Add initial support for the npm-health ScanGrimoireLab pipeline

Signed-off-by: ziad hany <ziadhany2016@gmail.com>

Author: ziadhany

pyproject.toml

@@ -171,6 +171,7 @@ resolve_dependencies = "scanpipe.pipelines.resolve_dependencies:ResolveDependenc
 scan_codebase = "scanpipe.pipelines.scan_codebase:ScanCodebase"
 scan_for_virus = "scanpipe.pipelines.scan_for_virus:ScanForVirus"
 scan_single_package = "scanpipe.pipelines.scan_single_package:ScanSinglePackage"
+scan_repo_grimoirelab = "scanpipe.pipelines.scan_repo_grimoirelab:ScanGrimoirelab"
 
 [tool.setuptools.packages.find]
 where = ["."]

scanpipe/pipelines/metrics_model.py

@@ -0,0 +1,75 @@
+#
+# Copyright (C) AboutCode
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+#
+
+import math
+
+# These coefficients were calculated with the notebooks and data available
+# at https://github.com/aboutcode-org/healthycode/blob/main/model/npm/README.md
+
+
+class npmModel:
+    # We have dropped the low-impact metrics, those with a coefficient close to 0
+    COEFFICIENTS = {
+        "elephant_factor": -1.635941,
+        "coefficient_of_variation": -1.404157,
+        "total_contributors": -0.991894,
+        "days_since_last_commit": 0.865738,
+        "contributor_growth_rate": 0.435875,
+        "commits_over_periods_rate": -0.410393,
+        "total_commits": -0.330035,
+        "message_size_mean": -0.320026,
+        "found_file_license": 0.266483,
+    }
+
+    # Model Intercept
+    Z = -0.549873845969752
+
+    def __init__(self):
+        self.coefficients = self.COEFFICIENTS.copy()
+        self.z = self.Z
+
+    def calculate_score(self, metrics: dict[str, float]) -> float:
+        """
+        Calculates the probability of a repository being 'Unhealthy' based on
+        the pruned logistic regression model metrics.
+
+        Parameters
+        ----------
+        metrics (dict): Dictionary containing the project feature names and values.
+
+        Returns
+        -------
+        float: Probability score between 0.0 (Healthy) and 1.0 (Unhealthy).
+
+        """
+        z = self.z
+
+        # Calculate the linear combination (log-odds)
+        for metric, coef in self.coefficients.items():
+            # FIXME. We set by default 0 if a metric is missing. Is this safe?
+            value = metrics.get(metric, 0.0)
+            z += coef * value
+
+        # Apply the Sigmoid function to get the final probability
+        try:
+            probability = 1 / (1 + math.exp(-z))
+        except OverflowError:
+            # Safeguard against extreme values of z
+            # FIXME Is this correct?
+            probability = 0.0 if z < 0 else 1.0
+
+        return probability

scanpipe/pipelines/scan_repo_grimoirelab.py

@@ -0,0 +1,166 @@
+# SPDX-License-Identifier: Apache-2.0
+#
+# http://nexb.com and https://github.com/aboutcode-org/scancode.io
+# The ScanCode.io software is licensed under the Apache License version 2.0.
+# Data generated with ScanCode.io is provided as-is without warranties.
+# ScanCode is a trademark of nexB Inc.
+#
+# You may not use this software except in compliance with the License.
+# You may obtain a copy of the License at: http://apache.org/licenses/LICENSE-2.0
+# Unless required by applicable law or agreed to in writing, software distributed
+# under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+# CONDITIONS OF ANY KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations under the License.
+#
+# Data Generated with ScanCode.io is provided on an "AS IS" BASIS, WITHOUT WARRANTIES
+# OR CONDITIONS OF ANY KIND, either express or implied. No content created from
+# ScanCode.io should be considered or used as legal advice. Consult an Attorney
+# for any legal advice.
+#
+# ScanCode.io is a free software code scanning tool from nexB Inc. and others.
+# Visit https://github.com/aboutcode-org/scancode.io for support and download.
+
+import json
+import subprocess
+
+from scanpipe.pipelines import Pipeline
+from scanpipe.pipelines.metrics_model import npmModel
+
+
+class ScanGrimoirelab(Pipeline):
+    results_url = "/project/{slug}/resources/?extra_data=grimoire_data"
+
+    @classmethod
+    def steps(cls):
+        return (
+            cls.collect_grimoire_metric,
+            cls.compute_and_store_metric_score,
+        )
+
+    def collect_grimoire_metric(self):
+        metrics_output_path = self.project.get_output_file_path("metrics", "json")
+        grimoire_config_path = self.project.get_output_file_path(
+            "grimoire_config", "json"
+        )
+        repo_url = "https://github.com/aboutcode-org/fetchcode.git"
+
+        grimoirelab_config = {
+            "spdxVersion": "SPDX-2.3",
+            "dataLicense": "CC0-1.0",
+            "SPDXID": "SPDXRef-DOCUMENT",
+            "name": "GrimoireLab Analysis",
+            "documentNamespace": "http://spdx.org/spdxdocs/grimoirelab-metrics",
+            "creationInfo": {
+                "creators": ["Tool: manual-conversion"],
+                "created": "2026-07-31T21:41:21Z",
+            },
+            "packages": [
+                {
+                    "name": "grimoirelab",
+                    "SPDXID": "SPDXRef-Package-grimoirelab",
+                    "downloadLocation": repo_url,
+                }
+            ],
+        }
+
+        with open(grimoire_config_path, "w") as f:
+            json.dump(grimoirelab_config, f, indent=2)
+
+        GRIMOIRELAB_METRICS_EXECUTABLE = (
+            "/home/ziad-hany/PycharmProjects/healthycode/venv/bin/grimoirelab-metrics"
+        )
+
+        GRIMOIRELAB_URL = "http://localhost:8000"
+        GRIMOIRELAB_USERNAME = "admin"
+        GRIMOIRELAB_PASSWORD = "admin"
+
+        OPENSEARCH_URL = "https://localhost:9200"
+        OPENSEARCH_INDEX = "events"
+        OPENSEARCH_USERNAME = "admin"
+        OPENSEARCH_PASSWORD = "GrimoireLab.1"
+
+        FROM_DATE = "2023-01-01"
+        TO_DATE = "2026-06-19"
+
+        REPOSITORY_TIMEOUT = "3600"
+
+        CODE_FILE_PATTERN = r"\.py$|\.js$"
+        BINARY_FILE_PATTERN = r"\.exe$|\.tar$"
+
+        PONY_THRESHOLD = "0.5"
+        ELEPHANT_THRESHOLD = "0.5"
+        DEVELOPER_CATEGORIES_THRESHOLDS = ["0.8", "0.95"]
+
+        cmd = [
+            GRIMOIRELAB_METRICS_EXECUTABLE,
+            str(grimoire_config_path),
+            "--grimoirelab-url",
+            GRIMOIRELAB_URL,
+            "--grimoirelab-user",
+            GRIMOIRELAB_USERNAME,
+            "--grimoirelab-password",
+            GRIMOIRELAB_PASSWORD,
+            "--opensearch-url",
+            OPENSEARCH_URL,
+            "--opensearch-index",
+            OPENSEARCH_INDEX,
+            "--opensearch-user",
+            OPENSEARCH_USERNAME,
+            "--opensearch-password",
+            OPENSEARCH_PASSWORD,
+            "--from-date",
+            FROM_DATE,
+            "--to-date",
+            TO_DATE,
+            "--repository-timeout",
+            REPOSITORY_TIMEOUT,
+            "--code-file-pattern",
+            CODE_FILE_PATTERN,
+            "--binary-file-pattern",
+            BINARY_FILE_PATTERN,
+            "--pony-threshold",
+            PONY_THRESHOLD,
+            "--elephant-threshold",
+            ELEPHANT_THRESHOLD,
+            "--dev-categories-thresholds",
+            *DEVELOPER_CATEGORIES_THRESHOLDS,
+            "--output",
+            str(metrics_output_path),
+        ]
+
+        try:
+            subprocess.run(
+                cmd,
+                capture_output=True,
+                text=True,
+                check=True,
+            )
+            self.log(f"Metrics successfully saved to {metrics_output_path}")
+            with open(metrics_output_path) as f:
+                self.metrics = json.load(f)
+
+        except subprocess.CalledProcessError as e:
+            self.log(f"failed with exit code {e.returncode}")
+        except FileNotFoundError:
+            self.log(
+                "Error: 'grimoirelab-metrics' command not found. Is it installed and on your PATH?"
+            )
+            raise
+
+    def compute_and_store_metric_score(self):
+        model = npmModel()
+        probability = model.calculate_score(self.metrics)
+        status = "Healthy" if probability >= 0.5 else "Unhealthy"
+
+        self.log(f"Repository Health: {status}, Probability: {probability:.2%}")
+        score_data = {
+            "status": status,
+            "probability": probability,
+            "metrics": self.metrics,
+        }
+
+        score_output_path = self.project.get_output_file_path("results", "json")
+        with open(score_output_path, "w") as f:
+            json.dump(score_data, f, indent=2)
+
+        return score_data

scanpipe/tests/pipes/test_scan_repo_grimoirelab.py

@@ -0,0 +1,9 @@
+from django.test import TestCase
+
+
+class ScanGrimoirelabTest(TestCase):
+    def test_collect_grimoire_metric(self):
+        raise NotImplementedError
+
+    def test_compute_and_store_metric_score(self):
+        raise NotImplementedError