nuvu-scan 1.3.8__py3-none-any.whl → 2.0.0__py3-none-any.whl

nuvu_scan/core/providers/gcp/gcp_scanner.py

@@ -50,11 +50,11 @@ class GCPScanner(CloudProviderScan):
         try:
             creds, _ = default()
             return creds
-        except DefaultCredentialsError:
+        except DefaultCredentialsError as e:
             raise ValueError(
                 "GCP credentials not found. Provide service_account_key_file, "
                 "service_account_key_json, or set GOOGLE_APPLICATION_CREDENTIALS"
-            )
+            ) from e
 
     def _get_project_id(self) -> str:
         """Get GCP project ID from credentials or config."""
@@ -72,17 +72,49 @@ class GCPScanner(CloudProviderScan):
 
         raise ValueError("GCP project_id is required. Set it in credentials or use --gcp-project")
 
+    # Map of collector names to their classes for filtering
+    COLLECTOR_MAP = {
+        "gcs": GCSCollector,
+        "bigquery": BigQueryCollector,
+        "dataproc": DataprocCollector,
+        "pubsub": PubSubCollector,
+        "iam": IAMCollector,
+        "gemini": GeminiCollector,
+    }
+
+    @classmethod
+    def get_available_collectors(cls) -> list[str]:
+        """Return list of available collector names."""
+        return list(cls.COLLECTOR_MAP.keys())
+
     def _initialize_collectors(self) -> list:
-        """Initialize all GCP service collectors."""
+        """Initialize GCP service collectors based on config."""
         collectors = []
 
-        # Initialize collectors for each service
-        collectors.append(GCSCollector(self.credentials, self.project_id))
-        collectors.append(BigQueryCollector(self.credentials, self.project_id))
-        collectors.append(DataprocCollector(self.credentials, self.project_id))
-        collectors.append(PubSubCollector(self.credentials, self.project_id))
-        collectors.append(IAMCollector(self.credentials, self.project_id))
-        collectors.append(GeminiCollector(self.credentials, self.project_id))
+        # Get requested collectors from config
+        requested = self.config.collectors if self.config.collectors else []
+
+        # Normalize to lowercase
+        requested_lower = [c.lower() for c in requested]
+
+        # If no specific collectors requested, use all
+        if not requested_lower:
+            for collector_cls in self.COLLECTOR_MAP.values():
+                collectors.append(collector_cls(self.credentials, self.project_id))
+        else:
+            # Filter to only requested collectors
+            for name, collector_cls in self.COLLECTOR_MAP.items():
+                if name in requested_lower:
+                    collectors.append(collector_cls(self.credentials, self.project_id))
+
+            # Warn about unknown collectors
+            known = set(self.COLLECTOR_MAP.keys())
+            unknown = set(requested_lower) - known
+            if unknown:
+                import sys
+
+                print(f"Warning: Unknown collectors ignored: {', '.join(unknown)}", file=sys.stderr)
+                print(f"Available collectors: {', '.join(sorted(known))}", file=sys.stderr)
 
         return collectors
 

{nuvu_scan-1.3.8.dist-info → nuvu_scan-2.0.0.dist-info}/METADATA

@@ -1,44 +1,53 @@
 Metadata-Version: 2.4
 Name: nuvu-scan
-Version: 1.3.8
-Summary: Multi-Cloud Data Asset Control - CLI tool for discovering and analyzing cloud data infrastructure
+Version: 2.0.0
+Summary: Multi-Cloud Data Asset Control - Discover, govern, and optimize your cloud data assets across AWS and GCP
 Project-URL: Homepage, https://nuvu.dev
 Project-URL: Documentation, https://github.com/nuvudev/nuvu-scan#readme
 Project-URL: Repository, https://github.com/nuvudev/nuvu-scan
 Project-URL: Issues, https://github.com/nuvudev/nuvu-scan/issues
+Project-URL: Changelog, https://github.com/nuvudev/nuvu-scan/blob/main/CHANGELOG.md
 Author-email: Nuvu <info@nuvu.dev>
 License: Apache-2.0
-Keywords: aws,cloud,data,governance,infrastructure,scanning
-Classifier: Development Status :: 3 - Alpha
+Keywords: aws,bigquery,cloud,cost-optimization,data,data-catalog,gcp,glue,governance,infrastructure,redshift,s3,scanning
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: System Administrators
 Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Database :: Database Engines/Servers
 Classifier: Topic :: System :: Systems Administration
 Requires-Python: >=3.10
 Requires-Dist: boto3>=1.28.0
+Requires-Dist: botocore>=1.31.0
 Requires-Dist: click>=8.0.0
 Requires-Dist: google-api-python-client>=2.100.0
 Requires-Dist: google-auth>=2.23.0
 Requires-Dist: google-cloud-bigquery>=3.11.0
 Requires-Dist: google-cloud-billing>=1.11.0
 Requires-Dist: google-cloud-dataproc>=5.4.0
+Requires-Dist: google-cloud-monitoring>=2.16.0
 Requires-Dist: google-cloud-pubsub>=2.18.0
 Requires-Dist: google-cloud-storage>=2.10.0
 Provides-Extra: dev
-Requires-Dist: black>=23.0.0; extra == 'dev'
+Requires-Dist: bandit>=1.7.0; extra == 'dev'
+Requires-Dist: boto3-stubs[essential]>=1.28.0; extra == 'dev'
 Requires-Dist: mypy>=1.0.0; extra == 'dev'
+Requires-Dist: pre-commit>=3.5.0; extra == 'dev'
 Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
 Requires-Dist: pytest>=7.0.0; extra == 'dev'
-Requires-Dist: ruff>=0.1.0; extra == 'dev'
+Requires-Dist: ruff>=0.8.0; extra == 'dev'
 Description-Content-Type: text/markdown
 
 # Nuvu Scan
 
-**Take Control of Your Cloud Data Estate**  
+**Take Control of Your Cloud Data Estate**
 Discover, govern, and optimize your cloud data assets across **AWS and GCP** — reduce wasted spend, enforce compliance, and gain full visibility into unused, idle, or risky resources.
 
 ---
@@ -71,7 +80,7 @@ pip install nuvu-scan
 
 ### Optional: Push results to Nuvu Cloud
 
-Nuvu Scan is fully open-source and runs standalone — no account required.  
+Nuvu Scan is fully open-source and runs standalone — no account required.
 If you want dashboards, team workflows, and long‑term history, you can optionally push results to Nuvu Cloud.
 
 ```bash
@@ -186,6 +195,41 @@ nuvu scan --provider gcp --gcp-credentials /path/to/service-account-key.json --g
 nuvu scan --provider gcp --gcp-project your-project-id --output-format json --output-file gcp-report.json
 ```
 
+### Selective Scanning (Collectors)
+
+Run focused scans on specific services instead of a full scan:
+
+```bash
+# List available collectors for a provider
+nuvu scan --provider aws --list-collectors
+# Output: athena, glue, iam, mwaa, redshift, s3
+
+nuvu scan --provider gcp --list-collectors
+# Output: bigquery, dataproc, gcs, gemini, iam, pubsub
+
+# Scan only Redshift
+nuvu scan --provider aws -c redshift --region us-west-2
+
+# Scan multiple specific collectors
+nuvu scan --provider aws -c redshift -c glue --region us-west-2
+
+# Scan only S3 buckets
+nuvu scan --provider aws -c s3 --output-format html
+
+# Full scan (default - all collectors)
+nuvu scan --provider aws  # Runs all collectors
+
+# GCP: Scan only BigQuery
+nuvu scan --provider gcp -c bigquery --gcp-project your-project
+```
+
+**Benefits of selective scanning:**
+- **Faster scans** - Focus on services you care about
+- **Reduced API calls** - Only query the services you need
+- **Targeted reports** - Generate reports for specific areas
+
+---
+
 ## Features
 
 - **Asset Discovery**: Automatically discovers cloud data assets:
@@ -225,7 +269,7 @@ Nuvu requires read-only access to your AWS account. The tool uses the following
    ```bash
    # Option 1: Create IAM user
    aws iam create-user --user-name nuvu-scan-readonly
-   
+
    # Option 2: Create IAM role (for EC2/ECS/Lambda)
    aws iam create-role --role-name nuvu-scan-readonly --assume-role-policy-document file://trust-policy.json
    ```
@@ -234,7 +278,7 @@ Nuvu requires read-only access to your AWS account. The tool uses the following
    ```bash
    # For IAM user
    aws iam put-user-policy --user-name nuvu-scan-readonly --policy-name NuvuScanReadOnly --policy-document file://aws-iam-policy.json
-   
+
    # For IAM role
    aws iam put-role-policy --role-name nuvu-scan-readonly --policy-name NuvuScanReadOnly --policy-document file://aws-iam-policy.json
    ```
@@ -254,7 +298,7 @@ Nuvu requires read-only access to your AWS account. The tool uses the following
    ```
 
    **Method 2: Temporary Credentials (Access Key + Secret Key + Session Token)**
-   
+
    If you're using AWS SSO, assumed roles, or other temporary credentials:
    ```bash
    export AWS_ACCESS_KEY_ID=your-access-key-id
@@ -264,7 +308,7 @@ Nuvu requires read-only access to your AWS account. The tool uses the following
    ```
 
    **Method 3: IAM Role Assumption**
-   
+
    To assume a role (useful for cross-account access or when using a role with more permissions):
    ```bash
    # With explicit credentials
@@ -272,11 +316,11 @@ Nuvu requires read-only access to your AWS account. The tool uses the following
      --access-key-id your-access-key-id \
      --secret-access-key your-secret-access-key \
      --role-arn arn:aws:iam::123456789012:role/MyRole
-   
+
    # From default credentials (e.g., EC2 instance role)
    nuvu scan --provider aws \
      --role-arn arn:aws:iam::123456789012:role/MyRole
-   
+
    # With external ID (if required by the role)
    nuvu scan --provider aws \
      --role-arn arn:aws:iam::123456789012:role/MyRole \

{nuvu_scan-1.3.8.dist-info → nuvu_scan-2.0.0.dist-info}/RECORD

@@ -1,29 +1,29 @@
-nuvu_scan/__init__.py,sha256=Z2ZCYc6IkTIx2-EJulsiSJIjX_PMm_k0H2OI-N9L2x0,68
+nuvu_scan/__init__.py,sha256=tsQim3nEvAmZ_2-lY6FPQSC5a4bAcUwltNYAn6bpaY0,68
 nuvu_scan/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nuvu_scan/cli/main.py,sha256=NPeHSkcyQv5j-mX_mlSKKmyAalPQ5hv2j-4Y5Lx_gdc,342
+nuvu_scan/cli/main.py,sha256=CI8ahTFALjd-HcGPAphXX8ZgJUtz7hG9l45MELOMwn0,396
 nuvu_scan/cli/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nuvu_scan/cli/commands/scan.py,sha256=Og6ZRKXEcgluuzi3sSHnv8kxzjGCly3yNreRLEn82BM,10582
+nuvu_scan/cli/commands/scan.py,sha256=1FTILZXhQ2apz0HuMw9MyT0gZS75EsS0fXJBxyKePws,11622
 nuvu_scan/cli/formatters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nuvu_scan/cli/formatters/csv.py,sha256=xGC8Kl1SKOcflLsZqBNJEucZUxgacSmlU8vogWQpskg,1719
-nuvu_scan/cli/formatters/html.py,sha256=GqbdNjZ9yRUkZYibsniETIqOJVaahQNZDZhH_K4e19M,6454
+nuvu_scan/cli/formatters/html.py,sha256=1uhZL6utjnv5-iyLPo_4QqQFUi0fvhbrb4DHZbnl1nc,17894
 nuvu_scan/cli/formatters/json.py,sha256=T2DoEOcQrqLRyEF8VnPPari-nD83U0kNwQwBBxySlFo,1668
 nuvu_scan/core/__init__.py,sha256=G6Iqb0-Td7mEi1PteLoImeqAnzbPzBTv-q1qJ1q4j1A,217
-nuvu_scan/core/base.py,sha256=2zPTmM_ChY5RKyTe_mDvTyhKDgU16e6gnArBmxWXfqA,6490
+nuvu_scan/core/base.py,sha256=4xEv-qujS-6TnDGv3Vqgw9omnzdVPnMaGY5r1g_oN2A,6811
 nuvu_scan/core/analyzers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nuvu_scan/core/models/__init__.py,sha256=osGjl3G0LOYqaJoG_60_i9ZhAeGJ_0stZuMoxRO77aw,188
 nuvu_scan/core/providers/__init__.py,sha256=aipXSMSaFB7TbLdjma4naxzChDOHFCo_VZbG-lbrpKs,105
 nuvu_scan/core/providers/aws/__init__.py,sha256=R5ZPCc-qybHZh4v5w_D0tZc8cYJNuhlfCPnLg3Zr28A,98
-nuvu_scan/core/providers/aws/aws_scanner.py,sha256=LaexEl8hUDYKrVRuGY31E4cjL-GJlzXOL7fs9qFHSxI,14568
+nuvu_scan/core/providers/aws/aws_scanner.py,sha256=gBqzuKWVh6ZZ8uK5A7pt5QEiO1hPgqukrUoOicFv_i0,15296
 nuvu_scan/core/providers/aws/collectors/__init__.py,sha256=uFPTKjtMFHCQwsZy9WmMSvKZpfuXU8SxCfQRhi6yUt0,373
-nuvu_scan/core/providers/aws/collectors/athena.py,sha256=zvDA46AklvnLx8QZyql7OpZun3GkkiGerJBtI-05ztE,5644
+nuvu_scan/core/providers/aws/collectors/athena.py,sha256=sHuFmZMZ1TM91DxmxrcCSZ6OiN9l7udlMQPnCg7nI70,5737
 nuvu_scan/core/providers/aws/collectors/cost_explorer.py,sha256=qas79Cm_rCyYDzeL4F0cER90Ohyg9rN33fBHh4VA9og,6730
-nuvu_scan/core/providers/aws/collectors/glue.py,sha256=hq3sfcjecg7xqyrCQFl08bv9mPuORbJBNUfOU7F7moI,6488
-nuvu_scan/core/providers/aws/collectors/iam.py,sha256=Ahw6OyJWOtCeVcLnlboTX43PYZZXDjxWaWWeoLs0ia4,10457
+nuvu_scan/core/providers/aws/collectors/glue.py,sha256=_FsdpQrBN3gpkrteRL1Usslq-zUmDWJdzYQp7eBSyZ4,25137
+nuvu_scan/core/providers/aws/collectors/iam.py,sha256=E3mifkmcDWym07OeUGX8s-UaWwa49W-pOMr5XvxdZmA,10771
 nuvu_scan/core/providers/aws/collectors/mwaa.py,sha256=WSXB2kPIxpy82-6JX6Jkqkzjgh9rPZZuMf4AetfnTKs,12397
-nuvu_scan/core/providers/aws/collectors/redshift.py,sha256=9OrKC13_e9G6agwpg-omvEV7TCHVhSm5zrBf0VkbHvs,9035
+nuvu_scan/core/providers/aws/collectors/redshift.py,sha256=b9dYIZ389xOtzmT-ml1-A_nkhCeHrJmjX0cmTLDLhYI,41612
 nuvu_scan/core/providers/aws/collectors/s3.py,sha256=Ma8LMgEpUucN64uohQ2zlGIkUbxmRNkUbeSfZpPe3Pw,13093
 nuvu_scan/core/providers/gcp/__init__.py,sha256=NZ8bStAq0Qt4IRcxaCBAkbJVUPQLQHRRTl0fUxVuTxg,98
-nuvu_scan/core/providers/gcp/gcp_scanner.py,sha256=3C0puhnuTvoBBnVBrDN9rSNWuZF7rQ4XcxsQUJYLNeY,6184
+nuvu_scan/core/providers/gcp/gcp_scanner.py,sha256=Vt2kRCMyLRTJsQjIyGHnNnJEGlgAh6bEpctR0L-_y5A,7264
 nuvu_scan/core/providers/gcp/collectors/__init__.py,sha256=HbtMXas5Vh6kYz6RS1d_q7WQgIvZ_N5-fIR-UKHSi9M,394
 nuvu_scan/core/providers/gcp/collectors/bigquery.py,sha256=K1uNN-I_PvR-jdyonY8hZT9LWyEftMKMxksizmkFfd8,14849
 nuvu_scan/core/providers/gcp/collectors/billing.py,sha256=pA2vbHdzQSQR4_yR6wPF8gWN1CoPjRCQ5LVQG8BKoYs,4735
@@ -32,7 +32,7 @@ nuvu_scan/core/providers/gcp/collectors/gcs.py,sha256=qf-QMW56dR8C0Qg5snF1w7JNDV
 nuvu_scan/core/providers/gcp/collectors/gemini.py,sha256=NsYTELcvdSGwSOFEmE3Zmp1bzto99iUCCr0yY4j54zg,17968
 nuvu_scan/core/providers/gcp/collectors/iam.py,sha256=lusayhIwPLjzzpBEE7UD61-oVmceR1cYHstHWZq4VPA,8332
 nuvu_scan/core/providers/gcp/collectors/pubsub.py,sha256=OMBSeWi2Hjp1jgpEQ-a8ecLxV1MRtVVgy0QlVlWnS2k,4953
-nuvu_scan-1.3.8.dist-info/METADATA,sha256=rGAek06u3uBqManQjCw0unmPuKrikK2MQLERRjjU0Hk,20014
-nuvu_scan-1.3.8.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-nuvu_scan-1.3.8.dist-info/entry_points.txt,sha256=69_WPJ2x1x4sS4TgVlEMZPIjGJYmQh8DBQerMEHIJQI,48
-nuvu_scan-1.3.8.dist-info/RECORD,,
+nuvu_scan-2.0.0.dist-info/METADATA,sha256=FO_K95EjcPKGYOnJ-canTLMoIDejXhQSRneRaEiC4bw,21526
+nuvu_scan-2.0.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+nuvu_scan-2.0.0.dist-info/entry_points.txt,sha256=dge4RP32Lsft0GA_oBPCwFAKZ_GgzD3eq-vD4LY-jPE,83
+nuvu_scan-2.0.0.dist-info/RECORD,,

{nuvu_scan-1.3.8.dist-info → nuvu_scan-2.0.0.dist-info}/entry_points.txt

@@ -1,2 +1,3 @@
 [console_scripts]
 nuvu = nuvu_scan.cli.main:cli
+nuvu-scan = nuvu_scan.cli.main:cli