diff options
Diffstat (limited to 'grobid_tei_xml')
-rw-r--r-- | grobid_tei_xml/__init__.py | 0 | ||||
-rwxr-xr-x | grobid_tei_xml/grobid2json.py | 2 |
2 files changed, 1 insertions, 1 deletions
diff --git a/grobid_tei_xml/__init__.py b/grobid_tei_xml/__init__.py new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/grobid_tei_xml/__init__.py diff --git a/grobid_tei_xml/grobid2json.py b/grobid_tei_xml/grobid2json.py index 5c44953..ac0710c 100755 --- a/grobid_tei_xml/grobid2json.py +++ b/grobid_tei_xml/grobid2json.py @@ -45,7 +45,7 @@ def all_authors(elem: Optional[ET.Element], ns: str = ns) -> List[Dict[str, Any] continue given_name = pn.findtext("./{%s}forename" % ns) or None surname = pn.findtext("./{%s}surname" % ns) or None - full_name = " ".join(pn.itertext()) + full_name = " ".join([t.strip() for t in pn.itertext() if t.strip()]).strip() obj: Dict[str, Any] = dict(name=full_name) if given_name: obj["given_name"] = given_name |