Add explicit Documents & Texts tab and native Image-to-PDF converter (/api/convert_pdf)

server.py

@@ -1407,6 +1407,95 @@ class Handler(BaseHTTPRequestHandler):
             paths = [r["path"] for r in filtered[:MAX_SELECT]]
             self._json({"paths": paths, "total": len(filtered), "capped": len(filtered) > MAX_SELECT})
 
+        elif self.path.startswith("/api/documents"):
+            parsed_url = urllib.parse.urlparse(self.path)
+            params = urllib.parse.parse_qs(parsed_url.query)
+            try:
+                limit = max(1, min(200, int(params.get("limit", ["60"])[0])))
+            except ValueError:
+                limit = 60
+            try:
+                offset = max(0, int(params.get("offset", ["0"])[0]))
+            except ValueError:
+                offset = 0
+            records = load_search_index()
+            docs = [r for r in records if r.get("category") == "Screenshots & Documents" or r.get("route") == "screenshot" or "text:" in (r.get("desc") or "").lower()]
+            total = len(docs)
+            page = [{k: v for k, v in r.items() if k not in ("_hay", "_mtime", "_ext")} for r in docs[offset:offset + limit]]
+            self._json({"results": page, "total": total, "offset": offset, "limit": limit})
+
+        elif self.path.startswith("/api/convert_pdf"):
+            parsed_url = urllib.parse.urlparse(self.path)
+            params = urllib.parse.parse_qs(parsed_url.query)
+            paths_param = params.get("paths", [""])[0] or params.get("path", [""])[0]
+            if not paths_param:
+                self._json({"error": "path parameter is required"}, 400); return
+            paths = [p for p in paths_param.split(",") if p and os.path.exists(p)]
+            if not paths:
+                self._json({"error": "files not found"}, 404); return
+
+            if len(paths) == 1:
+                src = paths[0]
+                base_name = os.path.splitext(os.path.basename(src))[0] + ".pdf"
+                tmp_pdf = tempfile.NamedTemporaryFile(suffix=".pdf", delete=False)
+                tmp_pdf.close()
+                try:
+                    cmd = ["sips", "-s", "format", "pdf", src, "--out", tmp_pdf.name]
+                    r = subprocess.run(cmd, capture_output=True, timeout=30)
+                    if r.returncode != 0 or not os.path.exists(tmp_pdf.name):
+                        raise RuntimeError(f"sips failed: {r.stderr.decode(errors='replace')}")
+                    with open(tmp_pdf.name, "rb") as f:
+                        pdf_data = f.read()
+                    self.send_response(200)
+                    self.send_header("Content-Type", "application/pdf")
+                    self.send_header("Content-Disposition", f'attachment; filename="{base_name}"')
+                    self.send_header("Content-Length", str(len(pdf_data)))
+                    self.end_headers()
+                    self.wfile.write(pdf_data)
+                except Exception as e:
+                    self._json({"error": f"Failed converting image to PDF: {e}"}, 500)
+                finally:
+                    try: os.remove(tmp_pdf.name)
+                    except Exception: pass
+            else:
+                tmp_zip = tempfile.NamedTemporaryFile(suffix=".zip", delete=False)
+                tmp_zip.close()
+                tmp_dir = tempfile.mkdtemp(prefix="photon_pdf_zip_")
+                try:
+                    used_names = set()
+                    with zipfile.ZipFile(tmp_zip.name, "w", zipfile.ZIP_STORED, allowZip64=True) as zf:
+                        for src in paths:
+                            base = os.path.splitext(os.path.basename(src))[0]
+                            pdf_name = base + ".pdf"
+                            i = 1
+                            while pdf_name in used_names:
+                                pdf_name = f"{base}_{i}.pdf"
+                                i += 1
+                            used_names.add(pdf_name)
+                            out_pdf = os.path.join(tmp_dir, pdf_name)
+                            cmd = ["sips", "-s", "format", "pdf", src, "--out", out_pdf]
+                            r = subprocess.run(cmd, capture_output=True, timeout=30)
+                            if r.returncode == 0 and os.path.exists(out_pdf):
+                                zf.write(out_pdf, arcname=pdf_name)
+                    size = os.path.getsize(tmp_zip.name)
+                    self.send_response(200)
+                    self.send_header("Content-Type", "application/zip")
+                    self.send_header("Content-Disposition", f'attachment; filename="photon_documents_pdf.zip"')
+                    self.send_header("Content-Length", str(size))
+                    self.end_headers()
+                    with open(tmp_zip.name, "rb") as f:
+                        while True:
+                            chunk = f.read(1024 * 1024)
+                            if not chunk: break
+                            self.wfile.write(chunk)
+                except Exception as e:
+                    self._json({"error": f"Failed converting batch PDFs: {e}"}, 500)
+                finally:
+                    try: os.remove(tmp_zip.name)
+                    except Exception: pass
+                    try: shutil.rmtree(tmp_dir)
+                    except Exception: pass
+
         elif self.path.startswith("/api/search"):
             parsed_url = urllib.parse.urlparse(self.path)
             params = urllib.parse.parse_qs(parsed_url.query)