INNER CODE UNIT · Python

evaluate_error_cases

grobidOrg/grobid · grobid-home/scripts/select_error_cases.py:106

def evaluate_error_cases(grobid_tei, jats_files, grobid_training=None, output=None):
    interesting_error_cases = []
    ns = {"tei": "http://www.tei-c.org/ns/1.0"}
    for root, directories, filenames in os.walk(grobid_tei):
        for filename in filenames: 
            if filename.endswith(".tei.xml"):
                tei_file = os.path.join(root, filename)
                jats_file = os.path.join(jats_files, filename.replace(".tei.xml", ""), filename.replace(".tei.xml", ".xml"))

                # apply some xpath on the files
                parser = ET.XMLParser(remove_comments=True)

                try:
                    tei_xml = ET.parse(tei_file, parser=parser)
                except:
                    #print("XML parsing error with", tei_file)
                    continue

View source record →