{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from paddleocr import PaddleOCR\n",
    "import os\n",
    "import cv2\n",
    "import xlsxwriter\n",
    "\n",
    "\n",
    "def ocr_image(image_path, ocr):\n",
    "    result = ocr.ocr(image_path, cls=True)\n",
    "    return result[0][0][1][0]\n",
    "\n",
    "\n",
    "def cropUI(image_path):\n",
    "    # small opencv window to crop the image\n",
    "    image = cv2.imread(image_path)\n",
    "    r = cv2.selectROI(image)\n",
    "    cv2.destroyAllWindows()\n",
    "\n",
    "    return r\n",
    "\n",
    "\n",
    "def cropImage(image_path, r, flip, cropped_folder):\n",
    "    # crop the image and save it\n",
    "    image = cv2.imread(image_path)\n",
    "    cropped = image[int(r[1]) : int(r[1] + r[3]), int(r[0]) : int(r[0] + r[2])]\n",
    "\n",
    "    # save with new name\n",
    "    if flip == \"y\":\n",
    "        cropped = cv2.flip(cropped, 1)\n",
    "\n",
    "    # save in subfolder cropped\n",
    "    new_name = os.path.join(cropped_folder, image_path.split(\"/\")[-1])\n",
    "    cv2.imwrite(new_name, cropped)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datetime import datetime\n",
    "\n",
    "\n",
    "def writeDate(worksheet, row, column, date, format):\n",
    "    original_format = \"%Y-%m-%d %H-%M-%S-%f\"\n",
    "    parsed_datetime = datetime.strptime(date, original_format)\n",
    "\n",
    "    worksheet.write_datetime(row, column, parsed_datetime, format)\n",
    "\n",
    "\n",
    "def data2excel(data):\n",
    "    # save the data in an excel file\n",
    "    fileName = \"data.xlsx\"\n",
    "    workbook = xlsxwriter.Workbook(fileName)\n",
    "    worksheet = workbook.add_worksheet()\n",
    "\n",
    "    dateFormat = workbook.add_format({\"num_format\": \"dd/mm/yy hh:mm:ss\"})\n",
    "\n",
    "    # write the data\n",
    "    row = 0\n",
    "    for key, value in data.items():\n",
    "        date = key.split(\" \", 1)[1][:-4]\n",
    "        writeDate(worksheet, row, 0, date, dateFormat)\n",
    "        worksheet.write(row, 1, value)\n",
    "        try:\n",
    "            worksheet.write(row, 2, float(value[:6]))\n",
    "        except Exception as _:\n",
    "            pass\n",
    "        row += 1\n",
    "\n",
    "    workbook.close()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "FOLDER = \"data/\"\n",
    "# ocr settings\n",
    "os.environ[\"KMP_DUPLICATE_LIB_OK\"] = \"TRUE\"\n",
    "ocr = PaddleOCR(use_angle_cls=True, lang=\"en\")\n",
    "\n",
    "# *** start GUIs ***\n",
    "images = [f for f in os.listdir(FOLDER) if f.endswith(\".jpg\")]\n",
    "region = cropUI(os.path.join(FOLDER, images[0]))\n",
    "\n",
    "flip = input(\"Do you want to flip the images horizontaly? (y/n): \")\n",
    "\n",
    "cropped_folder = os.path.join(FOLDER, \"cropped\")\n",
    "if not os.path.exists(cropped_folder):\n",
    "    os.makedirs(cropped_folder)\n",
    "\n",
    "# *** start cropping ***\n",
    "for image in images:\n",
    "    cropImage(os.path.join(FOLDER, image), region, flip, cropped_folder)\n",
    "\n",
    "# *** start OCR ***\n",
    "cropped_images = [f for f in os.listdir(cropped_folder) if f.endswith(\".jpg\")]\n",
    "data = {}\n",
    "for image in cropped_images:\n",
    "    try:\n",
    "        path = os.path.join(cropped_folder, image)\n",
    "        text = ocr_image(path, ocr)\n",
    "    except Exception as _:\n",
    "        print(\"Error in cropped image\")\n",
    "        continue\n",
    "\n",
    "    data[image] = text\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data2excel(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# clean excel file\n",
    "def data2cleanexcel(data):\n",
    "    # save the data in an excel file\n",
    "    fileName = \"data_clean.xlsx\"\n",
    "    workbook = xlsxwriter.Workbook(fileName)\n",
    "    worksheet = workbook.add_worksheet()\n",
    "\n",
    "    dateFormat = workbook.add_format({\"num_format\": \"dd/mm/yy hh:mm:ss\"})\n",
    "\n",
    "    # write the data\n",
    "    row = 0\n",
    "    for key, value in data.items():\n",
    "        try:\n",
    "            worksheet.write(row, 2, float(value[:6]))\n",
    "            date = key.split(\" \", 1)[1][:-4]\n",
    "            writeDate(worksheet, row, 0, date, dateFormat)\n",
    "            worksheet.write(row, 1, value)\n",
    "        except Exception as _:\n",
    "            continue\n",
    "\n",
    "        row += 1\n",
    "\n",
    "    workbook.close()\n",
    "\n",
    "data2cleanexcel(data)"
   ]
  }
 ],
 "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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}