From 73b9c55a72c586e0a6d22bd5bf9912aedce02b4e Mon Sep 17 00:00:00 2001
From: daxid <david.rouquet@tetras-libre.fr>
Date: Mon, 14 Apr 2025 15:16:42 +0200
Subject: [PATCH] fix infoboxes by putting html instead of md
---
tetras_extraction/script/src/transform.py | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/tetras_extraction/script/src/transform.py b/tetras_extraction/script/src/transform.py
index 9c87403..92a774e 100644
--- a/tetras_extraction/script/src/transform.py
+++ b/tetras_extraction/script/src/transform.py
@@ -2,6 +2,7 @@ from rdflib import OWL, RDF, Graph, Literal
from lxml import html
#import pandoc
from markitdown import MarkItDown
+from markdown import markdown
import tempfile
import re
from glob import glob
@@ -48,6 +49,7 @@ def markFileDown(filepath):
def prepareHTMLforMD(str):
+ str = str.replace("\r"," ")
# Identify audio content and add markups to identify them in the MD
regexAV = re.compile(r".*?PF_clipAV\('.*?', '(.*?).swf',.*")
str = regexAV.sub(r"@AUDIOSTART\1@AUDIOEND", str)
@@ -106,8 +108,8 @@ def postEditMD(str1):
try:
file = open(filepath, 'r', encoding='utf-8')
file.close()
- md = markFileDown(filepath)
- commentaireInfo_md = '<div class="commentaireInfo" commentaireId="'+str(i)+'">'+md+'</div>'
+ simpleHtml = markdown(markFileDown(filepath))
+ commentaireInfo_md = '<div class="commentaireInfo" commentaireId="'+str(i)+'">'+simpleHtml+'</div>'
str1 = str1.replace(match,str(i))
except FileNotFoundError:
pass
--
GitLab