From 1c392ccaec8d6439f2691aeda12be4d2953a3f5e Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Wed, 10 Nov 2021 14:41:37 -0800
Subject: grobid: extract more metadata in document TEI-XML

---
 python/sandcrawler/grobid.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/python/sandcrawler/grobid.py b/python/sandcrawler/grobid.py
index f221830..791e0fe 100644
--- a/python/sandcrawler/grobid.py
+++ b/python/sandcrawler/grobid.py
@@ -95,9 +95,14 @@ class GrobidClient(object):
                 self.host_url + "/api/processFulltextDocument",
                 files={
                     "input": blob,
+                },
+                data={
                     "consolidateHeader": consolidate_mode,
                     "consolidateCitations": 0,  # too expensive for now
                     "includeRawCitations": 1,
+                    "includeRawAffiliations": 1,
+                    "teiCoordinates": ["ref", "figure", "persName", "formula", "biblStruct"],
+                    "segmentSentences": 1,
                 },
                 timeout=180.0,
             )
-- 
cgit v1.2.3