summaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/importers/__init__.py
diff options
context:
space:
mode:
authorbnewbold <bnewbold@archive.org>2021-11-11 01:12:18 +0000
committerbnewbold <bnewbold@archive.org>2021-11-11 01:12:18 +0000
commit6ad9d24e4d7d901d6fc394e6e91575f6acba7ff4 (patch)
tree1b80344125152b46ae727dc8bbff73cc12abfd3e /python/fatcat_tools/importers/__init__.py
parent7e3f91f1a49ea85707cae31125021ba761f5373d (diff)
parent6eaf4f57c1f92b6f4f46adc38e5b39fd30b65d81 (diff)
downloadfatcat-6ad9d24e4d7d901d6fc394e6e91575f6acba7ff4.tar.gz
fatcat-6ad9d24e4d7d901d6fc394e6e91575f6acba7ff4.zip
Merge branch 'bnewbold-import-refactors' into 'master'
import refactors and deprecations Some of these are from old stale branches (the datacite subject metadata patch), but most are from yesterday and today. Sort of a hodge-podge, but the general theme is getting around to deferred cleanups and refactors specific to importer code before making some behavioral changes. The Datacite-specific stuff could use review here. Remove unused/deprecated/dead code: - cdl_dash_dat and wayback_static importers, which were for specific early example entities and have been superseded by other importers - "extid map" sqlite3 feature from several importers, was only used for initial bulk imports (and maybe should not have been used) Refactors: - moved a number of large datastructures out of importer code and into a dedicated static file (`biblio_lookup_tables.py`). Didn't move all, just the ones that were either generic or very large (making it hard to read code) - shuffled around relative imports and some function names ("clean_str" vs. "clean") Some actual behavioral changes: - remove some Datacite-specific license slugs - stop trying to fix double-slashes in DOIs, that was causing more harm than help (some DOIs do actually have double-slashes!) - remove some excess metadata from datacite 'extra' fields
Diffstat (limited to 'python/fatcat_tools/importers/__init__.py')
-rw-r--r--python/fatcat_tools/importers/__init__.py8
1 files changed, 1 insertions, 7 deletions
diff --git a/python/fatcat_tools/importers/__init__.py b/python/fatcat_tools/importers/__init__.py
index 06ecfd58..654be2e9 100644
--- a/python/fatcat_tools/importers/__init__.py
+++ b/python/fatcat_tools/importers/__init__.py
@@ -13,10 +13,8 @@ To run an import you combine two classes; one each of:
from .arabesque import ARABESQUE_MATCH_WHERE_CLAUSE, ArabesqueMatchImporter
from .arxiv import ArxivRawImporter
-from .cdl_dash_dat import auto_cdl_dash_dat
from .chocula import ChoculaImporter
from .common import (
- LANG_MAP_MARC,
Bs4XmlFileListPusher,
Bs4XmlFilePusher,
Bs4XmlLargeFilePusher,
@@ -28,11 +26,8 @@ from .common import (
KafkaJsonPusher,
LinePusher,
SqlitePusher,
- clean,
- is_cjk,
- make_kafka_consumer,
)
-from .crossref import CROSSREF_TYPE_MAP, CrossrefImporter, lookup_license_slug
+from .crossref import CrossrefImporter
from .datacite import DataciteImporter
from .dblp_container import DblpContainerImporter
from .dblp_release import DblpReleaseImporter
@@ -55,4 +50,3 @@ from .matched import MatchedImporter
from .orcid import OrcidImporter
from .pubmed import PubmedImporter
from .shadow import ShadowLibraryImporter
-from .wayback_static import auto_wayback_static