ai-lls-lib 1.0.0__py3-none-any.whl → 1.0.0rc1__py3-none-any.whl

ai_lls_lib/core/processor.py

@@ -1,135 +1,295 @@
-"""
-Bulk CSV processing for phone verification
-"""
-import csv
-from typing import List, Optional
-from aws_lambda_powertools import Logger
-from .models import PhoneVerification
-from .verifier import PhoneVerifier
-
-logger = Logger()
-
-
-class BulkProcessor:
-    """Process CSV files for bulk phone verification"""
-
-    def __init__(self, verifier: PhoneVerifier):
-        self.verifier = verifier
-
-    def process_csv_sync(self, file_path: str, phone_column: str = "phone") -> List[PhoneVerification]:
-        """
-        Process CSV file synchronously.
-        Returns list of verification results.
-        """
-        results = []
-
-        try:
-            with open(file_path, 'r', encoding='utf-8-sig') as f:
-                reader = csv.DictReader(f)
-
-                # Find phone column (case-insensitive)
-                headers = reader.fieldnames or []
-                phone_col = self._find_phone_column(headers, phone_column)
-
-                if not phone_col:
-                    raise ValueError(f"Phone column '{phone_column}' not found in CSV")
-
-                for row_num, row in enumerate(reader, start=2):  # Start at 2 (header is 1)
-                    try:
-                        phone = row.get(phone_col, "").strip()
-                        if not phone:
-                            logger.warning(f"Empty phone at row {row_num}")
-                            continue
-
-                        # Verify phone
-                        result = self.verifier.verify_sync(phone)
-                        results.append(result)
-
-                        # Log progress every 100 rows
-                        if len(results) % 100 == 0:
-                            logger.info(f"Processed {len(results)} phones")
-
-                    except ValueError as e:
-                        logger.warning(f"Invalid phone at row {row_num}: {str(e)}")
-                        continue
-                    except Exception as e:
-                        logger.error(f"Error processing row {row_num}: {str(e)}")
-                        continue
-
-                logger.info(f"Completed processing {len(results)} valid phones")
-
-        except Exception as e:
-            logger.error(f"CSV processing failed: {str(e)}")
-            raise
-
-        return results
-
-    def _find_phone_column(self, headers: List[str], preferred: str) -> Optional[str]:
-        """Find phone column in headers (case-insensitive)"""
-        # First try exact match
-        for header in headers:
-            if header.lower() == preferred.lower():
-                return header
-
-        # Common phone column names
-        phone_patterns = [
-            "phone", "phone_number", "phonenumber", "mobile",
-            "cell", "telephone", "tel", "number", "contact"
-        ]
-
-        for header in headers:
-            header_lower = header.lower()
-            for pattern in phone_patterns:
-                if pattern in header_lower:
-                    logger.info(f"Using column '{header}' as phone column")
-                    return header
-
-        return None
-
-    def generate_results_csv(
-        self,
-        original_path: str,
-        results: List[PhoneVerification],
-        output_path: str
-    ) -> None:
-        """
-        Generate CSV with original data plus verification results.
-        Adds columns: line_type, dnc, cached
-        """
-        # Create lookup dict
-        results_map = {r.phone_number: r for r in results}
-
-        with open(original_path, 'r', encoding='utf-8-sig') as infile:
-            reader = csv.DictReader(infile)
-            headers = reader.fieldnames or []
-
-            # Add new columns
-            output_headers = headers + ["line_type", "dnc", "cached"]
-
-            with open(output_path, 'w', newline='', encoding='utf-8') as outfile:
-                writer = csv.DictWriter(outfile, fieldnames=output_headers)
-                writer.writeheader()
-
-                phone_col = self._find_phone_column(headers, "phone")
-
-                for row in reader:
-                    phone = row.get(phone_col, "").strip()
-
-                    # Try to normalize for lookup
-                    try:
-                        normalized = self.verifier.normalize_phone(phone)
-                        if normalized in results_map:
-                            result = results_map[normalized]
-                            row["line_type"] = result.line_type
-                            row["dnc"] = "true" if result.dnc else "false"
-                            row["cached"] = "true" if result.cached else "false"
-                        else:
-                            row["line_type"] = "unknown"
-                            row["dnc"] = ""
-                            row["cached"] = ""
-                    except:
-                        row["line_type"] = "invalid"
-                        row["dnc"] = ""
-                        row["cached"] = ""
-
-                    writer.writerow(row)
+"""
+Bulk CSV processing for phone verification
+"""
+import csv
+from io import StringIO
+from typing import List, Optional, Iterator, Iterable
+from aws_lambda_powertools import Logger
+from .models import PhoneVerification
+from .verifier import PhoneVerifier
+
+logger = Logger()
+
+
+class BulkProcessor:
+    """Process CSV files for bulk phone verification"""
+
+    def __init__(self, verifier: PhoneVerifier):
+        self.verifier = verifier
+
+    def process_csv(self, csv_text: str, phone_column: str = "phone") -> List[PhoneVerification]:
+        """
+        Process CSV text content.
+        Returns list of verification results.
+        """
+        results = []
+
+        try:
+            # Use StringIO to parse CSV text
+            csv_file = StringIO(csv_text)
+            reader = csv.DictReader(csv_file)
+
+            # Find phone column (case-insensitive)
+            headers = reader.fieldnames or []
+            phone_col = self._find_phone_column(headers, phone_column)
+
+            if not phone_col:
+                raise ValueError(f"Phone column '{phone_column}' not found in CSV")
+
+            for row_num, row in enumerate(reader, start=2):  # Start at 2 (header is 1)
+                try:
+                    phone = row.get(phone_col, "").strip()
+                    if not phone:
+                        logger.warning(f"Empty phone at row {row_num}")
+                        continue
+
+                    # Verify phone
+                    result = self.verifier.verify(phone)
+                    results.append(result)
+
+                    # Log progress every 100 rows
+                    if len(results) % 100 == 0:
+                        logger.info(f"Processed {len(results)} phones")
+
+                except ValueError as e:
+                    logger.warning(f"Invalid phone at row {row_num}: {str(e)}")
+                    continue
+                except Exception as e:
+                    logger.error(f"Error processing row {row_num}: {str(e)}")
+                    continue
+
+            logger.info(f"Completed processing {len(results)} valid phones")
+
+        except Exception as e:
+            logger.error(f"CSV processing failed: {str(e)}")
+            raise
+
+        return results
+
+    def _find_phone_column(self, headers: List[str], preferred: str) -> Optional[str]:
+        """Find phone column in headers (case-insensitive)"""
+        # First try exact match
+        for header in headers:
+            if header.lower() == preferred.lower():
+                return header
+
+        # Common phone column names
+        phone_patterns = [
+            "phone", "phone_number", "phonenumber", "mobile",
+            "cell", "telephone", "tel", "number", "contact"
+        ]
+
+        for header in headers:
+            header_lower = header.lower()
+            for pattern in phone_patterns:
+                if pattern in header_lower:
+                    logger.info(f"Using column '{header}' as phone column")
+                    return header
+
+        return None
+
+    def generate_results_csv(
+        self,
+        original_csv_text: str,
+        results: List[PhoneVerification]
+    ) -> str:
+        """
+        Generate CSV with original data plus verification results.
+        Adds columns: line_type, dnc, cached
+        Returns CSV text string.
+        """
+        # Create lookup dict
+        results_map = {r.phone_number: r for r in results}
+
+        # Parse original CSV
+        input_file = StringIO(original_csv_text)
+        reader = csv.DictReader(input_file)
+        headers = reader.fieldnames or []
+
+        # Add new columns
+        output_headers = headers + ["line_type", "dnc", "cached"]
+
+        # Create output CSV in memory
+        output = StringIO()
+        writer = csv.DictWriter(output, fieldnames=output_headers)
+        writer.writeheader()
+
+        phone_col = self._find_phone_column(headers, "phone")
+
+        for row in reader:
+            phone = row.get(phone_col, "").strip()
+
+            # Try to normalize for lookup
+            try:
+                normalized = self.verifier.normalize_phone(phone)
+                if normalized in results_map:
+                    result = results_map[normalized]
+                    row["line_type"] = result.line_type.value
+                    row["dnc"] = "true" if result.dnc else "false"
+                    row["cached"] = "true" if result.cached else "false"
+                else:
+                    row["line_type"] = "unknown"
+                    row["dnc"] = ""
+                    row["cached"] = ""
+            except:
+                row["line_type"] = "invalid"
+                row["dnc"] = ""
+                row["cached"] = ""
+
+            writer.writerow(row)
+
+        # Return CSV text
+        return output.getvalue()
+
+    def process_csv_stream(
+        self,
+        lines: Iterable[str],
+        phone_column: str = "phone",
+        batch_size: int = 100
+    ) -> Iterator[List[PhoneVerification]]:
+        """
+        Process CSV lines as a stream, yielding batches of results.
+        Memory-efficient for large files.
+
+        Args:
+            lines: Iterator of CSV lines (including header)
+            phone_column: Column name containing phone numbers
+            batch_size: Number of results to accumulate before yielding
+
+        Yields:
+            Batches of PhoneVerification results
+        """
+        lines_list = list(lines)  # Need to iterate twice - once for headers, once for data
+
+        if not lines_list:
+            logger.error("Empty CSV stream")
+            return
+
+        # Parse header
+        header_line = lines_list[0]
+        reader = csv.DictReader(StringIO(header_line))
+        headers = reader.fieldnames or []
+        phone_col = self._find_phone_column(headers, phone_column)
+
+        if not phone_col:
+            raise ValueError(f"Phone column '{phone_column}' not found in CSV")
+
+        batch = []
+        row_num = 2  # Start at 2 (header is 1)
+        total_processed = 0
+
+        # Process data lines
+        for line in lines_list[1:]:
+            if not line.strip():
+                continue
+
+            try:
+                # Parse single line
+                row = next(csv.DictReader(StringIO(line), fieldnames=headers))
+                phone = row.get(phone_col, "").strip()
+
+                if not phone:
+                    logger.warning(f"Empty phone at row {row_num}")
+                    row_num += 1
+                    continue
+
+                # Verify phone
+                result = self.verifier.verify(phone)
+                batch.append(result)
+                total_processed += 1
+
+                # Yield batch when full
+                if len(batch) >= batch_size:
+                    logger.info(f"Processed batch of {len(batch)} phones (total: {total_processed})")
+                    yield batch
+                    batch = []
+
+            except ValueError as e:
+                logger.warning(f"Invalid phone at row {row_num}: {str(e)}")
+            except Exception as e:
+                logger.error(f"Error processing row {row_num}: {str(e)}")
+            finally:
+                row_num += 1
+
+        # Yield remaining results
+        if batch:
+            logger.info(f"Processed final batch of {len(batch)} phones (total: {total_processed})")
+            yield batch
+
+        logger.info(f"Stream processing completed. Total processed: {total_processed}")
+
+    def generate_results_csv_stream(
+        self,
+        original_lines: Iterable[str],
+        results_stream: Iterator[List[PhoneVerification]],
+        phone_column: str = "phone"
+    ) -> Iterator[str]:
+        """
+        Generate CSV results as a stream, line by line.
+        Memory-efficient for large files.
+
+        Args:
+            original_lines: Iterator of original CSV lines
+            results_stream: Iterator of batched PhoneVerification results
+            phone_column: Column name containing phone numbers
+
+        Yields:
+            CSV lines with verification results added
+        """
+        lines_iter = iter(original_lines)
+
+        # Read and yield modified header
+        try:
+            header_line = next(lines_iter)
+            reader = csv.DictReader(StringIO(header_line))
+            headers = reader.fieldnames or []
+
+            # Add new columns
+            output_headers = headers + ["line_type", "dnc", "cached"]
+            yield ','.join(output_headers) + '\n'
+
+            phone_col = self._find_phone_column(headers, phone_column)
+
+        except StopIteration:
+            return
+
+        # Build results lookup from stream
+        results_map = {}
+        for batch in results_stream:
+            for result in batch:
+                results_map[result.phone_number] = result
+
+        # Reset lines iterator
+        lines_iter = iter(original_lines)
+        next(lines_iter)  # Skip header
+
+        # Process and yield data lines
+        for line in lines_iter:
+            if not line.strip():
+                continue
+
+            row = next(csv.DictReader(StringIO(line), fieldnames=headers))
+            phone = row.get(phone_col, "").strip()
+
+            # Add verification results
+            try:
+                normalized = self.verifier.normalize_phone(phone)
+                if normalized in results_map:
+                    result = results_map[normalized]
+                    row["line_type"] = result.line_type.value
+                    row["dnc"] = "true" if result.dnc else "false"
+                    row["cached"] = "true" if result.cached else "false"
+                else:
+                    row["line_type"] = "unknown"
+                    row["dnc"] = ""
+                    row["cached"] = ""
+            except:
+                row["line_type"] = "invalid"
+                row["dnc"] = ""
+                row["cached"] = ""
+
+            # Write row
+            output = StringIO()
+            writer = csv.DictWriter(output, fieldnames=output_headers)
+            writer.writerow(row)
+            yield output.getvalue()

ai_lls_lib/core/verifier.py

@@ -1,95 +1,84 @@
-"""
-Phone verification logic - checks line type and DNC status
-"""
-import os
-import re
-from datetime import datetime, timezone
-from typing import Optional
-import httpx
-import phonenumbers
-from aws_lambda_powertools import Logger
-from .models import PhoneVerification, LineType, VerificationSource
-from .cache import DynamoDBCache
-
-logger = Logger()
-
-
-class PhoneVerifier:
-    """Verifies phone numbers for line type and DNC status"""
-
-    def __init__(self, cache: DynamoDBCache):
-        self.cache = cache
-        self.dnc_api_key = os.environ.get("DNC_API_KEY", "")
-        self.phone_api_key = os.environ.get("PHONE_VERIFY_API_KEY", "")
-        self.http_client = httpx.Client(timeout=10.0)
-
-    def normalize_phone(self, phone: str) -> str:
-        """Normalize phone to E.164 format"""
-        try:
-            # Parse with US as default country
-            parsed = phonenumbers.parse(phone, "US")
-            if not phonenumbers.is_valid_number(parsed):
-                raise ValueError(f"Invalid phone number: {phone}")
-
-            # Format as E.164
-            return phonenumbers.format_number(parsed, phonenumbers.PhoneNumberFormat.E164)
-        except Exception as e:
-            logger.error(f"Phone normalization failed: {str(e)}")
-            raise ValueError(f"Invalid phone format: {phone}")
-
-    def verify_sync(self, phone: str) -> PhoneVerification:
-        """Synchronous verification for Lambda handlers"""
-        normalized = self.normalize_phone(phone)
-
-        # Check cache first
-        cached = self.cache.get(normalized)
-        if cached:
-            return cached
-
-        # Call external APIs
-        line_type = self._check_line_type_sync(normalized)
-        dnc_status = self._check_dnc_sync(normalized)
-
-        result = PhoneVerification(
-            phone_number=normalized,
-            line_type=line_type,
-            dnc=dnc_status,
-            cached=False,
-            verified_at=datetime.now(timezone.utc),
-            source=VerificationSource.API
-        )
-
-        # Store in cache
-        self.cache.set(normalized, result)
-
-        return result
-
-    def _check_line_type_sync(self, phone: str) -> LineType:
-        """Check if phone is mobile/landline/voip"""
-        # TODO: Implement actual API call to phone verification service
-        # Would use self.phone_api_key to authenticate
-        logger.info(f"Checking line type for {phone[:6]}***")
-
-        # Stub implementation based on last digit
-        last_digit = phone[-1] if phone else '5'
-        if last_digit in ['2', '0']:
-            return LineType.LANDLINE
-        else:
-            return LineType.MOBILE
-
-    def _check_dnc_sync(self, phone: str) -> bool:
-        """Check if phone is on DNC list"""
-        # TODO: Implement actual DNC API call
-        # Would use self.dnc_api_key or os.environ.get("DNC_CHECK_API_KEY")
-        logger.info(f"Checking DNC status for {phone[:6]}***")
-
-        # Stub implementation based on last digit:
-        # - Ends in 1 or 0: on DNC list
-        # - Otherwise: not on DNC
-        last_digit = phone[-1] if phone else '5'
-        return last_digit in ['1', '0']
-
-    def __del__(self):
-        """Cleanup HTTP client"""
-        if hasattr(self, 'http_client'):
-            self.http_client.close()
+"""
+Phone verification logic - checks line type and DNC status
+"""
+import os
+from datetime import datetime, timezone
+from typing import Optional
+import phonenumbers
+from aws_lambda_powertools import Logger
+from .models import PhoneVerification, LineType, VerificationSource
+from .cache import DynamoDBCache
+from ..providers import VerificationProvider, StubProvider
+
+logger = Logger()
+
+
+class PhoneVerifier:
+    """Verifies phone numbers for line type and DNC status"""
+
+    def __init__(self, cache: DynamoDBCache, provider: Optional[VerificationProvider] = None):
+        """
+        Initialize phone verifier.
+
+        Args:
+            cache: DynamoDB cache for storing results
+            provider: Verification provider (defaults to StubProvider)
+        """
+        self.cache = cache
+        self.provider = provider or StubProvider()
+
+    def normalize_phone(self, phone: str) -> str:
+        """Normalize phone to E.164 format"""
+        try:
+            # Parse with US as default country
+            parsed = phonenumbers.parse(phone, "US")
+            if not phonenumbers.is_valid_number(parsed):
+                raise ValueError(f"Invalid phone number: {phone}")
+
+            # Format as E.164
+            return phonenumbers.format_number(parsed, phonenumbers.PhoneNumberFormat.E164)
+        except Exception as e:
+            logger.error(f"Phone normalization failed: {str(e)}")
+            raise ValueError(f"Invalid phone format: {phone}")
+
+    def verify(self, phone: str) -> PhoneVerification:
+        """Verify phone number for line type and DNC status"""
+        normalized = self.normalize_phone(phone)
+
+        # Check cache first
+        cached = self.cache.get(normalized)
+        if cached:
+            return cached
+
+        # Use provider to verify
+        line_type, dnc_status = self.provider.verify_phone(normalized)
+
+        result = PhoneVerification(
+            phone_number=normalized,
+            line_type=line_type,
+            dnc=dnc_status,
+            cached=False,
+            verified_at=datetime.now(timezone.utc),
+            source=VerificationSource.API
+        )
+
+        # Store in cache
+        self.cache.set(normalized, result)
+
+        return result
+
+    def _check_line_type(self, phone: str) -> LineType:
+        """
+        Check line type (for backwards compatibility with CLI).
+        Delegates to provider.
+        """
+        line_type, _ = self.provider.verify_phone(phone)
+        return line_type
+
+    def _check_dnc(self, phone: str) -> bool:
+        """
+        Check DNC status (for backwards compatibility with CLI).
+        Delegates to provider.
+        """
+        _, dnc_status = self.provider.verify_phone(phone)
+        return dnc_status

ai_lls_lib/payment/__init__.py

@@ -0,0 +1,13 @@
+"""Payment module for Landline Scrubber."""
+
+from .models import Plan, PlanType, SubscriptionStatus
+from .stripe_manager import StripeManager
+from .credit_manager import CreditManager
+
+__all__ = [
+    "Plan",
+    "PlanType",
+    "SubscriptionStatus",
+    "StripeManager",
+    "CreditManager",
+]