INNER CODE UNIT · Python
normalize_content
grobidOrg/grobid · grobid-trainer/scripts/check_note_consistency.py:55
def normalize_content(content):
"""
Normalize content for better matching by removing extra whitespace and standardizing line breaks.
"""
# Replace multiple whitespace with single space
content = re.sub(r'\s+', ' ', content)
# Remove leading/trailing whitespace
content = content.strip()
return content
def check_file_consistency(xml_file_path, verbose=False):
"""
Check a single TEI file for internal consistency issues.
Returns list of inconsistencies found.
"""
headnotes, footnotes = extract_note_content(xml_file_path)
inconsistencies = []