aboutsummaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/importers
diff options
context:
space:
mode:
authorbnewbold <bnewbold@archive.org>2020-03-27 16:50:08 -0700
committerGitHub <noreply@github.com>2020-03-27 16:50:08 -0700
commit98abe2e751187aa7c2e751b355ffb56d9b1f8c6a (patch)
treef198efd4fcf070554bce164cd261de54d397cdfe /python/fatcat_tools/importers
parent5c4f5114b4dfeb7a5deca20d460c9fc5759a922a (diff)
parent94710b2803780ab16fb30b79010f8e27cf115512 (diff)
downloadfatcat-98abe2e751187aa7c2e751b355ffb56d9b1f8c6a.tar.gz
fatcat-98abe2e751187aa7c2e751b355ffb56d9b1f8c6a.zip
Merge pull request #53 from EdwardBetts/spelling
Correct spelling mistakes
Diffstat (limited to 'python/fatcat_tools/importers')
-rw-r--r--python/fatcat_tools/importers/common.py2
-rw-r--r--python/fatcat_tools/importers/crossref.py4
-rw-r--r--python/fatcat_tools/importers/datacite.py8
3 files changed, 7 insertions, 7 deletions
diff --git a/python/fatcat_tools/importers/common.py b/python/fatcat_tools/importers/common.py
index c000ad62..da611ecb 100644
--- a/python/fatcat_tools/importers/common.py
+++ b/python/fatcat_tools/importers/common.py
@@ -816,7 +816,7 @@ class KafkaJsonPusher(RecordPusher):
while True:
# Note: this is batch-oriented, because underlying importer is
# often batch-oriented, but this doesn't confirm that entire batch
- # has been pushed to fatcat before commiting offset. Eg, consider
+ # has been pushed to fatcat before committing offset. Eg, consider
# case where there there is one update and thousands of creates;
# update would be lingering in importer, and if importer crashed
# never created.
diff --git a/python/fatcat_tools/importers/crossref.py b/python/fatcat_tools/importers/crossref.py
index bd070ef1..9617299c 100644
--- a/python/fatcat_tools/importers/crossref.py
+++ b/python/fatcat_tools/importers/crossref.py
@@ -9,7 +9,7 @@ import fatcat_openapi_client
from .common import EntityImporter, clean
-# The docs/guide should be the cannonical home for these mappings; update there
+# The docs/guide should be the canonical home for these mappings; update there
# first
# Can get a list of Crossref types (with counts) via API:
# https://api.crossref.org/works?rows=0&facet=type-name:*
@@ -188,7 +188,7 @@ class CrossrefImporter(EntityImporter):
self.counts['skip-release-type'] += 1
return None
- # Do require the 'title' keys to exsit, as release entities do
+ # Do require the 'title' keys to exist, as release entities do
if (not 'title' in obj) or (not obj['title']):
self.counts['skip-blank-title'] += 1
return None
diff --git a/python/fatcat_tools/importers/datacite.py b/python/fatcat_tools/importers/datacite.py
index 5b736787..81f00876 100644
--- a/python/fatcat_tools/importers/datacite.py
+++ b/python/fatcat_tools/importers/datacite.py
@@ -3,7 +3,7 @@ Prototype importer for datacite.org data.
Example input document: https://api.datacite.org/dois/10.7916/d8-f93n-rk51
-Datacite being an aggregator, the data is heterogenous and exposes a couple of
+Datacite being an aggregator, the data is heterogeneous and exposes a couple of
problems in content and structure. A few fields have their own parsing
functions (parse_datacite_...), which may help testing.
"""
@@ -36,7 +36,7 @@ CONTAINER_TYPE_MAP = {
'Book Series': 'book-series',
}
-# The docs/guide should be the cannonical home for these mappings; update there
+# The docs/guide should be the canonical home for these mappings; update there
# first. Map various datacite type types to CSL-ish types. None means TODO or
# remove.
DATACITE_TYPE_MAP = {
@@ -228,7 +228,7 @@ class DataciteImporter(EntityImporter):
def lookup_ext_ids(self, doi):
"""
- Return dictionary of identifiers refering to the same things as the given DOI.
+ Return dictionary of identifiers referring to the same things as the given DOI.
"""
if self.extid_map_db is None:
return dict(core_id=None,
@@ -584,7 +584,7 @@ class DataciteImporter(EntityImporter):
# Include certain relations from relatedIdentifiers. Keeping the
# original structure of data here, which is a list of dicts, with
- # relation type, identifer and identifier type (mostly).
+ # relation type, identifier and identifier type (mostly).
relations = []
for rel in relIds:
if rel.get('relationType') in ('IsPartOf', 'Reviews', 'Continues',