datacompose 0.2.6.0__tar.gz → 0.2.6.1__tar.gz

{datacompose-0.2.6.0/datacompose.egg-info → datacompose-0.2.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacompose
-Version: 0.2.6.0
+Version: 0.2.6.1
 Summary: Copy-pasteable data transformation primitives for PySpark. Inspired by shadcn-svelte.
 Author: Datacompose Contributors
 Maintainer: Datacompose Contributors

{datacompose-0.2.6.0 → datacompose-0.2.6.1}/datacompose/cli/commands/init.py

@@ -380,7 +380,7 @@ def _run_init(force, output, verbose, yes, skip_completion) -> int:
     # Check if config already exists
     if config_path.exists() and not force:
         print(error(f"Configuration file already exists: {config_path}"))
-        print(dim("Use --force to overwrite"))
+        print(dim("Use datacompose init --force to overwrite"))
         return 1
 
     try:

{datacompose-0.2.6.0 → datacompose-0.2.6.1}/datacompose/transformers/text/addresses/pyspark/pyspark_primitives.py

@@ -544,7 +544,7 @@ def standardize_street_prefix(
 
     Args:
         col: Column containing street prefix
-        custom_mappings: Optional dict of custom prefix mappings (case insensitive)
+        custom_mappings (Optional): Dict of custom prefix mappings (case insensitive)
 
     Returns:
         Column with standardized prefix (always abbreviated per USPS standards)
@@ -614,7 +614,7 @@ def standardize_street_suffix(
 
     Args:
         col: Column containing street suffix
-        custom_mappings: Optional dict of custom suffix mappings (case insensitive)
+        custom_mappings (Optional): Dict of custom suffix mappings (case insensitive)
 
     Returns:
         Column with standardized suffix (always abbreviated per USPS standards)
@@ -896,7 +896,7 @@ def standardize_unit_type(
 
     Args:
         col: Column containing unit type
-        custom_mappings: Optional dict of custom unit type mappings
+        custom_mappings (Optional): Dict of custom unit type mappings
 
     Returns:
         Column with standardized unit type
@@ -1206,7 +1206,7 @@ def extract_city(col: Column, custom_cities: Optional[List] = None) -> Column:
 
     Args:
         col: Column containing address text
-        custom_cities: Optional list of custom city names to recognize (case-insensitive)
+        custom_cities (Optional): List of custom city names to recognize (case-insensitive)
 
     Returns:
         Column with extracted city name or empty string if not found
@@ -1371,7 +1371,7 @@ def extract_state(col: Column, custom_states: Optional[Dict] = None) -> Column:
 
     Args:
         col: Column containing address text with state information
-        custom_states: Optional dict mapping full state names to abbreviations
+        custom_states (Optional): Dict mapping full state names to abbreviations
                       e.g., {"ONTARIO": "ON", "QUEBEC": "QC"}
 
     Returns:
@@ -1445,9 +1445,9 @@ def validate_city(
 
     Args:
         col: Column containing city names to validate
-        known_cities: Optional list of valid city names to check against
-        min_length: Minimum valid city name length (default 2)
-        max_length: Maximum valid city name length (default 50)
+        known_cities (Optional): List of valid city names to check against
+        min_length (Optional): Minimum valid city name length (default 2)
+        max_length (Optional): Maximum valid city name length (default 50)
 
     Returns:
         Boolean column indicating if city name is valid
@@ -1523,7 +1523,7 @@ def standardize_city(col: Column, custom_mappings: Optional[Dict] = None) -> Col
 
     Args:
         col: Column containing city names to standardize
-        custom_mappings: Optional dict for city name corrections/standardization
+        custom_mappings (Optional): Dict for city name corrections/standardization
                         e.g., {"ST LOUIS": "St. Louis", "NEWYORK": "New York"}
 
     Returns:
@@ -1807,7 +1807,7 @@ def standardize_country(col: Column, custom_mappings: Optional[dict] = None) ->
 
     Args:
         col: Column containing country name or abbreviation
-        custom_mappings: Optional dict of custom country mappings
+        custom_mappings (Optional): Dict of custom country mappings
 
     Returns:
         Column with standardized country name

{datacompose-0.2.6.0 → datacompose-0.2.6.1}/datacompose/transformers/text/emails/pyspark/pyspark_primitives.py

@@ -255,8 +255,8 @@ def is_valid_email(col: Column, min_length: int = 6, max_length: int = 254) -> C
 
     Args:
         col: Column containing email address
-        min_length: Minimum length for valid email
-        max_length: Maximum length for valid email
+        min_length (Optional): Minimum length for valid email (default 6)
+        max_length (Optional): Maximum length for valid email (default 254)
 
     Returns:
         Column with boolean indicating validity
@@ -286,8 +286,8 @@ def is_valid_username(col: Column, min_length: int = 1, max_length: int = 64) ->
 
     Args:
         col: Column containing email address
-        min_length: Minimum length for valid username (default 1)
-        max_length: Maximum length for valid username (default 64 per RFC)
+        min_length (Optional): Minimum length for valid username (default 1)
+        max_length (Optional): Maximum length for valid username (default 64 per RFC)
 
     Returns:
         Column with boolean indicating username validity
@@ -351,7 +351,7 @@ def is_disposable_email(
 
     Args:
         col: Column containing email address
-        disposable_domains: List of disposable domains to check against
+        disposable_domains (Optional): List of disposable domains to check against
 
     Returns:
         Column with boolean indicating if email is disposable
@@ -389,7 +389,7 @@ def is_corporate_email(
 
     Args:
         col: Column containing email address
-        free_providers: List of free email provider domains to check against
+        free_providers (Optional): List of free email provider domains to check against
 
     Returns:
         Column with boolean indicating if email is corporate
@@ -535,8 +535,8 @@ def fix_common_typos(
 
     Args:
         col: Column containing email address
-        custom_mappings: Additional domain mappings to apply (extends DOMAIN_TYPO_MAPPINGS)
-        custom_tld_mappings: Additional TLD mappings to apply (extends TLD_TYPO_MAPPINGS)
+        custom_mappings (Optional): Additional domain mappings to apply (extends DOMAIN_TYPO_MAPPINGS)
+        custom_tld_mappings (Optional): Additional TLD mappings to apply (extends TLD_TYPO_MAPPINGS)
 
     Returns:
         Column with typos fixed
@@ -604,10 +604,10 @@ def standardize_email(
 
     Args:
         col: Column containing email address
-        lowercase: Convert to lowercase
-        remove_dots_gmail: Remove dots from Gmail addresses
-        remove_plus: Remove plus addressing
-        fix_typos: Fix common domain typos
+        lowercase (Optional): Convert to lowercase (default True)
+        remove_dots_gmail (Optional): Remove dots from Gmail addresses (default True)
+        remove_plus (Optional): Remove plus addressing (default False)
+        fix_typos (Optional): Fix common domain typos (default True)
 
     Returns:
         Column with standardized email
@@ -756,8 +756,8 @@ def mask_email(col: Column, mask_char: str = "*", keep_chars: int = 3) -> Column
 
     Args:
         col: Column containing email address
-        mask_char: Character to use for masking
-        keep_chars: Number of characters to keep at start
+        mask_char (Optional): Character to use for masking (default "*")
+        keep_chars (Optional): Number of characters to keep at start (default 3)
 
     Returns:
         Column with masked email

{datacompose-0.2.6.0 → datacompose-0.2.6.1}/datacompose/transformers/text/phone_numbers/pyspark/pyspark_primitives.py

@@ -350,8 +350,8 @@ def is_valid_international(
 
     Args:
         col: Column containing phone number
-        min_length: Minimum digits for international number
-        max_length: Maximum digits for international number
+        min_length (Optional): Minimum digits for international number (default 7)
+        max_length (Optional): Maximum digits for international number (default 15)
 
     Returns:
         Column with boolean indicating potential international validity

{datacompose-0.2.6.0 → datacompose-0.2.6.1/datacompose.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacompose
-Version: 0.2.6.0
+Version: 0.2.6.1
 Summary: Copy-pasteable data transformation primitives for PySpark. Inspired by shadcn-svelte.
 Author: Datacompose Contributors
 Maintainer: Datacompose Contributors

{datacompose-0.2.6.0 → datacompose-0.2.6.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "datacompose"
-version = "0.2.6.0"
+version = "0.2.6.1"
 description = "Copy-pasteable data transformation primitives for PySpark. Inspired by shadcn-svelte."
 authors = [
     {name = "Datacompose Contributors"},