diff options
author | Bryan Newbold <bnewbold@archive.org> | 2021-10-21 14:00:31 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2021-10-21 14:00:31 -0700 |
commit | e1679f1044b94d9ec2a9d3b67c8e12581e2f313c (patch) | |
tree | 8294dfcf3de91580b425ed58e3d04a329a00f401 /grobid_tei_xml | |
parent | 45870aa17b5dec6d63df8b7a2eb7839feac9afec (diff) | |
download | grobid_tei_xml-e1679f1044b94d9ec2a9d3b67c8e12581e2f313c.tar.gz grobid_tei_xml-e1679f1044b94d9ec2a9d3b67c8e12581e2f313c.zip |
get tests to start passing
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 |