Refactor unit tests using common py.test layout and fixtures

.gitignore

 *.pyc
+.cache
 /build
 /dist
 /mutalyzer.egg-info

.travis.yml

 # Validate this file using http://lint.travis-ci.org/
 language: python
+python: "2.7"
 addons:
   postgresql: "9.4"
-services:
-  - redis-server
-python:
-  - "2.7"
-env:
-  global:
-    - MUTALYZER_TEST_REDIS_URI=redis://localhost
-  matrix:
-    - MUTALYZER_TEST_DATABASE_URI=sqlite://
-    - MUTALYZER_TEST_DATABASE_URI=postgres://postgres@127.0.0.1/mutalyzer_test
-    - MUTALYZER_TEST_DATABASE_URI=mysql://travis@127.0.0.1/mutalyzer_test?charset=utf8
+services: redis-server
 before_install:
   - sudo apt-get update -qq
   - sudo apt-get install -y swig
   - pip install -r requirements.txt
-  - bash -c "if [[ '$MUTALYZER_TEST_DATABASE_URI' =~ 'postgres' ]]; then pip install psycopg2; fi"
-install:
-  - pip install .
+  - pip install psycopg2
+install: pip install .
 before_script:
-  - bash -c "if [[ '$MUTALYZER_TEST_DATABASE_URI' =~ 'postgres' ]]; then psql -c 'DROP DATABASE IF EXISTS mutalyzer_test;' -U postgres; fi"
-  - bash -c "if [[ '$MUTALYZER_TEST_DATABASE_URI' =~ 'postgres' ]]; then psql -c 'CREATE DATABASE mutalyzer_test;' -U postgres; fi"
-  - bash -c "if [[ '$MUTALYZER_TEST_DATABASE_URI' =~ 'mysql' ]]; then mysql -e 'CREATE DATABASE IF NOT EXISTS mutalyzer_test;'; fi"
-script:
-  - py.test
+  - psql -c 'DROP DATABASE IF EXISTS mutalyzer_test;' -U postgres
+  - psql -c 'CREATE DATABASE mutalyzer_test;' -U postgres
+  - mysql -e 'CREATE DATABASE IF NOT EXISTS mutalyzer_test;'
+script: py.test --redis-uri redis://localhost --database-uri sqlite:// --database-uri postgres://postgres@127.0.0.1/mutalyzer_test --database-uri mysql://travis@127.0.0.1/mutalyzer_test?charset=utf8

doc/testing.rst

@@ -16,23 +16,26 @@ the Mutalyzer source directory.
           tests.
 
 By default, the tests use an in-memory SQLite database. This can be customized
-by setting the `MUTALYZER_TEST_DATABASE_URI` to a valid `SQLAlchemy connection
-URI
+with the ``--database-uri` command line argument and a valid `SQLAlchemy
+connection URI
 <http://docs.sqlalchemy.org/en/rel_1_0/core/engines.html#database-urls>`_
 (obviously, the contents of this database will be lost). For example, to use
 an SQLite database on the filesystem::
 
-    $ MUTALYZER_TEST_DATABASE_URI=sqlite:////tmp/mutalyzer.sql py.test
+    $ py.test --database-uri sqlite:////tmp/mutalyzer.sql
 
 Or, using `pg_virtualenv
 <https://alioth.debian.org/scm/loggerhead/pkg-postgresql/postgresql-common/trunk/view/head:/pg_virtualenv>`_
 (included with the Debian PostgreSQL packages), to run the tests with
 PostgreSQL::
 
-    $ pg_virtualenv bash -c 'MUTALYZER_TEST_DATABASE_URI=postgres://${PGUSER}:${PGPASSWORD}@${PGHOST}:${PGPORT}/${PGDATABASE} py.test'
+    $ pg_virtualenv bash -c 'py.test --database-uri postgres://${PGUSER}:${PGPASSWORD}@${PGHOST}:${PGPORT}/${PGDATABASE}'
 
-Similarly, the `MUTALYZER_TEST_REDIS_URI` specifies a Redis server to use for
-testing. If unspecified, a mock Redis server is used.
+Multiple ``--database-uri`` arguments are allowed. Tests using the database
+will be run once for every database specified.
+
+Similarly, ``--redis-uri`` (only one allowed) specifies a Redis server to use
+for testing. If unspecified, a mock Redis server is used.
 
 Tests are `run automatically on Travis CI
 <https://travis-ci.org/mutalyzer/mutalyzer>`_ with SQLite, PostgreSQL, and

mutalyzer/db/__init__.py

@@ -30,6 +30,20 @@ def create_engine():
     """
     Create an SQLAlchemy connection engine from the current configuration.
     """
+    if not settings.DATABASE_URI:
+        # Just return silently when no database is configured (this function
+        # may still be called via the configuration settings hook). Of course
+        # actually using the database will fail.
+        return
+
+    # TODO: Remove when refactoring tests is complete. We should check that
+    # this is never reached with 'sqlite://' from the default_settings or with
+    # a value from MUTALYZER_SETTINGS during tests. The uri(s) configured in
+    # the tests should be used instead.
+    # This also makes sure that tests can never accidentally use the database
+    # without having it declared as a needed fixture.
+    print '!!!!!!!!!!!!! Creating session for', settings.DATABASE_URI
+
     url = make_url(settings.DATABASE_URI)
     options = {}
 

requirements.txt

@@ -3,6 +3,7 @@ description-extractor==2.2.1
 Flask==0.10.1
 Jinja2==2.7.3
 MySQL-python==1.2.5
+PyYAML==3.11
 SQLAlchemy==0.9.8
 Sphinx==1.2.3
 Werkzeug==0.9.6
@@ -14,7 +15,7 @@ lxml==3.4.0
 mock==1.0.1
 mockredispy==2.9.0.9
 pyparsing==2.0.3
-pytest==2.6.3
+pytest==2.8.2
 pytz==2014.7
 redis==2.10.3
 requests==2.4.3

tests/conftest.py

+"""
+Test configuration.
+"""
+
+
+from __future__ import unicode_literals
+
+from fixtures import *  # noqa
+
+
+DEFAULT_DATABASE_URIS = ['sqlite://']
+DEFAULT_REDIS_URI = None
+
+
+def pytest_addoption(parser):
+    parser.addoption(
+        '--database-uri', metavar='URI', dest='database_uris', default=[],
+        action='append',
+        help='Database connection, multiple allowed (default: in-memory '
+        'SQLite database)')
+    parser.addoption(
+        '--redis-uri', metavar='URI', dest='redis_uri',
+        default=DEFAULT_REDIS_URI,
+        help='Redis connection (default: mock Redis server)')
+
+
+def pytest_generate_tests(metafunc):
+    if 'database_uri' in metafunc.fixturenames:
+        metafunc.parametrize(
+            'database_uri',
+            metafunc.config.option.database_uris or DEFAULT_DATABASE_URIS)

tests/data/references.yml

+A1BG:
+  accession: UD_139015218717
+  checksum: e179de8b248806815394c4f7496ba872
+  filename: UD_139015218717.gb.bz2
+  links:
+  - - NM_001207009
+    - NP_001193938
+  - - NM_198458
+    - NP_940860
+  - - XM_005258578
+    - XP_005258635
+  - - XM_005258577
+    - XP_005258634
+  - - NR_015380
+    - null
+  - - NM_130786
+    - NP_570602
+  - - XM_005258393
+    - XP_005258450
+AA010203.1:
+  checksum: 57cee03becb77ce68a225b9c844afb24
+  filename: AA010203.1.gb.bz2
+  geninfo_id: '1471230'
+AB026906.1:
+  checksum: 29b003d5a71af74dc61a92d2ef5cd5d9
+  filename: AB026906.1.gb.bz2
+  geninfo_id: '5295993'
+AF230870.1:
+  checksum: 9fefa34f40d94910edb5de34a3f98910
+  filename: AF230870.1.gb.bz2
+  geninfo_id: '7739657'
+AL449423.14:
+  checksum: 00a014242818a3b003b4c077af9e10e0
+  filename: AL449423.14.gb.bz2
+  geninfo_id: '16944057'
+COL1A1:
+  accession: UD_139022298843
+  checksum: 815517e36fb380b52842ace6a6e78637
+  filename: UD_139022298843.gb.bz2
+  links:
+  - - XM_005257059
+    - XP_005257116
+  - - XM_005257058
+    - XP_005257115
+  - - NM_000088
+    - NP_000079
+DMD:
+  accession: UD_139262478721
+  checksum: d41d8cd98f00b204e9800998ecf8427e
+  filename: UD_139262478721.gb.bz2
+  links:
+  - - XM_006724469
+    - XP_006724532
+  - - XM_006724472
+    - XP_006724535
+  - - XM_006724473
+    - XP_006724536
+  - - XM_006724474
+    - XP_006724537
+  - - XM_006724475
+    - XP_006724538
+  - - XM_006724471
+    - XP_006724534
+  - - XM_006724470
+    - XP_006724533
+  - - XR_430491
+    - null
+  - - XM_006724468
+    - XP_006724531
+  - - XM_006724476
+    - XP_006724539
+  - - NM_000109
+    - NP_000100
+  - - NM_004006
+    - NP_003997
+  - - NM_004009
+    - NP_004000
+  - - NM_004010
+    - NP_004001
+  - - NM_004011
+    - NP_004002
+  - - NM_004012
+    - NP_004003
+  - - NM_004023
+    - NP_004014
+  - - NM_004020
+    - NP_004011
+  - - NM_004022
+    - NP_004013
+  - - NM_004021
+    - NP_004012
+  - - NM_004013
+    - NP_004004
+  - - NM_004014
+    - NP_004005
+  - - NM_004018
+    - NP_004009
+  - - NM_004017
+    - NP_004008
+  - - NM_004016
+    - NP_004007
+  - - NM_004015
+    - NP_004006
+  - - NM_004019
+    - NP_004010
+DPYD:
+  accession: UD_139015208095
+  checksum: b2b9d402a6e43f80ce1e9bbb72a3c0c6
+  filename: UD_139015208095.gb.bz2
+  links:
+  - - NR_046590
+    - null
+  - - XM_005270562
+    - XP_005270619
+  - - NM_000110
+    - NP_000101
+  - - XM_005270561
+    - XP_005270618
+  - - XM_005270563
+    - XP_005270620
+  - - XM_005270564
+    - XP_005270621
+  - - NM_001160301
+    - NP_001153773
+L41870.1:
+  checksum: 91b1e539a053f731f95d230a06710897
+  filename: L41870.1.gb.bz2
+  geninfo_id: '793994'
+LRG_1:
+  checksum: 5b8f5a39fcd9e3005688eddffd482746
+  filename: LRG_1.xml.bz2
+MARK1:
+  accession: UD_139015213982
+  checksum: 0d63a8fe5beddeb793940f6ae194b985
+  filename: UD_139015213982.gb.bz2
+  links:
+  - - NM_018650
+    - NP_061120
+  - - XM_005273133
+    - null
+  - - XM_005273134
+    - XP_005273191
+  - - XM_005273135
+    - null
+  - - XM_005273136
+    - null
+NG_008939.1:
+  checksum: 114a03e16ad2f63531d796c2fb0d7039
+  filename: NG_008939.1.gb.bz2
+  geninfo_id: '211938431'
+  links:
+  - - NM_000532
+    - NP_000523
+NG_009105.1:
+  checksum: f2579e6c4a8ead4566e485aad493ef7e
+  filename: NG_009105.1.gb.bz2
+  geninfo_id: '216548283'
+  links:
+  - - NM_020061
+    - NP_064445
+NG_012337.1:
+  checksum: ad712f4f225398d2b11b4f08110c70e6
+  filename: NG_012337.1.gb.bz2
+  geninfo_id: '254039638'
+  links:
+  - - NM_018195
+    - NP_060665
+  - - NM_001082969
+    - NP_001076438
+  - - NM_001082970
+    - NP_001076439
+  - - NM_003002
+    - NP_002993
+  - - NM_012459
+    - NP_036591
+NG_012772.1:
+  checksum: 163881f00c9c26516d52a4ddb34f941f
+  filename: NG_012772.1.gb.bz2
+  geninfo_id: '256574794'
+  links:
+  - - NM_052818
+    - NP_438169
+  - - NM_001079691
+    - NP_001073159
+  - - NM_000059
+    - NP_000050
+  - - NM_001136571
+    - NP_001130043
+NM_000059.3:
+  checksum: f93216b3a596adab279ebd7903258548
+  filename: NM_000059.3.gb.bz2
+  geninfo_id: '119395733'
+NM_000088.3:
+  checksum: 5d1f23e3c1799bdb5586c6786b5d5744
+  filename: NM_000088.3.gb.bz2
+  geninfo_id: '110349771'
+NM_000132.3:
+  checksum: 94569bee76d7c8b1168e17df4fe1dcb4
+  filename: NM_000132.3.gb.bz2
+  geninfo_id: '192448441'
+NM_000143.3:
+  checksum: c91799f40fdc0466bf7702af14cf070a
+  filename: NM_000143.3.gb.bz2
+  geninfo_id: '299758401'
+NM_000193.2:
+  checksum: 86d03e1cf38c1387d90116539ea0678f
+  filename: NM_000193.2.gb.bz2
+  geninfo_id: '21071042'
+NM_001199.3:
+  checksum: e750b6dcead66b8bb953ce445bcd3093
+  filename: NM_001199.3.gb.bz2
+NM_002001.2:
+  checksum: 7fd5aa4fe864fd5193f224fca8cea70d
+  filename: NM_002001.2.gb.bz2
+  geninfo_id: '31317229'
+NM_003002.2:
+  checksum: 990aa672364937335365609617df3050
+  filename: NM_003002.2.gb.bz2
+  geninfo_id: '222352156'
+NM_004006.1:
+  checksum: be8fea2905e146bfe096e25fbfda2eef
+  filename: NM_004006.1.gb.bz2
+  geninfo_id: '5032282'
+NM_004006.2:
+  checksum: ee2090536af19a13ac1d6faa46d0b12e
+  filename: NM_004006.2.gb.bz2
+  geninfo_id: '238018044'
+NM_024426.4:
+  checksum: 830a3beb9b7af3c6ba3e8a15b1bd0f54
+  filename: NM_024426.4.gb.bz2
+  geninfo_id: '309951095'
+NM_203473.1:
+  checksum: ec8fbdeda11ef8ec953e4ed39e9a84e5
+  filename: NM_203473.1
+  geninfo_id: '45439330'
+NP_064445.1:
+  checksum: 33ea9315882b4a9d8c33018a201be2fa
+  filename: NP_064445.1.gb.bz2
+  geninfo_id: '9910526'
+chr9_reverse:
+  accession: UD_139015349377
+  checksum: d21f92d09116c4831ce8d3ef832aa281
+  filename: UD_139015349377.gb.bz2
+  links:
+  - - NM_001195250
+    - NP_001182179
+  - - NR_036576
+    - null
+  - - NR_036577
+    - null
+  - - NM_001195252
+    - NP_001182181
+  - - NM_001195248
+    - NP_001182177
+  - - NM_175069
+    - NP_778239
+  - - NM_175073
+    - NP_778243
+  - - NM_001195251
+    - NP_001182180
+  - - NM_001195254
+    - NP_001182183
+  - - NR_036578
+    - null
+  - - NR_036579
+    - null
+  - - NM_001195249
+    - NP_001182178

tests/test_db_queries.py

@@ -5,63 +5,55 @@ Tests for the mutalyzer.db.queries module.
 
 from __future__ import unicode_literals
 
-#import logging; logging.basicConfig()
+import pytest
 
 from mutalyzer.db import queries
 
-from fixtures import database, cache
-from utils import MutalyzerTest
-from utils import fix
 
+pytestmark = [
+    pytest.mark.usefixtures('references'),
+    pytest.mark.parametrize('references', [['MARK1']], indirect=True)
+]
 
-class TestMutator(MutalyzerTest):
+
+def test_get_transcript_protein_link():
+    """
+    Query a transcript-protein link by transcript.
+    """
+    link = queries.get_transcript_protein_link('NM_018650')
+    assert link.transcript_accession == 'NM_018650'
+    assert link.protein_accession == 'NP_061120'
+
+
+def test_get_transcript_protein_link_negative():
+    """
+    Query a negative transcript-protein link by transcript.
+    """
+    link = queries.get_transcript_protein_link('XM_005273133')
+    assert link.transcript_accession == 'XM_005273133'
+    assert link.protein_accession is None
+
+
+def test_get_transcript_protein_link_missing():
+    """
+    Query a missing transcript-protein link by transcript.
+    """
+    link = queries.get_transcript_protein_link('NM_123456')
+    assert link is None
+
+
+def test_get_transcript_protein_link_reverse():
+    """
+    Query a transcript-protein link by protein.
+    """
+    link = queries.get_transcript_protein_link('NP_061120', reverse=True)
+    assert link.transcript_accession == 'NM_018650'
+    assert link.protein_accession == 'NP_061120'
+
+
+def test_get_transcript_protein_link_reverse_missing():
     """
-    Test the queries module.
+    Query a missing transcript-protein link by protein.
     """
-    fixtures = (database, )
-
-    def setup(self):
-        super(TestMutator, self).setup()
-
-    @fix(cache('MARK1'))
-    def test_get_transcript_protein_link(self):
-        """
-        Query a transcript-protein link by transcript.
-        """
-        link = queries.get_transcript_protein_link('NM_018650')
-        assert link.transcript_accession == 'NM_018650'
-        assert link.protein_accession == 'NP_061120'
-
-    @fix(cache('MARK1'))
-    def test_get_transcript_protein_link_negative(self):
-        """
-        Query a negative transcript-protein link by transcript.
-        """
-        link = queries.get_transcript_protein_link('XM_005273133')
-        assert link.transcript_accession == 'XM_005273133'
-        assert link.protein_accession is None
-
-    @fix(cache('MARK1'))
-    def test_get_transcript_protein_link_missing(self):
-        """
-        Query a missing transcript-protein link by transcript.
-        """
-        link = queries.get_transcript_protein_link('NM_123456')
-        assert link is None
-
-    @fix(cache('MARK1'))
-    def test_get_transcript_protein_link_reverse(self):
-        """
-        Query a transcript-protein link by protein.
-        """
-        link = queries.get_transcript_protein_link('NP_061120', reverse=True)
-        assert link.transcript_accession == 'NM_018650'
-        assert link.protein_accession == 'NP_061120'
-
-    @fix(cache('MARK1'))
-    def test_get_transcript_protein_link_reverse_missing(self):
-        """
-        Query a missing transcript-protein link by protein.
-        """
-        link = queries.get_transcript_protein_link('NP_123456')
-        assert link is None
+    link = queries.get_transcript_protein_link('NP_123456')
+    assert link is None

tests/test_grammar.py

@@ -5,148 +5,160 @@ Tests for the mutalyzer.grammar module.
 
 from __future__ import unicode_literals
 
-#import logging; logging.basicConfig()
-import os
+import pytest
 
-import mutalyzer
 from mutalyzer.grammar import Grammar
-from mutalyzer.output import Output
 
-from utils import MutalyzerTest
 
+@pytest.fixture
+def grammar(output):
+    return Grammar(output)
 
-class TestGrammar(MutalyzerTest):
+
+@pytest.fixture
+def parser(output, grammar):
+    def parse(description):
+        __tracebackhide__ = True
+        grammar.parse(description)
+        errors = output.getMessagesWithErrorCode('EPARSE')
+        if len(errors) > 0:
+            pytest.fail('failed to parse `%s`: %s' % (
+                description, errors[0].description))
+    return parse
+
+
+@pytest.mark.parametrize('description', [
+    'NM_002001.2:c.[12del]',
+    'NM_002001.2:c.[(12del)]',
+    'NM_002001.2:c.[(12del)?]',
+    'NM_002001.2:c.[(12del);(12del)]',
+    'NM_002001.2:c.[(12del;12del)]',
+    'NM_002001.2:c.[((12del)?;12del)?]'
+])
+def test_parse_variants(parser, description):
+    """
+    Parse some example variants.
+    """
+    parser(description)
+
+
+@pytest.mark.parametrize('description', [
+    'NM_002001.2:c.15_16insA',
+    'NM_002001.2:c.15_16insATC',
+    'NM_002001.2:c.15_16ins[A]',
+    'NM_002001.2:c.15_16ins[ATC]',
+    'NM_002001.2:c.15_16ins28_39',
+    'NM_002001.2:c.15_16ins[28_39]',
+    'NM_002001.2:c.15_16ins[28_39;A]',
+    'NM_002001.2:c.15_16ins[28_39;ATC]',
+    'NM_002001.2:c.15_16ins[28_39;A;ATC]',
+    'NM_002001.2:c.15_16ins28_39inv',
+    'NM_002001.2:c.15_16ins[28_39inv]',
+    'NM_002001.2:c.15_16ins[28_39inv;A]',
+    'NM_002001.2:c.15_16ins[28_39inv;ATC]',
+    'NM_002001.2:c.15_16ins[28_39inv;A;ATC]'
+])
+def test_parse_compound_insertion(parser, description):
+    """
+    Parse compound insertions.
+    """
+    parser(description)
+
+
+@pytest.mark.parametrize('description', [
+    'NM_002001.2:c.12_17delinsA',
+    'NM_002001.2:c.12_17delinsATC',
+    'NM_002001.2:c.12_17delins[A]',
+    'NM_002001.2:c.12_17delins[ATC]',
+    'NM_002001.2:c.12_17delins28_39',
+    'NM_002001.2:c.12_17delins[28_39]',
+    'NM_002001.2:c.12_17delins[28_39;A]',
+    'NM_002001.2:c.12_17delins[28_39;ATC]',
+    'NM_002001.2:c.12_17delins[28_39;A;ATC]',
+    'NM_002001.2:c.12_17delins28_39inv',
+    'NM_002001.2:c.12_17delins[28_39inv]',
+    'NM_002001.2:c.12_17delins[28_39inv;A]',
+    'NM_002001.2:c.12_17delins[28_39inv;ATC]',
+    'NM_002001.2:c.12_17delins[28_39inv;A;ATC]'
+])
+def test_parse_compound_delins(parser, description):
+    """
+    Parse compound deletion-insertions.
+    """
+    parser(description)
+
+
+@pytest.mark.parametrize('description', [
+    'NG_009105.1(OPN1LW):p.=',
+    'NG_009105.1(OPN1LW):p.?',
+    'NM_000076.2(CDKN1C):p.0',
+    'NM_000076.2(CDKN1C):p.0?',
+    'NG_009105.1(OPN1LW):p.(=)',
+    'NM_000076.2(CDKN1C):p.(Ala123del)',
+    'NM_000076.2(CDKN1C):p.(Ala123_Leu126del)',
+    'NM_000076.2(CDKN1C):p.(Ala123_Leu126delinsVal)',
+    'NM_000076.2(CDKN1C):p.Ala123del',
+    'NM_000076.2(CDKN1C):p.Ala123_Leu126del',
+    'NM_000076.2(CDKN1C):p.Ala123_Leu126delinsVal',
+    'NM_000076.2(CDKN1C):p.Ala123_*317delinsVal',
+    'NM_000076.2(CDKN1C):p.Ala123_X317delinsVal',
+    'NM_000076.2(CDKN1C):p.Ala123delinsVal',
+    'NM_000076.2(CDKN1C):p.Ala123delinsValPro',
+    'NM_000076.2(CDKN1C):p.Ala123delinsVP',
+    'NM_000076.2(CDKN1C):p.Ala123fs',
+    'NM_000076.2(CDKN1C_i001):p.(Glu124Serfs*148)',
+    'NM_000076.2(CDKN1C_i001):p.(Glu124SerfsX148)',
+    'NM_000076.2(CDKN1C_i001):p.(E124Sfs*148)',
+    'NM_000076.2(CDKN1C_i001):p.(E124SfsX148)',
+    'NG_009105.1(OPN1LW):p.Met1Leu',
+    'NP_064445.1(OPN1LW):p.Met1?',
+    'NP_064445.1(OPN1LW):p.M1?',
+    'NP_064445.1:p.Gln16del',
+    'NP_064445.1:p.Gln16dup',
+    'NP_064445.1:p.Gln3del',
+    'NP_064445.1:p.Q16del',
+    'NP_064445.1:p.Q16dup',
+    'NP_064445.1:p.Q16*',
+    'NP_064445.1:p.Q16X',
+    'NG_009105.1:p.Gln3Leu',
+    'NG_009105.1(OPN1LW):p.Gln3Leu',
+    'NG_009105.1(OPN1LW_i1):p.Gln3Leu',
+    'NG_009105.1(OPN1LW_v1):p.Gln3Leu',
+    'NG_009105.1(OPN1LW):p.Gln3_Gln4insLeu',
+    'NG_009105.1(OPN1LW):p.Gln3_Gln4insGln',
+    'NG_009105.1(OPN1LW):p.Gln3_Gln4dup',
+    'NG_009105.1(OPN1LW):p.Q3_Q4insQ',
+    'NG_009105.1(OPN1LW):p.Q3_Q4insQQ',
+    'NG_009105.1(OPN1LW):p.Q3_Q4dup',
+    'NG_009105.1(OPN1LW):p.Gln3_Leu7del',
+    'NG_009105.1(OPN1LW):p.Gln3_Leu7delinsValLeu',
+    'NG_009105.1(OPN1LW):p.Gln3_Leu7delinsValPro',
+    'NG_009105.1(OPN1LW):p.Gln3_Leu7delinsGlnGlnTrpSerLeu',
+    'NG_009105.1(OPN1LW):p.Q3_L7delinsGlnGlnTrpSerLeu',
+    'NG_009105.1(OPN1LW):p.Gln3_Leu7delinsQQWSL',
+    # 'NG_009105.1(OPN1LW):p.Met1AlaextMet-1',
+    # 'NG_009105.1(OPN1LW):p.M1AextM-1',
+    # 'NG_009105.1(OPN1LW):p.Gln3_Leu7[3]',
+    'NG_009105.1(OPN1LW):p.Gln3_Leu7(1_6)',
+    'NG_009105.1(OPN1LW):p.Gln3Leu',
+    'NG_009105.1(OPN1LW):p.Gln3Leu',
+    # 'NM_000076.2(CDKN1C_i001):p.(*317Trpext*3)',
+    'NM_000076.2(CDKN1C_i001):p.(*317TrpextX3)',
+    # 'NM_000076.2(CDKN1C_i001):p.(*317Cysext*1)',
+    'NM_000076.2(CDKN1C_i001):p.(*317CysextX1)',
+    # 'NM_000076.2(CDKN1C_i001):p.(*317Cext*1)',
+    'NM_000076.2(CDKN1C_i001):p.(*317CextX1)',
+    # 't(X;17)(DMD:p.Met1_Val1506; SGCA:p.Val250_*387)'
+])
+def test_parse_protein_variants(parser, description):
+    """
+    Parse protein variants.
+    """
+    parser(description)
+
+
+def test_parse_minus_in_gene_symbol(parser):
     """
-    Test the mytalyzer.grammar module.
+    Gene symbol is allowed to contain a minus character.
     """
-    def setup(self):
-        super(TestGrammar, self).setup()
-        self.output = Output(__file__)
-        self.grammar = Grammar(self.output)
-
-    def _parse(self, description):
-        """
-        Parse a variant description.
-        """
-        self.grammar.parse(description)
-        assert self.output.getOutput('parseError') == []
-
-    def test_some_variants(self):
-        """
-        Some example variants.
-        """
-        self._parse('NM_002001.2:c.[12del]')
-        self._parse('NM_002001.2:c.[(12del)]')
-        self._parse('NM_002001.2:c.[(12del)?]')
-        self._parse('NM_002001.2:c.[(12del);(12del)]')
-        self._parse('NM_002001.2:c.[(12del;12del)]')
-        self._parse('NM_002001.2:c.[((12del)?;12del)?]')
-
-    def test_compound_insertion(self):
-        """
-        Some some compound insertions.
-        """
-        self._parse('NM_002001.2:c.15_16insA')
-        self._parse('NM_002001.2:c.15_16insATC')
-        self._parse('NM_002001.2:c.15_16ins[A]')
-        self._parse('NM_002001.2:c.15_16ins[ATC]')
-        self._parse('NM_002001.2:c.15_16ins28_39')
-        self._parse('NM_002001.2:c.15_16ins[28_39]')
-        self._parse('NM_002001.2:c.15_16ins[28_39;A]')
-        self._parse('NM_002001.2:c.15_16ins[28_39;ATC]')
-        self._parse('NM_002001.2:c.15_16ins[28_39;A;ATC]')
-        self._parse('NM_002001.2:c.15_16ins28_39inv')
-        self._parse('NM_002001.2:c.15_16ins[28_39inv]')
-        self._parse('NM_002001.2:c.15_16ins[28_39inv;A]')
-        self._parse('NM_002001.2:c.15_16ins[28_39inv;ATC]')
-        self._parse('NM_002001.2:c.15_16ins[28_39inv;A;ATC]')
-
-    def test_compound_delins(self):
-        """
-        Some some compound deletion-insertions.
-        """
-        self._parse('NM_002001.2:c.12_17delinsA')
-        self._parse('NM_002001.2:c.12_17delinsATC')
-        self._parse('NM_002001.2:c.12_17delins[A]')
-        self._parse('NM_002001.2:c.12_17delins[ATC]')
-        self._parse('NM_002001.2:c.12_17delins28_39')
-        self._parse('NM_002001.2:c.12_17delins[28_39]')
-        self._parse('NM_002001.2:c.12_17delins[28_39;A]')
-        self._parse('NM_002001.2:c.12_17delins[28_39;ATC]')
-        self._parse('NM_002001.2:c.12_17delins[28_39;A;ATC]')
-        self._parse('NM_002001.2:c.12_17delins28_39inv')
-        self._parse('NM_002001.2:c.12_17delins[28_39inv]')
-        self._parse('NM_002001.2:c.12_17delins[28_39inv;A]')
-        self._parse('NM_002001.2:c.12_17delins[28_39inv;ATC]')
-        self._parse('NM_002001.2:c.12_17delins[28_39inv;A;ATC]')
-
-    def test_protein_variants(self):
-        """
-        Some protein variants.
-        """
-        self._parse('NG_009105.1(OPN1LW):p.=')
-        self._parse('NG_009105.1(OPN1LW):p.?')
-        self._parse('NM_000076.2(CDKN1C):p.0')
-        self._parse('NM_000076.2(CDKN1C):p.0?')
-        self._parse('NG_009105.1(OPN1LW):p.(=)')
-        self._parse('NM_000076.2(CDKN1C):p.(Ala123del)')
-        self._parse('NM_000076.2(CDKN1C):p.(Ala123_Leu126del)')
-        self._parse('NM_000076.2(CDKN1C):p.(Ala123_Leu126delinsVal)')
-        self._parse('NM_000076.2(CDKN1C):p.Ala123del')
-        self._parse('NM_000076.2(CDKN1C):p.Ala123_Leu126del')
-        self._parse('NM_000076.2(CDKN1C):p.Ala123_Leu126delinsVal')
-        self._parse('NM_000076.2(CDKN1C):p.Ala123_*317delinsVal')
-        self._parse('NM_000076.2(CDKN1C):p.Ala123_X317delinsVal')
-        self._parse('NM_000076.2(CDKN1C):p.Ala123delinsVal')
-        self._parse('NM_000076.2(CDKN1C):p.Ala123delinsValPro')
-        self._parse('NM_000076.2(CDKN1C):p.Ala123delinsVP')
-        self._parse('NM_000076.2(CDKN1C):p.Ala123fs')
-        self._parse('NM_000076.2(CDKN1C_i001):p.(Glu124Serfs*148)')
-        self._parse('NM_000076.2(CDKN1C_i001):p.(Glu124SerfsX148)')
-        self._parse('NM_000076.2(CDKN1C_i001):p.(E124Sfs*148)')
-        self._parse('NM_000076.2(CDKN1C_i001):p.(E124SfsX148)')
-        self._parse('NG_009105.1(OPN1LW):p.Met1Leu')
-        self._parse('NP_064445.1(OPN1LW):p.Met1?')
-        self._parse('NP_064445.1(OPN1LW):p.M1?')
-        self._parse('NP_064445.1:p.Gln16del')
-        self._parse('NP_064445.1:p.Gln16dup')
-        self._parse('NP_064445.1:p.Gln3del')
-        self._parse('NP_064445.1:p.Q16del')
-        self._parse('NP_064445.1:p.Q16dup')
-        self._parse('NP_064445.1:p.Q16*')
-        self._parse('NP_064445.1:p.Q16X')
-        self._parse('NG_009105.1:p.Gln3Leu')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3Leu')
-        self._parse('NG_009105.1(OPN1LW_i1):p.Gln3Leu')
-        self._parse('NG_009105.1(OPN1LW_v1):p.Gln3Leu')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3_Gln4insLeu')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3_Gln4insGln')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3_Gln4dup')
-        self._parse('NG_009105.1(OPN1LW):p.Q3_Q4insQ')
-        self._parse('NG_009105.1(OPN1LW):p.Q3_Q4insQQ')
-        self._parse('NG_009105.1(OPN1LW):p.Q3_Q4dup')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3_Leu7del')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3_Leu7delinsValLeu')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3_Leu7delinsValPro')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3_Leu7delinsGlnGlnTrpSerLeu')
-        self._parse('NG_009105.1(OPN1LW):p.Q3_L7delinsGlnGlnTrpSerLeu')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3_Leu7delinsQQWSL')
-        #self._parse('NG_009105.1(OPN1LW):p.Met1AlaextMet-1')
-        #self._parse('NG_009105.1(OPN1LW):p.M1AextM-1')
-        #self._parse('NG_009105.1(OPN1LW):p.Gln3_Leu7[3]')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3_Leu7(1_6)')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3Leu')
-        self._parse('NG_009105.1(OPN1LW):p.Gln3Leu')
-        #self._parse('NM_000076.2(CDKN1C_i001):p.(*317Trpext*3)')
-        self._parse('NM_000076.2(CDKN1C_i001):p.(*317TrpextX3)')
-        #self._parse('NM_000076.2(CDKN1C_i001):p.(*317Cysext*1)')
-        self._parse('NM_000076.2(CDKN1C_i001):p.(*317CysextX1)')
-        #self._parse('NM_000076.2(CDKN1C_i001):p.(*317Cext*1)')
-        self._parse('NM_000076.2(CDKN1C_i001):p.(*317CextX1)')
-        #self._parse('t(X;17)(DMD:p.Met1_Val1506; SGCA:p.Val250_*387)')
-
-    def test_minus_in_gene_symbol(self):
-        """
-        Gene symbol is allowed to contain a minus character.
-        """
-        self._parse('UD_132464528477(KRTAP2-4_v001):c.100del')
+    parser('UD_132464528477(KRTAP2-4_v001):c.100del')

tests/test_migrations.py

@@ -5,8 +5,6 @@ Test database migrations.
 
 from __future__ import unicode_literals
 
-import os
-
 import alembic.autogenerate
 import alembic.command
 import alembic.config
@@ -17,16 +15,11 @@ from sqlalchemy import create_engine, sql
 from mutalyzer import db
 
 
-def test_migrations():
+def test_migrations(database_uri):
     """
     Run all migrations and assert the result is up to date with the model
     definitions.
-
-    We don't use `utils.MutalyzerTest` here, or `mutalyzer.db.session` in any
-    way for that matter, since it will bootstrap the database schema.
     """
-    database_uri = os.getenv('MUTALYZER_TEST_DATABASE_URI', 'sqlite://')
-
     alembic_config = alembic.config.Config('migrations/alembic.ini')
     engine = create_engine(database_uri)
 

tests/test_parsers_genbank.py

@@ -5,52 +5,44 @@ Tests for the mutalyzer.parsers.genbank module.
 
 from __future__ import unicode_literals
 
-#import logging; logging.basicConfig()
 import os
 
-from mutalyzer.parsers import genbank
-from mutalyzer.config import settings
+import pytest
 
-from fixtures import REFERENCES
-from fixtures import database, cache
-from utils import MutalyzerTest
-from utils import fix
+from mutalyzer.parsers.genbank import GBparser
 
 
-class TestMutator(MutalyzerTest):
+@pytest.fixture
+def parser():
+    return GBparser()
+
+
+@pytest.mark.parametrize('products,expected', [
+    (['a b c d e', 'a b C D e', 'a b c d e'], (2, 1)),
+    (['a b c d e', 'a b C d e', 'a B c d e'], (1, 2)),
+    (['a c d a', 'a b a', 'a a', 'a'], (1, 1)),
+    ([''], (-1, -1)),
+    (['', ''], (-1, -1)),
+    (['a', 'a'], (-1, -1)),
+    (['a', 'b'], (0, 0)),
+    (['a b c', 'a b c'], (-1, -1)),
+    (['a b c d a b', 'a b'], (2, 2))
+])
+def test_product_lists_mismatch(parser, products, expected):
+    """
+    Test finding mismatches in some product lists.
+    """
+    assert parser._find_mismatch(products) == expected
+
+
+@pytest.mark.parametrize('references', [['A1BG']], indirect=True)
+def test_only_complete_genes_included(settings, references, parser):
     """
-    Test the mutator module.
+    Incomplete genes from the reference file should be ignored.
     """
-    fixtures = (database, )
-
-    def setup(self):
-        super(TestMutator, self).setup()
-        self.gb_parser = genbank.GBparser()
-
-    def test_product_lists_mismatch(self):
-        """
-        Test finding mismatches in some product lists.
-        """
-        tests = [(['a b c d e', 'a b C D e', 'a b c d e'], (2, 1)),
-                 (['a b c d e', 'a b C d e', 'a B c d e'], (1, 2)),
-                 (['a c d a', 'a b a', 'a a', 'a'], (1, 1)),
-                 ([''], (-1, -1)),
-                 (['', ''], (-1, -1)),
-                 (['a', 'a'], (-1, -1)),
-                 (['a', 'b'], (0, 0)),
-                 (['a b c', 'a b c'], (-1, -1)),
-                 (['a b c d a b', 'a b'], (2, 2))]
-        for test in tests:
-            assert self.gb_parser._find_mismatch(test[0]) == test[1]
-
-    @fix(cache('A1BG'))
-    def test_only_complete_genes_included(self):
-        """
-        Incomplete genes from the reference file should be ignored.
-        """
-        # contains A1BG (complete) and A1BG-AS1, ZNF497, LOC100419840
-        # (incomplete).
-        genbank_filename = os.path.join(settings.CACHE_DIR,
-                                        REFERENCES['A1BG']['filename'])
-        record = self.gb_parser.create_record(genbank_filename)
-        assert [g.name for g in record.geneList] == ['A1BG']
+    # contains A1BG (complete) and A1BG-AS1, ZNF497, LOC100419840
+    # (incomplete).
+    accession = references[0].accession
+    filename = os.path.join(settings.CACHE_DIR, '%s.gb.bz2' % accession)
+    record = parser.create_record(filename)
+    assert [g.name for g in record.geneList] == ['A1BG']