{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Sydney Stock Exchange – view trading on a particular day\n",
    "\n",
    "Select a date to view details of that day's trading (if any). "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This notebook is designed to run in Voila as an app (with the code hidden).\n",
    "# To launch this notebook in Voila, just select 'View > Open with Voila in New Browser Tab'\n",
    "# Your browser might ask for permission to open the new tab as a popup."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import datetime\n",
    "import os\n",
    "from collections import Counter\n",
    "from urllib.parse import parse_qs, quote_plus\n",
    "\n",
    "import arrow\n",
    "import ipywidgets as widgets\n",
    "import pandas as pd\n",
    "from IPython.display import HTML, Image, display\n",
    "\n",
    "from page_data_master import pages_per_vol\n",
    "\n",
    "SESSIONS = {\"M\": \"Morning\", \"N\": \"Noon\", \"A\": \"Afternoon\", \"U\": \"Unknown\"}\n",
    "\n",
    "CLOUDSTOR_URL = \"https://cloudstor.aarnet.edu.au/plus/s/i02k4gxeEpMAUkm\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_pages(vol_num, page_num):\n",
    "    for key, pages in pages_per_vol.items():\n",
    "        vols = key.split(\"_\")\n",
    "        vols = [int(y) for y in vols]\n",
    "        if len(vols) == 2:\n",
    "            vols = list(range(vols[0], vols[1] + 1))\n",
    "        if vol_num in vols:\n",
    "            for p_key, p_pages in pages.items():\n",
    "                p_range = p_key.split(\"_\")\n",
    "                if p_range[1] == \"*\":\n",
    "                    if page_num >= int(p_range[0]):\n",
    "                        return p_pages\n",
    "                else:\n",
    "                    if page_num >= int(p_range[0]) and page_num <= int(p_range[1]):\n",
    "                        return p_pages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get the list of dates\n",
    "df_dates = pd.read_csv(\"complete_date_list.csv\", parse_dates=[\"date\"])\n",
    "# Get the list of pages\n",
    "df_pages = pd.read_csv(\"complete_page_list.csv\", parse_dates=[\"date\"])\n",
    "# Merge dates and pages on the date field\n",
    "df = pd.merge(df_dates, df_pages, how=\"left\", on=\"date\").sort_values(\n",
    "    by=[\"date\", \"page_num\"]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def highlight_missing(row):\n",
    "    \"\"\"\n",
    "    Highlight missing pages.\n",
    "    \"\"\"\n",
    "    if row[\"pages expected\"] == row[\"pages found\"]:\n",
    "        return [\"\", \"\"]\n",
    "    else:\n",
    "        return [\"\", \"background-color: yellow\"]\n",
    "\n",
    "\n",
    "def find_pages():\n",
    "    results.clear_output()\n",
    "    date = arrow.get(date_picker.value)\n",
    "    with results:\n",
    "        display(HTML(f'<h2>{date.format(\"D MMMM YYYY\")}</h2>'))\n",
    "        rows = df.loc[df[\"date\"] == pd.Timestamp(date_picker.value)]\n",
    "        first_page = rows.iloc[0][\"page_num\"]\n",
    "        vol_num = rows.iloc[0][\"vol_num\"]\n",
    "        num_pages = rows.iloc[0][\"pages\"]\n",
    "        if date.weekday() < 6 and pd.notnull(vol_num):\n",
    "\n",
    "            # Get the expected number of pages\n",
    "            expected = get_pages(int(vol_num), int(first_page))\n",
    "            if date.weekday() < 5:\n",
    "                expected_pages = expected[\"weekday\"]\n",
    "            elif date.weekday() == 5:\n",
    "                expected_pages = expected[\"saturday\"]\n",
    "            expected_num_pages = expected_pages[0]\n",
    "            display(\n",
    "                HTML(\n",
    "                    f\"<p><b>Number of pages</b>: {expected_num_pages} expected / {int(num_pages)} found</p>\"\n",
    "                )\n",
    "            )\n",
    "\n",
    "            # Display a breakdown of the number of pages per session\n",
    "            expected_sessions = dict(Counter(expected_pages[1]))\n",
    "            actual_sessions = rows[\"session\"].value_counts().to_dict()\n",
    "            sessions = []\n",
    "            for session, number in expected_sessions.items():\n",
    "                try:\n",
    "                    sessions.append(\n",
    "                        {\n",
    "                            \"session\": SESSIONS[session],\n",
    "                            \"pages expected\": number,\n",
    "                            \"pages found\": actual_sessions[session],\n",
    "                        }\n",
    "                    )\n",
    "                except KeyError:\n",
    "                    sessions.append(\n",
    "                        {\n",
    "                            \"session\": SESSIONS[session],\n",
    "                            \"pages expected\": number,\n",
    "                            \"pages found\": 0,\n",
    "                        }\n",
    "                    )\n",
    "            display(\n",
    "                pd.DataFrame(sessions)\n",
    "                .set_index(keys=\"session\")\n",
    "                .style.apply(highlight_missing, axis=1)\n",
    "            )\n",
    "\n",
    "        # Show page images\n",
    "        for row in rows.itertuples():\n",
    "            if pd.isnull(row.vol_title):\n",
    "                print(row.reason)\n",
    "            else:\n",
    "                image_url = f\"{CLOUDSTOR_URL}/download?path={quote_plus(row.vol_title)}&files=N193-{int(row.vol_num):03}_{int(row.page_num):04}.jpg\"\n",
    "                display(\n",
    "                    HTML(\n",
    "                        f'<h4>{SESSIONS[row.session]}</h4><p>{row.vol_title}, page {int(row.page_num)} – <a href=\"{image_url}\">Download image</a></p>'\n",
    "                    )\n",
    "                )\n",
    "                display(Image(url=image_url))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def start(b):\n",
    "    find_pages()\n",
    "\n",
    "\n",
    "date_picker = widgets.DatePicker(\n",
    "    description=\"Pick a Date\", disabled=False, value=datetime.date(1901, 1, 1)\n",
    ")\n",
    "\n",
    "# with results:\n",
    "#    print(os.environ.get('QUERY_STRING', ''))\n",
    "query_string = os.environ.get(\"QUERY_STRING\", \"\")\n",
    "parameters = parse_qs(query_string)\n",
    "date = parameters.get(\"date\")\n",
    "\n",
    "find = widgets.Button(\n",
    "    description=\"Find pages\",\n",
    "    disabled=False,\n",
    "    button_style=\"primary\",  # 'success', 'info', 'warning', 'danger' or ''\n",
    "    tooltip=\"Click me\",\n",
    "    icon=\"search\",\n",
    ")\n",
    "\n",
    "find.on_click(start)\n",
    "results = widgets.Output()\n",
    "display(widgets.VBox([widgets.HBox([date_picker, find]), results]))\n",
    "# display(widgets.HBox([date_picker, find]))\n",
    "# display(results)\n",
    "\n",
    "\n",
    "if date:\n",
    "    date_picker.value = arrow.get(date[0]).date()\n",
    "    find_pages()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "Created by [Tim Sherratt](https://timsherratt.org) for the [GLAM Workbench](https://glam-workbench.github.io/)."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.12"
  },
  "voila": {
   "template": "material"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}