Spaces:

GodsDevProject
/

FOIA_Doc_Search

Sleeping

App Files Files Community

GodsDevProject commited on Jan 10

Commit

f768e52

verified ·

1 Parent(s): f9878e1

Update app.py

Browse files

Files changed (1) hide show

app.py +73 -86

app.py CHANGED Viewed

@@ -27,9 +27,7 @@ except Exception:
 # CONFIG / FEATURE GATES
 # ======================================================
-ENABLE_SEMANTIC = False          # Opt-in only
-ENABLE_PDF_EXPORT = True
-ENABLE_HEATMAP = True
 ENABLE_PDF_THUMBNAILS = True
 ENABLE_ENTITY_GRAPHS = True
 ENABLE_TIMELINES = True
@@ -47,7 +45,6 @@ class FOIAAdapter:
         start = time.time()
         url = self.search_url.format(q=quote_plus(query))
         latency = round(time.time() - start, 3)
         return [{
             "agency": self.agency,
             "title": f"{self.agency} FOIA Search Results",
@@ -100,7 +97,6 @@ class StubAdapter(FOIAAdapter):
     def __init__(self, agency):
         self.agency = agency
         self.search_url = ""
     def search(self, query):
         return [{
             "agency": self.agency,
@@ -158,7 +154,6 @@ def run_search(query, include_stubs, semantic_mode):
             coverage[r["agency"]] += 1
             if r["is_live"]:
                 LAST_LIVE_RECORDS.append(r)
             rows.append([
                 r["agency"],
                 "LIVE" if r["is_live"] else "STUB",
@@ -181,17 +176,12 @@ def run_search(query, include_stubs, semantic_mode):
 # ======================================================
 def build_pdf_thumbnail_gallery():
-    if not ENABLE_PDF_THUMBNAILS:
-        return "<i>PDF previews disabled</i>"
     cards = []
     for r in LAST_LIVE_RECORDS:
         url = r["url"]
-        if not url or not url.lower().endswith(".pdf"):
             continue
-        card = f"""
         <div style="border:1px solid #ddd;border-radius:8px;padding:12px;margin-bottom:16px;">
             <b>{r['agency']} — {r['title']}</b><br><br>
             <iframe src="{url}" width="100%" height="220"></iframe>
@@ -202,13 +192,74 @@ def build_pdf_thumbnail_gallery():
                 <a href="#" onclick="askAI('{r['agency']}', '{r['title']}', '{url}')">Ask AI</a>
             </div>
         </div>
         """
-        cards.append(card)
-    return "".join(cards) if cards else "<i>No PDF documents found.</i>"
 # ======================================================
-# CLIENT JS
 # ======================================================
 JS_HELPERS = """
@@ -221,71 +272,16 @@ function shareDoc(url) {
         alert("Link copied to clipboard");
     }
 }
-function askAI(agency, title, url) {
-    alert(
-        "AI Summary (Preview)\\n\\n" +
-        "Agency: " + agency + "\\n" +
-        "Title: " + title + "\\n\\n" +
-        "Semantic analysis, entities, and citations can be enabled in opt-in AI mode."
-    );
 }
 </script>
 """
-# ======================================================
-# ENTITY GRAPH + TIMELINE
-# ======================================================
-def build_entity_graph():
-    domains = Counter(urlparse(r["url"]).netloc for r in LAST_LIVE_RECORDS)
-    return go.Figure([go.Bar(x=list(domains.keys()), y=list(domains.values()))])
-def build_timeline():
-    dates = Counter(r["timestamp"][:10] for r in LAST_LIVE_RECORDS)
-    return go.Figure([go.Bar(x=list(dates.keys()), y=list(dates.values()))])
-# ======================================================
-# FOIA REQUEST GENERATOR
-# ======================================================
-def generate_foia_request(requester, description):
-    buffer = io.BytesIO()
-    doc = SimpleDocTemplate(buffer)
-    styles = getSampleStyleSheet()
-    story = []
-    story.append(Paragraph("<b>Freedom of Information Act Request</b>", styles["Title"]))
-    story.append(Spacer(1, 12))
-    story.append(Paragraph(f"<b>Requester:</b> {requester}", styles["Normal"]))
-    story.append(Spacer(1, 8))
-    story.append(Paragraph("<b>Description:</b>", styles["Normal"]))
-    story.append(Paragraph(description, styles["Normal"]))
-    story.append(Spacer(1, 12))
-    agencies = ", ".join(sorted({r["agency"] for r in LAST_LIVE_RECORDS}))
-    story.append(Paragraph(f"<b>Agencies:</b> {agencies}", styles["Normal"]))
-    doc.build(story)
-    buffer.seek(0)
-    return buffer
-# ======================================================
-# UI
-# ======================================================
 with gr.Blocks(title="Federal FOIA Intelligence Search") as app:
     gr.HTML(JS_HELPERS)
-    gr.Markdown(
-        """
-        # 🏛️ Federal FOIA Intelligence Search
-        **Public FOIA Electronic Reading Rooms Only**
-        ✔ LIVE = court-ready
-        ⚠ STUB = informational only
-        """
-    )
     query = gr.Textbox(label="Search FOIA Libraries")
     include_stubs = gr.Checkbox(label="Include Extended Coverage (STUB)", value=False)
@@ -310,17 +306,8 @@ with gr.Blocks(title="Federal FOIA Intelligence Search") as app:
     gr.Markdown("## 📄 PDF Document Previews")
     pdf_gallery.render()
-    gr.Markdown("## FOIA Request Generator")
-    requester = gr.Textbox(label="Your Name / Organization")
-    description = gr.Textbox(label="Describe the records requested", lines=4)
-    gr.Button("Generate FOIA Request PDF").click(
-        generate_foia_request,
-        inputs=[requester, description],
-        outputs=gr.File()
-    )
-    gr.Button("Show Entity Graph").click(build_entity_graph, outputs=gr.Plot())
-    gr.Button("Show Timeline").click(build_timeline, outputs=gr.Plot())
 app.launch()

 # CONFIG / FEATURE GATES
 # ======================================================
+ENABLE_SEMANTIC = False
 ENABLE_PDF_THUMBNAILS = True
 ENABLE_ENTITY_GRAPHS = True
 ENABLE_TIMELINES = True
         start = time.time()
         url = self.search_url.format(q=quote_plus(query))
         latency = round(time.time() - start, 3)
         return [{
             "agency": self.agency,
             "title": f"{self.agency} FOIA Search Results",
     def __init__(self, agency):
         self.agency = agency
         self.search_url = ""
     def search(self, query):
         return [{
             "agency": self.agency,
             coverage[r["agency"]] += 1
             if r["is_live"]:
                 LAST_LIVE_RECORDS.append(r)
             rows.append([
                 r["agency"],
                 "LIVE" if r["is_live"] else "STUB",
 # ======================================================
 def build_pdf_thumbnail_gallery():
     cards = []
     for r in LAST_LIVE_RECORDS:
         url = r["url"]
+        if not url.lower().endswith(".pdf"):
             continue
+        cards.append(f"""
         <div style="border:1px solid #ddd;border-radius:8px;padding:12px;margin-bottom:16px;">
             <b>{r['agency']} — {r['title']}</b><br><br>
             <iframe src="{url}" width="100%" height="220"></iframe>
                 <a href="#" onclick="askAI('{r['agency']}', '{r['title']}', '{url}')">Ask AI</a>
             </div>
         </div>
+        """)
+    return "".join(cards) if cards else "<i>No PDF documents found.</i>"
+# ======================================================
+# JOURNALIST ZIP EXPORT (LINKS + CITATIONS ONLY)
+# ======================================================
+def generate_journalist_zip():
+    if not LAST_LIVE_RECORDS:
+        return None
+    mem = io.BytesIO()
+    with zipfile.ZipFile(mem, "w", zipfile.ZIP_DEFLATED) as z:
+        z.writestr(
+            "README.txt",
+            "Public FOIA sources only.\n"
+            "This ZIP contains links and citations only.\n"
+            "No documents are hosted or redistributed.\n"
+        )
+        z.writestr(
+            "citations.txt",
+            "\n\n".join(bluebook_full(r) for r in LAST_LIVE_RECORDS)
+        )
+        csv = "agency,title,url,retrieved\n"
+        for r in LAST_LIVE_RECORDS:
+            csv += f"{r['agency']},{r['title']},{r['url']},{r['timestamp']}\n"
+        z.writestr("links.csv", csv)
+        pdf_links = "\n".join(
+            r["url"] for r in LAST_LIVE_RECORDS if r["url"].lower().endswith(".pdf")
+        )
+        z.writestr("pdf_links.txt", pdf_links)
+    mem.seek(0)
+    return mem
+# ======================================================
+# PUBLIC SHAREABLE RESULT PAGE (STATIC HTML)
+# ======================================================
+def generate_share_page():
+    if not LAST_LIVE_RECORDS:
+        return None
+    html = """
+    <html><head><title>FOIA Search Results</title></head><body>
+    <h1>Federal FOIA Search Results</h1>
+    <p>Public electronic reading rooms only.</p><hr>
+    """
+    for r in LAST_LIVE_RECORDS:
+        html += f"""
+        <h3>{r['agency']} — {r['title']}</h3>
+        <p><a href="{r['url']}" target="_blank">{r['url']}</a></p>
+        <p><b>Citation:</b> {bluebook_full(r)}</p>
+        <p><b>Hash:</b> {citation_hash(r)}</p>
+        <hr>
         """
+    html += "</body></html>"
+    buf = io.BytesIO(html.encode("utf-8"))
+    return buf
 # ======================================================
+# UI
 # ======================================================
 JS_HELPERS = """
         alert("Link copied to clipboard");
     }
 }
+function askAI(a,t,u){
+    alert("AI analysis placeholder for: " + t);
 }
 </script>
 """
 with gr.Blocks(title="Federal FOIA Intelligence Search") as app:
     gr.HTML(JS_HELPERS)
+    gr.Markdown("# 🏛️ Federal FOIA Intelligence Search")
     query = gr.Textbox(label="Search FOIA Libraries")
     include_stubs = gr.Checkbox(label="Include Extended Coverage (STUB)", value=False)
     gr.Markdown("## 📄 PDF Document Previews")
     pdf_gallery.render()
+    gr.Markdown("## 🗂 Journalist Tools")
+    gr.Button("Download Journalist ZIP").click(generate_journalist_zip, outputs=gr.File())
+    gr.Button("Generate Shareable Result Page").click(generate_share_page, outputs=gr.File())
 app.launch()