From 8f87c31152432e38743653503c3dd7e3b0a873f1 Mon Sep 17 00:00:00 2001
From: Minasuki Hikimuna <minasuki.hikimuna@chiefsclub.com>
Date: Tue, 27 Aug 2024 18:06:31 +0300
Subject: [PATCH] Notebook for merging StashDB tags to matched scenes

---
 pandas/stashdb_tags_to_matched_scenes.ipynb | 133 ++++++++++++++++++++
 1 file changed, 133 insertions(+)
 create mode 100644 pandas/stashdb_tags_to_matched_scenes.ipynb

diff --git a/pandas/stashdb_tags_to_matched_scenes.ipynb b/pandas/stashdb_tags_to_matched_scenes.ipynb
new file mode 100644
index 0000000..4e1a041
--- /dev/null
+++ b/pandas/stashdb_tags_to_matched_scenes.ipynb
@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import dotenv\n",
+    "import os\n",
+    "from libraries.client_stashapp import get_stashapp_client\n",
+    "from libraries.StashDbClient import StashDbClient\n",
+    "\n",
+    "dotenv.load_dotenv()\n",
+    "\n",
+    "stash = get_stashapp_client()\n",
+    "\n",
+    "stashbox_client = StashDbClient(\n",
+    "    os.getenv(\"STASHDB_ENDPOINT\"),\n",
+    "    os.getenv(\"STASHDB_API_KEY\"),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_scenes_with_stashdb_id():\n",
+    "    scenes = stash.find_scenes(\n",
+    "        {\n",
+    "            \"stash_id_endpoint\": {\n",
+    "                \"endpoint\": \"https://stashdb.org/graphql\",\n",
+    "                \"modifier\": \"NOT_NULL\",\n",
+    "            },\n",
+    "            \"tags\": {\n",
+    "                \"value\": [],\n",
+    "                \"modifier\": \"IS_NULL\"\n",
+    "            }\n",
+    "        },\n",
+    "        filter = {\n",
+    "            \"per_page\": 1000,\n",
+    "            \"page\": 1\n",
+    "        }\n",
+    "    )\n",
+    "    return scenes\n",
+    "\n",
+    "scenes_with_stashdb_id = get_scenes_with_stashdb_id()\n",
+    "df_scenes = pd.DataFrame(scenes_with_stashdb_id)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Step 2: Extract StashDB IDs and existing tags\n",
+    "df_scenes['stashdb_id'] = df_scenes['stash_ids'].apply(\n",
+    "    lambda x: next((stash_id['stash_id'] for stash_id in x if stash_id['endpoint'] == 'https://stashdb.org/graphql'), None)\n",
+    ")\n",
+    "df_scenes['existing_tags'] = df_scenes['tags'].apply(lambda x: sorted([tag['name'] for tag in x]))\n",
+    "\n",
+    "# Step 3: Fetch StashDB data for each scene\n",
+    "def get_stashdb_data(stashdb_id):\n",
+    "    return stashbox_client.query_scenes(stashdb_id)\n",
+    "\n",
+    "df_scenes['stashdb_data'] = df_scenes['stashdb_id'].apply(get_stashdb_data)\n",
+    "\n",
+    "# Step 4: Extract tags from StashDB data\n",
+    "def extract_tags(stashdb_data):\n",
+    "    if stashdb_data and 'data' in stashdb_data and 'findScene' in stashdb_data['data']:\n",
+    "        return sorted([tag['name'] for tag in stashdb_data['data']['findScene']['tags']])\n",
+    "    return []\n",
+    "\n",
+    "df_scenes['stashdb_tags'] = df_scenes['stashdb_data'].apply(extract_tags)\n",
+    "\n",
+    "# Step 5: Merge existing tags with StashDB tags\n",
+    "df_scenes['merged_tags'] = df_scenes.apply(lambda row: sorted(list(set(row['existing_tags'] + row['stashdb_tags']))), axis=1)\n",
+    "\n",
+    "# Step 6: Compare existing tags with merged tags\n",
+    "df_scenes['tags_identical'] = df_scenes.apply(lambda row: set(row['existing_tags']) == set(row['merged_tags']), axis=1)\n",
+    "\n",
+    "# Step 7: Find corresponding tags in local Stash for merged tags\n",
+    "def find_stash_tags(tag_names):\n",
+    "    return sorted([stash.find_tag(tag_name) for tag_name in tag_names], key=lambda x: x['name'] if x else '')\n",
+    "\n",
+    "df_scenes['stash_tags'] = df_scenes['merged_tags'].apply(find_stash_tags)\n",
+    "\n",
+    "# Step 8: Select relevant columns\n",
+    "df_selected = df_scenes[['id', 'title', 'details', 'date', 'existing_tags', 'stashdb_tags', 'merged_tags', 'tags_identical', 'stash_tags']]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Update tags for scenes where tags are not identical\n",
+    "for index, row in df_selected.iterrows():\n",
+    "    if not row['tags_identical'] and row['stash_tags']:\n",
+    "        stash.update_scene({\n",
+    "            \"id\": row['id'],\n",
+    "            \"tag_ids\": [tag['id'] for tag in row['stash_tags'] if tag]\n",
+    "        })"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "name_of_my_env",
+   "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": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}