Added NSFW Content Detection

.github/workflows/toxicity-check.yml

@@ -0,0 +1,55 @@
+name: Check for Toxic Content
+#hi
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+
+jobs:
+  moderate-content:
+    runs-on: ubuntu-latest  
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3  
+
+      - name: Set up Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.x"  
+
+      - name: Cache Hugging Face models
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/huggingface  
+          key: huggingface-toxicity-model
+
+      - name: Install dependencies
+        run: pip install transformers torch beautifulsoup4 python-magic
+
+      - name: Get changed files
+        id: changed-files
+        uses: tj-actions/changed-files@v35  
+        with:
+          files: "**/*"
+
+      - name: Run toxicity check
+        run: |
+          for file in ${{ steps.changed-files.outputs.all_modified_files }}; do
+            python scripts/check_toxicity.py "$file"
+          done
+
+      - name: Auto-approve PR if no offensive content is found
+        if: success()
+        uses: hmarr/auto-approve-action@v3
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Comment on PR if offensive content is detected
+        if: failure()
+        run: echo "🚨 Offensive content detected. Please review your PR." | tee comment.txt
+
+      - name: Post comment on PR
+        if: failure()
+        uses: thollander/actions-comment-pull-request@v2
+        with:
+          message: file://comment.txt

contributors/harlanenciso112.html

@@ -0,0 +1,43 @@
+<article>
+  <h3>Harlanenciso112</h3>
+  <p>I'm Software Developer with experience languages with Python and Java.</p>
+  <h4>Programming languages I use</h4>
+  <section class="container">
+    <div class="badge" style="background-color: #3874a4; color: white">
+      Python
+    </div>
+    <div class="badge" style="background-color: #f7991e; color: black;">
+      Java
+    </div>
+  </section>
+
+  <h4>Tools I use</h4>
+  <section class="container">
+    <img
+      class="icon"   
+      src="https://cdn.jsdelivr.net/gh/devicons/devicon@latest/icons/python/python-original-wordmark.svg"
+    />
+    <img
+      class="icon"
+
+      src="https://cdn.jsdelivr.net/gh/devicons/devicon@latest/icons/java/java-original-wordmark.svg"
+    />
+  </section>
+</article>
+<style>
+  body {
+    font-family: sans-serif;
+  }
+  .container {
+    display: flex;
+    flex-wrap: wrap;
+    gap: 1rem;
+  }
+  .badge {
+    padding: 0.5rem;
+    border-radius: 0.25rem;
+  }
+  .icon {
+    width: 2rem;
+  }
+</style>

scripts/check_toxicity.py

@@ -0,0 +1,80 @@
+import sys
+import os
+import magic
+from bs4 import BeautifulSoup
+from transformers import pipeline
+
+# Load the toxicity detection model
+classifier = pipeline("text-classification", model="unitary/toxic-bert")
+
+# List of offensive words (modify as needed)
+OFFENSIVE_WORDS = ["fuck", "shit", "bitch"]  
+
+def is_text_file(file_path):
+    """Check if the file is a text-based file (not binary)"""
+    mime = magic.Magic(mime=True)
+    file_type = mime.from_file(file_path)
+    return file_type.startswith("text")
+
+def check_text(text):
+    """Analyze text using the toxicity classifier"""
+    result = classifier(text[:512])  # Limit to 512 tokens (model constraint)
+    label = result[0]["label"]
+    score = result[0]["score"]
+
+    return label == "toxic" and score > 0.7  # If toxic, return True
+
+def check_file_content(file_path):
+    """Read file and analyze its content for toxicity"""
+    if not is_text_file(file_path):
+        print(f"⚠️ Skipping binary file: {file_path}")
+        return False
+
+    with open(file_path, "r", encoding="utf-8", errors="ignore") as file:
+        content = file.read()
+
+        # If it's an HTML file, extract text
+        if file_path.endswith(".html"):
+            soup = BeautifulSoup(content, "html.parser")
+            content = soup.get_text()
+
+        return check_text(content)
+
+def check_filename(file_name):
+    """Check if the filename contains offensive words"""
+    lower_name = file_name.lower()
+    for word in OFFENSIVE_WORDS:
+        if word in lower_name:
+            print(f"❌ Offensive word detected in filename: {file_name}")
+            return True
+    return False
+
+def main():
+    """Check all modified files in the PR"""
+    offensive_found = False
+
+    # Get list of modified files from Git
+    modified_files = os.popen("git diff --name-only HEAD^ HEAD").read().split()
+
+    for file in modified_files:
+        if not os.path.exists(file):
+            continue  # Skip deleted files
+
+        # Check filename for offensive words
+        if check_filename(file):
+            offensive_found = True
+
+        # Check file content for toxicity
+        if check_file_content(file):
+            print(f"❌ Offensive content detected in {file}")
+            offensive_found = True
+
+    # Block the PR if any offensive content was found
+    if offensive_found:
+        sys.exit(1)
+    else:
+        print("✅ No offensive content found.")
+        sys.exit(0)
+
+if __name__ == "__main__":
+    main()

scripts/contributors.js

@@ -1,4 +1,5 @@
 const contributorFiles = [
+  "harlanenciso112.html",
   "roshanjossey.html",
-  "gokultp.html",
+  "gokultp.html"
 ];