From 7ebda2e051b51e49544ab75673b19ec5f27d9d45 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@robocracy.org>
Date: Mon, 12 Nov 2018 23:37:28 -0800
Subject: more python module refactoring

---
 python/fatcat_export.py                         |   2 +-
 python/fatcat_import.py                         |  10 +--
 python/fatcat_tools/changelog_workers.py        |   2 +-
 python/fatcat_tools/crossref_importer.py        |   2 +-
 python/fatcat_tools/elastic_workers.py          |   4 +-
 python/fatcat_tools/entity_helpers.py           | 100 ------------------------
 python/fatcat_tools/grobid_metadata_importer.py |   2 +-
 python/fatcat_tools/issn_importer.py            |   2 +-
 python/fatcat_tools/matched_importer.py         |   2 +-
 python/fatcat_tools/orcid_importer.py           |   2 +-
 python/fatcat_tools/transforms.py               | 100 ++++++++++++++++++++++++
 python/fatcat_worker.py                         |   4 +-
 python/tests/crossref.py                        |   2 +-
 python/tests/entity_helpers.py                  |  15 ----
 python/tests/fixtures.py                        |   8 +-
 python/tests/grobid_metadata_importer.py        |  56 -------------
 python/tests/grobid_metadata_importer_test.py   |  56 +++++++++++++
 python/tests/importer.py                        |   2 +-
 python/tests/issn.py                            |   2 +-
 python/tests/matched_importer.py                |  32 --------
 python/tests/matched_importer_test.py           |  32 ++++++++
 python/tests/orcid.py                           |   2 +-
 python/tests/routes.py                          |   1 -
 python/tests/transform_tests.py                 |  15 ++++
 24 files changed, 227 insertions(+), 228 deletions(-)
 delete mode 100644 python/fatcat_tools/entity_helpers.py
 create mode 100644 python/fatcat_tools/transforms.py
 delete mode 100644 python/tests/entity_helpers.py
 delete mode 100644 python/tests/grobid_metadata_importer.py
 create mode 100644 python/tests/grobid_metadata_importer_test.py
 delete mode 100644 python/tests/matched_importer.py
 create mode 100644 python/tests/matched_importer_test.py
 create mode 100644 python/tests/transform_tests.py

diff --git a/python/fatcat_export.py b/python/fatcat_export.py
index 6c4502af..eadf69ab 100755
--- a/python/fatcat_export.py
+++ b/python/fatcat_export.py
@@ -5,7 +5,7 @@ import json
 import argparse
 import fatcat_client
 from fatcat_client.rest import ApiException
-from fatcat.fcid import uuid2fcid
+from fatcat_tools.fcid import uuid2fcid
 
 def run_export_releases(args):
     conf = fatcat_client.Configuration()
diff --git a/python/fatcat_import.py b/python/fatcat_import.py
index c5610344..6c66d98a 100755
--- a/python/fatcat_import.py
+++ b/python/fatcat_import.py
@@ -2,11 +2,11 @@
 
 import sys
 import argparse
-from fatcat.crossref_importer import FatcatCrossrefImporter
-from fatcat.orcid_importer import FatcatOrcidImporter
-from fatcat.issn_importer import FatcatIssnImporter
-from fatcat.matched_importer import FatcatMatchedImporter
-from fatcat.grobid_metadata_importer import FatcatGrobidMetadataImporter
+from fatcat_tools.crossref_importer import FatcatCrossrefImporter
+from fatcat_tools.orcid_importer import FatcatOrcidImporter
+from fatcat_tools.issn_importer import FatcatIssnImporter
+from fatcat_tools.matched_importer import FatcatMatchedImporter
+from fatcat_tools.grobid_metadata_importer import FatcatGrobidMetadataImporter
 
 def run_import_crossref(args):
     fci = FatcatCrossrefImporter(args.host_url, args.issn_map_file,
diff --git a/python/fatcat_tools/changelog_workers.py b/python/fatcat_tools/changelog_workers.py
index e341ea32..223d4478 100644
--- a/python/fatcat_tools/changelog_workers.py
+++ b/python/fatcat_tools/changelog_workers.py
@@ -2,7 +2,7 @@
 import json
 import time
 from itertools import islice
-from fatcat.worker_common import FatcatWorker
+from fatcat_tools.worker_common import FatcatWorker
 from pykafka.common import OffsetType
 
 
diff --git a/python/fatcat_tools/crossref_importer.py b/python/fatcat_tools/crossref_importer.py
index 37005965..6a5ad824 100644
--- a/python/fatcat_tools/crossref_importer.py
+++ b/python/fatcat_tools/crossref_importer.py
@@ -5,7 +5,7 @@ import sqlite3
 import datetime
 import itertools
 import fatcat_client
-from fatcat.importer_common import FatcatImporter
+from fatcat_tools.importer_common import FatcatImporter
 
 
 class FatcatCrossrefImporter(FatcatImporter):
diff --git a/python/fatcat_tools/elastic_workers.py b/python/fatcat_tools/elastic_workers.py
index 3d2e9c39..eac8d6b0 100644
--- a/python/fatcat_tools/elastic_workers.py
+++ b/python/fatcat_tools/elastic_workers.py
@@ -2,9 +2,9 @@
 import json
 import time
 import requests
-from fatcat.worker_common import FatcatWorker
+from fatcat_tools.worker_common import FatcatWorker
 from fatcat_client.models import ReleaseEntity
-from fatcat.entity_helpers import *
+from fatcat_tools.transforms import *
 from pykafka.common import OffsetType
 
 
diff --git a/python/fatcat_tools/entity_helpers.py b/python/fatcat_tools/entity_helpers.py
deleted file mode 100644
index c454536b..00000000
--- a/python/fatcat_tools/entity_helpers.py
+++ /dev/null
@@ -1,100 +0,0 @@
-
-import collections
-from fatcat_client.models import ReleaseEntity
-from fatcat_client.api_client import ApiClient
-
-def entity_to_json(entity):
-    ac = ApiClient()
-    return ac.sanitize_for_serialization(entity)
-
-def entity_from_json(json_str, entity_type):
-    """
-    Hack to take advantage of the code-generated deserialization code
-    """
-    ac = ApiClient()
-    thing = collections.namedtuple('Thing', ['data'])
-    thing.data = json_str
-    return ac.deserialize(thing, entity_type)
-
-def release_elastic_dict(release):
-    """
-    Converts from an entity model/schema to elasticsearch oriented schema.
-
-    Returns: dict
-    """
-
-    if release.state != 'active':
-        raise ValueError("Entity is not 'active'")
-
-    # First, the easy ones (direct copy)
-    t = dict(
-        ident = release.ident,
-        revision = release.revision,
-        title = release.title,
-        release_type = release.release_type,
-        release_status = release.release_status,
-        language = release.language,
-        doi = release.doi,
-        pmid = release.pmid,
-        pmcid = release.pmcid,
-        isbn13 = release.isbn13,
-        core_id = release.core_id,
-        wikidata_qid = release.wikidata_qid
-    )
-
-    if release.release_date:
-        # TODO: resolve why this can be either a string or datetime
-        if type(release.release_date) == str:
-            t['release_date'] = release.release_date
-        else:
-            t['release_date'] = release.release_date.strftime('%F')
-
-    container = release.container
-    container_is_kept = False
-    if container:
-        t['publisher'] = container.publisher
-        t['container_name'] = container.name
-        t['container_issnl'] = container.issnl
-        container_extra = container.extra
-        if container_extra:
-            t['container_is_oa'] = container_extra.get('is_oa')
-            container_is_kept = container_extra.get('is_kept', False)
-            t['container_is_longtail_oa'] = container_extra.get('is_longtail_oa')
-    else:
-        t['publisher'] = release.publisher
-
-    files = release.files or []
-    t['file_count'] = len(files)
-    in_wa = False
-    in_ia = False
-    t['file_pdf_url'] = None
-    for f in files:
-        is_pdf = 'pdf' in f.get('mimetype', '')
-        for url in f.get('urls', []):
-            if url.get('rel', '') == 'webarchive':
-                in_wa = True
-            if '//web.archive.org/' in url['url'] or '//archive.org/' in url['url']:
-                in_ia = True
-                if is_pdf:
-                    t['file_pdf_url'] = url['url']
-            if not t['file_pdf_url'] and is_pdf:
-                t['file_pdf_url'] = url['url']
-    t['file_in_webarchive'] = in_wa
-    t['file_in_ia'] = in_ia
-
-    extra = release.extra or dict()
-    if extra:
-        t['in_shadow'] = extra.get('in_shadow')
-        if extra.get('grobid') and extra['grobid'].get('is_longtail_oa'):
-            t['container_is_longtail_oa'] = True
-    t['any_abstract'] = bool(release.abstracts)
-    t['is_kept'] = container_is_kept or extra.get('is_kept', False)
-
-    t['ref_count'] = len(release.refs or [])
-    t['contrib_count'] = len(release.contribs or [])
-    contrib_names = []
-    for c in (release.contribs or []):
-        if c.raw_name:
-            contrib_names.append(c.raw_name)
-    t['contrib_names'] = contrib_names
-    return t
diff --git a/python/fatcat_tools/grobid_metadata_importer.py b/python/fatcat_tools/grobid_metadata_importer.py
index 95cc285e..effa0d94 100755
--- a/python/fatcat_tools/grobid_metadata_importer.py
+++ b/python/fatcat_tools/grobid_metadata_importer.py
@@ -5,7 +5,7 @@ import json
 import base64
 import datetime
 import fatcat_client
-from fatcat.importer_common import FatcatImporter
+from fatcat_tools.importer_common import FatcatImporter
 
 MAX_ABSTRACT_BYTES=4096
 
diff --git a/python/fatcat_tools/issn_importer.py b/python/fatcat_tools/issn_importer.py
index c9ef50b5..e3ed7382 100644
--- a/python/fatcat_tools/issn_importer.py
+++ b/python/fatcat_tools/issn_importer.py
@@ -3,7 +3,7 @@ import sys
 import json
 import itertools
 import fatcat_client
-from fatcat.importer_common import FatcatImporter
+from fatcat_tools.importer_common import FatcatImporter
 
 # CSV format (generated from git.archive.org/webgroup/oa-journal-analysis):
 # ISSN-L,in_doaj,in_road,in_norwegian,in_crossref,title,publisher,url,lang,ISSN-print,ISSN-electronic,doi_count,has_doi,is_oa,is_kept,publisher_size,url_live,url_live_status,url_live_final_status,url_live_final_url,url_live_status_simple,url_live_final_status_simple,url_domain,gwb_pdf_count
diff --git a/python/fatcat_tools/matched_importer.py b/python/fatcat_tools/matched_importer.py
index 7f55369b..627ab6f1 100644
--- a/python/fatcat_tools/matched_importer.py
+++ b/python/fatcat_tools/matched_importer.py
@@ -4,7 +4,7 @@ import json
 import sqlite3
 import itertools
 import fatcat_client
-from fatcat.importer_common import FatcatImporter
+from fatcat_tools.importer_common import FatcatImporter
 
 #row = row.split('\t')
 #assert len(row) == 2
diff --git a/python/fatcat_tools/orcid_importer.py b/python/fatcat_tools/orcid_importer.py
index e1f5943c..f2366c66 100644
--- a/python/fatcat_tools/orcid_importer.py
+++ b/python/fatcat_tools/orcid_importer.py
@@ -3,7 +3,7 @@ import sys
 import json
 import itertools
 import fatcat_client
-from fatcat.importer_common import FatcatImporter
+from fatcat_tools.importer_common import FatcatImporter
 
 def value_or_none(e):
     if type(e) == dict:
diff --git a/python/fatcat_tools/transforms.py b/python/fatcat_tools/transforms.py
new file mode 100644
index 00000000..c454536b
--- /dev/null
+++ b/python/fatcat_tools/transforms.py
@@ -0,0 +1,100 @@
+
+import collections
+from fatcat_client.models import ReleaseEntity
+from fatcat_client.api_client import ApiClient
+
+def entity_to_json(entity):
+    ac = ApiClient()
+    return ac.sanitize_for_serialization(entity)
+
+def entity_from_json(json_str, entity_type):
+    """
+    Hack to take advantage of the code-generated deserialization code
+    """
+    ac = ApiClient()
+    thing = collections.namedtuple('Thing', ['data'])
+    thing.data = json_str
+    return ac.deserialize(thing, entity_type)
+
+def release_elastic_dict(release):
+    """
+    Converts from an entity model/schema to elasticsearch oriented schema.
+
+    Returns: dict
+    """
+
+    if release.state != 'active':
+        raise ValueError("Entity is not 'active'")
+
+    # First, the easy ones (direct copy)
+    t = dict(
+        ident = release.ident,
+        revision = release.revision,
+        title = release.title,
+        release_type = release.release_type,
+        release_status = release.release_status,
+        language = release.language,
+        doi = release.doi,
+        pmid = release.pmid,
+        pmcid = release.pmcid,
+        isbn13 = release.isbn13,
+        core_id = release.core_id,
+        wikidata_qid = release.wikidata_qid
+    )
+
+    if release.release_date:
+        # TODO: resolve why this can be either a string or datetime
+        if type(release.release_date) == str:
+            t['release_date'] = release.release_date
+        else:
+            t['release_date'] = release.release_date.strftime('%F')
+
+    container = release.container
+    container_is_kept = False
+    if container:
+        t['publisher'] = container.publisher
+        t['container_name'] = container.name
+        t['container_issnl'] = container.issnl
+        container_extra = container.extra
+        if container_extra:
+            t['container_is_oa'] = container_extra.get('is_oa')
+            container_is_kept = container_extra.get('is_kept', False)
+            t['container_is_longtail_oa'] = container_extra.get('is_longtail_oa')
+    else:
+        t['publisher'] = release.publisher
+
+    files = release.files or []
+    t['file_count'] = len(files)
+    in_wa = False
+    in_ia = False
+    t['file_pdf_url'] = None
+    for f in files:
+        is_pdf = 'pdf' in f.get('mimetype', '')
+        for url in f.get('urls', []):
+            if url.get('rel', '') == 'webarchive':
+                in_wa = True
+            if '//web.archive.org/' in url['url'] or '//archive.org/' in url['url']:
+                in_ia = True
+                if is_pdf:
+                    t['file_pdf_url'] = url['url']
+            if not t['file_pdf_url'] and is_pdf:
+                t['file_pdf_url'] = url['url']
+    t['file_in_webarchive'] = in_wa
+    t['file_in_ia'] = in_ia
+
+    extra = release.extra or dict()
+    if extra:
+        t['in_shadow'] = extra.get('in_shadow')
+        if extra.get('grobid') and extra['grobid'].get('is_longtail_oa'):
+            t['container_is_longtail_oa'] = True
+    t['any_abstract'] = bool(release.abstracts)
+    t['is_kept'] = container_is_kept or extra.get('is_kept', False)
+
+    t['ref_count'] = len(release.refs or [])
+    t['contrib_count'] = len(release.contribs or [])
+    contrib_names = []
+    for c in (release.contribs or []):
+        if c.raw_name:
+            contrib_names.append(c.raw_name)
+    t['contrib_names'] = contrib_names
+    return t
diff --git a/python/fatcat_worker.py b/python/fatcat_worker.py
index 50ff0fb7..5d3731f6 100755
--- a/python/fatcat_worker.py
+++ b/python/fatcat_worker.py
@@ -2,8 +2,8 @@
 
 import sys
 import argparse
-from fatcat.changelog_workers import FatcatChangelogWorker, FatcatEntityUpdatesWorker
-from fatcat.elastic_workers import FatcatElasticReleaseWorker
+from fatcat_tools.changelog_workers import FatcatChangelogWorker, FatcatEntityUpdatesWorker
+from fatcat_tools.elastic_workers import FatcatElasticReleaseWorker
 
 def run_changelog_worker(args):
     topic = "fatcat-{}.changelog".format(args.env)
diff --git a/python/tests/crossref.py b/python/tests/crossref.py
index 59be9886..04ac5e8e 100644
--- a/python/tests/crossref.py
+++ b/python/tests/crossref.py
@@ -1,7 +1,7 @@
 
 import json
 import pytest
-from fatcat.crossref_importer import FatcatCrossrefImporter
+from fatcat_tools.crossref_importer import FatcatCrossrefImporter
 
 
 @pytest.fixture(scope="function")
diff --git a/python/tests/entity_helpers.py b/python/tests/entity_helpers.py
deleted file mode 100644
index dd6fa00a..00000000
--- a/python/tests/entity_helpers.py
+++ /dev/null
@@ -1,15 +0,0 @@
-
-import json
-import pytest
-from fatcat.crossref_importer import FatcatCrossrefImporter
-from fatcat.entity_helpers import *
-
-from crossref import crossref_importer
-
-def test_elastic_convert(crossref_importer):
-    with open('tests/files/crossref-works.single.json', 'r') as f:
-        # not a single line
-        raw = json.loads(f.read())
-        (r, c) = crossref_importer.parse_crossref_dict(raw)
-    r.state = 'active'
-    release_elastic_dict(r)
diff --git a/python/tests/fixtures.py b/python/tests/fixtures.py
index 6ff05495..6f68cf5c 100644
--- a/python/tests/fixtures.py
+++ b/python/tests/fixtures.py
@@ -4,14 +4,14 @@ import time
 import json
 import signal
 import pytest
-import fatcat
+import fatcat_web
 
 
 @pytest.fixture
 def full_app():
-    fatcat.app.testing = True
-    fatcat.app.debug = False
-    return fatcat.app
+    fatcat_web.app.testing = True
+    fatcat_web.app.debug = False
+    return fatcat_web.app
 
 @pytest.fixture
 def app(full_app):
diff --git a/python/tests/grobid_metadata_importer.py b/python/tests/grobid_metadata_importer.py
deleted file mode 100644
index 2c8565aa..00000000
--- a/python/tests/grobid_metadata_importer.py
+++ /dev/null
@@ -1,56 +0,0 @@
-
-import os
-import json
-import base64
-import pytest
-from fatcat.grobid_metadata_importer import FatcatGrobidMetadataImporter
-
-"""
-WARNING: these tests are currently very fragile because they have database
-side-effects. Should probably be disabled or re-written.
-"""
-
-@pytest.fixture(scope="function")
-def grobid_metadata_importer():
-    yield FatcatGrobidMetadataImporter("http://localhost:9411/v0")
-
-# TODO: use API to check that entities actually created...
-#def test_grobid_metadata_importer_batch(grobid_metadata_importer):
-#    with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
-#        grobid_metadata_importer.process_batch(f)
-
-def test_grobid_metadata_parse(grobid_metadata_importer):
-    with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
-        raw = json.loads(f.readline().split('\t')[4])
-        re = grobid_metadata_importer.parse_grobid_json(raw)
-        assert re
-        assert re.title == "PEMBELAJARAN FISIKA DENGAN PENDEKATAN KETERAMPILAN PROSES MELALUI METODE DEMONSTRASI MENGGUNAKAN MEDIA RIIL DAN MEDIA VIRTUIL DITINJAU DARI MOTIVASI DAN GAYA BERFIKIR SISWA"
-        assert len(re.contribs) == 5
-        print(re.contribs)
-        assert re.contribs[0].raw_name == "Wahyu Ary"
-        assert re.publisher == None
-        assert re.extra.get('container_name') == None
-        assert len(re.refs) == 27
-
-def test_file_metadata_parse(grobid_metadata_importer):
-    with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
-        f.readline()
-        raw = f.readline().split('\t')
-        # randomize sha1 so tests are repeatable
-        random_sha1 = "sha1:{}".format(base64.b32encode(os.urandom(20)).decode('utf-8').upper())
-        fe = grobid_metadata_importer.parse_file_metadata(
-            random_sha1, json.loads(raw[1]), raw[2], int(raw[3]))
-        assert fe
-        #assert fe.sha1 == "d4a841744719518bf8bdd5d91576ccedc55efbb5" # "sha1:2SUEC5CHDFIYX6F52XMRK5WM5XCV565V"
-        assert fe.md5 == None
-        assert fe.mimetype == "application/pdf"
-        assert fe.size == 142710
-        assert fe.urls[1].url.startswith("http://via.library.depaul.edu")
-        assert fe.urls[1].rel == "web"
-        assert fe.urls[0].url.startswith("https://web.archive.org/")
-        assert fe.urls[0].rel == "webarchive"
-        assert len(fe.releases) == 0
-
-def test_grobid_metadata_importer(grobid_metadata_importer):
-    with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
-        grobid_metadata_importer.process_source(f)
diff --git a/python/tests/grobid_metadata_importer_test.py b/python/tests/grobid_metadata_importer_test.py
new file mode 100644
index 00000000..502ca74a
--- /dev/null
+++ b/python/tests/grobid_metadata_importer_test.py
@@ -0,0 +1,56 @@
+
+import os
+import json
+import base64
+import pytest
+from fatcat_tools.grobid_metadata_importer import FatcatGrobidMetadataImporter
+
+"""
+WARNING: these tests are currently very fragile because they have database
+side-effects. Should probably be disabled or re-written.
+"""
+
+@pytest.fixture(scope="function")
+def grobid_metadata_importer():
+    yield FatcatGrobidMetadataImporter("http://localhost:9411/v0")
+
+# TODO: use API to check that entities actually created...
+#def test_grobid_metadata_importer_batch(grobid_metadata_importer):
+#    with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
+#        grobid_metadata_importer.process_batch(f)
+
+def test_grobid_metadata_parse(grobid_metadata_importer):
+    with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
+        raw = json.loads(f.readline().split('\t')[4])
+        re = grobid_metadata_importer.parse_grobid_json(raw)
+        assert re
+        assert re.title == "PEMBELAJARAN FISIKA DENGAN PENDEKATAN KETERAMPILAN PROSES MELALUI METODE DEMONSTRASI MENGGUNAKAN MEDIA RIIL DAN MEDIA VIRTUIL DITINJAU DARI MOTIVASI DAN GAYA BERFIKIR SISWA"
+        assert len(re.contribs) == 5
+        print(re.contribs)
+        assert re.contribs[0].raw_name == "Wahyu Ary"
+        assert re.publisher == None
+        assert re.extra.get('container_name') == None
+        assert len(re.refs) == 27
+
+def test_file_metadata_parse(grobid_metadata_importer):
+    with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
+        f.readline()
+        raw = f.readline().split('\t')
+        # randomize sha1 so tests are repeatable
+        random_sha1 = "sha1:{}".format(base64.b32encode(os.urandom(20)).decode('utf-8').upper())
+        fe = grobid_metadata_importer.parse_file_metadata(
+            random_sha1, json.loads(raw[1]), raw[2], int(raw[3]))
+        assert fe
+        #assert fe.sha1 == "d4a841744719518bf8bdd5d91576ccedc55efbb5" # "sha1:2SUEC5CHDFIYX6F52XMRK5WM5XCV565V"
+        assert fe.md5 == None
+        assert fe.mimetype == "application/pdf"
+        assert fe.size == 142710
+        assert fe.urls[1].url.startswith("http://via.library.depaul.edu")
+        assert fe.urls[1].rel == "web"
+        assert fe.urls[0].url.startswith("https://web.archive.org/")
+        assert fe.urls[0].rel == "webarchive"
+        assert len(fe.releases) == 0
+
+def test_grobid_metadata_importer(grobid_metadata_importer):
+    with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
+        grobid_metadata_importer.process_source(f)
diff --git a/python/tests/importer.py b/python/tests/importer.py
index 22af37ed..0de86635 100644
--- a/python/tests/importer.py
+++ b/python/tests/importer.py
@@ -1,7 +1,7 @@
 
 
 import pytest
-from fatcat.importer_common import FatcatImporter
+from fatcat_tools.importer_common import FatcatImporter
 
 
 def test_issnl_mapping_lookup():
diff --git a/python/tests/issn.py b/python/tests/issn.py
index fff112f7..76c8aecb 100644
--- a/python/tests/issn.py
+++ b/python/tests/issn.py
@@ -1,6 +1,6 @@
 
 import pytest
-from fatcat.issn_importer import FatcatIssnImporter
+from fatcat_tools.issn_importer import FatcatIssnImporter
 
 
 @pytest.fixture(scope="function")
diff --git a/python/tests/matched_importer.py b/python/tests/matched_importer.py
deleted file mode 100644
index 9cc6aa32..00000000
--- a/python/tests/matched_importer.py
+++ /dev/null
@@ -1,32 +0,0 @@
-
-import json
-import pytest
-from fatcat.matched_importer import FatcatMatchedImporter
-
-
-@pytest.fixture(scope="function")
-def matched_importer():
-    yield FatcatMatchedImporter("http://localhost:9411/v0")
-
-# TODO: use API to check that entities actually created...
-def test_matched_importer_batch(matched_importer):
-    with open('tests/files/example_matched.json', 'r') as f:
-        matched_importer.process_batch(f)
-
-def test_matched_importer(matched_importer):
-    with open('tests/files/example_matched.json', 'r') as f:
-        matched_importer.process_source(f)
-
-def test_matched_dict_parse(matched_importer):
-    with open('tests/files/example_matched.json', 'r') as f:
-        raw = json.loads(f.readline())
-        f = matched_importer.parse_matched_dict(raw)
-        assert f.sha1 == "00242a192acc258bdfdb151943419437f440c313"
-        assert f.md5 == "f4de91152c7ab9fdc2a128f962faebff"
-        assert f.mimetype == "application/pdf"
-        assert f.size == 255629
-        assert f.urls[1].url.startswith("http://journals.plos.org")
-        assert f.urls[1].rel == "web"
-        assert f.urls[0].url.startswith("https://web.archive.org/")
-        assert f.urls[0].rel == "webarchive"
-        assert len(f.releases) == 1
diff --git a/python/tests/matched_importer_test.py b/python/tests/matched_importer_test.py
new file mode 100644
index 00000000..4042eabb
--- /dev/null
+++ b/python/tests/matched_importer_test.py
@@ -0,0 +1,32 @@
+
+import json
+import pytest
+from fatcat_tools.matched_importer import FatcatMatchedImporter
+
+
+@pytest.fixture(scope="function")
+def matched_importer():
+    yield FatcatMatchedImporter("http://localhost:9411/v0")
+
+# TODO: use API to check that entities actually created...
+def test_matched_importer_batch(matched_importer):
+    with open('tests/files/example_matched.json', 'r') as f:
+        matched_importer.process_batch(f)
+
+def test_matched_importer(matched_importer):
+    with open('tests/files/example_matched.json', 'r') as f:
+        matched_importer.process_source(f)
+
+def test_matched_dict_parse(matched_importer):
+    with open('tests/files/example_matched.json', 'r') as f:
+        raw = json.loads(f.readline())
+        f = matched_importer.parse_matched_dict(raw)
+        assert f.sha1 == "00242a192acc258bdfdb151943419437f440c313"
+        assert f.md5 == "f4de91152c7ab9fdc2a128f962faebff"
+        assert f.mimetype == "application/pdf"
+        assert f.size == 255629
+        assert f.urls[1].url.startswith("http://journals.plos.org")
+        assert f.urls[1].rel == "web"
+        assert f.urls[0].url.startswith("https://web.archive.org/")
+        assert f.urls[0].rel == "webarchive"
+        assert len(f.releases) == 1
diff --git a/python/tests/orcid.py b/python/tests/orcid.py
index ae3d0d0b..f8228cc0 100644
--- a/python/tests/orcid.py
+++ b/python/tests/orcid.py
@@ -1,7 +1,7 @@
 
 import json
 import pytest
-from fatcat.orcid_importer import FatcatOrcidImporter
+from fatcat_tools.orcid_importer import FatcatOrcidImporter
 
 
 @pytest.fixture(scope="function")
diff --git a/python/tests/routes.py b/python/tests/routes.py
index 8607e7c0..2e208d22 100644
--- a/python/tests/routes.py
+++ b/python/tests/routes.py
@@ -2,7 +2,6 @@
 import json
 import tempfile
 import pytest
-import fatcat
 from fatcat_client.rest import ApiException
 from fixtures import *
 
diff --git a/python/tests/transform_tests.py b/python/tests/transform_tests.py
new file mode 100644
index 00000000..669c2526
--- /dev/null
+++ b/python/tests/transform_tests.py
@@ -0,0 +1,15 @@
+
+import json
+import pytest
+from fatcat_tools.crossref_importer import FatcatCrossrefImporter
+from fatcat_tools.transforms import *
+
+from crossref import crossref_importer
+
+def test_elastic_convert(crossref_importer):
+    with open('tests/files/crossref-works.single.json', 'r') as f:
+        # not a single line
+        raw = json.loads(f.read())
+        (r, c) = crossref_importer.parse_crossref_dict(raw)
+    r.state = 'active'
+    release_elastic_dict(r)
-- 
cgit v1.2.3