Create app.py

app.py

@@ -0,0 +1,163 @@
+import streamlit as st
+from transformers import pipeline
+import pdfplumber
+import docx
+from PIL import Image
+import pytesseract
+from textblob import TextBlob
+import re
+import fitz  # ✅ PyMuPDF instead of pdf2image
+import os
+
+# ------------------------
+# Hugging Face Model
+# ------------------------
+classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+
+# ------------------------
+# Extraction Functions
+# ------------------------
+def extract_text_from_pdf(file_path):
+    text = ""
+    with pdfplumber.open(file_path) as pdf:
+        for page in pdf.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text + "\n"
+
+    # OCR fallback if no text extracted
+    if not text.strip():
+        ocr_text = ""
+        doc = fitz.open(file_path)
+        for page_num in range(len(doc)):
+            page = doc[page_num]
+            pix = page.get_pixmap()
+            img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+            ocr_text += pytesseract.image_to_string(img) + "\n"
+        text = ocr_text
+    return text.strip()
+
+def extract_text_from_docx(file_path):
+    doc = docx.Document(file_path)
+    return "\n".join([p.text for p in doc.paragraphs]).strip()
+
+def extract_text_from_image(file_path):
+    return pytesseract.image_to_string(Image.open(file_path)).strip()
+
+def check_grammar(text):
+    blob = TextBlob(text)
+    corrected_text = str(blob.correct())
+    return corrected_text != text
+
+def extract_dates(text):
+    date_patterns = [
+        r'\b\d{1,2}[/-]\d{1,2}[/-]\d{2,4}\b',
+        r'\b\d{1,2}\.\d{1,2}\.\d{2,4}\b',
+        r'\b\d{1,2}(?:st|nd|rd|th)?\s+\w+\s*,?\s*\d{2,4}\b',
+        r'\b\w+\s+\d{1,2},\s*\d{4}\b',
+    ]
+    dates_found = []
+    for pattern in date_patterns:
+        matches = re.findall(pattern, text, flags=re.IGNORECASE)
+        dates_found.extend(matches)
+    return list(set(dates_found))
+
+def classify_dates(text, dates):
+    issue_keywords = ["issued on", "dated", "notified on", "circular no"]
+    event_keywords = ["holiday", "observed on", "exam on", "will be held on", "effective from"]
+
+    issue_dates = []
+    event_dates = []
+
+    for d in dates:
+        idx = text.lower().find(d.lower())
+        if idx != -1:
+            context = text[max(0, idx-60): idx+60].lower()
+            if any(k in context for k in issue_keywords):
+                issue_dates.append(d)
+            elif any(k in context for k in event_keywords):
+                after_text = text[idx: idx+80]
+                match = re.search(rf"{re.escape(d)}[^\n]*", after_text)
+                if match:
+                    event_dates.append(match.group().strip())
+                else:
+                    event_dates.append(d)
+
+    if not issue_dates and dates:
+        issue_dates.append(dates[0])
+
+    return issue_dates, event_dates
+
+# ------------------------
+# Verification Logic
+# ------------------------
+def verify_text(text, source_type="TEXT"):
+    if not text.strip():
+        return "--- Evidence Report ---\n\n❌ No readable text provided."
+
+    grammar_issue = check_grammar(text)
+    dates = extract_dates(text)
+    issue_dates, event_dates = classify_dates(text, dates)
+
+    labels = ["REAL", "FAKE"]
+    result = classifier(text[:1000], candidate_labels=labels)
+
+    report = "📄 Evidence Report\n\n"
+    report += "🔎 Document Analysis\n\n"
+    report += f"Source: {source_type}\n\n"
+
+    report += "✅ Evidence Considered\n\n"
+    if grammar_issue:
+        report += "Minor grammar/spelling issues were detected but do not affect authenticity.\n\n"
+    else:
+        report += "No major grammar or spelling issues detected.\n\n"
+
+    if issue_dates:
+        report += f"📌 Document Issue Date(s): {', '.join(issue_dates)}\n"
+    if event_dates:
+        report += f"📌 Event/Holiday Date(s): {', '.join(event_dates)}\n"
+    if not dates:
+        report += "No specific dates were clearly detected.\n"
+
+    report += "\nDocument formatting and official tone resemble genuine university circulars.\n"
+    report += "Signatures and registrar details align with standard official notices.\n\n"
+
+    report += "🏁 Classification Result\n\n"
+    report += f"Verdict: {result['labels'][0]}\n"
+    report += f"Confidence: {result['scores'][0]:.2f}\n"
+
+    return report
+
+def verify_document(file):
+    if file is None:
+        return "❌ Please upload a file."
+    file_path = file.name
+    ext = file_path.split('.')[-1].lower()
+    if ext == "pdf":
+        text = extract_text_from_pdf(file_path)
+    elif ext == "docx":
+        text = extract_text_from_docx(file_path)
+    elif ext in ["png", "jpg", "jpeg"]:
+        text = extract_text_from_image(file_path)
+    else:
+        return "Unsupported file type."
+    return verify_text(text, source_type=ext.upper())
+
+# ------------------------
+# Streamlit UI
+# ------------------------
+st.set_page_config(page_title="📑 Document Authenticity Verifier", layout="wide")
+
+st.title("📑 Document Authenticity Verifier")
+st.write("Upload a **PDF, DOCX, or Image** to verify authenticity.")
+
+uploaded_file = st.file_uploader("Upload Document", type=["pdf", "docx", "png", "jpg", "jpeg"])
+
+if st.button("Verify Document"):
+    if uploaded_file is not None:
+        with open(uploaded_file.name, "wb") as f:
+            f.write(uploaded_file.getbuffer())
+        report = verify_document(uploaded_file)
+        st.text_area("Verification Report", report, height=400)
+    else:
+        st.warning("Please upload a document first.")