Upload 3 files

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.11-slim
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PORT=7860
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["gunicorn","app:app","--preload","-w","2","-b","0.0.0.0:7860"]

app.py

@@ -0,0 +1,268 @@
+import io, re, json, datetime
+from typing import Dict, Any, List, Tuple, Optional
+
+from flask import Flask, request, jsonify, render_template_string, redirect, url_for
+from flask_cors import CORS
+import requests
+from bs4 import BeautifulSoup
+from PyPDF2 import PdfReader
+
+app = Flask(__name__)
+CORS(app, resources={r"/api/*": {"origins": "*"}})
+
+app.config["MAX_CONTENT_LENGTH"] = 16 * 1024 * 1024  # 16 MB upload cap
+
+THIS_YEAR = datetime.date.today().year
+DOI_RX = re.compile(r"(10\.\d{4,9}/[-._;()/:A-Z0-9]+)", re.I)
+
+def _clean(s: Optional[str]) -> str:
+    return (s or "").strip()
+
+def year_from_any(x: str) -> Optional[int]:
+    if not x: return None
+    m = re.search(r"(19|20)\d{2}", x)
+    if m:
+        y = int(m.group(0))
+        if 1900 <= y <= 2100:
+            return y
+    return None
+
+def fetch_url_metadata(url_or_doi: str):
+    warnings = []
+    url = url_or_doi
+    m = DOI_RX.search(url_or_doi)
+    if m and not url_or_doi.lower().startswith("http"):
+        url = f"https://doi.org/{m.group(1)}"
+    try:
+        r = requests.get(url, timeout=20, headers={"User-Agent":"CRAAPBot/1.0"})
+        r.raise_for_status()
+    except Exception as e:
+        return {}, "", [f"Failed to fetch URL/DOI: {e}"]
+    html = r.text
+    soup = BeautifulSoup(html, "html.parser")
+    meta = {}
+    def mget(*names):
+        for n in names:
+            tag = soup.find("meta", attrs={"name": n}) or soup.find("meta", attrs={"property": n})
+            if tag and tag.get("content"):
+                return tag["content"]
+        return None
+    meta["title"] = _clean(mget("citation_title") or (soup.title.string if soup.title else ""))
+    authors = soup.find_all("meta", attrs={"name":"citation_author"})
+    if authors:
+        meta["authors"] = [_clean(a.get("content","")) for a in authors if _clean(a.get("content",""))]
+    else:
+        meta["authors"] = [_clean(mget("author") or "")]
+        meta["authors"] = [a for a in meta["authors"] if a]
+    meta["venue"] = _clean(mget("citation_journal_title") or mget("og:site_name") or "")
+    y = year_from_any(_clean(mget("citation_publication_date") or mget("date") or mget("article:published_time") or ""))
+    meta["year"] = y if y else year_from_any(html)
+    doi = _clean(mget("citation_doi") or (DOI_RX.search(html).group(1) if DOI_RX.search(html) else ""))
+    meta["identifier"] = {"doi": doi if doi else None, "url": url}
+    abst = mget("citation_abstract")
+    if not abst:
+        absnode = soup.find(lambda tag: tag.name in ["section","div","p"] and tag.get_text(strip=True).lower().startswith("abstract"))
+        if absnode:
+            abst = absnode.get_text(" ", strip=True)
+    text_excerpt = (abst or "")[:4000]
+    return meta, text_excerpt, warnings
+
+def extract_pdf_text_and_guess_meta(file_storage):
+    warnings = []
+    try:
+        data = file_storage.read()
+        reader = PdfReader(io.BytesIO(data))
+        n = len(reader.pages)
+        if n == 0:
+            return {}, "", ["PDF appears empty."]
+        head_pages = min(2, n)
+        body_pages = min(10, n)
+        head = []
+        body = []
+        for i in range(head_pages):
+            head.append(reader.pages[i].extract_text() or "")
+        for i in range(body_pages):
+            body.append(reader.pages[i].extract_text() or "")
+        head_txt = "\n".join(head)
+        body_txt = "\n".join(body)
+        lines = [l.strip() for l in head_txt.splitlines() if l.strip()]
+        title = lines[0] if lines else ""
+        authors_line = ""
+        for l in lines[0:10]:
+            if re.search(r"[A-Z][a-z]+(?:\s[A-Z]\.){0,3}", l) and ("," in l or " and " in l.lower()):
+                authors_line = l; break
+        authors = [a.strip() for a in re.split(r",|;| and ", authors_line) if a.strip()] if authors_line else []
+        venue = ""
+        y = year_from_any(head_txt)
+        m = DOI_RX.search(head_txt) or DOI_RX.search(body_txt)
+        doi = m.group(1) if m else None
+        meta = {
+            "title": _clean(title),
+            "authors": authors,
+            "venue": _clean(venue),
+            "year": y,
+            "identifier": {"doi": doi, "url": None}
+        }
+        if body_pages < 5:
+            warnings.append("Only a small portion of the PDF text was extracted; Accuracy/Purpose may be provisional.")
+        return meta, body_txt[:20000], warnings
+    except Exception as e:
+        return {}, "", [f"Failed to parse PDF: {e}"]
+
+def score_currency(year: Optional[int]):
+    if not year:
+        return 2, "Publication year unknown.", ["Could not find a clear date; treat with caution."]
+    age = max(0, THIS_YEAR - year)
+    if age <= 2: return 5, f"Published in {year} (≤2 years old).", ["Recent for fast-moving fields."]
+    if age <= 5: return 4, f"Published in {year} (~{age} years old).", []
+    if age <= 10: return 3, f"Published in {year} (~{age} years old).", []
+    return 2, f"Published in {year} (>10 years old).", ["Potentially outdated."]
+
+def score_authority(meta: Dict[str,Any]):
+    score = 1
+    notes = []
+    if meta.get("venue"):
+        score += 1; notes.append(f"Venue: {meta['venue']}.")
+    if meta.get("identifier",{}).get("doi"):
+        score += 1; notes.append("Has DOI.")
+    if meta.get("authors"):
+        a_count = len(meta["authors"])
+        if a_count >= 3: score += 1
+        notes.append(f"Authors: {a_count}.")
+    return min(score,5), "; ".join(notes) if notes else "Insufficient venue/author info."
+
+def score_accuracy(text_excerpt: str):
+    keys_present = sum(1 for k in ["methods","materials","results","limitations","confidence interval","validation","dataset","sample size"] if k in text_excerpt.lower())
+    if not text_excerpt:
+        return 2, "No body text available; cannot inspect methods."
+    if keys_present >= 5: return 5, "Detailed methodological cues detected (methods/results/validation/etc.)."
+    if keys_present >= 3: return 4, "Some methodological cues present."
+    if keys_present >= 1: return 3, "Limited methodological signals."
+    return 2, "Minimal methodological detail detected (likely a commentary/overview)."
+
+def score_purpose(text_excerpt: str):
+    lower = text_excerpt.lower()
+    bias_hits = any(w in lower for w in ["sponsored", "advertisement", "marketing"])
+    conflicts = "conflict of interest" in lower or "competing interest" in lower
+    funding = "funding" in lower or "grant" in lower
+    if bias_hits:
+        return 2, "Potential promotional language detected."
+    if conflicts and not funding:
+        return 3, "Conflicts noted, funding unclear."
+    if funding or conflicts:
+        return 4, "Academic tone with disclosures/funding statements."
+    return 4, "Academic/educational purpose inferred."
+
+def score_relevance(assignment_context: str, meta: Dict[str,Any], text_excerpt: str):
+    if not assignment_context:
+        return 4, "General relevance assumed (no assignment context provided)."
+    ctx = assignment_context.lower()
+    hay = (meta.get("title","") + " " + text_excerpt).lower()
+    hits = sum(1 for tok in set(re.findall(r"[a-zA-Z]{4,}", ctx)) if tok in hay)
+    if hits >= 6: return 5, "Strong topical overlap with assignment context."
+    if hits >= 3: return 4, "Good topical overlap."
+    if hits >= 1: return 3, "Partial topical overlap."
+    return 2, "Low topical overlap; may be tangential."
+
+def aggregate_scores(meta: Dict[str,Any], text: str, assignment_context: str, provisional: bool):
+    currency_score, currency_evd, currency_checks = score_currency(meta.get("year"))
+    authority_score, authority_evd = score_authority(meta)
+    accuracy_score, accuracy_evd = score_accuracy(text)
+    purpose_score, purpose_evd = score_purpose(text)
+    relevance_score, relevance_evd = score_relevance(assignment_context, meta, text)
+    if provisional:
+        accuracy_score = min(accuracy_score, 3)
+        purpose_score = min(purpose_score, 4)
+    craap = {
+        "Currency": {"score": currency_score, "evidence": currency_evd, "checks": currency_checks},
+        "Relevance": {"score": relevance_score, "evidence": relevance_evd},
+        "Authority": {"score": authority_score, "evidence": authority_evd},
+        "Accuracy": {"score": accuracy_score, "evidence": accuracy_evd},
+        "Purpose": {"score": purpose_score, "evidence": purpose_evd}
+    }
+    avg = round(sum(v["score"] for v in craap.values())/5, 2)
+    verdict = "use" if avg >= 4.0 else ("use with caution" if avg >= 2.5 else "avoid")
+    return {"metadata": meta, "craap": craap, "overall": {"average": avg, "verdict": verdict}}
+
+INDEX_HTML = """
+<!doctype html><html><head><meta charset="utf-8"/><title>CRAAP Bot (Flask)</title>
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<style>
+body{font:16px system-ui,Segoe UI,Roboto,sans-serif;max-width:880px;margin:2rem auto;padding:0 1rem}
+form,.card{border:1px solid #e5e7eb;border-radius:12px;padding:1rem;margin:1rem 0;background:#fff;box-shadow:0 1px 2px rgba(0,0,0,.04)}
+label{display:block;font-weight:600;margin:.5rem 0 .25rem}
+input[type="text"],textarea{width:100%;padding:.6rem .7rem;border:1px solid #d1d5db;border-radius:8px}
+input[type="file"]{margin:.25rem 0 .75rem}button{background:#111827;color:#fff;border:0;padding:.6rem 1rem;border-radius:8px;cursor:pointer}
+pre{background:#0b1020;color:#d7e7ff;padding:1rem;border-radius:12px;overflow:auto}.muted{color:#6b7280}.warn{padding:.6rem .8rem;background:#fff7ed;border:1px solid #fed7aa;border-radius:8px;margin:.5rem 0}
+.tag{display:inline-block;padding:.1rem .5rem;border-radius:999px;border:1px solid #d1d5db;margin-right:.4rem}
+</style></head><body>
+<header><h1>CRAAP Bot</h1><span class="tag">Flask</span><span class="tag">Hugging Face</span></header>
+<div class="card"><form method="POST" action="{{ url_for('analyze') }}" enctype="multipart/form-data">
+<label>URL or DOI</label><input type="text" name="paper_source" placeholder="https://doi.org/10.xxxx/..."/>
+<label>Or upload PDF</label><input type="file" name="pdf" accept="application/pdf"/>
+<label>Assignment context (optional)</label><input type="text" name="assignment_context" placeholder="e.g., AI for zoonotic disease 2023-2025"/>
+<button type="submit">Analyze</button></form>
+<p class="muted">Tip: DOI or full PDF gives best results. Partial PDFs limit Accuracy/Purpose.</p></div>
+{% if result %}{% if warnings %}<div class="warn">⚠️ {{ warnings|join(' · ') }}</div>{% endif %}
+<div class="card"><h2>JSON</h2><pre>{{ result | tojson(indent=2) }}</pre></div>
+<div class="card"><h2>CRAAP Evaluation Summary</h2>
+<p><strong>{{ result.metadata.title or '[unknown title]' }}</strong></p>
+<p class="muted">{{ (result.metadata.authors or [])|join(', ') }} · {{ result.metadata.venue or 'unknown venue' }}{% if result.metadata.year %} · {{ result.metadata.year }}{% endif %}</p>
+<ul>
+<li><strong>Currency</strong>: {{ result.craap.Currency.score }}/5 — {{ result.craap.Currency.evidence }}</li>
+<li><strong>Relevance</strong>: {{ result.craap.Relevance.score }}/5 — {{ result.craap.Relevance.evidence }}</li>
+<li><strong>Authority</strong>: {{ result.craap.Authority.score }}/5 — {{ result.craap.Authority.evidence }}</li>
+<li><strong>Accuracy</strong>: {{ result.craap.Accuracy.score }}/5 — {{ result.craap.Accuracy.evidence }}</li>
+<li><strong>Purpose</strong>: {{ result.craap.Purpose.score }}/5 — {{ result.craap.Purpose.evidence }}</li>
+</ul><p><strong>Overall:</strong> {{ result.overall.average }} — <em>{{ result.overall.verdict }}</em></p>
+<h3>What to verify next</h3>
+<ol>
+<li>Confirm publication date & peer-review at the DOI/URL.</li>
+<li>Skim methods/results for sample size, validation, limitations.</li>
+<li>Check author affiliations and profiles (Semantic Scholar/ORCID).</li>
+<li>Look for funding/conflict-of-interest statements.</li>
+<li>Search for newer papers (last 1–2 years) that cite or challenge it.</li>
+</ol>
+</div>{% endif %}</body></html>
+"""
+
+@app.route("/", methods=["GET"])
+def index():
+    return render_template_string(INDEX_HTML, result=None, warnings=None)
+
+@app.route("/analyze", methods=["POST"])
+def analyze():
+    paper_source = _clean(request.form.get("paper_source", ""))
+    assignment_context = _clean(request.form.get("assignment_context", ""))
+    provisional = False
+    warnings: List[str] = []
+    meta, text = {}, ""
+    if paper_source:
+        meta, text, w = fetch_url_metadata(paper_source)
+        warnings.extend(w)
+    elif "pdf" in request.files and request.files["pdf"].filename:
+        meta, text, w = extract_pdf_text_and_guess_meta(request.files["pdf"])
+        warnings.extend(w); provisional = True
+    else:
+        return redirect(url_for("index"))
+    result = aggregate_scores(meta, text, assignment_context, provisional or bool(warnings))
+    if not text:
+        warnings.append("Full text not available — Accuracy/Purpose are provisional. Provide a DOI/URL or full PDF for deeper evaluation.")
+    return render_template_string(INDEX_HTML, result=result, warnings=warnings)
+
+@app.route("/api/analyze", methods=["POST"])
+def api_analyze():
+    data = request.json or {}
+    paper_source = _clean(data.get("paper_source",""))
+    assignment_context = _clean(data.get("assignment_context",""))
+    meta, text, warnings = ({}, "", [])
+    provisional = False
+    if paper_source:
+        meta, text, warnings = fetch_url_metadata(paper_source)
+    else:
+        return jsonify({"error":"Provide paper_source (URL/DOI) or use /analyze form for PDF upload"}), 400
+    result = aggregate_scores(meta, text, assignment_context, provisional or bool(warnings))
+    return jsonify({"result": result, "warnings": warnings})
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=8000, debug=True)

requirements.txt

@@ -0,0 +1,6 @@
+flask==3.0.3
+requests==2.32.3
+beautifulsoup4==4.12.3
+PyPDF2==3.0.1
+flask-cors==4.0.1
+gunicorn==22.0.0