Merge pull request #390 from Hawksight-AI/utils

ci: Optimize CI/CD Workflows — Scope Triggers to Avoid Redundant Runs

.github/workflows/benchmark.yml

@@ -2,9 +2,13 @@ name: Semantica Performance Suite
 
 on:
   push:
-    branches: [main, master]
-  pull_request:
-    branches: [main, master]
+    branches: [main]
+    paths-ignore:
+      - 'docs/**'
+      - 'mkdocs.yml'
+      - 'requirements-docs.txt'
+      - '**/*.md'
+  workflow_dispatch:
 
 jobs:
   performance-test:

.github/workflows/ci.yml

@@ -3,8 +3,18 @@ name: CI
 on:
   push:
     branches: [main]
+    paths-ignore:
+      - 'docs/**'
+      - 'mkdocs.yml'
+      - 'requirements-docs.txt'
+      - '**/*.md'
   pull_request:
     branches: [main]
+    paths-ignore:
+      - 'docs/**'
+      - 'mkdocs.yml'
+      - 'requirements-docs.txt'
+      - '**/*.md'
 
 jobs:
   build:

.github/workflows/docs.yml

@@ -8,11 +8,12 @@ on:
     branches: [main]
     paths:
       - 'docs/**'
-      - 'semantica/**'
       - 'mkdocs.yml'
       - 'requirements-docs.txt'
       - 'CHANGELOG.md'
       - 'RELEASE.md'
+  release:
+    types: [published]
   workflow_dispatch:
 
 # Permissions needed to deploy to GitHub Pages

.github/workflows/security-scan.yml

@@ -4,9 +4,19 @@ on:
   schedule:
     - cron: '30 1 * * 1,4'  # Mon/Thu 7 AM IST
   push:
-    branches: [ main ]
+    branches: [main]
+    paths-ignore:
+      - 'docs/**'
+      - 'mkdocs.yml'
+      - 'requirements-docs.txt'
+      - '**/*.md'
   pull_request:
-    branches: [ main ]
+    branches: [main]
+    paths-ignore:
+      - 'docs/**'
+      - 'mkdocs.yml'
+      - 'requirements-docs.txt'
+      - '**/*.md'
 
 jobs:
   security-scan:
@@ -158,7 +168,7 @@ jobs:
             }
             
             // Create summary comment
-            const comment = `# 🔒 Security Scan Results\\n\\n${safetyResults}\\n\\n${banditResults}\\n\\n${semgrepResults}\\n\\n---\\n\\n*This security scan runs automatically on every PR and bi-weekly.*\\n\\n📊 **Security Policy**: CI fails on vulnerabilities and HIGH severity issues.`;
+            const comment = `# 🔒 Security Scan Results\\n\\n${safetyResults}\\n\\n${banditResults}\\n\\n${semgrepResults}\\n\\n---\\n\\n*This security scan runs automatically on source-code PRs and bi-weekly (skipped for doc/markdown-only changes).*\\n\\n📊 **Security Policy**: CI fails on vulnerabilities and HIGH severity issues.`;
             
             // Post comment with error handling
             try {

pyproject.toml

@@ -220,3 +220,6 @@ profile = "black"
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
+markers = [
+    "integration: marks tests that require external services or API keys (deselect with '-m not integration')",
+]

semantica/context/decision_query.py

@@ -951,10 +951,11 @@ class DecisionQuery:
                 
                 for measure_type, measure_data in centrality_measures.items():
                     if isinstance(measure_data, dict) and 'centrality' in measure_data:
-                        decision_measures[measure_type] = measure_data['centrality'].get(decision_id, 0.0)
-                
+                        val = measure_data['centrality'].get(decision_id, 0.0)
+                        decision_measures[measure_type] = val if isinstance(val, (int, float)) else 0.0
+
                 analysis["centrality_measures"] = decision_measures
-                
+
                 # Calculate overall influence score
                 measures = analysis["centrality_measures"]
                 analysis["influence_score"] = (

semantica/ingest/db_ingestor.py

@@ -34,10 +34,6 @@ from datetime import datetime
 from typing import Any, Dict, List, Optional
 from urllib.parse import urlparse
 
-import sqlalchemy
-from sqlalchemy import create_engine, inspect, text
-from sqlalchemy.engine import Engine
-
 from ..utils.exceptions import ProcessingError, ValidationError
 from ..utils.logging import get_logger
 from ..utils.progress_tracker import get_progress_tracker
@@ -101,13 +97,13 @@ class DatabaseConnector:
         self.logger = get_logger("database_connector")
         self.db_type = db_type.lower() if db_type else ""
         self.config = config
-        self.engine: Optional[Engine] = None
+        self.engine: Optional[Any] = None
 
         self.logger.debug(
             f"Database connector initialized: db_type={db_type or 'auto-detect'}"
         )
 
-    def connect(self, connection_string: str) -> Engine:
+    def connect(self, connection_string: str) -> Any:
         """
         Establish database connection.
 
@@ -129,6 +125,14 @@ class DatabaseConnector:
             ProcessingError: If connection fails or database type is unsupported
         """
         try:
+            try:
+                from sqlalchemy import create_engine, text
+            except ImportError:
+                raise ProcessingError(
+                    "sqlalchemy is required for database ingestion. "
+                    "Install with: pip install sqlalchemy"
+                )
+
             # Parse connection string to detect database type
             parsed = urlparse(connection_string)
 
@@ -188,6 +192,7 @@ class DatabaseConnector:
             bool: True if connection successful, False otherwise
         """
         try:
+            from sqlalchemy import create_engine, text
             engine = create_engine(connection_string)
             with engine.connect() as conn:
                 conn.execute(text("SELECT 1"))
@@ -226,7 +231,7 @@ class DataExporter:
 
     def export_table_data(
         self,
-        connection: Engine,
+        connection: Any,
         table_name: str,
         schema: Optional[str] = None,
         limit: Optional[int] = None,
@@ -264,6 +269,7 @@ class DataExporter:
             ProcessingError: If table export fails
         """
         try:
+            from sqlalchemy import inspect
             inspector = inspect(connection)
 
             # Get column information
@@ -379,7 +385,7 @@ class DataExporter:
         return transformed
 
     def export_schema(
-        self, connection: Engine, schema: Optional[str] = None
+        self, connection: Any, schema: Optional[str] = None
     ) -> Dict[str, Any]:
         """
         Export database schema information.
@@ -406,6 +412,7 @@ class DataExporter:
             ProcessingError: If schema export fails
         """
         try:
+            from sqlalchemy import inspect
             inspector = inspect(connection)
 
             schema_info = {"tables": [], "views": [], "foreign_keys": []}
@@ -591,6 +598,7 @@ class DBIngestor:
                 schema = self.analyze_schema(connection_string)
 
                 # Get all table names
+                from sqlalchemy import inspect
                 inspector = inspect(engine)
                 all_tables = inspector.get_table_names()
 

semantica/parse/pdf_parser.py

@@ -33,9 +33,6 @@ from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 
-import pdfplumber
-from PIL import Image
-
 from ..utils.exceptions import ProcessingError, ValidationError
 from ..utils.logging import get_logger
 from ..utils.progress_tracker import get_progress_tracker
@@ -119,6 +116,13 @@ class PDFParser:
                 raise ValidationError(f"File is not a PDF: {file_path}")
 
             try:
+                try:
+                    import pdfplumber
+                except ImportError:
+                    raise ProcessingError(
+                        "pdfplumber is required for PDF parsing. "
+                        "Install with: pip install pdfplumber"
+                    )
                 with pdfplumber.open(str(file_path)) as pdf:
                     # Extract metadata
                     metadata = self._extract_metadata(pdf)

semantica/parse/pptx_parser.py

@@ -32,8 +32,6 @@ from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 
-from pptx import Presentation
-
 from ..utils.exceptions import ProcessingError, ValidationError
 from ..utils.logging import get_logger
 from ..utils.progress_tracker import get_progress_tracker
@@ -97,6 +95,13 @@ class PPTXParser:
             raise ValidationError(f"File is not a PPTX: {file_path}")
 
         try:
+            try:
+                from pptx import Presentation
+            except ImportError:
+                raise ProcessingError(
+                    "python-pptx is required for PPTX parsing. "
+                    "Install with: pip install python-pptx"
+                )
             prs = Presentation(str(file_path))
 
             # Extract metadata
@@ -220,7 +225,7 @@ class PPTXParser:
             images=images,
         )
 
-    def _extract_metadata(self, prs: Presentation) -> Dict[str, Any]:
+    def _extract_metadata(self, prs: Any) -> Dict[str, Any]:
         """Extract presentation metadata."""
         metadata = {}
 

tests/test_novita_integration.py

@@ -11,7 +11,7 @@ from semantica.semantic_extract.methods import (
     extract_triplets_llm,
 )
 from semantica.semantic_extract.providers import create_provider
-from semantica.semantic_extract.models import Entity
+from semantica.semantic_extract import Entity
 
 NOVITA_API_KEY = os.environ.get("NOVITA_API_KEY")
 NOVITA_MODEL = "deepseek/deepseek-v3.2"