{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Spectra exported from Topspin as follows\n",
    "- process (1D) spectrum with \"fp\"\n",
    "- aplly automatic phase correction of orders 0 and 1 with \"apk\"\n",
    "- autozoom\n",
    "- rightclick in display window to choose \"Save Display Region To...\" (chose not to save imaginary part)\n",
    "- -> a file is created with some header lines and the y-values for the real part of the spectrum\n",
    "- this python script searches the header lines for the x-range and pieces x- and y-values together."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "filename input: 298K-c\n"
     ]
    }
   ],
   "source": [
    "#option to set a fixed path:\n",
    "# in pieces\n",
    "path_piece = \"/autohome/saeckech/Promotion/Messungen/Bayreuth/1GHz/Spectr1H/\"\n",
    "file_piece = str(input(\"filename input: \"))\n",
    "filedir = path_piece+file_piece\n",
    "# full path\n",
    "#filedir = \"/autohome/saeckech/Promotion/Messungen/Auswertung/PNIP-Bulk-in-D2O_NIPAM-Bulk-in-D2O_P90-T1/PNIPAM-CN0E_2H-NMR_InvRec_rTemp-MonoExp_2022-Sep_PTS46704360Hz_fitparameter_Aligned.dat\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "filename:\n",
      " 298K-c\n",
      "location:\n",
      " /autohome/saeckech/Promotion/Messungen/Bayreuth/1GHz/Spectra_1H/\n"
     ]
    }
   ],
   "source": [
    "filename = filedir.split(\"/\")[-1]\n",
    "location = filedir.strip(filename)\n",
    "\n",
    "print(\"filename:\\n\",filename)\n",
    "print(\"location:\\n\",location)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#fixed search patterns\n",
    "identifier_chemshift_preline = \"# Spectral Region:\"\n",
    "identifier_numpoints = \"# SIZE = \"\n",
    "chemshift_regex_search = \"# LEFT = (-?\\d{1,3}.\\d+) ppm. RIGHT = (-?\\d{1,3}.\\d+) ppm.\"\n",
    "size_regex_search = \"# SIZE = (\\d+) \\( = number of points\\)\"\n",
    "\n",
    "#clear variables from potential previous executions of the cell\n",
    "chemshift_linenum = None\n",
    "numpoints_linenum = None\n",
    "chemshift_left = None\n",
    "chemshift_right = None\n",
    "size = None\n",
    "xvals = []\n",
    "yvals = []\n",
    "broken1 = \"bad\"\n",
    "broken2 = \"bad\"\n",
    "\n",
    "#process file\n",
    "with open(filedir) as file:\n",
    "    lines = file.readlines()\n",
    "    for line_num in range(len(lines)):\n",
    "        if lines[line_num].startswith(identifier_chemshift_preline):\n",
    "            if chemshift_linenum is None:\n",
    "                chemshift_linenum = line_num+1\n",
    "            elif chemshift_linenum is not None:\n",
    "                print(\"found more than one match to identifier '\"+identifier_chemshift_preline+\"'! Breaking\")\n",
    "                break\n",
    "        if lines[line_num].startswith(identifier_numpoints):\n",
    "            if numpoints_linenum is None:\n",
    "                numpoints_linenum = line_num\n",
    "            elif numpoints_linenum is not None:\n",
    "                print(\"found more than one match to identifier '\"+identifier_numpoints+\"'! Breaking\")\n",
    "                break\n",
    "        if not lines[line_num].startswith(\"#\"):\n",
    "            yvals.append(float(lines[line_num]))\n",
    "    if chemshift_linenum is None:\n",
    "        print(\"Could not find a match to identifier '\"+identifier_chemshift_preline+\"'.\")\n",
    "    if numpoints_linenum is None:\n",
    "        print(\"Could not find a match to identifier '\"+identifier_numpoints+\"'.\")\n",
    "    chemshift_match = re.findall(chemshift_regex_search,lines[chemshift_linenum])\n",
    "    if len(chemshift_match) == 1:\n",
    "        chemshift_left = float(chemshift_match[0][0])\n",
    "        chemshift_right = float(chemshift_match[0][1])\n",
    "    size_match = re.findall(size_regex_search,lines[numpoints_linenum])\n",
    "    if len(size_match) == 1:\n",
    "        size = float(size_match[0])\n",
    "        if not size.is_integer():\n",
    "            print(\"Number of points in spectrum not recognized as integer!\")\n",
    "            print(\"Prompting user input to draw attention to this.\")\n",
    "            broken1 = input(\"This should not have happened\")\n",
    "    for row_counter in range(len(yvals)):\n",
    "        xvals.append(chemshift_left-row_counter*(chemshift_left-chemshift_right)/(size-1))\n",
    "    if not xvals[0]==chemshift_left or not xvals[-1]==chemshift_right:\n",
    "        print(\"xvalue assignment is off!\")\n",
    "        print(\"Prompting user input to draw attention to this.\")\n",
    "        broken2 = input(\"This should not have happened\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(list(zip(xvals, yvals)), columns=[\"#chemical_shift_in_ppm\", \"spectrum_real_in_au\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "#option to view spectrum\n",
    "view_plot = False\n",
    "if view_plot:\n",
    "    df.plot(x=\"#chemical_shift_in_ppm\", y=\"spectrum_real_in_au\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "save_as = location+filename #overwrite old file. May choose new filename instead."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saved as:\n",
      " /autohome/saeckech/Promotion/Messungen/Bayreuth/1GHz/Spectra_1H/298K-c\n"
     ]
    }
   ],
   "source": [
    "with open(save_as, \"w\") as file:\n",
    "    file.write(df.to_csv(index=False, sep=\"\\t\"))\n",
    "    #file.write(\"\\n\") #write end of line to please xmgrace's parser\n",
    "    print(\"Saved as:\\n\", save_as)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}