From 007f037de54792f0a0ff189521eee86006c47e4d Mon Sep 17 00:00:00 2001
From: Simon Mayer <simon.mayer@onb.ac.at>
Date: Thu, 12 Sep 2024 13:47:51 +0200
Subject: [PATCH] Add forced encoding for txt files while running the notebook
on Windows machines
---
OCR_samples.ipynb | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/OCR_samples.ipynb b/OCR_samples.ipynb
index 2c69ba2..7e7907e 100644
--- a/OCR_samples.ipynb
+++ b/OCR_samples.ipynb
@@ -29,7 +29,7 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 2,
"id": "195c1f7d-9056-40f7-86cb-835d9a5052a9",
"metadata": {},
"outputs": [],
@@ -148,7 +148,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 4,
"id": "1ac51927-4cba-457a-a8e9-9fd9d7b52f65",
"metadata": {},
"outputs": [
@@ -187,7 +187,7 @@
"\n",
"txtpaths = sorted(Path('data').glob('*1815*.txt'))\n",
"strpaths = list(filter(lambda x: 'new' not in x, [str(p) for p in txtpaths]))\n",
- "txts = [open(txt).read() for txt in strpaths]\n",
+ "txts = [open(txt, 'r', encoding='utf-8').read() for txt in strpaths]\n",
"txt_df = pd.DataFrame([txts], columns=strpaths)\n",
"pd.set_option(\"display.max_colwidth\", None)\n",
"display(HTML(txt_df.to_html().replace(\"\\\\n\",\"<br>\")))"
@@ -195,7 +195,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 5,
"id": "b9542753-a848-421e-81f3-65b07f3818b4",
"metadata": {},
"outputs": [
@@ -232,7 +232,7 @@
"source": [
"txtpaths = sorted(Path('data').glob('*1870*.txt'))\n",
"strpaths = list(filter(lambda x: 'new' not in x, [str(p) for p in txtpaths]))\n",
- "txts = [open(txt).read() for txt in strpaths]\n",
+ "txts = [open(txt, 'r', encoding='utf-8').read() for txt in strpaths]\n",
"txt_df = pd.DataFrame([txts], columns=strpaths)\n",
"pd.set_option(\"display.max_colwidth\", None)\n",
"display(HTML(txt_df.to_html().replace(\"\\\\n\",\"<br>\")))"
@@ -277,7 +277,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 6,
"id": "22f88237-22da-4fe1-8546-86ee4070f743",
"metadata": {},
"outputs": [
@@ -311,7 +311,7 @@
],
"source": [
"txtpaths = sorted(Path('data').glob('*new.txt'))\n",
- "txts = [open(txt).read() for txt in txtpaths]\n",
+ "txts = [open(txt, 'r', encoding='utf-8').read() for txt in txtpaths]\n",
"txt_df = pd.DataFrame([txts], columns=txtpaths)\n",
"pd.set_option(\"display.max_colwidth\", None)\n",
"display(HTML(txt_df.to_html().replace(\"\\\\n\",\"<br>\")))"
--
GitLab