diff options
author | Bryan Newbold <bnewbold@archive.org> | 2021-10-27 19:10:35 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2021-10-27 19:10:35 -0700 |
commit | a0e275a4bad46ef41585f0207d6dfa1e3c38bc35 (patch) | |
tree | 92dead8a85e6ff38808beefada8a42693261ceff /python/sandcrawler/persist.py | |
parent | 40adf5ed09d917b8a4b8f75680bbf90c147848b3 (diff) | |
download | sandcrawler-a0e275a4bad46ef41585f0207d6dfa1e3c38bc35.tar.gz sandcrawler-a0e275a4bad46ef41585f0207d6dfa1e3c38bc35.zip |
remove grobid2json helper file, replace with grobid_tei_xml
Diffstat (limited to 'python/sandcrawler/persist.py')
-rw-r--r-- | python/sandcrawler/persist.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/python/sandcrawler/persist.py b/python/sandcrawler/persist.py index c8c0c33..f50b9d1 100644 --- a/python/sandcrawler/persist.py +++ b/python/sandcrawler/persist.py @@ -395,7 +395,7 @@ class PersistGrobidWorker(SandcrawlerWorker): ) self.counts["s3-put"] += 1 - # enhance with teixml2json metadata, if available + # enhance with GROBID TEI-XML metadata, if available try: metadata = self.grobid.metadata(r) except xml.etree.ElementTree.ParseError as xml_e: |