Skip to content

removing the unwanted name spaces and correcting the software number #167

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Mazztok45 merged 1 commit into from
Feb 11, 2025
Merged

removing the unwanted name spaces and correcting the software number #167

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 5 additions & 4 deletions src/swmath2swh/staging_deposit_v2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,7 @@
from swmath2swh.restApi_software_Json import process_metadata
from swmath2swh.convertSoftware_from_json_toXml import convert_json_to_xml

import defusedxml.ElementTree as DET # Using defusedxml for safe XML parsing
from defusedxml.lxml import fromstring
import lxml.etree as ET
import pandas as pd
import subprocess
import time
import tempfile
Expand All @@ -15,7 +13,7 @@
env['SWMATH_USER_DEPOSIT'] = os.getenv('SWMATH_USER_DEPOSIT')
env['SWMATH_PWD_DEPOSIT'] = os.getenv('SWMATH_PWD_DEPOSIT')

xsl_filename = '../xslt/software/xslt_SWH_deposit.xslt'
xsl_filename = '../../xslt/software/xslt_SWH_deposit.xslt'

# Fetch XML data
r = requests.get("https://oai.portal.mardi4nfdi.de/oai/OAIHandler?verb=GetRecord&metadataPrefix=codemeta&identifier=oai:swmath.org:4532")
Expand All @@ -34,8 +32,11 @@
transform = ET.XSLT(xslt)
newdom = transform(lxml_dom)
formatted_newdom = ET.tostring(newdom, pretty_print=True, encoding='unicode')
formatted_newdom = re.sub(r'xmlns:xsi="[^"]+"', '', formatted_newdom)
formatted_newdom = re.sub(r'xmlns:ns\d+="[^"]+"', '', formatted_newdom)
formatted_newdom = re.sub(r'ns\d+:', 'codemeta:', formatted_newdom)
formatted_newdom = re.sub(r'<\s*([^>]+?)\s*>', r'<\1>', formatted_newdom)
formatted_newdom = re.sub(r'<\s*/\s*([^>]+?)\s*>', r'</\1>', formatted_newdom)
print(formatted_newdom)

# Write transformed XML to a temporary file
Expand Down