Merge branch '16100-mime-types'
[arvados.git] / services / fuse / tests / test_mount.py
index bef7d27f7980626d2070072dba353142e7b346ae..593d945cff0be54e46cb360712efd20b28e1658d 100644 (file)
@@ -2,6 +2,11 @@
 #
 # SPDX-License-Identifier: AGPL-3.0
 
+from __future__ import absolute_import
+from future.utils import viewitems
+from builtins import str
+from builtins import object
+from six import assertRegex
 import json
 import llfuse
 import logging
@@ -13,9 +18,10 @@ import unittest
 
 import arvados
 import arvados_fuse as fuse
-import run_test_server
+from . import run_test_server
 
-from mount_test_base import MountTestBase
+from .integration_test import IntegrationTest
+from .mount_test_base import MountTestBase
 
 logger = logging.getLogger('arvados.arv-mount')
 
@@ -31,7 +37,7 @@ class AssertWithTimeout(object):
         self.done = False
         return self
 
-    def next(self):
+    def __next__(self):
         if self.done:
             raise StopIteration
         return self.attempt
@@ -78,11 +84,11 @@ class FuseMountTest(MountTestBase):
         cw.write("data 8")
 
         cw.start_new_stream('edgecases')
-        for f in ":/.../-/*/\x01\\/ ".split("/"):
+        for f in ":/.../-/*/ ".split("/"):
             cw.start_new_file(f)
             cw.write('x')
 
-        for f in ":/.../-/*/\x01\\/ ".split("/"):
+        for f in ":/.../-/*/ ".split("/"):
             cw.start_new_stream('edgecases/dirs/' + f)
             cw.start_new_file('x/x')
             cw.write('x')
@@ -99,9 +105,9 @@ class FuseMountTest(MountTestBase):
         self.assertDirContents('dir2', ['thing5.txt', 'thing6.txt', 'dir3'])
         self.assertDirContents('dir2/dir3', ['thing7.txt', 'thing8.txt'])
         self.assertDirContents('edgecases',
-                               "dirs/:/.../-/*/\x01\\/ ".split("/"))
+                               "dirs/:/.../-/*/ ".split("/"))
         self.assertDirContents('edgecases/dirs',
-                               ":/.../-/*/\x01\\/ ".split("/"))
+                               ":/.../-/*/ ".split("/"))
 
         files = {'thing1.txt': 'data 1',
                  'thing2.txt': 'data 2',
@@ -112,33 +118,19 @@ class FuseMountTest(MountTestBase):
                  'dir2/dir3/thing7.txt': 'data 7',
                  'dir2/dir3/thing8.txt': 'data 8'}
 
-        for k, v in files.items():
-            with open(os.path.join(self.mounttmp, k)) as f:
-                self.assertEqual(v, f.read())
-
-
-class FuseNoAPITest(MountTestBase):
-    def setUp(self):
-        super(FuseNoAPITest, self).setUp()
-        keep = arvados.keep.KeepClient(local_store=self.keeptmp)
-        self.file_data = "API-free text\n"
-        self.file_loc = keep.put(self.file_data)
-        self.coll_loc = keep.put(". {} 0:{}:api-free.txt\n".format(
-                self.file_loc, len(self.file_data)))
-
-    def runTest(self):
-        self.make_mount(fuse.MagicDirectory)
-        self.assertDirContents(self.coll_loc, ['api-free.txt'])
-        with open(os.path.join(
-                self.mounttmp, self.coll_loc, 'api-free.txt')) as keep_file:
-            actual = keep_file.read(-1)
-        self.assertEqual(self.file_data, actual)
+        for k, v in viewitems(files):
+            with open(os.path.join(self.mounttmp, k), 'rb') as f:
+                self.assertEqual(v, f.read().decode())
 
 
 class FuseMagicTest(MountTestBase):
     def setUp(self, api=None):
         super(FuseMagicTest, self).setUp(api=api)
 
+        self.test_project = run_test_server.fixture('groups')['aproject']['uuid']
+        self.non_project_group = run_test_server.fixture('groups')['public']['uuid']
+        self.collection_in_test_project = run_test_server.fixture('collections')['foo_collection_in_aproject']['name']
+
         cw = arvados.CollectionWriter()
 
         cw.start_new_file('thing1.txt')
@@ -146,7 +138,8 @@ class FuseMagicTest(MountTestBase):
 
         self.testcollection = cw.finish()
         self.test_manifest = cw.manifest_text()
-        self.api.collections().create(body={"manifest_text":self.test_manifest}).execute()
+        coll = self.api.collections().create(body={"manifest_text":self.test_manifest}).execute()
+        self.test_manifest_pdh = coll['portable_data_hash']
 
     def runTest(self):
         self.make_mount(fuse.MagicDirectory)
@@ -156,22 +149,33 @@ class FuseMagicTest(MountTestBase):
         self.assertFalse(any(arvados.util.keep_locator_pattern.match(fn) or
                              arvados.util.uuid_pattern.match(fn)
                              for fn in mount_ls),
-                         "new FUSE MagicDirectory lists Collection")
+                         "new FUSE MagicDirectory has no collections or projects")
         self.assertDirContents(self.testcollection, ['thing1.txt'])
         self.assertDirContents(os.path.join('by_id', self.testcollection),
                                ['thing1.txt'])
+        self.assertIn(self.collection_in_test_project,
+                      llfuse.listdir(os.path.join(self.mounttmp, self.test_project)))
+        self.assertIn(self.collection_in_test_project,
+                      llfuse.listdir(os.path.join(self.mounttmp, 'by_id', self.test_project)))
+
         mount_ls = llfuse.listdir(self.mounttmp)
         self.assertIn('README', mount_ls)
         self.assertIn(self.testcollection, mount_ls)
         self.assertIn(self.testcollection,
                       llfuse.listdir(os.path.join(self.mounttmp, 'by_id')))
+        self.assertIn(self.test_project, mount_ls)
+        self.assertIn(self.test_project,
+                      llfuse.listdir(os.path.join(self.mounttmp, 'by_id')))
+
+        with self.assertRaises(OSError):
+            llfuse.listdir(os.path.join(self.mounttmp, 'by_id', self.non_project_group))
 
         files = {}
         files[os.path.join(self.mounttmp, self.testcollection, 'thing1.txt')] = 'data 1'
 
-        for k, v in files.items():
-            with open(os.path.join(self.mounttmp, k)) as f:
-                self.assertEqual(v, f.read())
+        for k, v in viewitems(files):
+            with open(os.path.join(self.mounttmp, k), 'rb') as f:
+                self.assertEqual(v, f.read().decode())
 
 
 class FuseTagsTest(MountTestBase):
@@ -237,7 +241,7 @@ def fuseSharedTestHelper(mounttmp):
             # check mtime on collection
             st = os.stat(baz_path)
             try:
-                mtime = st.st_mtime_ns / 1000000000
+                mtime = st.st_mtime_ns // 1000000000
             except AttributeError:
                 mtime = st.st_mtime
             self.assertEqual(mtime, 1391448174)
@@ -273,7 +277,7 @@ class FuseSharedTest(MountTestBase):
         self.make_mount(fuse.SharedDirectory,
                         exclude=self.api.users().current().execute()['uuid'])
         keep = arvados.keep.KeepClient()
-        keep.put("baz")
+        keep.put("baz".encode())
 
         self.pool.apply(fuseSharedTestHelper, (self.mounttmp,))
 
@@ -291,7 +295,7 @@ class FuseHomeTest(MountTestBase):
             'anonymously_accessible_project']
         found_in = 0
         found_not_in = 0
-        for name, item in run_test_server.fixture('collections').iteritems():
+        for name, item in viewitems(run_test_server.fixture('collections')):
             if 'name' not in item:
                 pass
             elif item['owner_uuid'] == public_project['uuid']:
@@ -426,7 +430,7 @@ class FuseCreateFileTest(MountTestBase):
         self.assertEqual(["file1.txt"], d1)
 
         collection2 = self.api.collections().get(uuid=collection.manifest_locator()).execute()
-        self.assertRegexpMatches(collection2["manifest_text"],
+        assertRegex(self, collection2["manifest_text"],
             r'\. d41d8cd98f00b204e9800998ecf8427e\+0\+A\S+ 0:0:file1\.txt$')
 
 
@@ -468,7 +472,7 @@ class FuseWriteFileTest(MountTestBase):
         self.assertEqual(12, self.operations.read_counter.get())
 
         collection2 = self.api.collections().get(uuid=collection.manifest_locator()).execute()
-        self.assertRegexpMatches(collection2["manifest_text"],
+        assertRegex(self, collection2["manifest_text"],
             r'\. 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$')
 
 
@@ -506,7 +510,7 @@ class FuseUpdateFileTest(MountTestBase):
         self.pool.apply(fuseUpdateFileTestHelper, (self.mounttmp,))
 
         collection2 = self.api.collections().get(uuid=collection.manifest_locator()).execute()
-        self.assertRegexpMatches(collection2["manifest_text"],
+        assertRegex(self, collection2["manifest_text"],
             r'\. daaef200ebb921e011e3ae922dd3266b\+11\+A\S+ 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:11:file1\.txt 22:1:file1\.txt$')
 
 
@@ -546,7 +550,7 @@ class FuseMkdirTest(MountTestBase):
         self.pool.apply(fuseMkdirTestHelper, (self.mounttmp,))
 
         collection2 = self.api.collections().get(uuid=collection.manifest_locator()).execute()
-        self.assertRegexpMatches(collection2["manifest_text"],
+        assertRegex(self, collection2["manifest_text"],
             r'\./testdir 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$')
 
 
@@ -613,13 +617,14 @@ class FuseRmTest(MountTestBase):
 
         # Starting manifest
         collection2 = self.api.collections().get(uuid=collection.manifest_locator()).execute()
-        self.assertRegexpMatches(collection2["manifest_text"],
+        assertRegex(self, collection2["manifest_text"],
             r'\./testdir 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$')
         self.pool.apply(fuseRmTestHelperDeleteFile, (self.mounttmp,))
 
-        # Can't have empty directories :-( so manifest will be empty.
+        # Empty directories are represented by an empty file named "."
         collection2 = self.api.collections().get(uuid=collection.manifest_locator()).execute()
-        self.assertEqual(collection2["manifest_text"], "")
+        assertRegex(self, collection2["manifest_text"],
+                                 r'./testdir d41d8cd98f00b204e9800998ecf8427e\+0\+A\S+ 0:0:\\056\n')
 
         self.pool.apply(fuseRmTestHelperRmdir, (self.mounttmp,))
 
@@ -669,14 +674,14 @@ class FuseMvFileTest(MountTestBase):
 
         # Starting manifest
         collection2 = self.api.collections().get(uuid=collection.manifest_locator()).execute()
-        self.assertRegexpMatches(collection2["manifest_text"],
+        assertRegex(self, collection2["manifest_text"],
             r'\./testdir 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$')
 
         self.pool.apply(fuseMvFileTestHelperMoveFile, (self.mounttmp,))
 
         collection2 = self.api.collections().get(uuid=collection.manifest_locator()).execute()
-        self.assertRegexpMatches(collection2["manifest_text"],
-            r'\. 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$')
+        assertRegex(self, collection2["manifest_text"],
+            r'\. 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt\n\./testdir d41d8cd98f00b204e9800998ecf8427e\+0\+A\S+ 0:0:\\056\n')
 
 
 def fuseRenameTestHelper(mounttmp):
@@ -703,7 +708,7 @@ class FuseRenameTest(MountTestBase):
 
         # Starting manifest
         collection2 = self.api.collections().get(uuid=collection.manifest_locator()).execute()
-        self.assertRegexpMatches(collection2["manifest_text"],
+        assertRegex(self, collection2["manifest_text"],
             r'\./testdir 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$')
 
         d1 = llfuse.listdir(os.path.join(self.mounttmp))
@@ -719,7 +724,7 @@ class FuseRenameTest(MountTestBase):
         self.assertEqual(["file1.txt"], d1)
 
         collection2 = self.api.collections().get(uuid=collection.manifest_locator()).execute()
-        self.assertRegexpMatches(collection2["manifest_text"],
+        assertRegex(self, collection2["manifest_text"],
             r'\./testdir2 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$')
 
 
@@ -785,7 +790,7 @@ def fuseFileConflictTestHelper(mounttmp):
             with open(os.path.join(mounttmp, "file1.txt"), "r") as f:
                 self.assertEqual(f.read(), "bar")
 
-            self.assertRegexpMatches(d1[1],
+            assertRegex(self, d1[1],
                 r'file1\.txt~\d\d\d\d\d\d\d\d-\d\d\d\d\d\d~conflict~')
 
             with open(os.path.join(mounttmp, d1[1]), "r") as f:
@@ -894,7 +899,7 @@ class FuseMvFileBetweenCollectionsTest(MountTestBase):
         collection1.update()
         collection2.update()
 
-        self.assertRegexpMatches(collection1.manifest_text(), r"\. 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$")
+        assertRegex(self, collection1.manifest_text(), r"\. 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$")
         self.assertEqual(collection2.manifest_text(), "")
 
         self.pool.apply(fuseMvFileBetweenCollectionsTest2, (self.mounttmp,
@@ -905,7 +910,7 @@ class FuseMvFileBetweenCollectionsTest(MountTestBase):
         collection2.update()
 
         self.assertEqual(collection1.manifest_text(), "")
-        self.assertRegexpMatches(collection2.manifest_text(), r"\. 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file2\.txt$")
+        assertRegex(self, collection2.manifest_text(), r"\. 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file2\.txt$")
 
         collection1.stop_threads()
         collection2.stop_threads()
@@ -965,7 +970,7 @@ class FuseMvDirBetweenCollectionsTest(MountTestBase):
         collection1.update()
         collection2.update()
 
-        self.assertRegexpMatches(collection1.manifest_text(), r"\./testdir 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$")
+        assertRegex(self, collection1.manifest_text(), r"\./testdir 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$")
         self.assertEqual(collection2.manifest_text(), "")
 
         self.pool.apply(fuseMvDirBetweenCollectionsTest2, (self.mounttmp,
@@ -976,7 +981,7 @@ class FuseMvDirBetweenCollectionsTest(MountTestBase):
         collection2.update()
 
         self.assertEqual(collection1.manifest_text(), "")
-        self.assertRegexpMatches(collection2.manifest_text(), r"\./testdir2 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$")
+        assertRegex(self, collection2.manifest_text(), r"\./testdir2 86fb269d190d2c85f6e0468ceca42a20\+12\+A\S+ 0:12:file1\.txt$")
 
         collection1.stop_threads()
         collection2.stop_threads()
@@ -1072,23 +1077,31 @@ class MagicDirApiError(FuseMagicTest):
     def setUp(self):
         api = mock.MagicMock()
         super(MagicDirApiError, self).setUp(api=api)
-        api.collections().get().execute.side_effect = iter([Exception('API fail'), {"manifest_text": self.test_manifest}])
+        api.collections().get().execute.side_effect = iter([
+            Exception('API fail'),
+            {
+                "manifest_text": self.test_manifest,
+                "portable_data_hash": self.test_manifest_pdh,
+            },
+        ])
         api.keep.get.side_effect = Exception('Keep fail')
 
     def runTest(self):
-        self.make_mount(fuse.MagicDirectory)
+        with mock.patch('arvados_fuse.fresh.FreshBase._poll_time', new_callable=mock.PropertyMock, return_value=60) as mock_poll_time:
+            self.make_mount(fuse.MagicDirectory)
 
-        self.operations.inodes.inode_cache.cap = 1
-        self.operations.inodes.inode_cache.min_entries = 2
+            self.operations.inodes.inode_cache.cap = 1
+            self.operations.inodes.inode_cache.min_entries = 2
 
-        with self.assertRaises(OSError):
-            llfuse.listdir(os.path.join(self.mounttmp, self.testcollection))
+            with self.assertRaises(OSError):
+                llfuse.listdir(os.path.join(self.mounttmp, self.testcollection))
 
-        llfuse.listdir(os.path.join(self.mounttmp, self.testcollection))
+            llfuse.listdir(os.path.join(self.mounttmp, self.testcollection))
 
 
-class FuseUnitTest(unittest.TestCase):
+class SanitizeFilenameTest(MountTestBase):
     def test_sanitize_filename(self):
+        pdir = fuse.ProjectDirectory(1, {}, self.api, 0, project_object=self.api.users().current().execute())
         acceptable = [
             "foo.txt",
             ".foo",
@@ -1108,15 +1121,15 @@ class FuseUnitTest(unittest.TestCase):
             "//",
             ]
         for f in acceptable:
-            self.assertEqual(f, fuse.sanitize_filename(f))
+            self.assertEqual(f, pdir.sanitize_filename(f))
         for f in unacceptable:
-            self.assertNotEqual(f, fuse.sanitize_filename(f))
+            self.assertNotEqual(f, pdir.sanitize_filename(f))
             # The sanitized filename should be the same length, though.
-            self.assertEqual(len(f), len(fuse.sanitize_filename(f)))
+            self.assertEqual(len(f), len(pdir.sanitize_filename(f)))
         # Special cases
-        self.assertEqual("_", fuse.sanitize_filename(""))
-        self.assertEqual("_", fuse.sanitize_filename("."))
-        self.assertEqual("__", fuse.sanitize_filename(".."))
+        self.assertEqual("_", pdir.sanitize_filename(""))
+        self.assertEqual("_", pdir.sanitize_filename("."))
+        self.assertEqual("__", pdir.sanitize_filename(".."))
 
 
 class FuseMagicTestPDHOnly(MountTestBase):
@@ -1159,9 +1172,9 @@ class FuseMagicTestPDHOnly(MountTestBase):
         files = {}
         files[os.path.join(self.mounttmp, self.testcollection, 'thing1.txt')] = 'data 1'
 
-        for k, v in files.items():
-            with open(os.path.join(self.mounttmp, k)) as f:
-                self.assertEqual(v, f.read())
+        for k, v in viewitems(files):
+            with open(os.path.join(self.mounttmp, k), 'rb') as f:
+                self.assertEqual(v, f.read().decode())
 
         # look up using uuid should fail when pdh_only is set
         if pdh_only is True:
@@ -1180,3 +1193,63 @@ class FuseMagicTestPDHOnly(MountTestBase):
 
     def test_with_default_by_id(self):
         self.verify_pdh_only(skip_pdh_only=True)
+
+
+class SlashSubstitutionTest(IntegrationTest):
+    mnt_args = [
+        '--read-write',
+        '--mount-home', 'zzz',
+    ]
+
+    def setUp(self):
+        super(SlashSubstitutionTest, self).setUp()
+        self.api = arvados.safeapi.ThreadSafeApiCache(arvados.config.settings())
+        self.api.config = lambda: {"Collections": {"ForwardSlashNameSubstitution": "[SLASH]"}}
+        self.testcoll = self.api.collections().create(body={"name": "foo/bar/baz"}).execute()
+        self.testcolleasy = self.api.collections().create(body={"name": "foo-bar-baz"}).execute()
+        self.fusename = 'foo[SLASH]bar[SLASH]baz'
+
+    @IntegrationTest.mount(argv=mnt_args)
+    @mock.patch('arvados.util.get_config_once')
+    def test_slash_substitution_before_listing(self, get_config_once):
+        get_config_once.return_value = {"Collections": {"ForwardSlashNameSubstitution": "[SLASH]"}}
+        self.pool_test(os.path.join(self.mnt, 'zzz'), self.fusename)
+        self.checkContents()
+    @staticmethod
+    def _test_slash_substitution_before_listing(self, tmpdir, fusename):
+        with open(os.path.join(tmpdir, 'foo-bar-baz', 'waz'), 'w') as f:
+            f.write('xxx')
+        with open(os.path.join(tmpdir, fusename, 'waz'), 'w') as f:
+            f.write('foo')
+
+    @IntegrationTest.mount(argv=mnt_args)
+    @mock.patch('arvados.util.get_config_once')
+    def test_slash_substitution_after_listing(self, get_config_once):
+        get_config_once.return_value = {"Collections": {"ForwardSlashNameSubstitution": "[SLASH]"}}
+        self.pool_test(os.path.join(self.mnt, 'zzz'), self.fusename)
+        self.checkContents()
+    @staticmethod
+    def _test_slash_substitution_after_listing(self, tmpdir, fusename):
+        with open(os.path.join(tmpdir, 'foo-bar-baz', 'waz'), 'w') as f:
+            f.write('xxx')
+        os.listdir(tmpdir)
+        with open(os.path.join(tmpdir, fusename, 'waz'), 'w') as f:
+            f.write('foo')
+
+    def checkContents(self):
+        self.assertRegexpMatches(self.api.collections().get(uuid=self.testcoll['uuid']).execute()['manifest_text'], ' acbd18db') # md5(foo)
+        self.assertRegexpMatches(self.api.collections().get(uuid=self.testcolleasy['uuid']).execute()['manifest_text'], ' f561aaf6') # md5(xxx)
+
+    @IntegrationTest.mount(argv=mnt_args)
+    @mock.patch('arvados.util.get_config_once')
+    def test_slash_substitution_conflict(self, get_config_once):
+        self.testcollconflict = self.api.collections().create(body={"name": self.fusename}).execute()
+        get_config_once.return_value = {"Collections": {"ForwardSlashNameSubstitution": "[SLASH]"}}
+        self.pool_test(os.path.join(self.mnt, 'zzz'), self.fusename)
+        self.assertRegexpMatches(self.api.collections().get(uuid=self.testcollconflict['uuid']).execute()['manifest_text'], ' acbd18db') # md5(foo)
+        # foo/bar/baz collection unchanged, because it is masked by foo[SLASH]bar[SLASH]baz
+        self.assertEqual(self.api.collections().get(uuid=self.testcoll['uuid']).execute()['manifest_text'], '')
+    @staticmethod
+    def _test_slash_substitution_conflict(self, tmpdir, fusename):
+        with open(os.path.join(tmpdir, fusename, 'waz'), 'w') as f:
+            f.write('foo')