column) -> Column:
     )
 
 
+@phone_numbers.register()
+def hash_phone_numbers_sha256(col:Column, salt:str="", standardize_first:bool=True) -> Column:
+    """Hash email with SHA256, with email-specific preprocessing."""
+    if standardize_first:
+        phone_number = standardize_phone_numbers_e164(col)
+
+    else:
+        phone_number = col
+
+    return F.when(
+        is_valid_phone_numbers(phone_number), 
+        F.sha2(F.concat(phone_number, F.lit(salt)), 256)
+    ).otherwise(F.lit(None))
+
+
 @phone_numbers.register()
 def mask_phone_numbers(col: Column) -> Column:
     """

datacompose-0.2.7.0.dist-info/METADATA

@@ -0,0 +1,176 @@
+Metadata-Version: 2.4
+Name: datacompose
+Version: 0.2.7.0
+Summary: Copy-pasteable data transformation primitives for PySpark. Inspired by shadcn-svelte.
+Author: Datacompose Contributors
+Maintainer: Datacompose Contributors
+License: MIT
+Project-URL: Homepage, https://github.com/tc-cole/datacompose
+Project-URL: Documentation, https://github.com/tc-cole/datacompose/tree/main/docs
+Project-URL: Repository, https://github.com/tc-cole/datacompose.git
+Project-URL: Issues, https://github.com/tc-cole/datacompose/issues
+Project-URL: Changelog, https://github.com/tc-cole/datacompose/blob/main/CHANGELOG.md
+Keywords: data-cleaning,data-quality,udf,spark,postgres,code-generation,data-pipeline,etl
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Software Development :: Code Generators
+Classifier: Topic :: Database
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: jinja2>=3.0.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: click>=8.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: mkdocs>=1.5.3; extra == "docs"
+Requires-Dist: mkdocs-material>=9.5.0; extra == "docs"
+Requires-Dist: mkdocs-material-extensions>=1.3; extra == "docs"
+Requires-Dist: mkdocs-minify-plugin>=0.7.1; extra == "docs"
+Requires-Dist: mkdocs-redirects>=1.2.1; extra == "docs"
+Requires-Dist: mike>=2.0.0; extra == "docs"
+Requires-Dist: pymdown-extensions>=10.5; extra == "docs"
+Requires-Dist: pygments>=2.17.0; extra == "docs"
+Requires-Dist: mkdocs-git-revision-date-localized-plugin>=1.2.2; extra == "docs"
+Requires-Dist: mkdocs-glightbox>=0.3.5; extra == "docs"
+Dynamic: license-file
+
+# DataCompose
+
+PySpark transformations you can actually own and modify. No black boxes.
+
+## Before vs After
+
+```python
+# Before: Regex nightmare for addresses
+df = df.withColumn("state_clean",
+    F.when(F.col("address").rlike(".*\\b(NY|N\\.Y\\.|New York|NewYork|Newyork)\\b.*"), "NY")
+    .when(F.col("address").rlike(".*\\b(CA|Cal\\.|Calif\\.|California)\\b.*"), "CA")
+    .when(F.col("address").rlike(".*\\b(IL|Ill\\.|Illinois|Illinios)\\b.*"), "IL")
+    .when(F.upper(F.col("address")).contains("NEW YORK"), "NY")
+    .when(F.regexp_extract(F.col("address"), ",\\s*([A-Z]{2})\\s+\\d{5}", 1) == "NY", "NY")
+    .when(F.regexp_extract(F.col("address"), "\\s+([A-Z]{2})\\s*$", 1) == "NY", "NY")
+    # ... handle "N.Y 10001" vs "NY, 10001" vs "New York 10001"
+    # ... handle misspellings like "Californai" or "Illnois"  
+    # ... 50 more states × 10 variations each
+)
+
+# After: One line
+from builders.transformers.addresses import addresses
+df = df.withColumn("state", addresses.standardize_state(F.col("address")))
+```
+
+## Installation
+
+```bash
+pip install datacompose
+```
+
+## How It Works
+
+```bash
+# Copy transformers into YOUR repo
+datacompose add phones
+datacompose add addresses
+datacompose add emails
+```
+
+```python
+# Use them like any Python module - this is your code now
+from transformers.pyspark.addresses import addresses
+
+df = (df
+    .withColumn("street_number", addresses.extract_street_number(F.col("address")))
+    .withColumn("street_name", addresses.extract_street_name(F.col("address")))
+    .withColumn("city", addresses.extract_city(F.col("address")))
+    .withColumn("state", addresses.standardize_state(F.col("address")))
+    .withColumn("zip", addresses.extract_zip_code(F.col("address")))
+)
+
+# Result:
++----------------------------------------+-------------+------------+-----------+-----+-------+
+|address                                 |street_number|street_name |city       |state|zip    |
++----------------------------------------+-------------+------------+-----------+-----+-------+
+|123 Main St, New York, NY 10001        |123          |Main        |New York   |NY   |10001  |
+|456 Oak Ave Apt 5B, Los Angeles, CA 90001|456        |Oak         |Los Angeles|CA   |90001  |
+|789 Pine Blvd, Chicago, IL 60601       |789          |Pine        |Chicago    |IL   |60601  |
++----------------------------------------+-------------+------------+-----------+-----+-------+
+```
+
+The code lives in your repo. Modify it. Delete what you don't need. No external dependencies.
+
+## Why Copy-to-Own?
+
+- **Your data is weird** - Phone numbers with "ask for Bob"? We can't predict that. You can fix it.
+- **No breaking changes** - Library updates can't break your pipeline at 2 AM
+- **Actually debuggable** - Stack traces point to YOUR code, not site-packages
+- **No dependency hell** - It's just PySpark. If Spark runs, this runs.
+
+## Available Transformers
+
+**Phones** - Standardize formats, extract from text, validate, handle extensions  
+**Addresses** - Parse components, standardize states, validate zips, detect PO boxes  
+**Emails** - Validate, extract domains, fix typos (gmial→gmail), standardize
+
+More coming based on what you need.
+
+## Real Example
+
+```python
+# Messy customer data
+df = spark.createDataFrame([
+    ("(555) 123-4567 ext 89", "john.doe@gmial.com", "123 Main St Apt 4B"),
+    ("555.987.6543", "JANE@COMPANY.COM", "456 Oak Ave, NY, NY 10001")
+])
+
+# Clean it
+clean_df = (df
+    .withColumn("phone", phones.standardize_phone(F.col("phone")))
+    .withColumn("email", emails.fix_common_typos(F.col("email")))
+    .withColumn("street", addresses.extract_street_address(F.col("address")))
+)
+```
+
+## The Philosophy
+
+```
+█████████████ 60% - Already clean
+████████ 30% - Common patterns (formatting, typos)
+██ 8% - Edge cases (weird but fixable)
+▌ 2% - Complete chaos (that's what interns are for)
+```
+
+We handle the 38% with patterns. You handle the 2% chaos.
+
+## Documentation
+
+Full docs at [datacompose.io](https://datacompose.io)
+
+## Key Features
+
+- **Zero dependencies** - Just PySpark code that runs anywhere Spark runs
+- **Fully modifiable** - It's in your repo. Change whatever you need
+- **Battle-tested patterns** - Built from real production data cleaning challenges  
+- **Composable functions** - Chain simple operations into complex pipelines
+- **No breaking changes** - You control when and how to update
+
+## License
+
+MIT - It's your code now.
+
+---
+
+*Inspired by [shadcn/ui](https://ui.shadcn.com/) and [Svelte](https://svelte.dev/)'s approach to components - copy, don't install.*

{datacompose-0.2.6.1.dist-info → datacompose-0.2.7.0.dist-info}/RECORD

@@ -1,31 +1,31 @@
 datacompose/__init__.py,sha256=kbQEzEvheAMsm3-MT4nWSuX42fjrfgDWoR8WZmC_WX4,34
-datacompose/cli/__init__.py,sha256=UuHpU3QypWZC9NEjI89BNUW_PcRfMUyJbZDKJvAm1hQ,109
+datacompose/cli/__init__.py,sha256=DdkpcOpc9wicaH39CPFZKf2JX1BSEKxpxbgd6pum67g,109
 datacompose/cli/colors.py,sha256=Ax7jHhdAIuq5x3663gJ7_MzFCBOJv38DqNXts5t4SLs,1756
-datacompose/cli/config.py,sha256=vvY6xGgIdybUuujdPrDI_CsSUUD9CEfODG8Kem4jqVQ,2353
-datacompose/cli/main.py,sha256=d87hG1nxDVNTRZVi7ctNQQ06lwe5KbLGJMChlHtR3Kc,1343
+datacompose/cli/config.py,sha256=xzZ2uP43_gAWSHxjBgJxWR-nUYfPviHJdJCzINtevbo,2413
+datacompose/cli/main.py,sha256=dx_woCHc9_nYygKZ009-CN2tLoP1oyQPfPym-wKQTS4,1345
 datacompose/cli/validation.py,sha256=8WMZ9wtPgFk9eBgMS_wtkncFz_-BmH4E8V57tjp3YoI,2526
 datacompose/cli/commands/__init__.py,sha256=Bu58UsnkGRbVFS92U2Px_KxlUPrdlbSY6wlvP6tet2o,38
-datacompose/cli/commands/add.py,sha256=N4tqtOEXmaP6vpO4ZfhFH6qBznmFOYRU3y9TEvc2da0,7707
+datacompose/cli/commands/add.py,sha256=0ICXRQqVrdczPWok48gHRPXam15GQdgGQvdgC_lJpuI,8160
 datacompose/cli/commands/init.py,sha256=44QZEyqjAXOahfbFNBZAnEq2JCzT6UDB0GqC-fmyOko,18003
 datacompose/cli/commands/list.py,sha256=mXihUMrnwLUoIG-FpNb8-XJ0VZfh0v3exHq1m_Mrprg,3855
 datacompose/generators/__init__.py,sha256=dFJWJScu8mkP0ZKIQtVlJ36PQW-LwCYBijuNwLSevZw,48
 datacompose/generators/base.py,sha256=EgpHwaaSxAP1Ygq5Wtyq4ez-wG0oPwDEbiKgLsEilD0,6761
 datacompose/generators/pyspark/__init__.py,sha256=ayoKDGtbt2KwFcNt2QxHKt8z83Kzy4ySw9Gg7j9ZMTY,33
 datacompose/generators/pyspark/generator.py,sha256=be4GATA8rmLAg4_wZ3Ox3vC3up_OXMOajjIUJQrDQ10,1735
-datacompose/operators/__init__.py,sha256=Eacc0JDCzeuTeLGO_N9Nz9pOc1D3_6BxEcpCibzrpz8,588
+datacompose/operators/__init__.py,sha256=AREDlwEsqlK5ZQsQpwsNIF_He-Wlpct9-Wp6wBW4QQU,588
 datacompose/operators/primitives.py,sha256=FxhtgP7aizKsnNBgh5oTqwc9m8QSjLTpRoG5zu6rFns,23615
 datacompose/transformers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datacompose/transformers/discovery.py,sha256=JgMtmd8PkhmwLqS17NeKSv9MRneY9tdOsOK32A6luOQ,7048
 datacompose/transformers/text/__init__.py,sha256=Mq0UmgYlBV8T18IkvHAS1TImEzWyGciCqxaCv324hFQ,36
 datacompose/transformers/text/addresses/__init__.py,sha256=l5TItGrGBn69Mlq0CaRGJa-SwpyuUEYWvG5N26s3Pco,39
-datacompose/transformers/text/addresses/pyspark/pyspark_primitives.py,sha256=u6vu5wevFc_15jYbIfM50rrEfRtJn_P-8MKEtceX08k,62427
+datacompose/transformers/text/addresses/pyspark/pyspark_primitives.py,sha256=AVneGoXX5TtHGfwOL2qD645YqiIBiV46_zEUnAhSwoE,62429
 datacompose/transformers/text/emails/__init__.py,sha256=snZLOJsxrPDOi8gIISlRxc6YlskKxUyu0NnOZCE5cIU,34
-datacompose/transformers/text/emails/pyspark/pyspark_primitives.py,sha256=TSuUrILHHK3SjGC-J7YICgzQqj-FOYcaXyfhRaEg4d4,24052
+datacompose/transformers/text/emails/pyspark/pyspark_primitives.py,sha256=tWdKjG6daAXMLRp8BnbMfNqbh7zUci-XUjaep6wTbNk,24552
 datacompose/transformers/text/phone_numbers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datacompose/transformers/text/phone_numbers/pyspark/pyspark_primitives.py,sha256=O9wjGi9S_0sp7xkycMGUccp1XSgln9XJ9Mfs25FVyQU,28903
-datacompose-0.2.6.1.dist-info/licenses/LICENSE,sha256=SCPOqmPhMikiyYDlKZ877fGHaE2O45cDBoJIomrlpDU,1067
-datacompose-0.2.6.1.dist-info/METADATA,sha256=geD3OWaiLYbprfVhuf0wEXdX54o6Jei3frYnmAnFhhQ,4352
-datacompose-0.2.6.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datacompose-0.2.6.1.dist-info/entry_points.txt,sha256=oeG9oGgDwajk4v0C1awdUTBx2GmhLpuNHCTAV-jurUc,58
-datacompose-0.2.6.1.dist-info/top_level.txt,sha256=AX1qGkuJMD2YJLZKo40h-w4MeFxDZL6W1vbKKuTpW8I,12
-datacompose-0.2.6.1.dist-info/RECORD,,
+datacompose/transformers/text/phone_numbers/pyspark/pyspark_primitives.py,sha256=mCIq1jHts2tFs4wx8SNvws53rZ38HI1T4ynbu60w7E8,29371
+datacompose-0.2.7.0.dist-info/licenses/LICENSE,sha256=SCPOqmPhMikiyYDlKZ877fGHaE2O45cDBoJIomrlpDU,1067
+datacompose-0.2.7.0.dist-info/METADATA,sha256=ecGxOlDfjHvin7olozaB_MjecgWXIeoNmiQ3xhHaxx8,6898
+datacompose-0.2.7.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datacompose-0.2.7.0.dist-info/entry_points.txt,sha256=oeG9oGgDwajk4v0C1awdUTBx2GmhLpuNHCTAV-jurUc,58
+datacompose-0.2.7.0.dist-info/top_level.txt,sha256=AX1qGkuJMD2YJLZKo40h-w4MeFxDZL6W1vbKKuTpW8I,12
+datacompose-0.2.7.0.dist-info/RECORD,,

datacompose-0.2.6.1.dist-info/METADATA

@@ -1,94 +0,0 @@
-Metadata-Version: 2.4
-Name: datacompose
-Version: 0.2.6.1
-Summary: Copy-pasteable data transformation primitives for PySpark. Inspired by shadcn-svelte.
-Author: Datacompose Contributors
-Maintainer: Datacompose Contributors
-License: MIT
-Project-URL: Homepage, https://github.com/tc-cole/datacompose
-Project-URL: Documentation, https://github.com/tc-cole/datacompose/tree/main/docs
-Project-URL: Repository, https://github.com/tc-cole/datacompose.git
-Project-URL: Issues, https://github.com/tc-cole/datacompose/issues
-Project-URL: Changelog, https://github.com/tc-cole/datacompose/blob/main/CHANGELOG.md
-Keywords: data-cleaning,data-quality,udf,spark,postgres,code-generation,data-pipeline,etl
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: Topic :: Software Development :: Code Generators
-Classifier: Topic :: Database
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: jinja2>=3.0.0
-Requires-Dist: pyyaml>=6.0
-Requires-Dist: click>=8.0.0
-Provides-Extra: dev
-Requires-Dist: pytest>=7.0.0; extra == "dev"
-Requires-Dist: black>=23.0.0; extra == "dev"
-Requires-Dist: mypy>=1.0.0; extra == "dev"
-Requires-Dist: ruff>=0.1.0; extra == "dev"
-Provides-Extra: docs
-Requires-Dist: mkdocs>=1.5.3; extra == "docs"
-Requires-Dist: mkdocs-material>=9.5.0; extra == "docs"
-Requires-Dist: mkdocs-material-extensions>=1.3; extra == "docs"
-Requires-Dist: mkdocs-minify-plugin>=0.7.1; extra == "docs"
-Requires-Dist: mkdocs-redirects>=1.2.1; extra == "docs"
-Requires-Dist: mike>=2.0.0; extra == "docs"
-Requires-Dist: pymdown-extensions>=10.5; extra == "docs"
-Requires-Dist: pygments>=2.17.0; extra == "docs"
-Requires-Dist: mkdocs-git-revision-date-localized-plugin>=1.2.2; extra == "docs"
-Requires-Dist: mkdocs-glightbox>=0.3.5; extra == "docs"
-Dynamic: license-file
-
-# Datacompose
-
-[![PyPI version](https://badge.fury.io/py/datacompose.svg)](https://pypi.org/project/datacompose/)
-[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
-[![Coverage](https://img.shields.io/badge/coverage-92%25-brightgreen.svg)](https://github.com/your-username/datacompose)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-
-A powerful data transformation framework for building reusable, composable data cleaning pipelines in PySpark.
-
-## Installation
-
-```bash
-pip install datacompose
-```
-
-## What is Datacompose?
-
-Datacompose provides production-ready PySpark data transformation primitives that become part of YOUR codebase. Inspired by [shadcn](https://ui.shadcn.com/)'s approach to components, we believe in giving you full ownership and control over your code.
-
-### Key Features
-
-- **No Runtime Dependencies**: Standalone PySpark code that runs without Datacompose
-- **Composable Primitives**: Build complex transformations from simple, reusable functions
-- **Smart Partial Application**: Pre-configure transformations with parameters for reuse
-- **Optimized Operations**: Efficient Spark transformations with minimal overhead
-- **Comprehensive Libraries**: Pre-built primitives for emails, addresses, and phone numbers
-
-### Available Transformers
-
-- **Emails**: Validation, extraction, standardization, typo correction
-- **Addresses**: Street parsing, state/zip validation, PO Box detection  
-- **Phone Numbers**: NANP/international validation, formatting, toll-free detection
-
-## Documentation
-
-For detailed documentation, examples, and API reference, visit [datacompose.io](https://datacompose.io).
-
-## Philosophy
-
-This is NOT a traditional library - it gives you production-ready data transformation primitives that you can modify to fit your exact needs. You own the code, with no external dependencies to manage or worry about breaking changes.
-
-## License
-
-MIT License - see LICENSE file for details