aboutsummaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools
diff options
context:
space:
mode:
Diffstat (limited to 'python/fatcat_tools')
-rw-r--r--python/fatcat_tools/harvest/harvest_common.py4
-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
4 files changed, 9 insertions, 9 deletions
diff --git a/python/fatcat_tools/harvest/harvest_common.py b/python/fatcat_tools/harvest/harvest_common.py
index 310366bd..5f7aa084 100644
--- a/python/fatcat_tools/harvest/harvest_common.py
+++ b/python/fatcat_tools/harvest/harvest_common.py
@@ -133,7 +133,7 @@ class HarvestState:
def fail_fast(err, msg):
if err:
raise KafkaException(err)
- print("Commiting status to Kafka: {}".format(kafka_topic), file=sys.stderr)
+ print("Committing status to Kafka: {}".format(kafka_topic), file=sys.stderr)
producer_conf = kafka_config.copy()
producer_conf.update({
'delivery.report.only.error': True,
@@ -164,7 +164,7 @@ class HarvestState:
raise KafkaException(err)
conf = kafka_config.copy()
conf.update({
- 'group.id': 'dummy_init_group', # should never be commited
+ 'group.id': 'dummy_init_group', # should never be committed
'enable.auto.commit': False,
'auto.offset.reset': 'earliest',
'session.timeout.ms': 10000,
diff --git a/python/fatcat_tools/importers/common.py b/python/fatcat_tools/importers/common.py
index a84ce90f..694ef359 100644
--- a/python/fatcat_tools/importers/common.py
+++ b/python/fatcat_tools/importers/common.py
@@ -751,7 +751,7 @@ 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 d8abf3eb..18703a1a 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:*
@@ -180,7 +180,7 @@ 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 4e382348..9250fc5e 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 = {
@@ -227,7 +227,7 @@ 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,
@@ -577,7 +577,7 @@ 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',