From 2182fae8fed235b266bf0c01ec0c289447ea86c3 Mon Sep 17 00:00:00 2001
From: Christian Boulanger <boulanger@lhlt.mpg.de>
Date: Mon, 30 Sep 2024 09:14:42 +0200
Subject: [PATCH] Publish diff files on gitlab pages
---
convert-anystyle-data/anystyle-to-tei.ipynb | 52 ++++++++++++++-------
1 file changed, 35 insertions(+), 17 deletions(-)
diff --git a/convert-anystyle-data/anystyle-to-tei.ipynb b/convert-anystyle-data/anystyle-to-tei.ipynb
index 37af644..049c9ce 100644
--- a/convert-anystyle-data/anystyle-to-tei.ipynb
+++ b/convert-anystyle-data/anystyle-to-tei.ipynb
@@ -690,8 +690,8 @@
{
"metadata": {
"ExecuteTime": {
- "end_time": "2024-09-30T07:07:29.730Z",
- "start_time": "2024-09-30T07:07:29.371437300Z"
+ "end_time": "2024-09-30T07:14:09.985435200Z",
+ "start_time": "2024-09-30T07:14:09.618955100Z"
}
},
"cell_type": "code",
@@ -728,7 +728,7 @@
"for input_path in glob.glob('tei-bibl-corrected/*.xml'):\n",
" base_name = os.path.basename(input_path)\n",
" id = os.path.splitext(base_name)[0]\n",
- " print(f'Extracting and comparing input data for {id} ...')\n",
+ " \n",
" with open(input_path, 'r', encoding='utf-8') as f:\n",
" tei_input_data = tei_to_ground_truth_input(f.read())\n",
" anystyle_input_path = f'refs/{id}.txt'\n",
@@ -738,27 +738,45 @@
" html_diff = HtmlDiff().make_file(anystyle_input_data, tei_input_data)\n",
" with open(f\"../public/convert-anystyle-data/diffs/{id}.diff.html\", \"w\", encoding=\"utf-8\") as f:\n",
" f.write(html_diff)\n",
- " print(f' View diff at https://experiments-boulanger-27b5c1c5c975b0350675064f0f85580e618945eef.pages.gwdg.de/convert-anystyle-data/diffs/{id}.diff.html')\n",
+ " display(HTML(f'<p>Extracted and compared input data for {id} (<a href=\"https://experiments-boulanger-27b5c1c5c975b0350675064f0f85580e618945eef.pages.gwdg.de/convert-anystyle-data/diffs/{id}.diff.html\" target=_blank>See diff</a>)'))\n",
" "
],
"id": "4c19609699dc79c",
"outputs": [
{
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Extracting and comparing input data for 10.1111_1467-6478.00057 ...\n",
- " View diff at https://experiments-boulanger-27b5c1c5c975b0350675064f0f85580e618945eef.pages.gwdg.de/convert-anystyle-data/diffs/10.1111_1467-6478.00057.diff.html\n",
- "Extracting and comparing input data for 10.1111_1467-6478.00080 ...\n",
- " View diff at https://experiments-boulanger-27b5c1c5c975b0350675064f0f85580e618945eef.pages.gwdg.de/convert-anystyle-data/diffs/10.1111_1467-6478.00080.diff.html\n",
- "Extracting and comparing input data for 10.1515_zfrs-1980-0103 ...\n",
- " View diff at https://experiments-boulanger-27b5c1c5c975b0350675064f0f85580e618945eef.pages.gwdg.de/convert-anystyle-data/diffs/10.1515_zfrs-1980-0103.diff.html\n",
- "Extracting and comparing input data for 10.1515_zfrs-1980-0104 ...\n",
- " View diff at https://experiments-boulanger-27b5c1c5c975b0350675064f0f85580e618945eef.pages.gwdg.de/convert-anystyle-data/diffs/10.1515_zfrs-1980-0104.diff.html\n"
- ]
+ "data": {
+ "text/plain": "<IPython.core.display.HTML object>",
+ "text/html": "<p>Extracted and compared input data for 10.1111_1467-6478.00057 (<a href=\"https://experiments-boulanger-27b5c1c5c975b0350675064f0f85580e618945eef.pages.gwdg.de/convert-anystyle-data/diffs/10.1111_1467-6478.00057.diff.html\" target=_blank>See diff</a>)"
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/plain": "<IPython.core.display.HTML object>",
+ "text/html": "<p>Extracted and compared input data for 10.1111_1467-6478.00080 (<a href=\"https://experiments-boulanger-27b5c1c5c975b0350675064f0f85580e618945eef.pages.gwdg.de/convert-anystyle-data/diffs/10.1111_1467-6478.00080.diff.html\" target=_blank>See diff</a>)"
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/plain": "<IPython.core.display.HTML object>",
+ "text/html": "<p>Extracted and compared input data for 10.1515_zfrs-1980-0103 (<a href=\"https://experiments-boulanger-27b5c1c5c975b0350675064f0f85580e618945eef.pages.gwdg.de/convert-anystyle-data/diffs/10.1515_zfrs-1980-0103.diff.html\" target=_blank>See diff</a>)"
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/plain": "<IPython.core.display.HTML object>",
+ "text/html": "<p>Extracted and compared input data for 10.1515_zfrs-1980-0104 (<a href=\"https://experiments-boulanger-27b5c1c5c975b0350675064f0f85580e618945eef.pages.gwdg.de/convert-anystyle-data/diffs/10.1515_zfrs-1980-0104.diff.html\" target=_blank>See diff</a>)"
+ },
+ "metadata": {},
+ "output_type": "display_data"
}
],
- "execution_count": 2
+ "execution_count": 4
},
{
"metadata": {},
--
GitLab