datacompose 0.2.5.2__py3-none-any.whl → 0.2.6.1__py3-none-any.whl

datacompose/cli/__init__.py

@@ -2,4 +2,4 @@
 Datacompose CLI - Command-line interface for generating data cleaning UDFs.
 """
 
-__version__ = "0.2.4"
+__version__ = "0.2.6.0"

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/operators/__init__.py

@@ -18,4 +18,4 @@ __all__ = [
     "PrimitiveRegistry",
 ]
 
-__version__ = "0.2.4"
+__version__ = "0.2.6.0"

datacompose/operators/primitives.py

@@ -16,9 +16,13 @@ from typing import Any, Callable, Dict, List, Optional, Sequence
 logger = logging.getLogger(__name__)
 
 try:
-    from pyspark.sql import Column  # type: ignore
+    from pyspark.sql import Column
+    from pyspark.sql import functions as F
 except ImportError:
-    pass
+    logging.debug("PySpark not available")
+
+# Set up module logger
+logger = logging.getLogger(__name__)
 
 
 class SmartPrimitive:
@@ -120,11 +124,15 @@ class PrimitiveRegistry:
         self._primitives = {}
         self._conditionals = {}
 
-    def register(self, name: Optional[str] = None, is_conditional: bool = False):
+    def register(
+        self, name: Optional[str] = None, is_conditional: Optional[bool] = None
+    ):
         """Decorator to register a function as a SmartPrimitive in this namespace.
 
         Args:
             name: Optional name for the primitive (defaults to function name)
+            is_conditional: Optional flag to mark as conditional. If None, auto-detects
+                          based on function name patterns.
 
         Returns:
             Decorator function that wraps the target function as a SmartPrimitive
@@ -139,7 +147,29 @@ class PrimitiveRegistry:
         def decorator(func: Callable):
             primitive_name = name or func.__name__
 
-            if is_conditional:
+            # Auto-detect conditional if not explicitly specified
+            if is_conditional is None:
+                # Check common naming patterns for conditional functions
+                conditional_patterns = [
+                    "is_",
+                    "has_",
+                    "needs_",
+                    "should_",
+                    "can_",
+                    "contains_",
+                    "matches_",
+                    "equals_",
+                    "starts_with_",
+                    "ends_with_",
+                ]
+                is_conditional_auto = any(
+                    primitive_name.startswith(pattern)
+                    for pattern in conditional_patterns
+                )
+            else:
+                is_conditional_auto = is_conditional
+
+            if is_conditional_auto:
                 self._conditionals[primitive_name] = SmartPrimitive(
                     func, primitive_name
                 )
@@ -217,9 +247,17 @@ class PrimitiveRegistry:
                 pipeline.__doc__ = func.__doc__
                 return pipeline
 
+            # Auto-detect ALL namespace instances from func.__globals__
+            # This allows using multiple namespaces without explicitly passing them
+            for var_name, var_value in func.__globals__.items():
+                if isinstance(var_value, PrimitiveRegistry):
+                    # Found a namespace instance
+                    if var_name not in namespaces:
+                        namespaces[var_name] = var_value
+
             # Try to get the function as a string and parse it
             try:
-                compiler = PipelineCompiler(namespaces, debug)
+                compiler = PipelineCompiler(namespaces, debug, func.__globals__)
                 pipeline = compiler.compile(func)
 
                 if debug and pipeline.steps:
@@ -270,7 +308,11 @@ def _fallback_compose(func: Callable, namespaces: Dict, debug: bool) -> Callable
                         method_name = node.value.func.attr
                         namespace = (
                             namespaces.get(namespace_name) if namespace_name else None
-                        ) or (globals().get(namespace_name) if namespace_name else None)
+                        ) or (
+                            func.__globals__.get(namespace_name)
+                            if namespace_name
+                            else None
+                        )
                         if namespace and hasattr(namespace, method_name):
                             method = getattr(namespace, method_name)
 
@@ -312,16 +354,6 @@ def _fallback_compose(func: Callable, namespaces: Dict, debug: bool) -> Callable
         return pipeline
 
 
-try:
-    from pyspark.sql import Column
-    from pyspark.sql import functions as F
-except ImportError:
-    logging.debug("PySpark not available")
-
-# Set up module logger
-logger = logging.getLogger(__name__)
-
-
 @dataclass
 class CompiledStep:
     """A compiled pipeline step"""
@@ -452,9 +484,15 @@ class StablePipeline:
 
 
 class PipelineCompiler:
-    def __init__(self, namespaces: Dict[str, Any], debug: bool = False):
+    def __init__(
+        self,
+        namespaces: Dict[str, Any],
+        debug: bool = False,
+        func_globals: Optional[Dict] = None,
+    ):
         self.namespaces = namespaces
         self.debug = debug
+        self.func_globals = func_globals or {}
 
     def compile(self, func: Callable) -> StablePipeline:
         try:
@@ -530,7 +568,7 @@ class PipelineCompiler:
 
             namespace = (
                 self.namespaces.get(namespace_name) if namespace_name else None
-            ) or (globals().get(namespace_name) if namespace_name else None)
+            ) or (self.func_globals.get(namespace_name) if namespace_name else None)
             if namespace and hasattr(namespace, method_name):
                 method = getattr(namespace, method_name)
 
@@ -552,7 +590,7 @@ class PipelineCompiler:
 
             namespace = (
                 self.namespaces.get(namespace_name) if namespace_name else None
-            ) or (globals().get(namespace_name) if namespace_name else None)
+            ) or (self.func_globals.get(namespace_name) if namespace_name else None)
             if namespace and hasattr(namespace, method_name):
                 method = getattr(namespace, method_name)
 

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

@@ -3,7 +3,7 @@ Phone number transformation primitives for PySpark.
 
 Preview Output:
 +------------------------+----------------+--------+---------+------------+-------+---------+------------+
-|phone                   |standardized    |is_valid|area_code|local_number|has_ext|extension|is_toll_free|
+|phone_numbers                   |standardized    |is_valid|area_code|local_number|has_ext|extension|is_toll_free|
 +------------------------+----------------+--------+---------+------------+-------+---------+------------+
 | (555) 123-4567         |(555) 123-4567  |true    |555      |1234567     |false  |null     |false       |
 |+1-800-555-1234         |+1 800-555-1234 |true    |800      |5551234     |false  |null     |true        |
@@ -29,23 +29,23 @@ data = [
     ("123-45-67",),
     ("1-800-FLOWERS",),
 ]
-df = spark.createDataFrame(data, ["phone"])
+df = spark.createDataFrame(data, ["phone_numbers"])
 
 # Apply transformations
 result_df = df.select(
-    F.col("phone"),
-    phone_numbers.standardize_phone(F.col("phone")).alias("standardized"),
-    phone_numbers.is_valid_phone(F.col("phone")).alias("is_valid"),
+    F.col("phone_numbers"),
+    phone_numbers.standardize_phone_numbers(F.col("phone_numbers")).alias("standardized"),
+    phone_numbers.is_valid_phone_numbers(F.col("phone_numbers")).alias("is_valid"),
     phone_numbers.extract_area_code(
-        phone_numbers.standardize_phone(F.col("phone"))
+        phone_numbers.standardize_phone_numbers(F.col("phone_numbers"))
     ).alias("area_code"),
     phone_numbers.extract_local_number(
-        phone_numbers.standardize_phone(F.col("phone"))
+        phone_numbers.standardize_phone_numbers(F.col("phone_numbers"))
     ).alias("local_number"),
-    phone_numbers.has_extension(F.col("phone")).alias("has_ext"),
-    phone_numbers.extract_extension(F.col("phone")).alias("extension"),
+    phone_numbers.has_extension(F.col("phone_numbers")).alias("has_ext"),
+    phone_numbers.extract_extension(F.col("phone_numbers")).alias("extension"),
     phone_numbers.is_toll_free(
-        phone_numbers.standardize_phone(F.col("phone"))
+        phone_numbers.standardize_phone_numbers(F.col("phone_numbers"))
     ).alias("is_toll_free")
 )
 
@@ -118,7 +118,7 @@ PHONE_KEYPAD_MAPPING = {
 
 
 @phone_numbers.register()
-def extract_phone_from_text(col: Column) -> Column:
+def extract_phone_numbers_from_text(col: Column) -> Column:
     """
     Extract first phone number from text using regex patterns.
 
@@ -126,21 +126,21 @@ def extract_phone_from_text(col: Column) -> Column:
         col: Column containing text with potential phone numbers
 
     Returns:
-        Column with extracted phone number or empty string
+        Column with extracted phone numbers or empty string
     """
-    # Comprehensive phone pattern that matches various formats
+    # Comprehensive phone_numbers pattern that matches various formats
     # Handles: +1-555-123-4567, (555) 123-4567, 555.123.4567, 555-123-4567, etc.
-    phone_pattern = (
+    phone_numbers_pattern = (
         r"(\+?\d{1,3}[-.\s]?)?\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}(\s*(ext|x)\.?\s*\d+)?"
     )
 
     return F.when(col.isNull(), F.lit("")).otherwise(
-        F.regexp_extract(col, phone_pattern, 0)
+        F.regexp_extract(col, phone_numbers_pattern, 0)
     )
 
 
 @phone_numbers.register()
-def extract_all_phones_from_text(col: Column) -> Column:
+def extract_all_phone_numbers_from_text(col: Column) -> Column:
     """
     Extract all phone numbers from text as an array.
 
@@ -150,13 +150,13 @@ def extract_all_phones_from_text(col: Column) -> Column:
     Returns:
         Column with array of phone numbers
     """
-    # For simplicity, we'll return an array with just the first phone found
+    # For simplicity, we'll return an array with just the first phone_numbers found
     # A proper implementation would require more complex regex or UDF
     # This is a limitation of Spark SQL's regex capabilities
-    first_phone = extract_phone_from_text(col)
+    first_phone_numbers = extract_phone_numbers_from_text(col)
 
     # Return array with single element or empty array
-    return F.when(first_phone != "", F.array(first_phone)).otherwise(F.array())
+    return F.when(first_phone_numbers != "", F.array(first_phone_numbers)).otherwise(F.array())
 
 
 @phone_numbers.register()
@@ -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
@@ -366,7 +366,7 @@ def is_valid_international(
 
 
 @phone_numbers.register()
-def is_valid_phone(col: Column) -> Column:
+def is_valid_phone_numbers(col: Column) -> Column:
     """
     Check if phone number is valid (NANP or international).
 
@@ -403,7 +403,7 @@ def is_premium_rate(col: Column) -> Column:
     Check if phone number is premium rate (900).
 
     Args:
-        col: Column containing phone number
+        col: Column containing phophonene_numbers number
 
     Returns:
         Column with boolean indicating if premium rate
@@ -546,11 +546,11 @@ def format_nanp(col: Column) -> Column:
     """
     # Remove extension for validation but preserve it
     extension = extract_extension(col)
-    phone_no_ext = remove_extension(col)
+    phone_numbers_no_ext = remove_extension(col)
 
-    area_code = extract_area_code(phone_no_ext)
-    exchange = extract_exchange(phone_no_ext)
-    subscriber = extract_subscriber(phone_no_ext)
+    area_code = extract_area_code(phone_numbers_no_ext)
+    exchange = extract_exchange(phone_numbers_no_ext)
+    subscriber = extract_subscriber(phone_numbers_no_ext)
 
     base_format = F.concat(area_code, F.lit("-"), exchange, F.lit("-"), subscriber)
 
@@ -559,7 +559,7 @@ def format_nanp(col: Column) -> Column:
         (extension != ""), F.concat(base_format, F.lit(" ext. "), extension)
     ).otherwise(base_format)
 
-    return F.when(is_valid_nanp(phone_no_ext), formatted).otherwise(F.lit(""))
+    return F.when(is_valid_nanp(phone_numbers_no_ext), formatted).otherwise(F.lit(""))
 
 
 @phone_numbers.register()
@@ -575,11 +575,11 @@ def format_nanp_paren(col: Column) -> Column:
     """
     # Remove extension for validation but preserve it
     extension = extract_extension(col)
-    phone_no_ext = remove_extension(col)
+    phone_numbers_no_ext = remove_extension(col)
 
-    area_code = extract_area_code(phone_no_ext)
-    exchange = extract_exchange(phone_no_ext)
-    subscriber = extract_subscriber(phone_no_ext)
+    area_code = extract_area_code(phone_numbers_no_ext)
+    exchange = extract_exchange(phone_numbers_no_ext)
+    subscriber = extract_subscriber(phone_numbers_no_ext)
 
     base_format = F.concat(
         F.lit("("), area_code, F.lit(") "), exchange, F.lit("-"), subscriber
@@ -590,7 +590,7 @@ def format_nanp_paren(col: Column) -> Column:
         (extension != ""), F.concat(base_format, F.lit(" ext. "), extension)
     ).otherwise(base_format)
 
-    return F.when(is_valid_nanp(phone_no_ext), formatted).otherwise(F.lit(""))
+    return F.when(is_valid_nanp(phone_numbers_no_ext), formatted).otherwise(F.lit(""))
 
 
 @phone_numbers.register()
@@ -606,11 +606,11 @@ def format_nanp_dot(col: Column) -> Column:
     """
     # Remove extension for validation but preserve it
     extension = extract_extension(col)
-    phone_no_ext = remove_extension(col)
+    phone_numbers_no_ext = remove_extension(col)
 
-    area_code = extract_area_code(phone_no_ext)
-    exchange = extract_exchange(phone_no_ext)
-    subscriber = extract_subscriber(phone_no_ext)
+    area_code = extract_area_code(phone_numbers_no_ext)
+    exchange = extract_exchange(phone_numbers_no_ext)
+    subscriber = extract_subscriber(phone_numbers_no_ext)
 
     base_format = F.concat(area_code, F.lit("."), exchange, F.lit("."), subscriber)
 
@@ -619,7 +619,7 @@ def format_nanp_dot(col: Column) -> Column:
         (extension != ""), F.concat(base_format, F.lit(" ext. "), extension)
     ).otherwise(base_format)
 
-    return F.when(is_valid_nanp(phone_no_ext), formatted).otherwise(F.lit(""))
+    return F.when(is_valid_nanp(phone_numbers_no_ext), formatted).otherwise(F.lit(""))
 
 
 @phone_numbers.register()
@@ -635,11 +635,11 @@ def format_nanp_space(col: Column) -> Column:
     """
     # Remove extension for validation but preserve it
     extension = extract_extension(col)
-    phone_no_ext = remove_extension(col)
+    phone_numbers_no_ext = remove_extension(col)
 
-    area_code = extract_area_code(phone_no_ext)
-    exchange = extract_exchange(phone_no_ext)
-    subscriber = extract_subscriber(phone_no_ext)
+    area_code = extract_area_code(phone_numbers_no_ext)
+    exchange = extract_exchange(phone_numbers_no_ext)
+    subscriber = extract_subscriber(phone_numbers_no_ext)
 
     base_format = F.concat(area_code, F.lit(" "), exchange, F.lit(" "), subscriber)
 
@@ -648,7 +648,7 @@ def format_nanp_space(col: Column) -> Column:
         (extension != ""), F.concat(base_format, F.lit(" ext. "), extension)
     ).otherwise(base_format)
 
-    return F.when(is_valid_nanp(phone_no_ext), formatted).otherwise(F.lit(""))
+    return F.when(is_valid_nanp(phone_numbers_no_ext), formatted).otherwise(F.lit(""))
 
 
 @phone_numbers.register()
@@ -707,7 +707,7 @@ def format_e164(col: Column) -> Column:
 
     # Build E.164 format - only for valid phones
     return F.when(
-        is_valid_phone(col),
+        is_valid_phone_numbers(col),
         F.when(
             (F.length(digits) == 10) & is_nanp, F.concat(F.lit("+"), F.lit("1"), digits)
         )
@@ -729,7 +729,7 @@ def format_e164(col: Column) -> Column:
 
 
 @phone_numbers.register()
-def standardize_phone(col: Column) -> Column:
+def standardize_phone_numbers(col: Column) -> Column:
     """
     Standardize phone number with cleaning and NANP formatting.
 
@@ -783,7 +783,7 @@ def standardize_phone(col: Column) -> Column:
 
 
 @phone_numbers.register()
-def standardize_phone_e164(col: Column) -> Column:
+def standardize_phone_numbers_e164(col: Column) -> Column:
     """
     Standardize phone number with cleaning and E.164 formatting.
 
@@ -800,11 +800,11 @@ def standardize_phone_e164(col: Column) -> Column:
     result = format_e164(cleaned)
 
     # Only return valid phone numbers
-    return F.when(is_valid_phone(cleaned), result).otherwise(F.lit(""))
+    return F.when(is_valid_phone_numbers(cleaned), result).otherwise(F.lit(""))
 
 
 @phone_numbers.register()
-def standardize_phone_digits(col: Column) -> Column:
+def standardize_phone_numbers_digits(col: Column) -> Column:
     """
     Standardize phone number and return digits only.
 
@@ -821,11 +821,11 @@ def standardize_phone_digits(col: Column) -> Column:
     result = extract_digits(cleaned)
 
     # Only return valid phone numbers
-    return F.when(is_valid_phone(cleaned), result).otherwise(F.lit(""))
+    return F.when(is_valid_phone_numbers(cleaned), result).otherwise(F.lit(""))
 
 
 @phone_numbers.register()
-def clean_phone(col: Column) -> Column:
+def clean_phone_numbers(col: Column) -> Column:
     """
     Clean and validate phone number, returning null for invalid numbers.
 
@@ -873,12 +873,12 @@ def clean_phone(col: Column) -> Column:
 
 
 @phone_numbers.register()
-def get_phone_type(col: Column) -> Column:
+def get_phone_numbers_type(col: Column) -> Column:
     """
     Get phone number type (toll-free, premium, standard, international).
 
     Args:
-        col: Column containing phone number
+        col: Column containing phone_numbers number
 
     Returns:
         Column with phone type
@@ -923,7 +923,7 @@ def get_region_from_area_code(col: Column) -> Column:
 
 
 @phone_numbers.register()
-def mask_phone(col: Column) -> Column:
+def mask_phone_numbers(col: Column) -> Column:
     """
     Mask phone number for privacy keeping last 4 digits (e.g., ***-***-1234).
 
@@ -950,9 +950,9 @@ def mask_phone(col: Column) -> Column:
 
 
 @phone_numbers.register()
-def filter_valid_phones(col: Column) -> Column:
+def filter_valid_phone_numbers_numbers(col: Column) -> Column:
     """
-    Return phone number only if valid, otherwise return null.
+    Return phone_numbers number only if valid, otherwise return null.
 
     Args:
         col: Column containing phone number
@@ -960,13 +960,13 @@ def filter_valid_phones(col: Column) -> Column:
     Returns:
         Column with valid phone or null
     """
-    return F.when(is_valid_phone(col), col).otherwise(F.lit(None))
+    return F.when(is_valid_phone_numbers(col), col).otherwise(F.lit(None))
 
 
 @phone_numbers.register()
-def filter_nanp_phones(col: Column) -> Column:
+def filter_nanp_phone_numbers_numbers(col: Column) -> Column:
     """
-    Return phone number only if valid NANP, otherwise return null.
+    Return phone_numbers number only if valid NANP, otherwise return null.
 
     Args:
         col: Column containing phone number
@@ -978,7 +978,7 @@ def filter_nanp_phones(col: Column) -> Column:
 
 
 @phone_numbers.register()
-def filter_toll_free_phones(col: Column) -> Column:
+def filter_toll_free_phone_numbers_numbers(col: Column) -> Column:
     """
     Return phone number only if toll-free, otherwise return null.
 

{datacompose-0.2.5.2.dist-info → datacompose-0.2.6.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacompose
-Version: 0.2.5.2
+Version: 0.2.6.1
 Summary: Copy-pasteable data transformation primitives for PySpark. Inspired by shadcn-svelte.
 Author: Datacompose Contributors
 Maintainer: Datacompose Contributors

{datacompose-0.2.5.2.dist-info → datacompose-0.2.6.1.dist-info}/RECORD

@@ -1,31 +1,31 @@
 datacompose/__init__.py,sha256=kbQEzEvheAMsm3-MT4nWSuX42fjrfgDWoR8WZmC_WX4,34
-datacompose/cli/__init__.py,sha256=a5UAbPnAm87gUq4YaoTPN5umknN5s2xgnztatI03So0,107
+datacompose/cli/__init__.py,sha256=UuHpU3QypWZC9NEjI89BNUW_PcRfMUyJbZDKJvAm1hQ,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/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/init.py,sha256=prLBWsvuAxRWiT8UhqqhaS9tWc9sUToM6MrGWCdjakM,17986
+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=6g7Hp5261TkPghRgTfxKrizx0OH3Zga3OKHZ37I9_4E,586
-datacompose/operators/primitives.py,sha256=rIERyKfPIULngHs9fRewXo6VjmbjyiOXvTCqiHGIur8,22022
+datacompose/operators/__init__.py,sha256=Eacc0JDCzeuTeLGO_N9Nz9pOc1D3_6BxEcpCibzrpz8,588
+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=gf_-UbCglfsT3HoNdw8ZAXUT7zS4h9uZ2BevG05GwpY,62389
+datacompose/transformers/text/addresses/pyspark/pyspark_primitives.py,sha256=u6vu5wevFc_15jYbIfM50rrEfRtJn_P-8MKEtceX08k,62427
 datacompose/transformers/text/emails/__init__.py,sha256=snZLOJsxrPDOi8gIISlRxc6YlskKxUyu0NnOZCE5cIU,34
-datacompose/transformers/text/emails/pyspark/pyspark_primitives.py,sha256=zQpntW4-RsDv5C1TWp0put10UyUEamP1BxvVYbr2Q58,23785
+datacompose/transformers/text/emails/pyspark/pyspark_primitives.py,sha256=TSuUrILHHK3SjGC-J7YICgzQqj-FOYcaXyfhRaEg4d4,24052
 datacompose/transformers/text/phone_numbers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datacompose/transformers/text/phone_numbers/pyspark/pyspark_primitives.py,sha256=tUGH8Q26FBRqXmwcg4SVT8NFxC5Q9SNCIBXPGrq5hVM,28326
-datacompose-0.2.5.2.dist-info/licenses/LICENSE,sha256=SCPOqmPhMikiyYDlKZ877fGHaE2O45cDBoJIomrlpDU,1067
-datacompose-0.2.5.2.dist-info/METADATA,sha256=hwtCLgwUJfITW5NOqUdo0xhGF5jS3M4g6fJblRnKwBo,4352
-datacompose-0.2.5.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datacompose-0.2.5.2.dist-info/entry_points.txt,sha256=oeG9oGgDwajk4v0C1awdUTBx2GmhLpuNHCTAV-jurUc,58
-datacompose-0.2.5.2.dist-info/top_level.txt,sha256=AX1qGkuJMD2YJLZKo40h-w4MeFxDZL6W1vbKKuTpW8I,12
-datacompose-0.2.5.2.dist-info/RECORD,,
+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,,