From 212b21bf5dfc904f83658326fa8c6e7377f9edc2 Mon Sep 17 00:00:00 2001
From: Christian Boulanger <boulanger@lhlt.mpg.de>
Date: Mon, 30 Sep 2024 11:59:56 +0200
Subject: [PATCH] Improve output for GS generation
---
.../tei-to-biblstruct-gs.ipynb | 29 +++++++------------
1 file changed, 10 insertions(+), 19 deletions(-)
diff --git a/convert-anystyle-data/tei-to-biblstruct-gs.ipynb b/convert-anystyle-data/tei-to-biblstruct-gs.ipynb
index 1c4eabf..e7545cd 100644
--- a/convert-anystyle-data/tei-to-biblstruct-gs.ipynb
+++ b/convert-anystyle-data/tei-to-biblstruct-gs.ipynb
@@ -95,12 +95,12 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 10,
"outputs": [
{
"data": {
"text/plain": "<IPython.core.display.Markdown object>",
- "text/markdown": "### Processing 10.1111_1467-6478.00057\n - [TEI/bibl](tei-bibl-corrected\\10.1111_1467-6478.00057.xml)\n - [TEI/biblStruct](tei-biblStruct/10.1111_1467-6478.00057.biblstruct.xml)"
+ "text/markdown": "### Processing 10.1111_1467-6478.00057\n - [TEI/bibl](tei-bibl-corrected/10.1111_1467-6478.00057.xml)\n - [TEI/biblStruct](tei-biblStruct/10.1111_1467-6478.00057.biblstruct.xml)"
},
"metadata": {},
"output_type": "display_data"
@@ -116,7 +116,7 @@
{
"data": {
"text/plain": "<IPython.core.display.Markdown object>",
- "text/markdown": "### Processing 10.1111_1467-6478.00080\n - [TEI/bibl](tei-bibl-corrected\\10.1111_1467-6478.00080.xml)\n - [TEI/biblStruct](tei-biblStruct/10.1111_1467-6478.00080.biblstruct.xml)"
+ "text/markdown": "### Processing 10.1111_1467-6478.00080\n - [TEI/bibl](tei-bibl-corrected/10.1111_1467-6478.00080.xml)\n - [TEI/biblStruct](tei-biblStruct/10.1111_1467-6478.00080.biblstruct.xml)"
},
"metadata": {},
"output_type": "display_data"
@@ -132,7 +132,7 @@
{
"data": {
"text/plain": "<IPython.core.display.Markdown object>",
- "text/markdown": "### Processing 10.1515_zfrs-1980-0103\n - [TEI/bibl](tei-bibl-corrected\\10.1515_zfrs-1980-0103.xml)\n - [TEI/biblStruct](tei-biblStruct/10.1515_zfrs-1980-0103.biblstruct.xml)"
+ "text/markdown": "### Processing 10.1515_zfrs-1980-0103\n - [TEI/bibl](tei-bibl-corrected/10.1515_zfrs-1980-0103.xml)\n - [TEI/biblStruct](tei-biblStruct/10.1515_zfrs-1980-0103.biblstruct.xml)"
},
"metadata": {},
"output_type": "display_data"
@@ -148,7 +148,7 @@
{
"data": {
"text/plain": "<IPython.core.display.Markdown object>",
- "text/markdown": "### Processing 10.1515_zfrs-1980-0104\n - [TEI/bibl](tei-bibl-corrected\\10.1515_zfrs-1980-0104.xml)\n - [TEI/biblStruct](tei-biblStruct/10.1515_zfrs-1980-0104.biblstruct.xml)"
+ "text/markdown": "### Processing 10.1515_zfrs-1980-0104\n - [TEI/bibl](tei-bibl-corrected/10.1515_zfrs-1980-0104.xml)\n - [TEI/biblStruct](tei-biblStruct/10.1515_zfrs-1980-0104.biblstruct.xml)"
},
"metadata": {},
"output_type": "display_data"
@@ -169,6 +169,7 @@
"from copy import deepcopy\n",
"from lib.string import remove_whitespace\n",
"from IPython.display import display, Markdown\n",
+ "from pathlib import Path\n",
"\n",
"def remove_encoding_declaration(xml_string):\n",
" return xml_string.replace('<?xml version=\"1.0\" encoding=\"UTF-8\"?>', '')\n",
@@ -261,8 +262,8 @@
"\n",
" # log\n",
" md_lines = [f'### Processing {file_id}']\n",
- " md_lines.append(f' - [TEI/bibl]({bibl_path})')\n",
- " md_lines.append(f' - [TEI/biblStruct]({biblstruct_path})')\n",
+ " md_lines.append(f' - [TEI/bibl]({Path(bibl_path).as_posix()})')\n",
+ " md_lines.append(f' - [TEI/biblStruct]({Path(biblstruct_path).as_posix()})')\n",
" display(Markdown(\"\\n\".join(md_lines)))\n",
"\n",
" with (open(bibl_path, 'r', encoding='utf-8') as bibl_file, \n",
@@ -281,21 +282,11 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
- "end_time": "2024-09-30T09:49:31.520651200Z",
- "start_time": "2024-09-30T09:49:30.856013600Z"
+ "end_time": "2024-09-30T09:59:48.158571300Z",
+ "start_time": "2024-09-30T09:59:47.826852300Z"
}
},
"id": "b658a0ceebfc73d9"
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "outputs": [],
- "source": [],
- "metadata": {
- "collapsed": false
- },
- "id": "6db741d584bcac88"
}
],
"metadata": {
--
GitLab