Author filter with initials

Author: Morgan Fouesneau

docs/MPIA daily digest.ipynb

@@ -69,44 +69,6 @@
     "warnings.simplefilter('always', AffiliationWarning)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "14622700",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# additional CSS to consider. \n",
-    "# TODO: Current into each exported file. \n",
-    "#       This should be set once into the webpages directly.\n",
-    "#       With only the class/id definitions in the .md files.\n",
-    "\n",
-    "debug_html = \"\"\"\n",
-    "<style>\n",
-    "#wrap{ overflow:auto; }\n",
-    "#fig1{ background:yellow; width:100%; float:left; padding:5px;  }\n",
-    "#fig2{ background:red; width:50%; float:left; clear:left; padding:5px;  }\n",
-    "#fig3{ background:green; width:50%; float:left; padding:5px;   }\n",
-    ".macros{ background:yellow; visibility:visible;}\n",
-    "h1 {margin: 0 0 0 0;}\n",
-    "mark {background-color:#fff3b6;}\n",
-    "img {object-fit:contain; max-height:250px; display:inline-block; text-align: center;}\n",
-    "</style>\n",
-    "\"\"\" \n",
-    "html = \"\"\"\n",
-    "<style>\n",
-    "#wrap{ overflow:auto; }\n",
-    "#fig1{ width:100%; float:left; padding: 5px;  }\n",
-    "#fig2{ width:50%; float:left; clear:left; padding: 5px;  }\n",
-    "#fig3{ width:50%; float:left; padding: 5px;  }\n",
-    ".macros{ visibility:hidden; height:0px; }\n",
-    "h1 {margin: 0em 0 0 0;}\n",
-    "mark {background-color:#fff3b6;}\n",
-    "img {object-fit:contain; max-height:250px; display:inline-block; text-align: center;}\n",
-    "</style>\n",
-    "\"\"\""
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "14bd6310",
@@ -128,20 +90,21 @@
     "# get list from MPIA website\n",
     "# it automatically filters identified non-scientists :func:`mpia.filter_non_scientists`\n",
     "mpia_authors = mpia.get_mpia_mitarbeiter_list()\n",
+    "normed_mpia_authors = [k[1] for k in mpia_authors]   # initials + fullname\n",
     "new_papers = get_new_papers()\n",
     "# add manual references\n",
     "add_paper_refs = []\n",
     "new_papers.extend([get_paper_from_identifier(k) for k in add_paper_refs])\n",
     "\n",
-    "# select only papers with matching author names and highlight authors\n",
-    "hl_list = [k[0] for k in mpia_authors]\n",
-    "\n",
     "candidates = []\n",
     "for paperk in new_papers:\n",
-    "    hl_authors = highlight_authors_in_list(paperk['authors'], hl_list)\n",
+    "    # Check author list with their initials\n",
+    "    normed_author_list = [mpia.get_initials(k) for k in paperk['authors']]\n",
+    "    hl_authors = highlight_authors_in_list(normed_author_list, normed_mpia_authors, verbose=True)\n",
     "    matches = [(hl, orig) for hl, orig in zip(hl_authors, paperk['authors']) if 'mark' in hl]\n",
     "    paperk['authors'] = hl_authors\n",
     "    if matches:\n",
+    "        # only select paper if an author matched our list\n",
     "        candidates.append(paperk)\n",
     "print(\"\"\"Arxiv has {0:,d} new papers today\"\"\".format(len(new_papers)))        \n",
     "print(\"\"\"          {0:,d} with possible author matches\"\"\".format(len(candidates)))"
@@ -201,7 +164,10 @@
     "        doc.comment = (get_markdown_badge(paper_id) + \n",
     "                       \"<mark>Appeared on: \" + paper['date'] + \"</mark> - \" +\n",
     "                       \"_\" + paper['comments'] + \"_\")\n",
-    "        doc.highlight_authors_in_list(hl_list)\n",
+    "        # highlight authors (FIXME: doc.highlight_authors)\n",
+    "        doc._authors = highlight_authors_in_list(\n",
+    "            [mpia.get_initials(k) for k in doc.authors], \n",
+    "            normed_mpia_authors, verbose=True)\n",
     "\n",
     "        full_md = doc.generate_markdown_text()\n",
     "        \n",
@@ -373,18 +339,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "cf665672",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "184  publications files modified in the last 7 days.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from datetime import datetime, timedelta, timezone\n",
     "from glob import glob\n",
@@ -408,18 +366,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "015de740",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "3  publications in the last 7 days.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import datetime\n",
     "from glob import glob\n",
@@ -462,7 +412,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "52ca0208",
    "metadata": {
     "scrolled": false
@@ -495,7 +445,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "a6eac5b6",
    "metadata": {
     "scrolled": false
@@ -519,18 +469,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "id": "adc1a1ec",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "1  publications in the last day.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# redo for today\n",
     "days = 1\n",
@@ -557,20 +499,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": null,
    "id": "00eece82",
    "metadata": {
     "scrolled": false
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "6  6 publications selected.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# Create the flat grid of the last N papers (fixed number regardless of dates)\n",
     "from itertools import islice \n",
@@ -598,7 +532,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": null,
    "id": "cab45692",
    "metadata": {},
    "outputs": [],
@@ -629,7 +563,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.10.10"
   },
   "vscode": {
    "interpreter": {