added convert_to_html

Signed-off-by: Peter Staar <[email protected]>
DS4SD · Jun 6, 2024 · 4857504 · 4857504
1 parent dcbbf00
commit 4857504
Show file tree

Hide file tree

Showing 3 changed files with 61 additions and 15 deletions.
diff --git a/examples/document_conversion_quick_start/convert_documents.ipynb b/examples/document_conversion_quick_start/convert_documents.ipynb
@@ -30,10 +30,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "id": "b01a4fd1",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Project key:  1234567890abcdefghijklmnopqrstvwyz123456\n"
+     ]
+    }
+   ],
    "source": [
     "from dsnotebooks.settings import ProjectNotebookSettings\n",
     "\n",
@@ -56,7 +64,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "id": "502cdef8",
    "metadata": {
     "ExecuteTime": {
@@ -72,7 +80,7 @@
     "from pathlib import Path\n",
     "from zipfile import ZipFile\n",
     "\n",
-    "from deepsearch.documents.core.export import export_to_markdown\n",
+    "from deepsearch.documents.core.export import export_to_markdown, export_to_html\n",
     "from IPython.display import display, Markdown, HTML, display_html"
    ]
   },
@@ -86,7 +94,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "id": "f44fbf08",
    "metadata": {},
    "outputs": [],
@@ -96,15 +104,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "ec83eb0b",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2022-08-02T12:14:49.216045Z",
      "start_time": "2022-08-02T12:14:25.380757Z"
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Processing input:     : 100%|\u001b[38;2;15;98;254m██████████████████████████████\u001b[0m| 1/1 [00:00<00:00, 39.65it/s]\u001b[38;2;15;98;254m                                                                                                                                                                                                                                                                                 \u001b[0m\n",
+      "Submitting input:     : 100%|\u001b[38;2;15;98;254m██████████████████████████████\u001b[0m| 1/1 [00:04<00:00,  4.48s/it]\u001b[38;2;15;98;254m                                                                                                                                                                                                                                                                                 \u001b[0m\n",
+      "Converting input:     : 100%|\u001b[38;2;15;98;254m██████████████████████████████\u001b[0m| 1/1 [00:36<00:00, 36.90s/it]\u001b[38;2;15;98;254m                                                                                                                                                                                                                                                                                 \u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'Total documents': 1, 'Successfully converted documents': 1}\n"
+     ]
+    }
+   ],
    "source": [
     "output_dir = Path(\"./converted_docs\")\n",
     "\n",
@@ -121,10 +146,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "382c4869-cca9-43fc-8052-c0ab7e9c175d",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "writing converted_docs/2206.01062.md\n",
+      "writing converted_docs/2206.01062.html\n"
+     ]
+    }
+   ],
    "source": [
     "# Iterare output files and visualize the output\n",
     "for output_file in output_dir.rglob(\"json*.zip\"):\n",
@@ -136,13 +170,23 @@
     "\n",
     "            basename = name.rstrip(\".json\")\n",
     "            doc_json = json.loads(archive.read(f\"{basename}.json\"))\n",
+    "            \n",
     "            doc_md = export_to_markdown(doc_json)\n",
     "\n",
     "            ofile = output_dir / f\"{basename}.md\"\n",
+    "            print(f\"writing {ofile}\")\n",
+    "            \n",
     "            with ofile.open(\"w\") as fw:\n",
     "                fw.write(doc_md)\n",
     "\n",
-    "            print(f\"writing {ofile}\")"
+    "            doc_html = export_to_html(doc_json)\n",
+    "\n",
+    "            ofile = output_dir / f\"{basename}.html\"\n",
+    "            print(f\"writing {ofile}\")\n",
+    "            \n",
+    "            with ofile.open(\"w\") as fw:\n",
+    "                fw.write(doc_html)\n",
+    "            "
    ]
   },
   {

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -11,7 +11,7 @@ packages = [
 
 [tool.poetry.dependencies]
 python = ">= 3.8, <3.11"
-deepsearch-toolkit = "^0.46.0"
+deepsearch-toolkit = "0.47.0"
 jupyter = "^1.0.0"
 ipywidgets = "^7"  # previous major release is needed bcause of mols2grid
 numpy = "^1.23.4"