done parsing

Princeton-CDH · Sep 19, 2023 · e5baa13 · e5baa13
1 parent 047c333
commit e5baa13
Showing 1 changed file with 79 additions and 7 deletions.
diff --git a/notebooks/001_unpack_ecco.ipynb b/notebooks/001_unpack_ecco.ipynb
@@ -640,7 +640,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 22,
    "id": "a13f27c6-9e95-45da-a9a1-64e928f53f19",
    "metadata": {},
    "outputs": [],
@@ -653,7 +653,10 @@
     "        if not text_id in cache:\n",
     "            paths = textid2paths[text_id]\n",
     "            cache[text_id] = parse_pages(paths)\n",
-    "\n"
+    "\n",
+    "def get_parsed_pages(text_id):\n",
+    "    with get_page_cache() as cache:\n",
+    "        return cache.get(text_id,{})"
    ]
   },
   {
@@ -712,26 +715,95 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 21,
    "id": "69c2b974-dca9-4d71-8e6e-c756a09dfa94",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "# parse_all_pages()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "8378462f-a774-472f-9ea9-bac02cb4dc25",
+   "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
-      "  1%|▎                           | 595/52686 [00:08<11:47, 73.64it/s]"
+      "3.46 ms ± 403 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
      ]
     }
    ],
    "source": [
-    "parse_all_pages()"
+    "%%timeit\n",
+    "eg_id=random.choice(text_ids)\n",
+    "get_parsed_pages(eg_id)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7b37ee7b-9ca3-44d3-8335-43508c467005",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "44c4e55c-b627-4655-9317-ad22304eced1",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "6e7028dd-6fd2-4308-838f-2b1275f58d67",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_parsed_page(text_id, page_id):\n",
+    "    try:\n",
+    "        with get_page_cache() as cache:\n",
+    "            return cache[text_id][page_id]\n",
+    "    except KeyError:\n",
+    "        return {}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "3612193f-feab-4348-a560-949c243a826c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'pageid': '00010',\n",
+       " 'assetid': '3328704639',\n",
+       " 'ocrlanguage': 'English',\n",
+       " 'ocr': 90.0,\n",
+       " 'imagelink': '157030013400010.TIF',\n",
+       " 'text': '\\n\\t\\t\\tTH E: WORKS OF M. DE VO LTAIR E. Vo L. XXXIV. Being Vo L. XXIV. of his PROSE WORKS.\\n\\t\\t'}"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "get_parsed_page(eg_id,'00010')"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ca862887-2503-4e98-80bf-358921246a9a",
+   "id": "f0f390be-cc56-4253-8068-880b11285f42",
    "metadata": {},
    "outputs": [],
    "source": []