From 552bc5d4a3573d727bbb9d8f1c559d2c3c2474d4 Mon Sep 17 00:00:00 2001
From: Marina D'Amato <marinadamato.md@gmail.com>
Date: Tue, 7 Nov 2023 20:08:32 +0100
Subject: [PATCH] Added code to merge bibfiles

---
 scripts/MergeChanges.ipynb | 196 +++++++++++++++++++++++++++++++++++++
 1 file changed, 196 insertions(+)
 create mode 100644 scripts/MergeChanges.ipynb

diff --git a/scripts/MergeChanges.ipynb b/scripts/MergeChanges.ipynb
new file mode 100644
index 0000000..71a82db
--- /dev/null
+++ b/scripts/MergeChanges.ipynb
@@ -0,0 +1,196 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d377a755",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import os\n",
+    "from bib_handling_code.processbib import read_bibfile\n",
+    "from bib_handling_code.processbib import save_to_file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f6cf2984",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def from_bib_to_csv(diag_bib_raw):\n",
+    "    bib_data = []\n",
+    "    bib_columns = ['bibkey', 'type', 'title', 'authors', 'doi', 'gs_citations', 'journal', 'year', 'all_ss_ids', 'pmid']\n",
+    "    \n",
+    "    for bib_entry in diag_bib_raw:\n",
+    "        if bib_entry.type == 'string':\n",
+    "            continue\n",
+    "\n",
+    "        bibkey = bib_entry.key\n",
+    "        bib_type = bib_entry.type\n",
+    "        fields = bib_entry.fields\n",
+    "        \n",
+    "        bib_authors = fields.get('author', '').strip('{}')\n",
+    "        bib_title = fields.get('title', '').strip('{}')\n",
+    "        bib_doi = fields.get('doi', '').strip('{}')\n",
+    "        bib_gscites = fields.get('gscites', '').strip('{}')\n",
+    "        bib_journal = fields.get('journal', '').strip('{}')\n",
+    "        bib_year = fields.get('year', '').strip('{}')\n",
+    "        bib_all_ss_ids = fields.get('all_ss_ids', '').strip('{}')\n",
+    "        bib_pmid = fields.get('pmid', '').strip('{}')\n",
+    "        \n",
+    "        bib_data.append([bibkey, bib_type, bib_title, bib_authors, bib_doi, bib_gscites, bib_journal, bib_year, bib_all_ss_ids, bib_pmid])\n",
+    "\n",
+    "    df_bib_data = pd.DataFrame(bib_data, columns=bib_columns)\n",
+    "    return df_bib_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5b5596e1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_diag_bib = os.path.join('..', 'diag.bib')\n",
+    "diag_bib_raw = read_bibfile(None, path_diag_bib)\n",
+    "bibfile = from_bib_to_csv(diag_bib_raw)\n",
+    "path_new_bib = os.path.join('script_data/', 'diag_ss_new.bib')\n",
+    "updated_bib_raw = read_bibfile(None, path_new_bib)\n",
+    "newbibfile = from_bib_to_csv(updated_bib_raw)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "98489bba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new_bibkeys = newbibfile['bibkey'].tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2374dcc9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "old_bibkeys = bibfile['bibkey'].tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f38e2c4c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_entry(bibfile, bibkey_toupdate):\n",
+    "    for entry in bibfile:\n",
+    "        bibkey = entry.key\n",
+    "        if bibkey == bibkey_toupdate:\n",
+    "            return entry"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "366debbe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Update existing bibitems\n",
+    "for entry in diag_bib_raw:\n",
+    "    if entry.type == 'string':\n",
+    "        continue\n",
+    "    bibkey = entry.key\n",
+    "    if bibkey in new_bibkeys:\n",
+    "        corresponding_entry = get_entry(updated_bib_raw, bibkey)\n",
+    "        if 'all_ss_ids' in corresponding_entry.fields:\n",
+    "            entry.fields['all_ss_ids'] = corresponding_entry.fields['all_ss_ids']\n",
+    "        if 'pmid' in corresponding_entry.fields:\n",
+    "            entry.fields['pmid'] = corresponding_entry.fields['pmid']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "21522e57",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bibkeys_toadd = set(new_bibkeys)-set(old_bibkeys)\n",
+    "df_to_add = newbibfile[newbibfile['bibkey'].isin(bibkeys_toadd)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3c023620",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bibkeys_toadd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "82d6aeeb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for entry in updated_bib_raw:\n",
+    "    bibkey = entry.key\n",
+    "    if bibkey in bibkeys_toadd:\n",
+    "        diag_bib_raw.append(entry)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6224df11",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "csv=from_bib_to_csv(diag_bib_raw)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cf941ddf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path_diag_bib = os.path.join('..', 'diag_latest_try.bib')\n",
+    "save_to_file(diag_bib_raw, path_diag_bib)"
+   ]
+  }
+ ],
+ "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": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}