pvw-cli 1.2.3__py3-none-any.whl → 1.2.4__py3-none-any.whl

purviewcli/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "1.2.3"
+__version__ = "1.2.4"
 
 # Import main client modules
 from .client import *

purviewcli/cli/lineage.py

@@ -54,7 +54,7 @@ def lineage(ctx):
 def import_cmd(ctx, csv_file):
     """Import lineage relationships from CSV file (calls client lineageCSVProcess)."""
     try:
-        if ctx.obj.get("mock"):
+        if ctx.obj and ctx.obj.get("mock"):
             console.print("[yellow][MOCK] lineage import command[/yellow]")
             console.print(f"[dim]File: {csv_file}[/dim]")
             console.print("[green]MOCK lineage import completed successfully[/green]")
@@ -68,6 +68,9 @@ def import_cmd(ctx, csv_file):
         console.print(json.dumps(result, indent=2))
     except Exception as e:
         console.print(f"[red]ERROR: Error executing lineage import: {str(e)}[/red]")
+        import traceback
+        if ctx.obj and ctx.obj.get("debug"):
+            console.print(f"[dim]{traceback.format_exc()}[/dim]")
 
 
 @lineage.command()

purviewcli/client/_lineage.py

@@ -209,20 +209,29 @@ class Lineage(Endpoint):
         # Read CSV file
         df = pd.read_csv(csv_file)
         
-        # Validate required columns
-        required_columns = ['source_qualified_name', 'target_qualified_name']
-        missing_columns = [col for col in required_columns if col not in df.columns]
-        if missing_columns:
-            raise ValueError(f"Missing required columns: {missing_columns}")
+        # Determine which format is being used (GUID-based or qualified name-based)
+        has_guid_columns = 'source_entity_guid' in df.columns and 'target_entity_guid' in df.columns
+        has_qn_columns = 'source_qualified_name' in df.columns and 'target_qualified_name' in df.columns
+        
+        if not has_guid_columns and not has_qn_columns:
+            raise ValueError(
+                "CSV must contain either (source_entity_guid, target_entity_guid) "
+                "or (source_qualified_name, target_qualified_name) columns"
+            )
         
         # Generate lineage entities and relationships
         lineage_entities = []
         lineage_relationships = []
         
-        for _, row in df.iterrows():
+        for idx, row in df.iterrows():
             # Create process entity for each lineage relationship
             process_guid = str(uuid.uuid4())
-            process_name = row.get('process_name', f"Process_{datetime.now().strftime('%Y%m%d_%H%M%S')}")
+            process_name = row.get('process_name', f"Process_{datetime.now().strftime('%Y%m%d_%H%M%S')}_{idx}")
+            
+            # Clean GUIDs if present (remove guid= prefix and quotes)
+            if has_guid_columns:
+                source_guid = str(row['source_entity_guid']).strip().replace('guid=', '').strip('"')
+                target_guid = str(row['target_entity_guid']).strip().replace('guid=', '').strip('"')
             
             # Process entity
             process_entity = {
@@ -231,8 +240,8 @@ class Lineage(Endpoint):
                 "attributes": {
                     "qualifiedName": f"{process_name}@{args.get('--cluster', 'default')}",
                     "name": process_name,
-                    "description": row.get('description', ''),
-                    "owner": row.get('owner', ''),
+                    "description": str(row.get('description', '')),
+                    "owner": str(row.get('owner', '')),
                 },
                 "classifications": [],
                 "meanings": []
@@ -241,7 +250,7 @@ class Lineage(Endpoint):
             # Add custom attributes if present
             custom_attrs = ['confidence_score', 'metadata', 'tags']
             for attr in custom_attrs:
-                if attr in row and pd.notna(row[attr]):
+                if attr in row and pd.notna(row[attr]) and str(row[attr]).strip():
                     if attr == 'tags':
                         process_entity["attributes"][attr] = str(row[attr]).split(',')
                     elif attr == 'metadata':
@@ -254,41 +263,74 @@ class Lineage(Endpoint):
             
             lineage_entities.append(process_entity)
             
-            # Input relationship (source -> process)
-            input_relationship = {
-                "guid": str(uuid.uuid4()),
-                "typeName": "Process",
-                "end1": {
-                    "guid": "-1",  # Will be resolved by qualified name
-                    "typeName": row.get('source_type', 'DataSet'),
-                    "uniqueAttributes": {
-                        "qualifiedName": row['source_qualified_name']
-                    }
-                },
-                "end2": {
-                    "guid": process_guid,
-                    "typeName": "Process"
-                },
-                "label": "inputToProcesses"
-            }
+            # Determine relationship type
+            relationship_type = str(row.get('relationship_type', 'Process')).strip() or 'Process'
             
-            # Output relationship (process -> target)
-            output_relationship = {
-                "guid": str(uuid.uuid4()),
-                "typeName": "Process",
-                "end1": {
-                    "guid": process_guid,
-                    "typeName": "Process"
-                },
-                "end2": {
-                    "guid": "-1",  # Will be resolved by qualified name
-                    "typeName": row.get('target_type', 'DataSet'),
-                    "uniqueAttributes": {
-                        "qualifiedName": row['target_qualified_name']
-                    }
-                },
-                "label": "outputFromProcesses"
-            }
+            # Input relationship (source -> process)
+            if has_guid_columns:
+                input_relationship = {
+                    "guid": str(uuid.uuid4()),
+                    "typeName": relationship_type,
+                    "end1": {
+                        "guid": source_guid,
+                        "typeName": row.get('source_type', 'DataSet')
+                    },
+                    "end2": {
+                        "guid": process_guid,
+                        "typeName": "Process"
+                    },
+                    "label": "inputToProcesses"
+                }
+                
+                # Output relationship (process -> target)
+                output_relationship = {
+                    "guid": str(uuid.uuid4()),
+                    "typeName": relationship_type,
+                    "end1": {
+                        "guid": process_guid,
+                        "typeName": "Process"
+                    },
+                    "end2": {
+                        "guid": target_guid,
+                        "typeName": row.get('target_type', 'DataSet')
+                    },
+                    "label": "outputFromProcesses"
+                }
+            else:
+                # Use qualified names
+                input_relationship = {
+                    "guid": str(uuid.uuid4()),
+                    "typeName": relationship_type,
+                    "end1": {
+                        "guid": "-1",
+                        "typeName": row.get('source_type', 'DataSet'),
+                        "uniqueAttributes": {
+                            "qualifiedName": row['source_qualified_name']
+                        }
+                    },
+                    "end2": {
+                        "guid": process_guid,
+                        "typeName": "Process"
+                    },
+                    "label": "inputToProcesses"
+                }
+                
+                output_relationship = {
+                    "guid": str(uuid.uuid4()),
+                    "typeName": relationship_type,
+                    "end1": {
+                        "guid": process_guid,
+                        "typeName": "Process"
+                    },
+                    "end2": {
+                        "guid": "-1",
+                        "typeName": row.get('target_type', 'DataSet'),
+                        "uniqueAttributes": {
+                            "qualifiedName": row['target_qualified_name']
+                        }
+                    },
+                    "label": "outputFromProcesses"
+                }
             
             lineage_relationships.extend([input_relationship, output_relationship])
         
@@ -298,6 +340,126 @@ class Lineage(Endpoint):
             "referredEntities": {}
         }
 
+    # === CSV LINEAGE OPERATIONS ===
+
+    @decorator
+    def lineageCSVProcess(self, args):
+        """Process CSV file and create lineage relationships"""
+        csv_file = args.get("csv_file") or args.get("--csv-file")
+        if not csv_file:
+            raise ValueError("CSV file path is required")
+        
+        # Process CSV and create lineage payload
+        lineage_data = self._process_csv_lineage(csv_file, args)
+        
+        # Create lineage using the API
+        self.method = "POST"
+        self.endpoint = ENDPOINTS["lineage"]["create_lineage"]
+        self.params = get_api_version_params("datamap")
+        self.payload = lineage_data
+        
+        # Return the payload for inspection (actual API call handled by decorator)
+        return lineage_data
+
+    def lineageCSVValidate(self, args):
+        """Validate CSV lineage file format (no API call)"""
+        import pandas as pd
+        
+        csv_file = args.get("csv_file") or args.get("--csv-file")
+        if not csv_file:
+            return {"success": False, "error": "CSV file path is required"}
+        
+        try:
+            # Read CSV
+            df = pd.read_csv(csv_file)
+            
+            # Check required columns
+            required_columns = ['source_entity_guid', 'target_entity_guid']
+            missing_columns = [col for col in required_columns if col not in df.columns]
+            
+            if missing_columns:
+                return {
+                    "success": False,
+                    "error": f"Missing required columns: {', '.join(missing_columns)}",
+                    "expected_columns": required_columns
+                }
+            
+            # Validate GUIDs format
+            import re
+            guid_pattern = re.compile(r'^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$', re.IGNORECASE)
+            
+            invalid_guids = []
+            for idx, row in df.iterrows():
+                source_guid = str(row['source_entity_guid']).strip()
+                target_guid = str(row['target_entity_guid']).strip()
+                
+                # Remove guid= prefix if present
+                source_guid = source_guid.replace('guid=', '').strip('"')
+                target_guid = target_guid.replace('guid=', '').strip('"')
+                
+                if not guid_pattern.match(source_guid):
+                    invalid_guids.append(f"Row {int(idx) + 1}: Invalid source GUID '{source_guid}'")
+                if not guid_pattern.match(target_guid):
+                    invalid_guids.append(f"Row {int(idx) + 1}: Invalid target GUID '{target_guid}'")
+            
+            if invalid_guids:
+                return {
+                    "success": False,
+                    "error": "Invalid GUID format(s) found",
+                    "details": invalid_guids
+                }
+            
+            return {
+                "success": True,
+                "rows": len(df),
+                "columns": list(df.columns)
+            }
+            
+        except Exception as e:
+            return {"success": False, "error": str(e)}
+
+    def lineageCSVSample(self, args):
+        """Generate sample CSV lineage file (no API call)"""
+        sample_data = """source_entity_guid,target_entity_guid,relationship_type,process_name,description,confidence_score,owner,metadata
+ea3412c3-7387-4bc1-9923-11f6f6f60000,2d21eba5-b08b-4571-b31d-7bf6f6f60000,Process,ETL_Customer_Transform,Transform customer data,0.95,data-engineering,"{""tool"": ""Azure Data Factory""}"
+2d21eba5-b08b-4571-b31d-7bf6f6f60000,4fae348b-e960-42f7-834c-38f6f6f60000,Process,Customer_Address_Join,Join customer with address,0.90,data-engineering,"{""tool"": ""Databricks""}"
+"""
+        output_file = args.get("--output-file") or args.get("output_file") or "lineage_sample.csv"
+        
+        try:
+            with open(output_file, 'w', encoding='utf-8') as f:
+                f.write(sample_data)
+            
+            return {
+                "success": True,
+                "file": output_file,
+                "message": f"Sample CSV file created: {output_file}"
+            }
+        except Exception as e:
+            return {"success": False, "error": str(e)}
+
+    def lineageCSVTemplates(self, args):
+        """Get available CSV lineage templates (no API call)"""
+        templates = {
+            "basic": {
+                "columns": ["source_entity_guid", "target_entity_guid", "relationship_type", "process_name"],
+                "description": "Basic lineage with source, target, and process name"
+            },
+            "detailed": {
+                "columns": ["source_entity_guid", "target_entity_guid", "relationship_type", "process_name", "description", "confidence_score", "owner", "metadata"],
+                "description": "Detailed lineage with additional metadata"
+            },
+            "qualified_names": {
+                "columns": ["source_qualified_name", "target_qualified_name", "source_type", "target_type", "process_name", "description"],
+                "description": "Lineage using qualified names instead of GUIDs"
+            }
+        }
+        
+        return {
+            "templates": templates,
+            "recommended": "detailed"
+        }
+
     # === LINEAGE ANALYTICS AND REPORTING ===
 
     @decorator

{pvw_cli-1.2.3.dist-info → pvw_cli-1.2.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pvw-cli
-Version: 1.2.3
+Version: 1.2.4
 Summary: Microsoft Purview CLI with comprehensive automation capabilities
 Author-email: AYOUB KEBAILI <keayoub@msn.com>
 Maintainer-email: AYOUB KEBAILI <keayoub@msn.com>
@@ -56,26 +56,28 @@ Requires-Dist: pytest-asyncio>=0.20.0; extra == "test"
 Requires-Dist: pytest-cov>=4.0.0; extra == "test"
 Requires-Dist: requests-mock>=1.9.0; extra == "test"
 
-# PURVIEW CLI v1.2.3 - Microsoft Purview Automation & Data Governance
-
-> **LATEST UPDATE v1.2.3 (October 2025):**
-> - **🔍 FIXED: Search API Integration** - Fixed `suggest` and `autocomplete` API payload format (HTTP 400 errors resolved)
-> - **📊 ENHANCED: Collection Display** - Improved collection name detection in search results with proper fallback logic
-> - **✅ VALIDATED: All Search Commands** - Comprehensive testing of query, browse, suggest, find-table operations
-> - **📦 NEW: Bulk Term Import/Export** - Import multiple terms from CSV/JSON with dry-run support
-> - **🗑️ NEW: Bulk Delete Scripts** - PowerShell and Python scripts for bulk term deletion
-> - **📊 NEW: Multiple Output Formats** - `--output` flag supports table, json, and jsonc formats
-> - **🔧 NEW: PowerShell Integration** - Plain JSON output works with `ConvertFrom-Json`
-> - **🚀 Complete Data Product CRUD** - Full update and delete support with smart partial updates
-> - **🏥 Health Monitoring API** - Automated governance health checks and recommendations
-> - **🔄 Workflow Management** - Approval workflows and business process automation
-> - **🚀 Complete Microsoft Purview Unified Catalog (UC)** - Full governance domains, glossary terms, data products, OKRs, and CDEs
+# PURVIEW CLI v1.2.4 - Microsoft Purview Automation & Data Governance
+
+> **LATEST UPDATE v1.2.4 (October 2025):**
+>
+> - **[NEW]** Lineage CSV Import - Bulk import lineage relationships from CSV files with validation and sample generation
+> - **[FIXED]** Search API Integration - Fixed `suggest` and `autocomplete` API payload format (HTTP 400 errors resolved)
+> - **[ENHANCED]** Collection Display - Improved collection name detection in search results with proper fallback logic
+> - **[OK]** All Search Commands - Comprehensive testing of query, browse, suggest, find-table operations
+> - **[NEW]** Bulk Term Import/Export - Import multiple terms from CSV/JSON with dry-run support
+> - **[NEW]** Bulk Delete Scripts - PowerShell and Python scripts for bulk term deletion
+> - **[NEW]** Multiple Output Formats - `--output` flag supports table, json, and jsonc formats
+> - **[NEW]** PowerShell Integration - Plain JSON output works with `ConvertFrom-Json`
+> - **[OK]** Complete Data Product CRUD - Full update and delete support with smart partial updates
+> - **[OK]** Health Monitoring API - Automated governance health checks and recommendations
+> - **[OK]** Workflow Management - Approval workflows and business process automation
+> - **[OK]** Complete Microsoft Purview Unified Catalog (UC) - Full governance domains, glossary terms, data products, OKRs, and CDEs
 
 ---
 
 ## What is PVW CLI?
 
-**PVW CLI v1.2.3** is a modern, full-featured command-line interface and Python library for Microsoft Purview. It enables automation and management of *all major Purview APIs* including:
+**PVW CLI v1.2.4** is a modern, full-featured command-line interface and Python library for Microsoft Purview. It enables automation and management of *all major Purview APIs* including:
 
 - **Unified Catalog (UC) Management** - Complete governance domains, glossary terms, data products, OKRs, CDEs
 - **Bulk Operations** - Import/export terms from CSV/JSON, bulk delete scripts with progress tracking
@@ -92,7 +94,7 @@ The CLI is designed for data engineers, stewards, architects, and platform teams
 
 ---
 
-## Getting Started 
+## Getting Started
 
 Follow this short flow to get PVW CLI installed and running quickly.
 
@@ -144,8 +146,8 @@ Follow this short flow to get PVW CLI installed and running quickly.
 
 3. Authenticate
 
-  - Run `az login` (recommended), or
-  - Provide Service Principal credentials via environment variables.
+- Run `az login` (recommended), or
+- Provide Service Principal credentials via environment variables.
 
 4. Try a few commands:
 
@@ -161,13 +163,13 @@ Follow this short flow to get PVW CLI installed and running quickly.
   pvw uc --help
   ```
 
-For more advanced usage, see the documentation in `doc/` or the project docs: https://pvw-cli.readthedocs.io/
+For more advanced usage, see the documentation in `doc/` or the project docs: <https://pvw-cli.readthedocs.io/>
 
 ---
 
 ## Overview
 
-**PVW CLI v1.2.3** is a modern command-line interface and Python library for Microsoft Purview, enabling:
+**PVW CLI v1.2.4** is a modern command-line interface and Python library for Microsoft Purview, enabling:
 
 - Advanced data catalog search and discovery
 - Bulk import/export of entities, glossary terms, and lineage
@@ -296,6 +298,7 @@ If you are signed in to Azure in Visual Studio or VS Code, `DefaultAzureCredenti
 ---
 
 **Note:**
+
 - The CLI will try all supported authentication methods in order. The first one that works will be used.
 - For most automation and CI/CD scenarios, service principal authentication is recommended.
 - For local development, Azure CLI authentication is easiest.
@@ -381,11 +384,13 @@ pvw uc dataproduct list --domain-id "abc-123" --output json
 ### Migration from Old --json Flag
 
 **Old (deprecated):**
+
 ```bash
 pvw uc term list --domain-id "abc-123" --json
 ```
 
 **New (recommended):**
+
 ```bash
 pvw uc term list --domain-id "abc-123" --output json    # Plain JSON for scripting
 pvw uc term list --domain-id "abc-123" --output jsonc   # Colored JSON (old behavior)
@@ -400,21 +405,25 @@ Before using PVW CLI, you need to set three essential environment variables. Her
 ### 🔍 **How to Find Your Purview Values**
 
 #### **1. PURVIEW_ACCOUNT_NAME**
+
 - This is your Purview account name as it appears in Azure Portal
 - Example: `kaydemopurview`
 
-#### **2. PURVIEW_ACCOUNT_ID** 
+#### **2. PURVIEW_ACCOUNT_ID**
+
 - This is the GUID that identifies your Purview account for Unified Catalog APIs
-- **✅ Important: For most Purview deployments, this is your Azure Tenant ID**
+- **Important: For most Purview deployments, this is your Azure Tenant ID**
 
 - **Method 1 - Get your Tenant ID (recommended):**
   
   **Bash/Command Prompt:**
+
   ```bash
   az account show --query tenantId -o tsv
   ```
   
   **PowerShell:**
+
   ```powershell
   az account show --query tenantId -o tsv
   # Or store directly in environment variable:
@@ -422,9 +431,11 @@ Before using PVW CLI, you need to set three essential environment variables. Her
   ```
 
 - **Method 2 - Azure CLI (extract from Atlas endpoint):**
+
   ```bash
   az purview account show --name YOUR_ACCOUNT_NAME --resource-group YOUR_RG --query endpoints.catalog -o tsv
   ```
+
   Extract the GUID from the URL (before `-api.purview-service.microsoft.com`)
 
 - **Method 3 - Azure Portal:**
@@ -433,12 +444,14 @@ Before using PVW CLI, you need to set three essential environment variables. Her
   3. Extract GUID from: `https://GUID-api.purview-service.microsoft.com/catalog`
 
 #### **3. PURVIEW_RESOURCE_GROUP**
+
 - The Azure resource group containing your Purview account
 - Example: `fabric-artifacts`
 
 ### 📋 **Setting the Variables**
 
 **Windows Command Prompt:**
+
 ```cmd
 set PURVIEW_ACCOUNT_NAME=your-purview-account
 set PURVIEW_ACCOUNT_ID=your-purview-account-id
@@ -446,6 +459,7 @@ set PURVIEW_RESOURCE_GROUP=your-resource-group
 ```
 
 **Windows PowerShell:**
+
 ```powershell
 $env:PURVIEW_ACCOUNT_NAME="your-purview-account"
 $env:PURVIEW_ACCOUNT_ID="your-purview-account-id" 
@@ -453,6 +467,7 @@ $env:PURVIEW_RESOURCE_GROUP="your-resource-group"
 ```
 
 **Linux/macOS:**
+
 ```bash
 export PURVIEW_ACCOUNT_NAME=your-purview-account
 export PURVIEW_ACCOUNT_ID=your-purview-account-id
@@ -460,6 +475,7 @@ export PURVIEW_RESOURCE_GROUP=your-resource-group
 ```
 
 **Permanent (Windows Command Prompt):**
+
 ```cmd
 setx PURVIEW_ACCOUNT_NAME "your-purview-account"
 setx PURVIEW_ACCOUNT_ID "your-purview-account-id"
@@ -467,17 +483,19 @@ setx PURVIEW_RESOURCE_GROUP "your-resource-group"
 ```
 
 **Permanent (Windows PowerShell):**
+
 ```powershell
 [Environment]::SetEnvironmentVariable("PURVIEW_ACCOUNT_NAME", "your-purview-account", "User")
 [Environment]::SetEnvironmentVariable("PURVIEW_ACCOUNT_ID", "your-purview-account-id", "User")
 [Environment]::SetEnvironmentVariable("PURVIEW_RESOURCE_GROUP", "your-resource-group", "User")
 ```
 
-### 🔧 **Debug Environment Issues**
+### **Debug Environment Issues**
 
 If you experience issues with environment variables between different terminals, use these debug commands:
 
 **Command Prompt/Bash:**
+
 ```bash
 # Run this to check your current environment
 python -c "
@@ -489,6 +507,7 @@ print('PURVIEW_RESOURCE_GROUP:', os.getenv('PURVIEW_RESOURCE_GROUP'))
 ```
 
 **PowerShell:**
+
 ```powershell
 # Check environment variables in PowerShell
 python -c "
@@ -514,14 +533,15 @@ The PVW CLI provides advanced search using the latest Microsoft Purview Discover
 - Use autocomplete and suggestion endpoints
 - Perform faceted, time-based, and entity-type-specific queries
 
-**✅ v1.2.3 Improvements:**
+**v1.2.4 Improvements:**
+
 - Fixed `suggest` and `autocomplete` API payload format (removed empty filter causing HTTP 400 errors)
 - Enhanced collection display with robust type checking and fallback logic
 - All search commands validated and working correctly (query, browse, suggest, find-table)
 
 ### CLI Usage Examples
 
-#### 🎯 **Multiple Output Formats**
+#### **Multiple Output Formats**
 
 ```bash
 # 1. Table Format (Default) - Quick overview
@@ -541,7 +561,7 @@ pvw search query --keywords="customer" --limit=5 --show-ids
 # → Table format + entity GUIDs for copy/paste into update commands
 ```
 
-#### 🔍 **Search Operations**
+#### **Search Operations**
 
 ```bash
 # Basic search for assets with keyword 'customer'
@@ -559,12 +579,12 @@ pvw search autocomplete --keywords="ord" --limit=3
 # Get search suggestions (fuzzy matching)
 pvw search suggest --keywords="prod" --limit=2
 
-**⚠️ IMPORTANT - Command Line Quoting:**
+**IMPORTANT - Command Line Quoting:**
 ```cmd
-# ✅ CORRECT - Use quotes around keywords
+# [OK] CORRECT - Use quotes around keywords
 pvw search query --keywords="customer" --limit=5
 
-# ✅ CORRECT - For wildcard searches, use quotes
+# [OK] CORRECT - For wildcard searches, use quotes
 pvw search query --keywords="*" --limit=5
 
 # ❌ WRONG - Don't use unquoted * (shell expands to file names)
@@ -586,7 +606,7 @@ pvw search query --keywords="audit" --createdAfter="2024-01-01" --limit=1
 pvw search query --keywords="finance" --entityTypes="Files,Tables" --limit=2
 ```
 
-#### 💡 **Usage Scenarios**
+#### **Usage Scenarios**
 
 - **Daily browsing**: Use default table format for quick scans
 - **Understanding assets**: Use `--detailed` for rich information panels  
@@ -629,7 +649,7 @@ See [`doc/commands/unified-catalog.md`](doc/commands/unified-catalog.md) for com
 
 ### Quick UC Examples
 
-#### 🏛️ **Governance Domains Management**
+#### **Governance Domains Management**
 
 ```bash
 # List all governance domains
@@ -645,7 +665,7 @@ pvw uc domain get --domain-id "abc-123-def-456"
 pvw uc domain update --domain-id "abc-123" --description "Updated financial governance"
 ```
 
-#### 📖 **Glossary Terms in UC**
+#### **Glossary Terms in UC**
 
 ```bash
 # List all terms in a domain
@@ -686,14 +706,16 @@ pvw uc term import-json --json-file "samples/json/term/uc_terms_bulk_example.jso
 ```
 
 **Bulk Import Features:**
-- ✅ Import from CSV or JSON files
-- ✅ Dry-run mode to preview before importing
-- ✅ Support for multiple owners (Entra ID Object IDs), acronyms, and resources
-- ✅ Progress tracking with Rich console output
-- ✅ Detailed error messages and summary reports
-- ✅ Sequential POST requests (no native bulk endpoint available)
+
+- [OK] Import from CSV or JSON files
+- [OK] Dry-run mode to preview before importing
+- [OK] Support for multiple owners (Entra ID Object IDs), acronyms, and resources
+- [OK] Progress tracking with Rich console output
+- [OK] Detailed error messages and summary reports
+- [OK] Sequential POST requests (no native bulk endpoint available)
 
 **CSV Format Example:**
+
 ```csv
 name,description,status,acronym,owner_id,resource_name,resource_url
 Customer Acquisition Cost,Cost to acquire new customer,Draft,CAC,<guid>,Metrics Guide,https://docs.example.com
@@ -701,6 +723,7 @@ Monthly Recurring Revenue,Predictable monthly revenue,Draft,MRR,<guid>,Finance D
 ```
 
 **JSON Format Example:**
+
 ```json
 {
   "terms": [
@@ -718,9 +741,10 @@ Monthly Recurring Revenue,Predictable monthly revenue,Draft,MRR,<guid>,Finance D
 ```
 
 **Important Notes:**
+
 - ⚠️ **Owner IDs must be Entra ID Object IDs (GUIDs)**, not email addresses
 - ⚠️ **Terms cannot be "Published" in unpublished domains** - use "Draft" status
-- ✅ Sample files available: `samples/csv/uc_terms_bulk_example.csv`, `samples/json/term/uc_terms_bulk_example.json`
+- [OK] Sample files available: `samples/csv/uc_terms_bulk_example.csv`, `samples/json/term/uc_terms_bulk_example.json`
 - 📖 Complete documentation: [`doc/commands/unified-catalog/term-bulk-import.md`](doc/commands/unified-catalog/term-bulk-import.md)
 
 **🗑️ Bulk Delete (NEW)**
@@ -744,14 +768,15 @@ python scripts/delete_all_uc_terms_v2.py --domain-id "abc-123" --force
 ```
 
 **Bulk Delete Features:**
-- ✅ Interactive confirmation prompts (type "DELETE" to confirm)
-- ✅ Beautiful progress display with colors
-- ✅ Success/failure tracking per term
-- ✅ Detailed summary reports
-- ✅ Rate limiting (200ms delay between deletes)
-- ✅ Graceful error handling and Ctrl+C support
 
-#### 📦 **Data Products Management**
+- [OK] Interactive confirmation prompts (type "DELETE" to confirm)
+- [OK] Beautiful progress display with colors
+- [OK] Success/failure tracking per term
+- [OK] Detailed summary reports
+- [OK] Rate limiting (200ms delay between deletes)
+- [OK] Graceful error handling and Ctrl+C support
+
+#### **Data Products Management**
 
 ```bash
 # List all data products in a domain
@@ -789,7 +814,7 @@ pvw uc dataproduct delete --product-id "prod-789"
 pvw uc dataproduct delete --product-id "prod-789" --yes
 ```
 
-#### 🎯 **Objectives & Key Results (OKRs)**
+#### **Objectives & Key Results (OKRs)**
 
 ```bash
 # List objectives for a domain
@@ -810,7 +835,7 @@ pvw uc objective update \
   --status "in-progress"
 ```
 
-#### 🔑 **Critical Data Elements (CDEs)**
+#### **Critical Data Elements (CDEs)**
 
 ```bash
 # List critical data elements
@@ -831,7 +856,7 @@ pvw uc cde link \
   --asset-id "ea3412c3-7387-4bc1-9923-11f6f6f60000"
 ```
 
-#### 🏥 **Health Monitoring (NEW)**
+#### **Health Monitoring (NEW)**
 
 Monitor governance health and get automated recommendations to improve your data governance posture.
 
@@ -864,6 +889,7 @@ pvw uc health query --json
 ```
 
 **Health Finding Types:**
+
 - Missing glossary terms on data products (High)
 - Data products without OKRs (Medium)
 - Missing data quality scores (Medium)
@@ -871,7 +897,7 @@ pvw uc health query --json
 - Description quality issues (Medium)
 - Business domains without critical data entities (Medium)
 
-#### 🔄 **Workflow Management (NEW)**
+#### **Workflow Management (NEW)**
 
 Manage approval workflows and business process automation in Purview.
 
@@ -905,12 +931,13 @@ pvw workflow list --json
 ```
 
 **Workflow Use Cases:**
+
 - Data access request approvals
 - Glossary term certification workflows
 - Data product publishing approvals
 - Classification review processes
 
-#### 🔄 **Integrated Workflow Example**
+#### **Integrated Workflow Example**
 
 ```bash
 # 1. Discover assets to govern
@@ -935,7 +962,7 @@ pvw uc objective create --definition "Ensure 100% PII classification compliance"
 
 PVW CLI provides comprehensive entity management capabilities for updating Purview assets like descriptions, classifications, and custom attributes.
 
-### 🔄 **Entity Update Examples**
+### **Entity Update Examples**
 
 #### **Update Asset Descriptions**
 
@@ -982,7 +1009,7 @@ pvw entity add-classification \
   --classification "MICROSOFT.PERSONAL.EMAIL"
 ```
 
-### 🔍 **Discovery to Update Workflow**
+### **Discovery to Update Workflow**
 
 ```bash
 # 1. Find assets that need updates
@@ -1003,6 +1030,90 @@ pvw search query --keywords="FOUND_GUID" --detailed
 
 ---
 
+## Lineage CSV Import & Management
+
+PVW CLI provides powerful lineage management capabilities including CSV-based bulk import for automating data lineage creation.
+
+### **Lineage CSV Import**
+
+Import lineage relationships from CSV files to automate the creation of data flow documentation in Microsoft Purview.
+
+#### **CSV Format**
+
+The CSV file must contain the following columns:
+
+**Required columns:**
+
+- `source_entity_guid` - GUID of the source entity
+- `target_entity_guid` - GUID of the target entity
+
+**Optional columns:**
+
+- `relationship_type` - Type of relationship (default: "Process")
+- `process_name` - Name of the transformation process
+- `description` - Description of the transformation
+- `confidence_score` - Confidence score (0-1)
+- `owner` - Process owner
+- `metadata` - Additional JSON metadata
+
+**Example CSV:**
+
+```csv
+source_entity_guid,target_entity_guid,relationship_type,process_name,description,confidence_score,owner,metadata
+dcfc99ed-c74d-49aa-bd0b-72f6f6f60000,1db9c650-acfb-4914-8bc5-1cf6f6f60000,Process,Transform_Product_Data,Transform product data for analytics,0.95,data-engineering,"{""tool"": ""Azure Data Factory""}"
+```
+
+#### **Lineage Commands**
+
+```bash
+# Validate CSV format before import (no API calls)
+pvw lineage validate lineage_data.csv
+
+# Import lineage relationships from CSV
+pvw lineage import lineage_data.csv
+
+# Generate sample CSV file with examples
+pvw lineage sample output.csv --num-samples 10 --template detailed
+
+# View available CSV templates
+pvw lineage templates
+```
+
+#### **Available Templates**
+
+- **`basic`** - Minimal columns (source, target, process name)
+- **`detailed`** - All columns including metadata and confidence scores
+- **`qualified_names`** - Use qualified names instead of GUIDs
+
+#### **Workflow Example**
+
+```bash
+# 1. Find entity GUIDs using search
+pvw search find-table --name "Product" --schema "dbo" --id-only
+
+# 2. Create CSV file with lineage relationships
+# (use the GUIDs from step 1)
+
+# 3. Validate CSV format
+pvw lineage validate my_lineage.csv
+# Output: SUCCESS: Lineage validation passed (5 rows, 8 columns)
+
+# 4. Import to Purview
+pvw lineage import my_lineage.csv
+# Output: SUCCESS: Lineage import completed successfully
+```
+
+#### **Advanced Features**
+
+- **GUID Validation**: Automatic validation of GUID format with helpful error messages
+- **Process Entity Creation**: Creates intermediate "Process" entities to link source→target relationships
+- **Metadata Support**: Add custom JSON metadata to each lineage relationship
+- **Dry-Run Validation**: Validate CSV format locally before making API calls
+
+**For detailed documentation, see:** [`doc/guides/lineage-csv-import.md`](doc/guides/lineage-csv-import.md)
+
+---
+
 ## Data Product Management (Legacy)
 
 PVW CLI also includes the original `data-product` command group for backward compatibility with traditional data product lifecycle management.
@@ -1032,15 +1143,18 @@ pvw data-product show-lineage --qualified-name="product.test.1"
 ## Core Features
 
 - **Unified Catalog (UC)**: Complete modern data governance (NEW)
+
   ```bash
   # Manage governance domains, terms, data products, OKRs, CDEs
   pvw uc domain list
   pvw uc term create --name "Customer" --domain-id "abc-123"
   pvw uc objective create --definition "Improve quality" --domain-id "abc-123"
   ```
+
 - **Discovery Query/Search**: Flexible, advanced search for all catalog assets
 - **Entity Management**: Bulk import/export, update, and validation
 - **Glossary Management**: Import/export terms, assign terms in bulk
+
   ```bash
   # List all terms in a glossary
   pvw glossary list-terms --glossary-guid "your-glossary-guid"
@@ -1048,7 +1162,20 @@ pvw data-product show-lineage --qualified-name="product.test.1"
   # Create and manage glossary terms
   pvw glossary create-term --payload-file term.json
   ```
-- **Lineage Operations**: Lineage discovery, CSV-based bulk lineage
+
+- **Lineage Operations**: Lineage discovery, CSV-based bulk lineage import/export
+
+  ```bash
+  # Import lineage relationships from CSV
+  pvw lineage import lineage_data.csv
+  
+  # Validate CSV format before import
+  pvw lineage validate lineage_data.csv
+  
+  # Generate sample CSV file
+  pvw lineage sample output.csv --num-samples 10
+  ```
+
 - **Monitoring & Analytics**: Real-time dashboards, metrics, and reporting
 - **Plugin System**: Extensible with custom plugins
 
@@ -1060,14 +1187,14 @@ PVW CLI provides comprehensive automation for all major Microsoft Purview APIs,
 
 ### Supported API Groups
 
-- **Unified Catalog**: Complete governance domains, glossary terms, data products, OKRs, CDEs management ✅
-  - **Health Monitoring**: Automated governance health checks and recommendations ✅ NEW
-  - **Workflows**: Approval workflows and business process automation ✅ NEW
-- **Data Map**: Full entity and lineage management ✅
-- **Discovery**: Advanced search, browse, and query capabilities ✅
-- **Collections**: Collection and account management ✅
-- **Management**: Administrative operations ✅
-- **Scan**: Data source scanning and configuration ✅
+- **Unified Catalog**: Complete governance domains, glossary terms, data products, OKRs, CDEs management [OK]
+  - **Health Monitoring**: Automated governance health checks and recommendations [OK] NEW
+  - **Workflows**: Approval workflows and business process automation [OK] NEW
+- **Data Map**: Full entity and lineage management [OK]
+- **Discovery**: Advanced search, browse, and query capabilities [OK]
+- **Collections**: Collection and account management [OK]
+- **Management**: Administrative operations [OK]
+- **Scan**: Data source scanning and configuration [OK]
 
 ### API Version Support
 
@@ -1079,6 +1206,7 @@ PVW CLI provides comprehensive automation for all major Microsoft Purview APIs,
 - Scan: **2018-12-01-preview**
 
 For the latest API documentation and updates, see:
+
 - [Microsoft Purview REST API reference](https://learn.microsoft.com/en-us/rest/api/purview/)
 - [Atlas 2.2 API documentation](https://learn.microsoft.com/en-us/purview/data-gov-api-atlas-2-2)
 - [Azure Updates](https://azure.microsoft.com/updates/) for new releases
@@ -1094,9 +1222,18 @@ PVW CLI includes comprehensive sample files and scripts for bulk operations:
 ### Bulk Import Samples
 
 - **CSV Samples:** `samples/csv/uc_terms_bulk_example.csv` (8 sample terms)
-- **JSON Samples:** 
+- **JSON Samples:**
   - `samples/json/term/uc_terms_bulk_example.json` (8 data management terms)
   - `samples/json/term/uc_terms_sample.json` (8 business terms)
+- **Lineage CSV Samples:** `samples/csv/lineage_example.csv` - Multiple lineage relationships with metadata
+
+### Lineage Documentation
+
+- **Comprehensive Guide:** `doc/guides/lineage-csv-import.md` - Complete lineage CSV import documentation
+  - CSV format specification with required/optional columns
+  - Command examples for validate, import, sample, templates
+  - Workflow recommendations and troubleshooting
+  - Advanced scenarios with metadata and multiple transformations
 
 ### Bulk Delete Scripts
 
@@ -1137,27 +1274,31 @@ PVW CLI includes comprehensive sample files and scripts for bulk operations:
 
 ## Recent Updates (October 2025)
 
-### ✅ Bulk Term Import/Export
+### Bulk Term Import/Export
+
 - Import multiple terms from CSV or JSON files
 - Dry-run mode for validation before import
 - Support for owners (Entra ID GUIDs), acronyms, resources
 - Progress tracking and detailed error reporting
 - 100% success rate in testing (8/8 terms)
 
-### ✅ PowerShell & Scripting Integration
+### PowerShell & Scripting Integration
+
 - New `--output` parameter with table/json/jsonc formats
 - Plain JSON works with PowerShell's `ConvertFrom-Json`
 - Compatible with jq, Python json module, and other tools
 - Migration from deprecated `--json` flag
 
-### ✅ Bulk Delete Scripts
+### Bulk Delete Scripts
+
 - PowerShell script with interactive confirmation ("DELETE" to confirm)
 - Python script with Rich progress bars
 - Beautiful UI with colored output
 - Success/failure tracking per term
 - Rate limiting (200ms delay)
 
-### ✅ Critical Fixes (v1.2.3)
+### Critical Fixes (v1.2.4)
+
 - **Search API Suggest/Autocomplete:** Fixed HTTP 400 errors by removing empty filter objects from payload
 - **Collection Display:** Enhanced collection name detection with proper fallback logic (isinstance checks)
 - **Owner ID Format:** Must use Entra ID Object IDs (GUIDs), not email addresses
@@ -1169,29 +1310,34 @@ PVW CLI includes comprehensive sample files and scripts for bulk operations:
 
 ## Key Features Summary
 
-### 🚀 **Unified Catalog (UC) - Complete Management**
+### **Unified Catalog (UC) - Complete Management**
+
 - Governance domains, glossary terms, data products
 - Objectives & Key Results (OKRs), Critical Data Elements (CDEs)
 - Health monitoring and workflow automation
 - Full CRUD operations with smart partial updates
 
-### 📦 **Bulk Operations**
+### **Bulk Operations**
+
 - CSV/JSON import with dry-run validation
 - PowerShell and Python bulk delete scripts
 - Progress tracking and error handling
 - Sample files and templates included
 
-### 📊 **Multiple Output Formats**
+### **Multiple Output Formats**
+
 - Table format for human viewing (default)
 - Plain JSON for PowerShell/bash scripting
 - Colored JSON for visual inspection
 
-### 🔧 **Automation & Integration**
+### **Automation & Integration**
+
 - Azure CLI, Service Principal, Managed Identity auth
 - Works in local development, CI/CD, and production
 - Compatible with PowerShell, bash, Python, jq
 
-### 📚 **Comprehensive Documentation**
+### **Comprehensive Documentation**
+
 - Complete API coverage documentation
 - Jupyter notebook examples
 - Troubleshooting guides
@@ -1214,9 +1360,10 @@ See [LICENSE](LICENSE) file for details.
 
 ---
 
-**PVW CLI v1.2.3 empowers data engineers, stewards, and architects to automate, scale, and enhance their Microsoft Purview experience with powerful command-line and programmatic capabilities.**
+**PVW CLI v1.2.4 empowers data engineers, stewards, and architects to automate, scale, and enhance their Microsoft Purview experience with powerful command-line and programmatic capabilities.**
+
+**Latest in v1.2.4:**
 
-**Latest in v1.2.3:**
 - Fixed Search API suggest/autocomplete (HTTP 400 errors resolved)
 - Enhanced collection display with robust fallback logic
 - Comprehensive search command validation

{pvw_cli-1.2.3.dist-info → pvw_cli-1.2.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-purviewcli/__init__.py,sha256=v5JNPN85G2EM5adxgzN03nNd_5Nv5Q_BM2foitqgsUw,413
+purviewcli/__init__.py,sha256=lSZ3EF_IssYkUVjlovhrmDVuTyx6CcOQDc2utNknygM,413
 purviewcli/__main__.py,sha256=n_PFo1PjW8L1OKCNLsW0vlVSo8tzac_saEYYLTu93iQ,372
 purviewcli/cli/__init__.py,sha256=UGMctZaXXsV2l2ycnmhTgyksH81_JBQjAPq3oRF2Dqk,56
 purviewcli/cli/account.py,sha256=Z_bwhKriMQpoBicOORM64wpQ1MJ94QG7jGKiaG-D_r8,7092
@@ -9,7 +9,7 @@ purviewcli/cli/entity.py,sha256=CMUnzYyRbHUQFGa_XLo2Yq189WcomZ16OyiSDzMvN4A,9484
 purviewcli/cli/glossary.py,sha256=6oTU7qPkUFkty4TPBPc8c1w2tbn1HicQ5qSxrP5vHFE,25696
 purviewcli/cli/health.py,sha256=_vuJgoLiihkKeU_L6bTzrCY2o9_gWqQS6gMXJ4EZyCA,10549
 purviewcli/cli/insight.py,sha256=dJYgTC9jQz62YnpDGUGj4ClXcdDsrGDr4sEvZbq90yE,3853
-purviewcli/cli/lineage.py,sha256=PWruMN_ttp-I-rv0adeaql5HXNFGiaVpr_pFKuj4ixU,21360
+purviewcli/cli/lineage.py,sha256=0im1sOlT0vtDkpdP68OLj_jggmzSDPeHsGMmlenawxk,21508
 purviewcli/cli/management.py,sha256=ArSN7ADWMKUJ-fVYjPiuab4g666GQUmxU2WZov3JxzI,7886
 purviewcli/cli/policystore.py,sha256=Xj3Yx6kNt9W8v577x2iacqSlPatR6AuFfMBpjtHTj1E,4439
 purviewcli/cli/relationship.py,sha256=Ky4klI-clKh6sRK7bsI7SwgtVrpo1ljegVyrbqjkeOY,2682
@@ -27,7 +27,7 @@ purviewcli/client/_entity.py,sha256=oGvnHpI8bFX7VOyH_aqgoGU37hnMqAjsXPEEBtk29vQ,
 purviewcli/client/_glossary.py,sha256=7kB3RXVOCCR1RGlaALmr_BwN6S76-xCoyVqD5ZMzt-k,20985
 purviewcli/client/_health.py,sha256=bKX2PChw2OB2kD_ZEfWlDxc093qQX3ai31YCQQ2VaKg,5921
 purviewcli/client/_insight.py,sha256=2KX6dVAkyFFMLuQ02Ko2J7WhARKlCLhSgtFkjFJxZ7c,16031
-purviewcli/client/_lineage.py,sha256=z-yckIduq4Ed9EXTWe-2hqBvl37t5yl87wzVPD_c3y0,14633
+purviewcli/client/_lineage.py,sha256=GsxeAnndtpxsV1X4mgY0461t27txHEaHOMdFEOS34L4,21864
 purviewcli/client/_management.py,sha256=2_ZXRSeEzGuHv1muUbn8mQb07enYYuHPI3NskIHIVbk,19549
 purviewcli/client/_policystore.py,sha256=wx9Yw6wcvj236ZmmitUKxW5u4YAtfJqAFNuxMpa7HIU,18078
 purviewcli/client/_relationship.py,sha256=KJZRltrzpTw7cfKjlZH2MuoTPS7eHxxp3cqU2etDSEA,9997
@@ -53,8 +53,8 @@ purviewcli/client/settings.py,sha256=nYdnYurTZsgv9vcgljnzVxLPtYVl9q6IplqOzi1aRvI
 purviewcli/client/sync_client.py,sha256=gwCqesJTNaXn1Q-j57O95R9mn3fIOhdP4sc8jBaBcYw,9493
 purviewcli/plugins/__init__.py,sha256=rpt3OhFt_wSE_o8Ga8AXvw1pqkdBxLmjrhYtE_-LuJo,29
 purviewcli/plugins/plugin_system.py,sha256=C-_dL4FUj90o1JS7Saxkpov6fz0GIF5PFhZTYwqBkWE,26774
-pvw_cli-1.2.3.dist-info/METADATA,sha256=rx7pJk-uMjIsZXSixs-R590RDEzxOYMeHmLYXVFUrtk,40276
-pvw_cli-1.2.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-pvw_cli-1.2.3.dist-info/entry_points.txt,sha256=VI6AAbc6sWahOCX7sn_lhJIr9OiJM0pHF7rmw1YVGlE,82
-pvw_cli-1.2.3.dist-info/top_level.txt,sha256=LrADzPoKwF1xY0pGKpWauyOVruHCIWKCkT7cwIl6IuI,11
-pvw_cli-1.2.3.dist-info/RECORD,,
+pvw_cli-1.2.4.dist-info/METADATA,sha256=hi7EZ8xiZ8tbkVj85fFnvqCM8qF-7O6BR8iQiAdYa0w,43762
+pvw_cli-1.2.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pvw_cli-1.2.4.dist-info/entry_points.txt,sha256=VI6AAbc6sWahOCX7sn_lhJIr9OiJM0pHF7rmw1YVGlE,82
+pvw_cli-1.2.4.dist-info/top_level.txt,sha256=LrADzPoKwF1xY0pGKpWauyOVruHCIWKCkT7cwIl6IuI,11
+pvw_cli-1.2.4.dist-info/RECORD,,