summaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/importers/common.py
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@robocracy.org>2019-01-08 16:28:27 -0800
committerBryan Newbold <bnewbold@robocracy.org>2019-01-08 16:28:27 -0800
commit16f2e78298dbd2231f5f337ea17c89a6a131a052 (patch)
tree6e72581e625e73c97cbab72d0f9c35665c99e5d7 /python/fatcat_tools/importers/common.py
parenteb40a5f274f3608db34309cfd16739a7642ef5e7 (diff)
parentffb721f90c5d97ee80885209bf45feb85ca9625c (diff)
downloadfatcat-16f2e78298dbd2231f5f337ea17c89a6a131a052.tar.gz
fatcat-16f2e78298dbd2231f5f337ea17c89a6a131a052.zip
Merge branch 'bnewbold-crude-auth'
Fixed a conflict in: python/fatcat_export.py
Diffstat (limited to 'python/fatcat_tools/importers/common.py')
-rw-r--r--python/fatcat_tools/importers/common.py36
1 files changed, 24 insertions, 12 deletions
diff --git a/python/fatcat_tools/importers/common.py b/python/fatcat_tools/importers/common.py
index e31cabf8..e39ec6c9 100644
--- a/python/fatcat_tools/importers/common.py
+++ b/python/fatcat_tools/importers/common.py
@@ -4,6 +4,7 @@ import sys
import csv
import json
import itertools
+import subprocess
from collections import Counter
import pykafka
@@ -37,19 +38,33 @@ class FatcatImporter:
Base class for fatcat importers
"""
- def __init__(self, host_url, issn_map_file=None):
- conf = fatcat_client.Configuration()
- conf.host = host_url
- self.api = fatcat_client.DefaultApi(fatcat_client.ApiClient(conf))
+ def __init__(self, api, **kwargs):
+
+ eg_extra = kwargs.get('editgroup_extra', dict())
+ eg_extra['git_rev'] = eg_extra.get('git_rev',
+ subprocess.check_output(["git", "describe", "--always"]).strip()).decode('utf-8')
+ eg_extra['agent'] = eg_extra.get('agent', 'fatcat_tools.FatcatImporter')
+
+ self.api = api
+ self._editgroup_description = kwargs.get('editgroup_description')
+ self._editgroup_extra = kwargs.get('editgroup_extra')
+ issn_map_file = kwargs.get('issn_map_file')
+
self._issnl_id_map = dict()
self._orcid_id_map = dict()
self._doi_id_map = dict()
- self._issn_issnl_map = None
- self._orcid_regex = re.compile("^\\d{4}-\\d{4}-\\d{4}-\\d{3}[\\dX]$")
if issn_map_file:
self.read_issn_map_file(issn_map_file)
+ self._orcid_regex = re.compile("^\\d{4}-\\d{4}-\\d{4}-\\d{3}[\\dX]$")
self.counts = Counter({'insert': 0, 'update': 0, 'processed_lines': 0})
+ def _editgroup(self):
+ eg = fatcat_client.Editgroup(
+ description=self._editgroup_description,
+ extra=self._editgroup_extra,
+ )
+ return self.api.create_editgroup(eg)
+
def describe_run(self):
print("Processed {} lines, inserted {}, updated {}.".format(
self.counts['processed_lines'], self.counts['insert'], self.counts['update']))
@@ -64,15 +79,13 @@ class FatcatImporter:
def process_source(self, source, group_size=100):
"""Creates and auto-accepts editgroup every group_size rows"""
- eg = self.api.create_editgroup(
- fatcat_client.Editgroup(editor_id='aaaaaaaaaaaabkvkaaaaaaaaae'))
+ eg = self._editgroup()
i = 0
for i, row in enumerate(source):
self.create_row(row, editgroup_id=eg.editgroup_id)
if i > 0 and (i % group_size) == 0:
self.api.accept_editgroup(eg.editgroup_id)
- eg = self.api.create_editgroup(
- fatcat_client.Editgroup(editor_id='aaaaaaaaaaaabkvkaaaaaaaaae'))
+ eg = self._editgroup()
self.counts['processed_lines'] += 1
if i == 0 or (i % group_size) != 0:
self.api.accept_editgroup(eg.editgroup_id)
@@ -83,8 +96,7 @@ class FatcatImporter:
if decode_kafka:
rows = [msg.value.decode('utf-8') for msg in rows]
self.counts['processed_lines'] += len(rows)
- eg = self.api.create_editgroup(
- fatcat_client.Editgroup(editor_id='aaaaaaaaaaaabkvkaaaaaaaaae'))
+ eg = self._editgroup()
self.create_batch(rows, editgroup_id=eg.editgroup_id)
def process_csv_source(self, source, group_size=100, delimiter=','):