From 88e010e59aee40c8e100ffa5243ae6a094b21cf5 Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Wed, 20 Dec 2017 16:07:21 -0500
Subject: [PATCH 01/20] use dataset_full_paths

---
 solvebio/cli/data.py | 23 +++++------------------
 solvebio/cli/main.py | 39 ++++-----------------------------------
 solvebio/client.py   |  1 +
 3 files changed, 10 insertions(+), 53 deletions(-)

diff --git a/solvebio/cli/data.py b/solvebio/cli/data.py
index 5506bbb6..65634f32 100644
--- a/solvebio/cli/data.py
+++ b/solvebio/cli/data.py
@@ -26,11 +26,6 @@ def create_dataset(args):
         * capacity
 
     """
-    if args.vault:
-        vault_name = args.vault
-    else:
-        vault_name = Vault.get_personal_vault().name
-
     # Accept a template_id or a template_file
     if args.template_id:
         # Validate the template ID
@@ -62,7 +57,7 @@ def create_dataset(args):
         print("A new dataset template was created with id: {0}".format(tpl.id))
     else:
         print("Creating a new dataset {0} without a template."
-              .format(args.dataset_name))
+              .format(args.dataset_full_path))
         tpl = None
         fields = []
         entity_type = None
@@ -70,14 +65,14 @@ def create_dataset(args):
 
     if tpl:
         print("Creating new dataset {0} using the template '{1}'."
-              .format(args.dataset_name, tpl.name))
+              .format(args.dataset_full_path, tpl.name))
         fields = tpl.fields
         entity_type = tpl.entity_type
         # include template used to create
         description = 'Created with dataset template: {0}'.format(str(tpl.id))
 
     return solvebio.Dataset.get_or_create_by_full_path(
-        ':'.join([vault_name, os.path.join(args.path, args.dataset_name)]),
+        args.dataset_full_path,
         capacity=args.capacity,
         entity_type=entity_type,
         fields=fields,
@@ -278,25 +273,17 @@ def import_file(args):
     if not solvebio.api_key:
         solvebio.login()
 
-    if args.vault:
-        vault_name = args.vault
-    else:
-        vault_name = Vault.get_personal_vault().name
-
     # Ensure the dataset exists. Create if necessary.
     if args.create_dataset:
         dataset = create_dataset(args)
     else:
         try:
-            full_path = solvebio.Dataset.make_full_path(vault_name,
-                                                        args.path,
-                                                        args.dataset_name)
-            dataset = solvebio.Dataset.get_by_full_path(full_path)
+            dataset = solvebio.Dataset.get_by_full_path(args.dataset_full_path)
         except solvebio.SolveError as e:
             if e.status_code != 404:
                 raise e
 
-            print("Dataset not found: {0}".format(args.dataset_name))
+            print("Dataset not found: {0}".format(args.dataset_full_path))
             print("Tip: use the --create-dataset flag "
                   "to create one from a template")
             sys.exit(1)
diff --git a/solvebio/cli/main.py b/solvebio/cli/main.py
index e367965e..171284ca 100644
--- a/solvebio/cli/main.py
+++ b/solvebio/cli/main.py
@@ -55,19 +55,6 @@ class SolveArgumentParser(argparse.ArgumentParser):
                     'action': 'store_true',
                     'help': 'Create the vault if it doesn\'t exist',
                 },
-                {
-                    'flags': '--vault',
-                    'help': 'The name of the vault to use when '
-                            'creating a new dataset (via --create-dataset), '
-                            'defaults to your personal vault',
-                },
-                {
-                    'flags': '--path',
-                    'default': '/',
-                    'help': 'The path in the vault where the dataset should '
-                            'be created when creating a new dataset'
-                            '(via --create-dataset), defaults to "/"',
-                },
                 {
                     'flags': '--template-id',
                     'help': 'The template ID used when '
@@ -103,8 +90,8 @@ class SolveArgumentParser(argparse.ArgumentParser):
                             'Options are "append" (default) or "overwrite".'
                 },
                 {
-                    'name': 'dataset_name',
-                    'help': 'The name of the dataset'
+                    'name': 'dataset_full_path',
+                    'help': 'The full path to the dataset in the following format: <domain>:<vault>:</object/path/variants>'  # noqa
                 },
                 {
                     'name': 'file',
@@ -122,19 +109,6 @@ class SolveArgumentParser(argparse.ArgumentParser):
                     'action': 'store_true',
                     'help': 'Create the vault if it doesn\'t exist',
                 },
-                {
-                    'flags': '--vault',
-                    'help': 'The name of the vault to use when '
-                            'creating a new dataset (via --create-dataset), '
-                            'defaults to your personal vault',
-                },
-                {
-                    'flags': '--path',
-                    'default': '/',
-                    'help': 'The path in the vault where the dataset should '
-                            'be created when creating a new dataset '
-                            '(via --create-dataset), defaults to "/"',
-                },
                 {
                     'flags': '--template-id',
                     'help': 'The template ID used when '
@@ -145,11 +119,6 @@ class SolveArgumentParser(argparse.ArgumentParser):
                     'help': 'A local template file to be used when '
                             'creating a new dataset (via --create-dataset)',
                 },
-                {
-                    'flags': '--genome-build',
-                    'help': 'If the dataset template is genomic, provide a '
-                            'genome build for your data (i.e. GRCh37)'
-                },
                 {
                     'flags': '--capacity',
                     'default': 'small',
@@ -158,8 +127,8 @@ class SolveArgumentParser(argparse.ArgumentParser):
                             'medium (<500M), large (>=500M)'
                 },
                 {
-                    'name': 'dataset_name',
-                    'help': 'The name of the dataset'
+                    'name': 'dataset_full_path',
+                    'help': 'The full path to the dataset in the following format: <domain>:<vault>:</object/path/variants>'  # noqa
                 }
             ]
         },
diff --git a/solvebio/client.py b/solvebio/client.py
index 0f3d1482..9945b945 100644
--- a/solvebio/client.py
+++ b/solvebio/client.py
@@ -275,4 +275,5 @@ def _log_raw_request(self, method, url, **kwargs):
     def __repr__(self):
         return '<SolveClient {0} {1}>'.format(self._host, self._auth.token)
 
+
 client = SolveClient(include_resources=False)

From c30974a399279e3040b0e5e5f8a57e9ea297307f Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Wed, 20 Dec 2017 16:29:00 -0500
Subject: [PATCH 02/20] fix test

---
 solvebio/test/test_shortcuts.py | 19 ++++++-------------
 1 file changed, 6 insertions(+), 13 deletions(-)

diff --git a/solvebio/test/test_shortcuts.py b/solvebio/test/test_shortcuts.py
index 04321fec..30639038 100644
--- a/solvebio/test/test_shortcuts.py
+++ b/solvebio/test/test_shortcuts.py
@@ -34,11 +34,8 @@ def test_create_dataset(self, DatasetCreate, ObjectAll, VaultAll):
         DatasetCreate.side_effect = fake_dataset_create
         ObjectAll.side_effect = fake_object_all
         VaultAll.side_effect = fake_vault_all
-
-        args = ['create-dataset', 'test-dataset',
-                   '--capacity', 'small',
-                   '--vault', 'test',
-                   '--path', '/']  # noqa
+        args = ['create-dataset', 'solvebio:test_vault:/test-dataset',
+                   '--capacity', 'small']  # noqa
         ds = main.main(args)
         self.assertEqual(ds.name, 'test-dataset')
         self.assertEqual(ds.path, '/test-dataset')
@@ -68,11 +65,9 @@ def test_create_dataset_upload_template(self, TmplCreate,
 
         template_path = os.path.join(os.path.dirname(__file__),
                                      "data/template.json")
-        args = ['create-dataset', 'test-dataset',
+        args = ['create-dataset', 'solvebio:test_vault:/test-dataset',
                    '--template-file', template_path,
-                   '--capacity', 'medium',
-                   '--vault', 'test',
-                   '--path', '/']  # noqa
+                   '--capacity', 'medium']  # noqa
 
         ds = main.main(args)
         self.assertEqual(ds.description,
@@ -96,11 +91,9 @@ def test_create_dataset_template_id(self, TmplRetrieve, DatasetCreate,
             tpl_json = json.load(fp)
 
         tpl = DatasetTemplate.create(**tpl_json)
-        args = ['create-dataset', 'test-dataset',
+        args = ['create-dataset', 'solvebio:test_vault:/test-dataset',
                    '--template-id', str(tpl.id),
-                   '--capacity', 'small',
-                   '--vault', 'test',
-                   '--path', '/']  # noqa
+                   '--capacity', 'small']  # noqa
 
         ds = main.main(args)
         self.assertEqual(ds.description,

From 0e9e15a6fc143323d6fa7a93556689ac145f4c80 Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Thu, 21 Dec 2017 11:36:24 -0500
Subject: [PATCH 03/20] use full paths in upload command as well

---
 solvebio/cli/data.py         | 128 ++++++++++++-----------------------
 solvebio/cli/main.py         |  10 +--
 solvebio/resource/dataset.py |  27 +-------
 solvebio/resource/object.py  |  38 +++++++++++
 4 files changed, 85 insertions(+), 118 deletions(-)

diff --git a/solvebio/cli/data.py b/solvebio/cli/data.py
index 65634f32..fe233951 100644
--- a/solvebio/cli/data.py
+++ b/solvebio/cli/data.py
@@ -10,8 +10,8 @@
 
 import solvebio
 
-from solvebio import Object, Vault
-from solvebio.client import client
+from solvebio import Vault
+from solvebio import Object
 from solvebio.utils.files import check_gzip_path
 from solvebio.errors import ObjectTypeError, NotFoundError
 
@@ -81,10 +81,6 @@ def create_dataset(args):
     )
 
 
-def _make_full_path(s1, s2, s3):
-    return ':'.join([s1, s2, s3])
-
-
 def _assert_object_type(obj, object_type):
     if obj.object_type != object_type:
         raise ObjectTypeError('{0} is a {1} but must be a folder'.format(
@@ -98,27 +94,18 @@ def upload(args):
     Given a folder or file, upload all the folders and files contained
     within it, skipping ones that already exist on the remote.
     """
-    if args.vault:
-        vault_name = args.vault
-    else:
-        vault_name = Vault.get_personal_vault().name
 
-    # '--path /remote/path1 local/path2'
-    # base_remote_path = /remote/path1
-    # base_local_path = local/path2
-    # local_shart = 'path2'
-    base_remote_path = args.path
     base_local_paths = args.local_path
+    base_remote_path, path_dict = Object._to_full_path_helper(args.path)
+    vault_path = path_dict['domain'] + ':' + path_dict['vault']
 
-    user = client.get('/v1/user', {})
-    domain = user['account']['domain']
+    # assert vault exists
+    vault = Vault.get_by_full_path(vault_path)
 
-    vaults = Vault.all(name=vault_name)
-
-    if len(vaults.data) == 0:
-        raise Exception('Vault not found with name "{0}"'.format(vault_name))
-    else:
-        vault = vaults.data[0]
+    # If not the vault root, validate remote path exists and is a folder
+    if path_dict['path'] != '/':
+        _assert_object_type(Object.get_by_full_path(
+            base_remote_path), 'folder')
 
     for local_path in base_local_paths:
 
@@ -126,55 +113,40 @@ def upload(args):
         local_start = os.path.basename(local_path)
 
         if os.path.isdir(local_path):
-            _upload_folder(domain, vault, base_remote_path,
-                           local_path, local_start)
+            _upload_folder(path_dict['domain'], vault,
+                           base_remote_path, local_path, local_start)
         else:
-            if base_remote_path != '/':
-                base_full_remote_path = _make_full_path(
-                    domain,
-                    vault.name,
-                    base_remote_path,
-                )
-                base_remote_object = Object.get_by_full_path(
-                    base_full_remote_path)
-                _assert_object_type(base_remote_object, 'folder')
-                base_remote_path = base_remote_object.path
-            else:
-                base_remote_path = '/'
+            Object.upload_file(
+                local_path, path_dict['path'], path_dict['vault'])
 
-            Object.upload_file(local_path, base_remote_path,
-                               vault.name)
 
+def _upload_folder(domain, vault, base_remote_path,
+                   base_local_path, local_start):
 
-def _upload_folder(domain, vault, base_remote_path, base_local_path,
-                   local_start):
-    # Create the root folder if it does not exist on the remote
+    # Create the upload root folder if it does not exist on the remote
     try:
-        full_root_path = _make_full_path(
-            domain,
-            vault.name,
-            os.path.join(base_remote_path, local_start),
+        upload_root_path, _ = Object._to_full_path_helper(
+            os.path.join(base_remote_path, local_start)
         )
-        root_object = Object.get_by_full_path(full_root_path)
-        _assert_object_type(root_object, 'folder')
+        obj = Object.get_by_full_path(upload_root_path)
+        _assert_object_type(obj, 'folder')
     except NotFoundError:
-        if base_remote_path == '/':
+        base_remote_path, path_dict = \
+            Object._to_full_path_helper(base_remote_path)
+
+        if path_dict['path'] == '/':
             parent_object_id = None
         else:
-            base_remote_full_path = _make_full_path(
-                domain,
-                vault.name,
-                base_remote_path,
-            )
-            obj = Object.get_by_full_path(base_remote_full_path)
+            obj = Object.get_by_full_path(base_remote_path)
             _assert_object_type(obj, 'folder')
             parent_object_id = obj.id
 
+        # Create base folder
         new_folder = Object.create(
             vault_id=vault.id,
             parent_object_id=parent_object_id,
             object_type='folder',
-            filename=local_start,
+            filename=local_start
         )
 
         print('Notice: Folder created for {0} at {1}'.format(
@@ -191,19 +163,15 @@ def _upload_folder(domain, vault, base_remote_path, base_local_path,
                 re.sub('^' + os.path.dirname(base_local_path), '', root).lstrip('/'),  # noqa
                 d
             )
-            full_path = _make_full_path(domain, vault.name, dirpath)
 
             try:
-                Object.get_by_full_path(full_path, object_type='folder')
+                Object.get_by_full_path(dirpath, object_type='folder')
             except NotFoundError:
                 # Create the folder
-                if os.path.dirname(dirpath) == '/':
+                if os.path.dirname(dirpath.split(':')[-1]) == '/':
                     parent_object_id = None
                 else:
-                    parent_full_path = _make_full_path(
-                        domain, vault.name,
-                        os.path.dirname(dirpath))
-
+                    parent_full_path = os.path.dirname(dirpath)
                     parent = Object.get_by_full_path(parent_full_path)
                     _assert_object_type(parent, 'folder')
                     parent_object_id = parent.id
@@ -221,31 +189,23 @@ def _upload_folder(domain, vault, base_remote_path, base_local_path,
 
         # Upload the files that do not yet exist on the remote
         for f in files:
-            file_full_path = _make_full_path(
-                domain,
-                vault.name,
-                os.path.join(
-                    base_remote_path,
-                    re.sub('^' + os.path.dirname(base_local_path),
-                           '',
-                           root).lstrip('/'),
-                    f,
-                )
+            file_full_path = os.path.join(
+                base_remote_path,
+                re.sub('^' + os.path.dirname(base_local_path),
+                       '',
+                       root).lstrip('/'),
+                f,
             )
             try:
                 Object.get_by_full_path(file_full_path)
             except NotFoundError:
-                parent_full_path = _make_full_path(
-                    domain,
-                    vault.name,
-                    os.path.dirname(
-                        os.path.join(
-                            base_remote_path,
-                            re.sub('^' + os.path.dirname(base_local_path),
-                                   '',
-                                   root).lstrip('/'),
-                            f,
-                        )
+                parent_full_path = os.path.dirname(
+                    os.path.join(
+                        base_remote_path,
+                        re.sub('^' + os.path.dirname(base_local_path),
+                               '',
+                               root).lstrip('/'),
+                        f,
                     )
                 )
                 parent = Object.get_by_full_path(parent_full_path)
diff --git a/solvebio/cli/main.py b/solvebio/cli/main.py
index 171284ca..729068b5 100644
--- a/solvebio/cli/main.py
+++ b/solvebio/cli/main.py
@@ -136,17 +136,11 @@ class SolveArgumentParser(argparse.ArgumentParser):
             'func': data.upload,
             'help': 'Upload a file or directory to a SolveBio Vault',
             'arguments': [
-                {
-                    'flags': '--vault',
-                    'help': 'The name of the vault to use when '
-                            'creating a new dataset (via --create-dataset), '
-                            'defaults to your personal vault',
-                },
                 {
                     'flags': '--path',
                     'default': '/',
-                    'help': 'The path in the vault where the files and '
-                            'folders should be created, defaults to "/"',
+                    'help': 'The full path where the files and folders should '
+                    'be created, defaults to "<personal-vault>:/"',
                 },
                 {
                     'name': 'local_path',
diff --git a/solvebio/resource/dataset.py b/solvebio/resource/dataset.py
index 0697ff5a..15a25431 100644
--- a/solvebio/resource/dataset.py
+++ b/solvebio/resource/dataset.py
@@ -61,32 +61,8 @@ def make_full_path(cls, vault_name, path, name, **kwargs):
     @classmethod
     def get_by_full_path(cls, full_path, **kwargs):
         from solvebio import Object
-
         _client = kwargs.pop('client', None) or cls._client or client
-        parts = full_path.split(':', 2)
-
-        if len(parts) == 3:
-            account_domain, vault_name, object_path = parts
-        elif len(parts) == 2:
-            vault_name, object_path = parts
-            user = _client.get('/v1/user', {})
-            account_domain = user['account']['domain']
-        else:
-            raise Exception('Full path must be of the format: '
-                            '"vault_name:object_path" or '
-                            '"account_domain:vault_name:object_path"')
-
-        if object_path[0] != '/':
-            raise Exception(
-                'Paths are absolute and must begin with a "/"'
-            )
-
-        # Remove double slashes and strip trailing slash
-        object_path = re.sub('//+', '/', object_path)
-        if object_path != '/':
-            object_path = object_path.rstrip('/')
-
-        test_path = ':'.join([account_domain, vault_name, object_path])
+        test_path, _ = Object._to_full_path_helper(full_path, client=_client)
         obj = Object.get_by_full_path(test_path, client=_client)
         dataset = Dataset.retrieve(obj['dataset_id'], client=_client, **kwargs)
         return dataset
@@ -106,7 +82,6 @@ def get_or_create_by_full_path(cls, full_path, **kwargs):
             pass
 
         # Dataset not found, create it step-by-step
-
         parts = full_path.split(':', 2)
 
         if len(parts) == 3:
diff --git a/solvebio/resource/object.py b/solvebio/resource/object.py
index 0f14ec0b..2096a545 100644
--- a/solvebio/resource/object.py
+++ b/solvebio/resource/object.py
@@ -1,5 +1,6 @@
 """Solvebio Object API resource"""
 import os
+import re
 import base64
 import binascii
 import mimetypes
@@ -41,6 +42,43 @@ class Object(CreateableAPIResource,
         ('description', 'Description'),
     )
 
+    @classmethod
+    def _to_full_path_helper(cls, full_path, **kwargs):
+        """ Helper method to return full path
+
+            If no vault, use personal vault.
+
+        """
+        _client = kwargs.pop('client', None) or cls._client or client
+        parts = full_path.split(':', 2)
+
+        if len(parts) == 3:
+            account_domain, vault_name, object_path = parts
+        else:
+            user = _client.get('/v1/user', {})
+            account_domain = user['account']['domain']
+            if len(parts) == 2:
+                vault_name, object_path = parts
+            else:
+                vault_name = 'user-{}'.format(user['id'])
+                object_path = full_path or '/'
+
+        if object_path[0] != '/':
+            raise Exception(
+                'Paths {} are absolute and must begin with a "/"'
+                .format(object_path)
+            )
+
+        # Remove double slashes and strip trailing slash
+        object_path = re.sub('//+', '/', object_path)
+        if object_path != '/':
+            object_path = object_path.rstrip('/')
+
+        path = ':'.join([account_domain, vault_name, object_path])
+        return path, dict(domain=account_domain,
+                          vault=vault_name,
+                          path=object_path)
+
     @classmethod
     def get_by_full_path(cls, full_path, **params):
         params.update({'full_path': full_path})

From 8a634e4d19614bff7b72a5800c07b6f58fe44676 Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Thu, 21 Dec 2017 13:12:52 -0500
Subject: [PATCH 04/20] rename vars/func, add vault path validator

---
 solvebio/cli/data.py         |  6 ++--
 solvebio/cli/main.py         |  2 +-
 solvebio/resource/dataset.py |  4 +--
 solvebio/resource/object.py  | 21 ++++++------
 solvebio/resource/vault.py   | 64 +++++++++++++++++++-----------------
 5 files changed, 50 insertions(+), 47 deletions(-)

diff --git a/solvebio/cli/data.py b/solvebio/cli/data.py
index fe233951..2586e913 100644
--- a/solvebio/cli/data.py
+++ b/solvebio/cli/data.py
@@ -96,7 +96,7 @@ def upload(args):
     """
 
     base_local_paths = args.local_path
-    base_remote_path, path_dict = Object._to_full_path_helper(args.path)
+    base_remote_path, path_dict = Object.validate_path(args.path)
     vault_path = path_dict['domain'] + ':' + path_dict['vault']
 
     # assert vault exists
@@ -125,14 +125,14 @@ def _upload_folder(domain, vault, base_remote_path,
 
     # Create the upload root folder if it does not exist on the remote
     try:
-        upload_root_path, _ = Object._to_full_path_helper(
+        upload_root_path, _ = Object.validate_path(
             os.path.join(base_remote_path, local_start)
         )
         obj = Object.get_by_full_path(upload_root_path)
         _assert_object_type(obj, 'folder')
     except NotFoundError:
         base_remote_path, path_dict = \
-            Object._to_full_path_helper(base_remote_path)
+            Object.validate_path(base_remote_path)
 
         if path_dict['path'] == '/':
             parent_object_id = None
diff --git a/solvebio/cli/main.py b/solvebio/cli/main.py
index 729068b5..348e5a87 100644
--- a/solvebio/cli/main.py
+++ b/solvebio/cli/main.py
@@ -91,7 +91,7 @@ class SolveArgumentParser(argparse.ArgumentParser):
                 },
                 {
                     'name': 'dataset_full_path',
-                    'help': 'The full path to the dataset in the following format: <domain>:<vault>:</object/path/variants>'  # noqa
+                    'help': 'The full path to the dataset in the following format: "domain:vault:/path/variants"'  # noqa
                 },
                 {
                     'name': 'file',
diff --git a/solvebio/resource/dataset.py b/solvebio/resource/dataset.py
index 15a25431..be16bb0b 100644
--- a/solvebio/resource/dataset.py
+++ b/solvebio/resource/dataset.py
@@ -1,5 +1,4 @@
 import os
-import re
 import time
 
 from ..client import client
@@ -40,6 +39,7 @@ class Dataset(CreateableAPIResource,
     @classmethod
     def make_full_path(cls, vault_name, path, name, **kwargs):
         from solvebio import SolveError
+w
 
         _client = kwargs.pop('client', None) or cls._client or client
 
@@ -62,7 +62,7 @@ def make_full_path(cls, vault_name, path, name, **kwargs):
     def get_by_full_path(cls, full_path, **kwargs):
         from solvebio import Object
         _client = kwargs.pop('client', None) or cls._client or client
-        test_path, _ = Object._to_full_path_helper(full_path, client=_client)
+        test_path, _ = Object.validate_path(full_path, client=_client)
         obj = Object.get_by_full_path(test_path, client=_client)
         dataset = Dataset.retrieve(obj['dataset_id'], client=_client, **kwargs)
         return dataset
diff --git a/solvebio/resource/object.py b/solvebio/resource/object.py
index 2096a545..c8450631 100644
--- a/solvebio/resource/object.py
+++ b/solvebio/resource/object.py
@@ -43,14 +43,15 @@ class Object(CreateableAPIResource,
     )
 
     @classmethod
-    def _to_full_path_helper(cls, full_path, **kwargs):
-        """ Helper method to return full path
-
-            If no vault, use personal vault.
+    def validate_path(cls, path, **kwargs):
+        """ Helper method to return a full path
 
+            If no account_domain, assumes user's account domain
+            If no vault, uses personal vault.
+            If no path, uses /
         """
         _client = kwargs.pop('client', None) or cls._client or client
-        parts = full_path.split(':', 2)
+        parts = path.split(':', 2)
 
         if len(parts) == 3:
             account_domain, vault_name, object_path = parts
@@ -61,7 +62,7 @@ def _to_full_path_helper(cls, full_path, **kwargs):
                 vault_name, object_path = parts
             else:
                 vault_name = 'user-{}'.format(user['id'])
-                object_path = full_path or '/'
+                object_path = path or '/'
 
         if object_path[0] != '/':
             raise Exception(
@@ -74,10 +75,10 @@ def _to_full_path_helper(cls, full_path, **kwargs):
         if object_path != '/':
             object_path = object_path.rstrip('/')
 
-        path = ':'.join([account_domain, vault_name, object_path])
-        return path, dict(domain=account_domain,
-                          vault=vault_name,
-                          path=object_path)
+        full_path = ':'.join([account_domain, vault_name, object_path])
+        return full_path, dict(domain=account_domain,
+                               vault=vault_name,
+                               path=object_path)
 
     @classmethod
     def get_by_full_path(cls, full_path, **params):
diff --git a/solvebio/resource/vault.py b/solvebio/resource/vault.py
index 062188b7..0bd01ff6 100644
--- a/solvebio/resource/vault.py
+++ b/solvebio/resource/vault.py
@@ -44,6 +44,27 @@ def _object_list_helper(self, **params):
         items = Object.all(client=self._client, **params)
         return items
 
+    @classmethod
+    def validate_path(cls, path, **kwargs):
+        """ Helper method to return a full path
+
+            If no account_domain, assumes user's account domain
+            If no vault, uses personal vault.
+        """
+        _client = kwargs.pop('client', None) or cls._client or client
+        parts = path.split(':', 1)
+
+        if len(parts) == 2:
+            account_domain, vault_name = parts
+        else:
+            user = _client.get('/v1/user', {})
+            account_domain = user['account']['domain']
+            vault_name = '{}:{}'.format(account_domain, path)
+
+        full_path = ':'.join([account_domain, vault_name])
+        return full_path, dict(domain=account_domain,
+                               vault=vault_name)
+
     def files(self, **params):
         return self._object_list_helper(object_type='file', **params)
 
@@ -68,15 +89,9 @@ def create_dataset(self, name, **params):
         if path == '/' or path is None:
             params['vault_parent_object_id'] = None
         else:
-            user = self._client.get('/v1/user', {})
-            account_domain = user['account']['domain']
-
-            parent_object = Object.get_by_full_path(':'.join([
-                account_domain,
-                self.name,
-                path,
-            ]))
-
+            parent_object = Object.get_by_full_path(
+                ':'.join([self.full_path, path])
+            )
             params['vault_parent_object_id'] = parent_object.id
 
         params['name'] = name
@@ -104,28 +119,16 @@ def search(self, query, **params):
 
     @classmethod
     def get_by_full_path(cls, full_path, **kwargs):
-        from solvebio import SolveError
-
         _client = kwargs.pop('client', None) or cls._client or client
-
-        parts = full_path.split(':')
-
-        if len(parts) == 1 or len(parts) == 2:
-            if len(parts) == 1:
-                try:
-                    user = _client.get('/v1/user', {})
-                    account_domain = user['account']['domain']
-                except SolveError as e:
-                    raise Exception("Error obtaining account domain: "
-                                    "{0}".format(e))
-            else:
-                account_domain, full_path = parts
-
-            return Vault._retrieve_helper('vault', 'name', parts[-1],
-                                          account_domain=account_domain,
-                                          name=parts[-1],
-                                          client=_client)
-        else:
+        try:
+            full_path, parts = cls.validate_path(full_path)
+            return Vault._retrieve_helper(
+                'vault', 'name', parts['vault'],
+                account_domain=parts['domain'],
+                name=parts['vault'],
+                client=_client
+            )
+        except:
             raise Exception('Full path must be of the form "vault_name" or '
                             '"account_domain:vault_name"')
 
@@ -139,7 +142,6 @@ def get_or_create_by_full_path(cls, full_path, **kwargs):
             pass
 
         # Vault not found, create it
-
         parts = full_path.split(':', 2)
         vault_name = parts[-1]
 

From c30d1875c7a37ba8e73270e53acfcc57eaad60a1 Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Thu, 21 Dec 2017 13:26:12 -0500
Subject: [PATCH 05/20] typo

---
 solvebio/resource/dataset.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/solvebio/resource/dataset.py b/solvebio/resource/dataset.py
index be16bb0b..390afdbb 100644
--- a/solvebio/resource/dataset.py
+++ b/solvebio/resource/dataset.py
@@ -39,7 +39,6 @@ class Dataset(CreateableAPIResource,
     @classmethod
     def make_full_path(cls, vault_name, path, name, **kwargs):
         from solvebio import SolveError
-w
 
         _client = kwargs.pop('client', None) or cls._client or client
 

From 7afec18f6d483dae11551b357eba395a75409b0d Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Thu, 21 Dec 2017 18:23:45 -0500
Subject: [PATCH 06/20] add tests

---
 solvebio/resource/object.py  | 35 ++++++++++++++++++----------
 solvebio/resource/vault.py   | 15 +++++++++---
 solvebio/test/test_object.py | 45 ++++++++++++++++++++++++++++++++++++
 solvebio/test/test_vault.py  | 29 ++++++++++++++++++++++-
 4 files changed, 108 insertions(+), 16 deletions(-)
 create mode 100644 solvebio/test/test_object.py

diff --git a/solvebio/resource/object.py b/solvebio/resource/object.py
index c8450631..4820793d 100644
--- a/solvebio/resource/object.py
+++ b/solvebio/resource/object.py
@@ -51,27 +51,38 @@ def validate_path(cls, path, **kwargs):
             If no path, uses /
         """
         _client = kwargs.pop('client', None) or cls._client or client
-        parts = path.split(':', 2)
 
+        # Remove double slashes and leading ':'
+        path = re.sub('//+', '/', path.lstrip(':'))
+
+        parts = path.split(':', 2)
         if len(parts) == 3:
             account_domain, vault_name, object_path = parts
+        elif len(parts) == 2:
+            # if no slash assume user means root
+            if '/' not in parts[1]:
+                account_domain, vault_name = parts
+                object_path = '/'
+            else:
+                # if second part begins with slash, assume missing domain
+                if parts[1][0] == '/':
+                    account_domain = \
+                        _client.get('/v1/user', {})['account']['domain']
+                    vault_name, object_path = parts
+                # else assumes missing ":" between vault and path
+                else:
+                    account_domain = parts[0]
+                    vault_name, object_path = parts[1].split('/', 1)
         else:
             user = _client.get('/v1/user', {})
             account_domain = user['account']['domain']
-            if len(parts) == 2:
-                vault_name, object_path = parts
-            else:
-                vault_name = 'user-{}'.format(user['id'])
-                object_path = path or '/'
+            vault_name = 'user-{}'.format(user['id'])
+            object_path = path or '/'
 
         if object_path[0] != '/':
-            raise Exception(
-                'Paths {} are absolute and must begin with a "/"'
-                .format(object_path)
-            )
+            object_path = '/' + object_path
 
-        # Remove double slashes and strip trailing slash
-        object_path = re.sub('//+', '/', object_path)
+        # Strip trailing slash
         if object_path != '/':
             object_path = object_path.rstrip('/')
 
diff --git a/solvebio/resource/vault.py b/solvebio/resource/vault.py
index 0bd01ff6..a4b016a5 100644
--- a/solvebio/resource/vault.py
+++ b/solvebio/resource/vault.py
@@ -52,14 +52,23 @@ def validate_path(cls, path, **kwargs):
             If no vault, uses personal vault.
         """
         _client = kwargs.pop('client', None) or cls._client or client
-        parts = path.split(':', 1)
+        parts = path.split(':')
 
-        if len(parts) == 2:
+        if not path or len(parts) > 2:
+            raise Exception(
+                'Vault path "{}" invalid. Must be of the format: '
+                '"account_domain:vault_name".'.format(path)
+            )
+        elif len(parts) == 2:
             account_domain, vault_name = parts
         else:
             user = _client.get('/v1/user', {})
             account_domain = user['account']['domain']
-            vault_name = '{}:{}'.format(account_domain, path)
+            vault_name = path
+
+        # Strip any paths from the vault_name
+        if '/' in vault_name:
+            vault_name = vault_name.split('/', 1)[0]
 
         full_path = ':'.join([account_domain, vault_name])
         return full_path, dict(domain=account_domain,
diff --git a/solvebio/test/test_object.py b/solvebio/test/test_object.py
new file mode 100644
index 00000000..7c9f9328
--- /dev/null
+++ b/solvebio/test/test_object.py
@@ -0,0 +1,45 @@
+from __future__ import absolute_import
+# from solvebio.resource import Vault
+
+from .helper import SolveBioTestCase
+
+
+class ObjectTests(SolveBioTestCase):
+
+    def test_object_paths(self):
+        vaults = self.client.Vault.all()
+        for vault in vaults:
+            for file_ in list(vault.ls().solve_objects())[:5]:
+                o_path, _ = self.client.Object.validate_path(file_.full_path)
+                self.assertEqual(o_path, file_.full_path)
+
+    def test_object_path_cases(self):
+
+        user = self.client.User.retrieve()
+        domain = user.account.domain
+        user_vault = '{}:user-{}'.format(domain, user.id)
+        test_cases = [
+            ['{}:myVault'.format(domain), '{}:myVault:/'.format(domain)],
+            ['acme:myVault', 'acme:myVault:/'],
+            ['myVault', '{}:/myVault'.format(user_vault)],
+            ['acme:myVault:/uploads_folder', 'acme:myVault:/uploads_folder'],
+            ['acme:myVault:/uploads_folder', 'acme:myVault:/uploads_folder'],
+            ['acme:myVault/uploads_folder', 'acme:myVault:/uploads_folder'],
+            ['myVault:/uploads_folder', '{}:myVault:/uploads_folder'.format(domain)],  # noqa
+            ['/uploads_folder', '{}:/uploads_folder'.format(user_vault)],
+            [':/uploads_folder', '{}:/uploads_folder'.format(user_vault)],
+            ['myVault/uploads_folder', '{}:/myVault/uploads_folder'.format(user_vault)],  # noqa
+        ]
+        for case, expected in test_cases:
+            print case
+            p, _ = self.client.Object.validate_path(case)
+            self.assertEqual(p, expected)
+
+        error_test_cases = [
+            '',
+            'myDomain:myVault:/the/heack',
+            'oops:myDomain:myVault',
+        ]
+        for case in error_test_cases:
+            with self.assertRaises(Exception):
+                v, v_paths = self.client.Vault.validate_path(case)
diff --git a/solvebio/test/test_vault.py b/solvebio/test/test_vault.py
index b0955b7b..63ee9649 100644
--- a/solvebio/test/test_vault.py
+++ b/solvebio/test/test_vault.py
@@ -1,5 +1,4 @@
 from __future__ import absolute_import
-# from solvebio.resource import Vault
 
 from .helper import SolveBioTestCase
 
@@ -27,3 +26,31 @@ def test_vaults(self):
 
         for f in check_fields:
             self.assertTrue(f in vault, '{0} field is present'.format(f))
+
+    def test_vault_paths(self):
+        vaults = self.client.Vault.all()
+        for vault in vaults:
+            v, v_paths = self.client.Vault.validate_path(vault.full_path)
+            self.assertEqual(v, vault.full_path)
+
+        domain = self.client.User.retrieve().account.domain
+        test_cases = [
+            ['myVault', '{}:myVault'.format(domain)],
+            ['{}:myVault'.format(domain), '{}:myVault'.format(domain)],
+            ['acme:myVault', 'acme:myVault'],
+            # this assumes user f-ed and forgot the semi-colon for path
+            ['acme:myVault/uploads_folder', 'acme:myVault'],
+            ['myVault/uploads_folder', '{}:myVault'.format(domain)],
+        ]
+        for case, expected in test_cases:
+            v, v_paths = self.client.Vault.validate_path(case)
+            self.assertEqual(v, expected)
+
+        error_test_cases = [
+            '',
+            'myDomain:myVault:/the/heack',
+            'oops:myDomain:myVault',
+        ]
+        for case in error_test_cases:
+            with self.assertRaises(Exception):
+                v, v_paths = self.client.Vault.validate_path(case)

From 60bf5a7ef1c9671a72aeb72db5ee3829604a6ba6 Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Thu, 21 Dec 2017 19:03:52 -0500
Subject: [PATCH 07/20] update readme

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index ff903ecb..008d1d53 100644
--- a/README.md
+++ b/README.md
@@ -234,11 +234,11 @@ remained unchanged.
 The `objects` property of a resource has been renamed `solve_objects`.
 
 6.  The `import` and `create-dataset` command-line utilities now require
-`--vault` and `--path` arguments.  The `dataset` argument (`test-dataset`
+`--dataset_full_path` arguments.  The `dataset` argument (`test-dataset`
 below) no longer can contain slashes.
 
 ```
-create-dataset --capacity=small --vault=test --path=/  test-dataset
+create-dataset --capacity=small --dataset_ful_path=acme:test:/examples test-dataset
 ```
 
 7. Removal of DatasetCommit approval. The `auto_approve`, `is_approved` and

From 87055b46644fa3843e87e75a045e0c8786a318ff Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Thu, 21 Dec 2017 19:17:21 -0500
Subject: [PATCH 08/20] python3 syntax

---
 solvebio/resource/object.py  |  2 +-
 solvebio/test/test_object.py | 14 +++++++-------
 solvebio/test/test_vault.py  |  6 +++---
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/solvebio/resource/object.py b/solvebio/resource/object.py
index 4820793d..b333ace0 100644
--- a/solvebio/resource/object.py
+++ b/solvebio/resource/object.py
@@ -76,7 +76,7 @@ def validate_path(cls, path, **kwargs):
         else:
             user = _client.get('/v1/user', {})
             account_domain = user['account']['domain']
-            vault_name = 'user-{}'.format(user['id'])
+            vault_name = 'user-{0}'.format(user['id'])
             object_path = path or '/'
 
         if object_path[0] != '/':
diff --git a/solvebio/test/test_object.py b/solvebio/test/test_object.py
index 7c9f9328..0597b937 100644
--- a/solvebio/test/test_object.py
+++ b/solvebio/test/test_object.py
@@ -17,18 +17,18 @@ def test_object_path_cases(self):
 
         user = self.client.User.retrieve()
         domain = user.account.domain
-        user_vault = '{}:user-{}'.format(domain, user.id)
+        user_vault = '{0}:user-{1}'.format(domain, user.id)
         test_cases = [
-            ['{}:myVault'.format(domain), '{}:myVault:/'.format(domain)],
+            ['{0}:myVault'.format(domain), '{0}:myVault:/'.format(domain)],
             ['acme:myVault', 'acme:myVault:/'],
-            ['myVault', '{}:/myVault'.format(user_vault)],
+            ['myVault', '{0}:/myVault'.format(user_vault)],
             ['acme:myVault:/uploads_folder', 'acme:myVault:/uploads_folder'],
             ['acme:myVault:/uploads_folder', 'acme:myVault:/uploads_folder'],
             ['acme:myVault/uploads_folder', 'acme:myVault:/uploads_folder'],
-            ['myVault:/uploads_folder', '{}:myVault:/uploads_folder'.format(domain)],  # noqa
-            ['/uploads_folder', '{}:/uploads_folder'.format(user_vault)],
-            [':/uploads_folder', '{}:/uploads_folder'.format(user_vault)],
-            ['myVault/uploads_folder', '{}:/myVault/uploads_folder'.format(user_vault)],  # noqa
+            ['myVault:/uploads_folder', '{0}:myVault:/uploads_folder'.format(domain)],  # noqa
+            ['/uploads_folder', '{0}:/uploads_folder'.format(user_vault)],
+            [':/uploads_folder', '{0}:/uploads_folder'.format(user_vault)],
+            ['myVault/uploads_folder', '{0}:/myVault/uploads_folder'.format(user_vault)],  # noqa
         ]
         for case, expected in test_cases:
             print case
diff --git a/solvebio/test/test_vault.py b/solvebio/test/test_vault.py
index 63ee9649..d5c0c6c3 100644
--- a/solvebio/test/test_vault.py
+++ b/solvebio/test/test_vault.py
@@ -35,12 +35,12 @@ def test_vault_paths(self):
 
         domain = self.client.User.retrieve().account.domain
         test_cases = [
-            ['myVault', '{}:myVault'.format(domain)],
-            ['{}:myVault'.format(domain), '{}:myVault'.format(domain)],
+            ['myVault', '{0}:myVault'.format(domain)],
+            ['{0}:myVault'.format(domain), '{0}:myVault'.format(domain)],
             ['acme:myVault', 'acme:myVault'],
             # this assumes user f-ed and forgot the semi-colon for path
             ['acme:myVault/uploads_folder', 'acme:myVault'],
-            ['myVault/uploads_folder', '{}:myVault'.format(domain)],
+            ['myVault/uploads_folder', '{0}:myVault'.format(domain)],
         ]
         for case, expected in test_cases:
             v, v_paths = self.client.Vault.validate_path(case)

From 6e5a2ebbac96febe02dbe519553e64c5448671a3 Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Thu, 21 Dec 2017 19:28:31 -0500
Subject: [PATCH 09/20] remove print

---
 solvebio/test/test_object.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/solvebio/test/test_object.py b/solvebio/test/test_object.py
index 0597b937..4bd1c8b3 100644
--- a/solvebio/test/test_object.py
+++ b/solvebio/test/test_object.py
@@ -31,7 +31,6 @@ def test_object_path_cases(self):
             ['myVault/uploads_folder', '{0}:/myVault/uploads_folder'.format(user_vault)],  # noqa
         ]
         for case, expected in test_cases:
-            print case
             p, _ = self.client.Object.validate_path(case)
             self.assertEqual(p, expected)
 

From e36c0f34d3b87c5ca1a724bf662c376cb92d888d Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Thu, 28 Dec 2017 16:07:44 -0500
Subject: [PATCH 10/20] standardize path variable to full-path/full_path and
 add deprecations

---
 README.md            |  4 +--
 solvebio/cli/data.py | 68 +++++++++++++++++++++++++++++++++++++-------
 solvebio/cli/main.py | 40 +++++++++++++++++++++++---
 3 files changed, 95 insertions(+), 17 deletions(-)

diff --git a/README.md b/README.md
index 008d1d53..72e674ab 100644
--- a/README.md
+++ b/README.md
@@ -234,11 +234,11 @@ remained unchanged.
 The `objects` property of a resource has been renamed `solve_objects`.
 
 6.  The `import` and `create-dataset` command-line utilities now require
-`--dataset_full_path` arguments.  The `dataset` argument (`test-dataset`
+`--full-path` arguments.  The `dataset` argument (`test-dataset`
 below) no longer can contain slashes.
 
 ```
-create-dataset --capacity=small --dataset_ful_path=acme:test:/examples test-dataset
+create-dataset --capacity=small --full-path=acme:test:/examples test-dataset
 ```
 
 7. Removal of DatasetCommit approval. The `auto_approve`, `is_approved` and
diff --git a/solvebio/cli/data.py b/solvebio/cli/data.py
index 2586e913..e31ae539 100644
--- a/solvebio/cli/data.py
+++ b/solvebio/cli/data.py
@@ -20,12 +20,37 @@ def create_dataset(args):
     """
     Attempt to create a new dataset given the following params:
 
-        * dataset (full name)
+        * full_path
         * template_id
         * template_file
         * capacity
+        * create_vault
 
     """
+
+    #
+    # Deprecations
+    #
+    if args.vault:
+        raise Exception(
+            '[Deprecated] Pass vault path as part of "full_path"'
+        )
+
+    if args.path:
+        raise Exception(
+            '[Deprecated] Pass path as part of "full_path"'
+        )
+
+    if args.dataset_name:
+        raise Exception(
+            '[Deprecated] Pass dataset_name as part of "full_path"'
+        )
+
+    if args.genome_build:
+        raise Exception(
+            '[Deprecated] The genome_build parameter has been deprecated.'
+        )
+
     # Accept a template_id or a template_file
     if args.template_id:
         # Validate the template ID
@@ -57,7 +82,7 @@ def create_dataset(args):
         print("A new dataset template was created with id: {0}".format(tpl.id))
     else:
         print("Creating a new dataset {0} without a template."
-              .format(args.dataset_full_path))
+              .format(args.full_path))
         tpl = None
         fields = []
         entity_type = None
@@ -65,14 +90,14 @@ def create_dataset(args):
 
     if tpl:
         print("Creating new dataset {0} using the template '{1}'."
-              .format(args.dataset_full_path, tpl.name))
+              .format(args.full_path, tpl.name))
         fields = tpl.fields
         entity_type = tpl.entity_type
         # include template used to create
         description = 'Created with dataset template: {0}'.format(str(tpl.id))
 
     return solvebio.Dataset.get_or_create_by_full_path(
-        args.dataset_full_path,
+        args.full_path,
         capacity=args.capacity,
         entity_type=entity_type,
         fields=fields,
@@ -94,9 +119,13 @@ def upload(args):
     Given a folder or file, upload all the folders and files contained
     within it, skipping ones that already exist on the remote.
     """
+    if args.path:
+        raise Exception(
+            '[Deprecated] Use --full-path instead'
+        )
 
     base_local_paths = args.local_path
-    base_remote_path, path_dict = Object.validate_path(args.path)
+    base_remote_path, path_dict = Object.validate_path(args.full_path)
     vault_path = path_dict['domain'] + ':' + path_dict['vault']
 
     # assert vault exists
@@ -222,14 +251,31 @@ def import_file(args):
 
         * create_dataset
         * template_id
-        * vault_name
-        * path
-        * follow (default: False)
-        * dataset
+        * full_path
+        * commit_mode
         * capacity
         * file (list)
+        * follow (default: False)
 
     """
+    #
+    # Deprecations
+    #
+    if args.vault:
+        raise Exception(
+            '[Deprecated] Pass vault path as part of "full_path"'
+        )
+
+    if args.path:
+        raise Exception(
+            '[Deprecated] Pass path as part of "full_path"'
+        )
+
+    if args.dataset_name:
+        raise Exception(
+            '[Deprecated] Pass dataset_name as part of "full_path"'
+        )
+
     if not solvebio.api_key:
         solvebio.login()
 
@@ -238,12 +284,12 @@ def import_file(args):
         dataset = create_dataset(args)
     else:
         try:
-            dataset = solvebio.Dataset.get_by_full_path(args.dataset_full_path)
+            dataset = solvebio.Dataset.get_by_full_path(args.full_path)
         except solvebio.SolveError as e:
             if e.status_code != 404:
                 raise e
 
-            print("Dataset not found: {0}".format(args.dataset_full_path))
+            print("Dataset not found: {0}".format(args.full_path))
             print("Tip: use the --create-dataset flag "
                   "to create one from a template")
             sys.exit(1)
diff --git a/solvebio/cli/main.py b/solvebio/cli/main.py
index 348e5a87..14a663bc 100644
--- a/solvebio/cli/main.py
+++ b/solvebio/cli/main.py
@@ -90,13 +90,25 @@ class SolveArgumentParser(argparse.ArgumentParser):
                             'Options are "append" (default) or "overwrite".'
                 },
                 {
-                    'name': 'dataset_full_path',
+                    'name': 'full_path',
                     'help': 'The full path to the dataset in the following format: "domain:vault:/path/variants"'  # noqa
                 },
                 {
                     'name': 'file',
                     'help': 'One or more local files to import',
                     'nargs': '+'
+                },
+                {
+                    'flags': '--vault',
+                    'help': '[Deprecated] Pass vault path as part of "full_path"'  # noqa
+                },
+                {
+                    'flags': '--path',
+                    'help': '[Deprecated] Pass path as part of "full_path"'  # noqa
+                },
+                {
+                    'name': 'dataset_name',
+                    'help': '[Deprecated] Pass dataset_name as part of "full_path"'  # noqa
                 }
             ]
         },
@@ -127,9 +139,25 @@ class SolveArgumentParser(argparse.ArgumentParser):
                             'medium (<500M), large (>=500M)'
                 },
                 {
-                    'name': 'dataset_full_path',
+                    'name': 'full_path',
                     'help': 'The full path to the dataset in the following format: <domain>:<vault>:</object/path/variants>'  # noqa
-                }
+                },
+                {
+                    'flags': '--vault',
+                    'help': '[Deprecated] Pass vault path as part of "full_path"'  # noqa
+                },
+                {
+                    'flags': '--path',
+                    'help': '[Deprecated] Pass path as part of "full_path"'  # noqa
+                },
+                {
+                    'name': 'dataset_name',
+                    'help': '[Deprecated] Pass dataset_name as part of "full_path"'  # noqa
+                },
+                {
+                    'flags': '--genome-build',
+                    'help': '[Deprecated] This parameter is no longer in use."'  # noqa
+                },
             ]
         },
         'upload': {
@@ -137,7 +165,7 @@ class SolveArgumentParser(argparse.ArgumentParser):
             'help': 'Upload a file or directory to a SolveBio Vault',
             'arguments': [
                 {
-                    'flags': '--path',
+                    'flags': '--full-path',
                     'default': '/',
                     'help': 'The full path where the files and folders should '
                     'be created, defaults to "<personal-vault>:/"',
@@ -147,6 +175,10 @@ class SolveArgumentParser(argparse.ArgumentParser):
                     'help': 'The path to the local file or directory '
                             'to upload',
                     'nargs': '+'
+                },
+                {
+                    'flags': '--path',
+                    'help': '[Deprecated] Use --full-path'
                 }
             ]
         },

From 37b2134aefda8f291ca71c53534567c6da224bfb Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Thu, 28 Dec 2017 16:13:09 -0500
Subject: [PATCH 11/20] update messages

---
 solvebio/cli/data.py | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/solvebio/cli/data.py b/solvebio/cli/data.py
index e31ae539..5c670bb4 100644
--- a/solvebio/cli/data.py
+++ b/solvebio/cli/data.py
@@ -33,22 +33,22 @@ def create_dataset(args):
     #
     if args.vault:
         raise Exception(
-            '[Deprecated] Pass vault path as part of "full_path"'
+            '[Deprecated] --vault has been deprecated. Pass vault path as part of "full_path"'  # noqa
         )
 
     if args.path:
         raise Exception(
-            '[Deprecated] Pass path as part of "full_path"'
+            '[Deprecated] --path has been deprecated. Pass path as part of "full_path"'  # noqa
         )
 
     if args.dataset_name:
         raise Exception(
-            '[Deprecated] Pass dataset_name as part of "full_path"'
+            '[Deprecated] "dataset_name" has been deprecated. Pass as part of "full_path"'  # noqa
         )
 
     if args.genome_build:
         raise Exception(
-            '[Deprecated] The genome_build parameter has been deprecated.'
+            '[Deprecated] The --genome_build parameter has been deprecated.'
         )
 
     # Accept a template_id or a template_file
@@ -121,7 +121,7 @@ def upload(args):
     """
     if args.path:
         raise Exception(
-            '[Deprecated] Use --full-path instead'
+            '[Deprecated] Flag --path has been deprecated. Use --full-path instead'  # noqa
         )
 
     base_local_paths = args.local_path
@@ -263,17 +263,17 @@ def import_file(args):
     #
     if args.vault:
         raise Exception(
-            '[Deprecated] Pass vault path as part of "full_path"'
+            '[Deprecated] --vault has been deprecated. Pass vault path as part of "full_path"'  # noqa
         )
 
     if args.path:
         raise Exception(
-            '[Deprecated] Pass path as part of "full_path"'
+            '[Deprecated] --path has been deprecated. Pass path as part of "full_path"'  # noqa
         )
 
     if args.dataset_name:
         raise Exception(
-            '[Deprecated] Pass dataset_name as part of "full_path"'
+            '[Deprecated] "dataset_name" has been deprecated. Pass as part of "full_path"'  # noqa
         )
 
     if not solvebio.api_key:

From 2151143e492719a633fc971824fa7a54401138e0 Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Thu, 28 Dec 2017 16:50:54 -0500
Subject: [PATCH 12/20] update cases

---
 solvebio/resource/object.py  | 27 ++++++++++++++++++++-------
 solvebio/test/test_object.py | 10 ++++------
 2 files changed, 24 insertions(+), 13 deletions(-)

diff --git a/solvebio/resource/object.py b/solvebio/resource/object.py
index b333ace0..84e876bc 100644
--- a/solvebio/resource/object.py
+++ b/solvebio/resource/object.py
@@ -50,6 +50,8 @@ def validate_path(cls, path, **kwargs):
             If no vault, uses personal vault.
             If no path, uses /
         """
+        from solvebio.resource.vault import Vault
+
         _client = kwargs.pop('client', None) or cls._client or client
 
         # Remove double slashes and leading ':'
@@ -69,15 +71,26 @@ def validate_path(cls, path, **kwargs):
                     account_domain = \
                         _client.get('/v1/user', {})['account']['domain']
                     vault_name, object_path = parts
-                # else assumes missing ":" between vault and path
                 else:
-                    account_domain = parts[0]
-                    vault_name, object_path = parts[1].split('/', 1)
+                    raise Exception('Full path must be of the format: '
+                                    '"vault_name:object_path" or '
+                                    '"account_domain:vault_name:object_path"')
+                    # TODO maybe no good
+                    # assumes missing ":" between vault and path
+                    #   mydomain:myvault/here/is/path
+                    #   myvault:here/is/path
+                    # account_domain = parts[0]
+                    # vault_name, object_path = parts[1].split('/', 1)
         else:
-            user = _client.get('/v1/user', {})
-            account_domain = user['account']['domain']
-            vault_name = 'user-{0}'.format(user['id'])
-            object_path = path or '/'
+            # if slash assume user means private vault
+            if '/' in parts[0]:
+                vault = Vault.get_personal_vault(client=_client)
+                account_domain, vault_name = vault.full_path.split(':')
+                object_path = parts[0]
+            else:
+                raise Exception('Full path must be of the format: '
+                                '"vault_name:object_path" or '
+                                '"account_domain:vault_name:object_path"')
 
         if object_path[0] != '/':
             object_path = '/' + object_path
diff --git a/solvebio/test/test_object.py b/solvebio/test/test_object.py
index 4bd1c8b3..2595df87 100644
--- a/solvebio/test/test_object.py
+++ b/solvebio/test/test_object.py
@@ -21,14 +21,12 @@ def test_object_path_cases(self):
         test_cases = [
             ['{0}:myVault'.format(domain), '{0}:myVault:/'.format(domain)],
             ['acme:myVault', 'acme:myVault:/'],
-            ['myVault', '{0}:/myVault'.format(user_vault)],
             ['acme:myVault:/uploads_folder', 'acme:myVault:/uploads_folder'],
-            ['acme:myVault:/uploads_folder', 'acme:myVault:/uploads_folder'],
-            ['acme:myVault/uploads_folder', 'acme:myVault:/uploads_folder'],
             ['myVault:/uploads_folder', '{0}:myVault:/uploads_folder'.format(domain)],  # noqa
             ['/uploads_folder', '{0}:/uploads_folder'.format(user_vault)],
             [':/uploads_folder', '{0}:/uploads_folder'.format(user_vault)],
             ['myVault/uploads_folder', '{0}:/myVault/uploads_folder'.format(user_vault)],  # noqa
+            ['oops:myDomain:myVault', 'oops:myDomain:/myVault'],
         ]
         for case, expected in test_cases:
             p, _ = self.client.Object.validate_path(case)
@@ -36,9 +34,9 @@ def test_object_path_cases(self):
 
         error_test_cases = [
             '',
-            'myDomain:myVault:/the/heack',
-            'oops:myDomain:myVault',
+            'myVault',
+            'acme:myVault/uploads_folder'
         ]
         for case in error_test_cases:
             with self.assertRaises(Exception):
-                v, v_paths = self.client.Vault.validate_path(case)
+                v, v_paths = self.client.Object.validate_path(case)

From 549b1aa7d3ddeae0c7aef0ba018631fc5c506223 Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Fri, 29 Dec 2017 10:13:47 -0500
Subject: [PATCH 13/20] remove deprecation

---
 solvebio/cli/data.py | 5 -----
 solvebio/cli/main.py | 4 ----
 2 files changed, 9 deletions(-)

diff --git a/solvebio/cli/data.py b/solvebio/cli/data.py
index 5c670bb4..11301868 100644
--- a/solvebio/cli/data.py
+++ b/solvebio/cli/data.py
@@ -41,11 +41,6 @@ def create_dataset(args):
             '[Deprecated] --path has been deprecated. Pass path as part of "full_path"'  # noqa
         )
 
-    if args.dataset_name:
-        raise Exception(
-            '[Deprecated] "dataset_name" has been deprecated. Pass as part of "full_path"'  # noqa
-        )
-
     if args.genome_build:
         raise Exception(
             '[Deprecated] The --genome_build parameter has been deprecated.'
diff --git a/solvebio/cli/main.py b/solvebio/cli/main.py
index 14a663bc..f5846d3a 100644
--- a/solvebio/cli/main.py
+++ b/solvebio/cli/main.py
@@ -150,10 +150,6 @@ class SolveArgumentParser(argparse.ArgumentParser):
                     'flags': '--path',
                     'help': '[Deprecated] Pass path as part of "full_path"'  # noqa
                 },
-                {
-                    'name': 'dataset_name',
-                    'help': '[Deprecated] Pass dataset_name as part of "full_path"'  # noqa
-                },
                 {
                     'flags': '--genome-build',
                     'help': '[Deprecated] This parameter is no longer in use."'  # noqa

From 5fb70d5c6f5b95d4a62e47aae7591f5c7c112e64 Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Fri, 29 Dec 2017 12:11:04 -0500
Subject: [PATCH 14/20] remove except statement that masked already handled
 error

---
 solvebio/resource/apiresource.py |  1 -
 solvebio/resource/vault.py       | 18 +++++++-----------
 2 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/solvebio/resource/apiresource.py b/solvebio/resource/apiresource.py
index c6496544..a1a66b65 100644
--- a/solvebio/resource/apiresource.py
+++ b/solvebio/resource/apiresource.py
@@ -245,7 +245,6 @@ def _retrieve_helper(cls, model_name, field_name, error_value, **params):
         results = convert_to_solve_object(response, client=_client)
         objects = results.data
         allow_multiple = params.pop('allow_multiple', None)
-
         if len(objects) > 1:
             if allow_multiple:
                 return objects
diff --git a/solvebio/resource/vault.py b/solvebio/resource/vault.py
index a4b016a5..3de835d8 100644
--- a/solvebio/resource/vault.py
+++ b/solvebio/resource/vault.py
@@ -129,17 +129,13 @@ def search(self, query, **params):
     @classmethod
     def get_by_full_path(cls, full_path, **kwargs):
         _client = kwargs.pop('client', None) or cls._client or client
-        try:
-            full_path, parts = cls.validate_path(full_path)
-            return Vault._retrieve_helper(
-                'vault', 'name', parts['vault'],
-                account_domain=parts['domain'],
-                name=parts['vault'],
-                client=_client
-            )
-        except:
-            raise Exception('Full path must be of the form "vault_name" or '
-                            '"account_domain:vault_name"')
+        full_path, parts = cls.validate_path(full_path)
+        return Vault._retrieve_helper(
+            'vault', 'name', full_path,
+            account_domain=parts['domain'],
+            name=parts['vault'],
+            client=_client
+        )
 
     @classmethod
     def get_or_create_by_full_path(cls, full_path, **kwargs):

From 9d43da2cd706cc4df164831fce7de74f656ee0a6 Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Fri, 29 Dec 2017 12:20:53 -0500
Subject: [PATCH 15/20] update path handling for creating datasets and errors

---
 solvebio/resource/dataset.py | 23 +++++++++++------------
 solvebio/resource/object.py  |  8 ++++----
 2 files changed, 15 insertions(+), 16 deletions(-)

diff --git a/solvebio/resource/dataset.py b/solvebio/resource/dataset.py
index 390afdbb..2720223f 100644
--- a/solvebio/resource/dataset.py
+++ b/solvebio/resource/dataset.py
@@ -75,34 +75,33 @@ def get_or_create_by_full_path(cls, full_path, **kwargs):
         create_vault = kwargs.pop('create_vault', False)
         create_folders = kwargs.pop('create_folders', True)
 
+        # Validate path
+
         try:
             return Dataset.get_by_full_path(full_path, client=_client)
         except NotFoundError:
             pass
 
         # Dataset not found, create it step-by-step
-        parts = full_path.split(':', 2)
-
-        if len(parts) == 3:
-            account_domain, vault_name, object_path = parts
-        elif len(parts) == 2:
-            vault_name, object_path = parts
-            user = _client.get('/v1/user', {})
-            account_domain = user['account']['domain']
+        full_path, parts = Object.validate_path(full_path, client=_client)
 
         if create_vault:
             vault = Vault.get_or_create_by_full_path(
-                '{0}:{1}'.format(account_domain, vault_name),
+                '{0}:{1}'.format(parts['domain'], parts['vault']),
                 client=_client)
         else:
-            vaults = Vault.all(account_domain=account_domain, name=vault_name,
+            vaults = Vault.all(account_domain=parts['domain'],
+                               name=parts['vault'],
                                client=_client)
             if len(vaults.solve_objects()) == 0:
-                raise Exception('Vault does not exist with name {0}'.format(
-                    vault_name))
+                raise Exception(
+                    'Vault does not exist with name {0}:{1}'.format(
+                        parts['domain'], parts['vault'])
+                )
             vault = vaults.solve_objects()[0]
 
         # Create the folders to hold the dataset if they do not already exist.
+        object_path = parts['path']
         curr_path = os.path.dirname(object_path)
         folders_to_create = []
         new_folders = []
diff --git a/solvebio/resource/object.py b/solvebio/resource/object.py
index 84e876bc..4f57463c 100644
--- a/solvebio/resource/object.py
+++ b/solvebio/resource/object.py
@@ -73,8 +73,8 @@ def validate_path(cls, path, **kwargs):
                     vault_name, object_path = parts
                 else:
                     raise Exception('Full path must be of the format: '
-                                    '"vault_name:object_path" or '
-                                    '"account_domain:vault_name:object_path"')
+                                    '"vault_name:/object_path" or '
+                                    '"account_domain:vault_name:/object_path"')
                     # TODO maybe no good
                     # assumes missing ":" between vault and path
                     #   mydomain:myvault/here/is/path
@@ -89,8 +89,8 @@ def validate_path(cls, path, **kwargs):
                 object_path = parts[0]
             else:
                 raise Exception('Full path must be of the format: '
-                                '"vault_name:object_path" or '
-                                '"account_domain:vault_name:object_path"')
+                                '"vault_name:/object_path" or '
+                                '"account_domain:vault_name:/object_path"')
 
         if object_path[0] != '/':
             object_path = '/' + object_path

From 4e0b745e54f19725aa25c915ca7cba0941017fdd Mon Sep 17 00:00:00 2001
From: Jeff Hull <jsh2134@gmail.com>
Date: Fri, 29 Dec 2017 12:26:18 -0500
Subject: [PATCH 16/20] including these deprecations is very confusing

---
 solvebio/cli/data.py | 15 ---------------
 solvebio/cli/main.py |  8 --------
 2 files changed, 23 deletions(-)

diff --git a/solvebio/cli/data.py b/solvebio/cli/data.py
index 11301868..0f7f8dba 100644
--- a/solvebio/cli/data.py
+++ b/solvebio/cli/data.py
@@ -36,11 +36,6 @@ def create_dataset(args):
             '[Deprecated] --vault has been deprecated. Pass vault path as part of "full_path"'  # noqa
         )
 
-    if args.path:
-        raise Exception(
-            '[Deprecated] --path has been deprecated. Pass path as part of "full_path"'  # noqa
-        )
-
     if args.genome_build:
         raise Exception(
             '[Deprecated] The --genome_build parameter has been deprecated.'
@@ -261,16 +256,6 @@ def import_file(args):
             '[Deprecated] --vault has been deprecated. Pass vault path as part of "full_path"'  # noqa
         )
 
-    if args.path:
-        raise Exception(
-            '[Deprecated] --path has been deprecated. Pass path as part of "full_path"'  # noqa
-        )
-
-    if args.dataset_name:
-        raise Exception(
-            '[Deprecated] "dataset_name" has been deprecated. Pass as part of "full_path"'  # noqa
-        )
-
     if not solvebio.api_key:
         solvebio.login()
 
diff --git a/solvebio/cli/main.py b/solvebio/cli/main.py
index f5846d3a..2805c575 100644
--- a/solvebio/cli/main.py
+++ b/solvebio/cli/main.py
@@ -101,14 +101,6 @@ class SolveArgumentParser(argparse.ArgumentParser):
                 {
                     'flags': '--vault',
                     'help': '[Deprecated] Pass vault path as part of "full_path"'  # noqa
-                },
-                {
-                    'flags': '--path',
-                    'help': '[Deprecated] Pass path as part of "full_path"'  # noqa
-                },
-                {
-                    'name': 'dataset_name',
-                    'help': '[Deprecated] Pass dataset_name as part of "full_path"'  # noqa
                 }
             ]
         },

From d8328d10c2db240b8fb0ed5e81525bc8582fff8e Mon Sep 17 00:00:00 2001
From: David Caplan <dcaplan@gmail.com>
Date: Wed, 3 Jan 2018 16:36:55 -0500
Subject: [PATCH 17/20] add back --vault and --path, but ensure --full-path
 overrides

---
 solvebio/cli/data.py | 239 ++++++++++++++++++++++---------------------
 solvebio/cli/main.py |  61 +++++++----
 2 files changed, 161 insertions(+), 139 deletions(-)

diff --git a/solvebio/cli/data.py b/solvebio/cli/data.py
index 0f7f8dba..55ec363e 100644
--- a/solvebio/cli/data.py
+++ b/solvebio/cli/data.py
@@ -16,84 +16,25 @@
 from solvebio.errors import ObjectTypeError, NotFoundError
 
 
-def create_dataset(args):
-    """
-    Attempt to create a new dataset given the following params:
-
-        * full_path
-        * template_id
-        * template_file
-        * capacity
-        * create_vault
-
+def _full_path_from_args(args):
     """
+    Handles the following args:
 
-    #
-    # Deprecations
-    #
-    if args.vault:
-        raise Exception(
-            '[Deprecated] --vault has been deprecated. Pass vault path as part of "full_path"'  # noqa
-        )
-
-    if args.genome_build:
-        raise Exception(
-            '[Deprecated] The --genome_build parameter has been deprecated.'
-        )
-
-    # Accept a template_id or a template_file
-    if args.template_id:
-        # Validate the template ID
-        try:
-            tpl = solvebio.DatasetTemplate.retrieve(args.template_id)
-        except solvebio.SolveError as e:
-            if e.status_code != 404:
-                raise e
-            print("No template with ID {0} found!"
-                  .format(args.template_id))
-            sys.exit(1)
-    elif args.template_file:
-        mode = 'r'
-        fopen = open
-        if check_gzip_path(args.template_file):
-            mode = 'rb'
-            fopen = gzip.open
+    * full-path
+    * vault
+    * path
 
-        # Validate the template file
-        with fopen(args.template_file, mode) as fp:
-            try:
-                tpl_json = json.load(fp)
-            except:
-                print('Template file {0} could not be loaded. Please '
-                      'pass valid JSON'.format(args.template_file))
-                sys.exit(1)
+    Always uses "full_path" if provided (overrides vault and path).
+    Otherwise, attempts to use "vault" and "path".
 
-        tpl = solvebio.DatasetTemplate.create(**tpl_json)
-        print("A new dataset template was created with id: {0}".format(tpl.id))
-    else:
-        print("Creating a new dataset {0} without a template."
-              .format(args.full_path))
-        tpl = None
-        fields = []
-        entity_type = None
-        description = None
+    If no paths are specified, defaults to personal-vault:/
+    """
+    if args.full_path:
+        return args.full_path
 
-    if tpl:
-        print("Creating new dataset {0} using the template '{1}'."
-              .format(args.full_path, tpl.name))
-        fields = tpl.fields
-        entity_type = tpl.entity_type
-        # include template used to create
-        description = 'Created with dataset template: {0}'.format(str(tpl.id))
-
-    return solvebio.Dataset.get_or_create_by_full_path(
-        args.full_path,
-        capacity=args.capacity,
-        entity_type=entity_type,
-        fields=fields,
-        description=description,
-        create_vault=args.create_vault,
-    )
+    return '{0}:{1}'.format(
+        args.vault or Vault.get_personal_vault().name,
+        args.path or '/')
 
 
 def _assert_object_type(obj, object_type):
@@ -104,41 +45,6 @@ def _assert_object_type(obj, object_type):
         ))
 
 
-def upload(args):
-    """
-    Given a folder or file, upload all the folders and files contained
-    within it, skipping ones that already exist on the remote.
-    """
-    if args.path:
-        raise Exception(
-            '[Deprecated] Flag --path has been deprecated. Use --full-path instead'  # noqa
-        )
-
-    base_local_paths = args.local_path
-    base_remote_path, path_dict = Object.validate_path(args.full_path)
-    vault_path = path_dict['domain'] + ':' + path_dict['vault']
-
-    # assert vault exists
-    vault = Vault.get_by_full_path(vault_path)
-
-    # If not the vault root, validate remote path exists and is a folder
-    if path_dict['path'] != '/':
-        _assert_object_type(Object.get_by_full_path(
-            base_remote_path), 'folder')
-
-    for local_path in base_local_paths:
-
-        local_path = local_path.rstrip('/')
-        local_start = os.path.basename(local_path)
-
-        if os.path.isdir(local_path):
-            _upload_folder(path_dict['domain'], vault,
-                           base_remote_path, local_path, local_start)
-        else:
-            Object.upload_file(
-                local_path, path_dict['path'], path_dict['vault'])
-
-
 def _upload_folder(domain, vault, base_remote_path,
                    base_local_path, local_start):
 
@@ -233,6 +139,106 @@ def _upload_folder(domain, vault, base_remote_path,
                                    vault.name)
 
 
+def create_dataset(args):
+    """
+    Attempt to create a new dataset given the following params:
+
+        * full_path (or vault & path)
+        * template_id
+        * template_file
+        * capacity
+        * create_vault
+
+    NOTE: genome_build has been deprecated and is no longer used.
+
+    """
+    full_path = _full_path_from_args(args)
+
+    # Accept a template_id or a template_file
+    if args.template_id:
+        # Validate the template ID
+        try:
+            tpl = solvebio.DatasetTemplate.retrieve(args.template_id)
+        except solvebio.SolveError as e:
+            if e.status_code != 404:
+                raise e
+            print("No template with ID {0} found!"
+                  .format(args.template_id))
+            sys.exit(1)
+    elif args.template_file:
+        mode = 'r'
+        fopen = open
+        if check_gzip_path(args.template_file):
+            mode = 'rb'
+            fopen = gzip.open
+
+        # Validate the template file
+        with fopen(args.template_file, mode) as fp:
+            try:
+                tpl_json = json.load(fp)
+            except:
+                print('Template file {0} could not be loaded. Please '
+                      'pass valid JSON'.format(args.template_file))
+                sys.exit(1)
+
+        tpl = solvebio.DatasetTemplate.create(**tpl_json)
+        print("A new dataset template was created with id: {0}".format(tpl.id))
+    else:
+        print("Creating a new dataset {0} without a template."
+              .format(full_path))
+        tpl = None
+        fields = []
+        entity_type = None
+        description = None
+
+    if tpl:
+        print("Creating new dataset {0} using the template '{1}'."
+              .format(full_path, tpl.name))
+        fields = tpl.fields
+        entity_type = tpl.entity_type
+        # include template used to create
+        description = 'Created with dataset template: {0}'.format(str(tpl.id))
+
+    return solvebio.Dataset.get_or_create_by_full_path(
+        full_path,
+        capacity=args.capacity,
+        entity_type=entity_type,
+        fields=fields,
+        description=description,
+        create_vault=args.create_vault,
+    )
+
+
+def upload(args):
+    """
+    Given a folder or file, upload all the folders and files contained
+    within it, skipping ones that already exist on the remote.
+    """
+
+    full_path = _full_path_from_args(args)
+    base_remote_path, path_dict = Object.validate_path(full_path)
+    vault_path = path_dict['domain'] + ':' + path_dict['vault']
+
+    # Assert the vault exists and is accessible
+    vault = Vault.get_by_full_path(vault_path)
+
+    # If not the vault root, validate remote path exists and is a folder
+    if path_dict['path'] != '/':
+        _assert_object_type(Object.get_by_full_path(
+            base_remote_path), 'folder')
+
+    for local_path in args.local_path:
+        local_path = local_path.rstrip('/')
+        local_start = os.path.basename(local_path)
+
+        if os.path.isdir(local_path):
+            _upload_folder(path_dict['domain'], vault,
+                           base_remote_path, local_path, local_start)
+        else:
+            Object.upload_file(
+                local_path, path_dict['path'], path_dict['vault'])
+
+
 def import_file(args):
     """
     Given a dataset and a local path, upload and import the file(s).
@@ -241,35 +247,30 @@ def import_file(args):
 
         * create_dataset
         * template_id
-        * full_path
+        * full_path (or vault & path)
         * commit_mode
         * capacity
         * file (list)
         * follow (default: False)
 
     """
-    #
-    # Deprecations
-    #
-    if args.vault:
-        raise Exception(
-            '[Deprecated] --vault has been deprecated. Pass vault path as part of "full_path"'  # noqa
-        )
-
+    # FIXME: Does this need to be here? What about other commands?
     if not solvebio.api_key:
         solvebio.login()
 
+    full_path = _full_path_from_args(args)
+
     # Ensure the dataset exists. Create if necessary.
     if args.create_dataset:
         dataset = create_dataset(args)
     else:
         try:
-            dataset = solvebio.Dataset.get_by_full_path(args.full_path)
+            dataset = solvebio.Dataset.get_by_full_path(full_path)
         except solvebio.SolveError as e:
             if e.status_code != 404:
                 raise e
 
-            print("Dataset not found: {0}".format(args.full_path))
+            print("Dataset not found: {0}".format(full_path))
             print("Tip: use the --create-dataset flag "
                   "to create one from a template")
             sys.exit(1)
diff --git a/solvebio/cli/main.py b/solvebio/cli/main.py
index 2805c575..2111c42b 100644
--- a/solvebio/cli/main.py
+++ b/solvebio/cli/main.py
@@ -90,18 +90,28 @@ class SolveArgumentParser(argparse.ArgumentParser):
                             'Options are "append" (default) or "overwrite".'
                 },
                 {
-                    'name': 'full_path',
-                    'help': 'The full path to the dataset in the following format: "domain:vault:/path/variants"'  # noqa
+                    'flags': '--full-path',
+                    'help': 'The full path to the dataset in the format: '
+                    '"domain:vault:/path/dataset". '
+                    'Overrides --vault and --path'
+                },
+                {
+                    'flags': '--vault',
+                    'help':
+                    'The vault containing the dataset (use with --path). '
+                    'Defaults to your personal vault. '
+                    'Overridden by --full-path'
+                },
+                {
+                    'flags': '--path',
+                    'help': 'The path to the dataset (relative to the vault). '
+                    'Used with --vault, overridden by --full-path'
                 },
                 {
                     'name': 'file',
                     'help': 'One or more local files to import',
                     'nargs': '+'
                 },
-                {
-                    'flags': '--vault',
-                    'help': '[Deprecated] Pass vault path as part of "full_path"'  # noqa
-                }
             ]
         },
         'create-dataset': {
@@ -131,20 +141,22 @@ class SolveArgumentParser(argparse.ArgumentParser):
                             'medium (<500M), large (>=500M)'
                 },
                 {
-                    'name': 'full_path',
-                    'help': 'The full path to the dataset in the following format: <domain>:<vault>:</object/path/variants>'  # noqa
+                    'flags': '--full-path',
+                    'help': 'The full path to the dataset in the format: '
+                    '"domain:vault:/path/dataset". '
+                    'Overrides --vault and --path'
                 },
                 {
                     'flags': '--vault',
-                    'help': '[Deprecated] Pass vault path as part of "full_path"'  # noqa
+                    'help':
+                    'The vault containing the dataset (use with --path). '
+                    'Defaults to your personal vault. '
+                    'Overridden by --full-path'
                 },
                 {
                     'flags': '--path',
-                    'help': '[Deprecated] Pass path as part of "full_path"'  # noqa
-                },
-                {
-                    'flags': '--genome-build',
-                    'help': '[Deprecated] This parameter is no longer in use."'  # noqa
+                    'help': 'The path to the dataset (relative to the vault). '
+                    'Used with --vault, overridden by --full-path'
                 },
             ]
         },
@@ -154,19 +166,28 @@ class SolveArgumentParser(argparse.ArgumentParser):
             'arguments': [
                 {
                     'flags': '--full-path',
-                    'default': '/',
                     'help': 'The full path where the files and folders should '
-                    'be created, defaults to "<personal-vault>:/"',
+                    'be created, defaults to the root of your personal vault. '
+                    'Overrides --vault and --path'
+                },
+                {
+                    'flags': '--vault',
+                    'help': 'The vault where the files will be uploaded. '
+                    'Defaults to your personal vault. '
+                    'Overridden by --full-path'
+                },
+                {
+                    'flags': '--path',
+                    'help': 'The path (relative to a vault) '
+                    'where the files will be uploaded. '
+                    'Defaults to the root directory (/). '
+                    'Overridden by --full-path'
                 },
                 {
                     'name': 'local_path',
                     'help': 'The path to the local file or directory '
                             'to upload',
                     'nargs': '+'
-                },
-                {
-                    'flags': '--path',
-                    'help': '[Deprecated] Use --full-path'
                 }
             ]
         },

From c3c4383d53fefc642203e2de0db099e89351a38a Mon Sep 17 00:00:00 2001
From: David Caplan <dcaplan@gmail.com>
Date: Thu, 11 Jan 2018 09:54:35 -0500
Subject: [PATCH 18/20] try refactoring path validators with regex (#218)

* refactor full path validators with regex
* fix issues with regexes and overrides; use explicit function names
* switch to tilde for personal vault
---
 solvebio/cli/data.py            |  49 ++++--------
 solvebio/cli/main.py            |  39 +++++----
 solvebio/resource/dataset.py    |   4 +-
 solvebio/resource/object.py     | 136 ++++++++++++++++++++------------
 solvebio/resource/vault.py      |  83 ++++++++++++++-----
 solvebio/test/test_object.py    |  69 +++++++++++++---
 solvebio/test/test_shortcuts.py |   2 +-
 solvebio/test/test_vault.py     |  30 +++++--
 8 files changed, 269 insertions(+), 143 deletions(-)

diff --git a/solvebio/cli/data.py b/solvebio/cli/data.py
index 55ec363e..3d897a8e 100644
--- a/solvebio/cli/data.py
+++ b/solvebio/cli/data.py
@@ -16,32 +16,12 @@
 from solvebio.errors import ObjectTypeError, NotFoundError
 
 
-def _full_path_from_args(args):
-    """
-    Handles the following args:
-
-    * full-path
-    * vault
-    * path
-
-    Always uses "full_path" if provided (overrides vault and path).
-    Otherwise, attempts to use "vault" and "path".
-
-    If no paths are specified, defaults to personal-vault:/
-    """
-    if args.full_path:
-        return args.full_path
-
-    return '{0}:{1}'.format(
-        args.vault or Vault.get_personal_vault().name,
-        args.path or '/')
-
-
 def _assert_object_type(obj, object_type):
     if obj.object_type != object_type:
-        raise ObjectTypeError('{0} is a {1} but must be a folder'.format(
+        raise ObjectTypeError('{0} is a {1} but must be a {2}'.format(
             obj.path,
             obj.object_type,
+            object_type
         ))
 
 
@@ -50,14 +30,14 @@ def _upload_folder(domain, vault, base_remote_path,
 
     # Create the upload root folder if it does not exist on the remote
     try:
-        upload_root_path, _ = Object.validate_path(
+        upload_root_path, _ = Object.validate_full_path(
             os.path.join(base_remote_path, local_start)
         )
         obj = Object.get_by_full_path(upload_root_path)
         _assert_object_type(obj, 'folder')
     except NotFoundError:
         base_remote_path, path_dict = \
-            Object.validate_path(base_remote_path)
+            Object.validate_full_path(base_remote_path)
 
         if path_dict['path'] == '/':
             parent_object_id = None
@@ -143,16 +123,18 @@ def create_dataset(args):
     """
     Attempt to create a new dataset given the following params:
 
-        * full_path (or vault & path)
         * template_id
         * template_file
         * capacity
         * create_vault
+        * [argument] dataset name or full path
 
     NOTE: genome_build has been deprecated and is no longer used.
 
     """
-    full_path = _full_path_from_args(args)
+    # TODO: Support for a parent object path argument?
+    full_path, path_dict = Object.validate_full_path(
+        args.full_path, vault=args.vault, path=args.path)
 
     # Accept a template_id or a template_file
     if args.template_id:
@@ -214,13 +196,11 @@ def upload(args):
     Given a folder or file, upload all the folders and files contained
     within it, skipping ones that already exist on the remote.
     """
-
-    full_path = _full_path_from_args(args)
-    base_remote_path, path_dict = Object.validate_path(full_path)
-    vault_path = path_dict['domain'] + ':' + path_dict['vault']
+    base_remote_path, path_dict = Object.validate_full_path(
+        args.full_path, vault=args.vault, path=args.path)
 
     # Assert the vault exists and is accessible
-    vault = Vault.get_by_full_path(vault_path)
+    vault = Vault.get_by_full_path(path_dict['vault_full_path'])
 
     # If not the vault root, validate remote path exists and is a folder
     if path_dict['path'] != '/':
@@ -247,7 +227,9 @@ def import_file(args):
 
         * create_dataset
         * template_id
-        * full_path (or vault & path)
+        * full_path
+        * vault (optional, overrides the vault in full_path)
+        * path (optional, overrides the path in full_path)
         * commit_mode
         * capacity
         * file (list)
@@ -258,7 +240,8 @@ def import_file(args):
     if not solvebio.api_key:
         solvebio.login()
 
-    full_path = _full_path_from_args(args)
+    full_path, path_dict = Object.validate_full_path(
+        args.full_path, vault=args.vault, path=args.path)
 
     # Ensure the dataset exists. Create if necessary.
     if args.create_dataset:
diff --git a/solvebio/cli/main.py b/solvebio/cli/main.py
index 2111c42b..737cb308 100644
--- a/solvebio/cli/main.py
+++ b/solvebio/cli/main.py
@@ -97,15 +97,14 @@ class SolveArgumentParser(argparse.ArgumentParser):
                 },
                 {
                     'flags': '--vault',
-                    'help':
-                    'The vault containing the dataset (use with --path). '
+                    'help': 'The vault containing the dataset. '
                     'Defaults to your personal vault. '
-                    'Overridden by --full-path'
+                    'Overrides the vault component of --full-path'
                 },
                 {
                     'flags': '--path',
-                    'help': 'The path to the dataset (relative to the vault). '
-                    'Used with --vault, overridden by --full-path'
+                    'help': 'The path to the dataset (relative to a vault). '
+                    'Overrides the path component of --full-path'
                 },
                 {
                     'name': 'file',
@@ -140,23 +139,25 @@ class SolveArgumentParser(argparse.ArgumentParser):
                             'small (default, <100M records), '
                             'medium (<500M), large (>=500M)'
                 },
-                {
-                    'flags': '--full-path',
-                    'help': 'The full path to the dataset in the format: '
-                    '"domain:vault:/path/dataset". '
-                    'Overrides --vault and --path'
-                },
                 {
                     'flags': '--vault',
                     'help':
-                    'The vault containing the dataset (use with --path). '
-                    'Defaults to your personal vault. '
-                    'Overridden by --full-path'
+                    'The vault containing the dataset. '
+                    'Overrides the vault component of the full path argument'
                 },
                 {
                     'flags': '--path',
                     'help': 'The path to the dataset (relative to the vault). '
-                    'Used with --vault, overridden by --full-path'
+                    'Overrides the path component of the full path argument'
+                },
+                {
+                    'name': 'full_path',
+                    'help': 'The full path to the dataset in the format: '
+                    '"domain:vault:/path/dataset". '
+                    'Defaults to your personal vault if no vault is provided. '
+                    'Defaults to the vault root if no path is provided. '
+                    'Override the vault with --vault '
+                    'and/or the path with --path'
                 },
             ]
         },
@@ -167,21 +168,19 @@ class SolveArgumentParser(argparse.ArgumentParser):
                 {
                     'flags': '--full-path',
                     'help': 'The full path where the files and folders should '
-                    'be created, defaults to the root of your personal vault. '
-                    'Overrides --vault and --path'
+                    'be created, defaults to the root of your personal vault'
                 },
                 {
                     'flags': '--vault',
                     'help': 'The vault where the files will be uploaded. '
                     'Defaults to your personal vault. '
-                    'Overridden by --full-path'
+                    'Overrides the vault component of --full-path'
                 },
                 {
                     'flags': '--path',
                     'help': 'The path (relative to a vault) '
                     'where the files will be uploaded. '
-                    'Defaults to the root directory (/). '
-                    'Overridden by --full-path'
+                    'Overrides the path component of --full-path'
                 },
                 {
                     'name': 'local_path',
diff --git a/solvebio/resource/dataset.py b/solvebio/resource/dataset.py
index 2720223f..c95684f3 100644
--- a/solvebio/resource/dataset.py
+++ b/solvebio/resource/dataset.py
@@ -61,7 +61,7 @@ def make_full_path(cls, vault_name, path, name, **kwargs):
     def get_by_full_path(cls, full_path, **kwargs):
         from solvebio import Object
         _client = kwargs.pop('client', None) or cls._client or client
-        test_path, _ = Object.validate_path(full_path, client=_client)
+        test_path, _ = Object.validate_full_path(full_path, client=_client)
         obj = Object.get_by_full_path(test_path, client=_client)
         dataset = Dataset.retrieve(obj['dataset_id'], client=_client, **kwargs)
         return dataset
@@ -83,7 +83,7 @@ def get_or_create_by_full_path(cls, full_path, **kwargs):
             pass
 
         # Dataset not found, create it step-by-step
-        full_path, parts = Object.validate_path(full_path, client=_client)
+        full_path, parts = Object.validate_full_path(full_path, client=_client)
 
         if create_vault:
             vault = Vault.get_or_create_by_full_path(
diff --git a/solvebio/resource/object.py b/solvebio/resource/object.py
index 4f57463c..f1cea87f 100644
--- a/solvebio/resource/object.py
+++ b/solvebio/resource/object.py
@@ -42,67 +42,103 @@ class Object(CreateableAPIResource,
         ('description', 'Description'),
     )
 
+    # Regex describing an object path.
+    PATH_RE = re.compile(r'^[^\/]*(?P<path>(\/[^\/]*)+)$')
+
     @classmethod
-    def validate_path(cls, path, **kwargs):
-        """ Helper method to return a full path
+    def validate_full_path(cls, full_path, **kwargs):
+        """Helper method to parse a full or partial path and
+        return a full path as well as a dict containing path parts.
+
+        Uses the following rules when processing the path:
+
+            * If no domain, uses the current user's account domain
+            * If no vault, uses the current user's personal vault.
+            * If no path, uses '/' (vault root)
+
+        Returns a tuple containing:
+
+            * The validated full_path
+            * A dictionary with the components:
+                * domain: the domain of the vault
+                * vault: the name of the vault, without domain
+                * vault_full_path: domain:vault
+                * path: the object path within the vault
+                * parent_path: the parent path to the object
+                * filename: the object's filename (if any)
+                * full_path: the validated full path
+
+        The following components may be overridden using kwargs:
+
+            * vault
+            * path
+
+        Object paths (also known as "paths") must begin with a forward slash.
+
+        The following path formats are supported:
+
+            domain:vault:/path -> object "path" in the root of "domain:vault"
+            domain:vault/path  -> object "path" in the root of "domain:vault"
+            vault:/path        -> object "path" in the root of "vault"
+            vault/path         -> object "path" in the root of "vault"
+            ~/path             -> object "path" in the root of personal vault
+            vault/             -> root of "vault"
+            ~/                 -> root of your personal vault
+
+        The following two formats are not supported:
+
+            path               -> invalid/ambiguous path (exception)
+            vault:path         -> invalid/ambiguous path (exception)
+            vault:path/path    -> unsupported, interpreted as domain:vault/path
 
-            If no account_domain, assumes user's account domain
-            If no vault, uses personal vault.
-            If no path, uses /
         """
         from solvebio.resource.vault import Vault
 
         _client = kwargs.pop('client', None) or cls._client or client
 
-        # Remove double slashes and leading ':'
-        path = re.sub('//+', '/', path.lstrip(':'))
-
-        parts = path.split(':', 2)
-        if len(parts) == 3:
-            account_domain, vault_name, object_path = parts
-        elif len(parts) == 2:
-            # if no slash assume user means root
-            if '/' not in parts[1]:
-                account_domain, vault_name = parts
-                object_path = '/'
-            else:
-                # if second part begins with slash, assume missing domain
-                if parts[1][0] == '/':
-                    account_domain = \
-                        _client.get('/v1/user', {})['account']['domain']
-                    vault_name, object_path = parts
-                else:
-                    raise Exception('Full path must be of the format: '
-                                    '"vault_name:/object_path" or '
-                                    '"account_domain:vault_name:/object_path"')
-                    # TODO maybe no good
-                    # assumes missing ":" between vault and path
-                    #   mydomain:myvault/here/is/path
-                    #   myvault:here/is/path
-                    # account_domain = parts[0]
-                    # vault_name, object_path = parts[1].split('/', 1)
+        if not full_path:
+            raise Exception(
+                'Invalid path: ',
+                'Full path must be in one of the following formats: '
+                '"vault:/path", "domain:vault:/path", or "~/path"')
+
+        # Parse the vault's full_path, using overrides if any
+        input_vault = kwargs.get('vault') or full_path
+        try:
+            vault_full_path, path_dict = \
+                Vault.validate_full_path(input_vault, client=_client)
+        except:
+            raise Exception(
+                'Could not determine vault from "{0}". '
+                'Full path must be in one of the following formats: '
+                '"vault:/path", "domain:vault:/path", or "~/path"'
+                .format(input_vault))
+
+        if kwargs.get('path'):
+            # Allow override of the object_path.
+            full_path = '{0}:/{1}'.format(vault_full_path, kwargs['path'])
+
+        match = cls.PATH_RE.match(full_path)
+        if match:
+            object_path = match.groupdict()['path']
         else:
-            # if slash assume user means private vault
-            if '/' in parts[0]:
-                vault = Vault.get_personal_vault(client=_client)
-                account_domain, vault_name = vault.full_path.split(':')
-                object_path = parts[0]
-            else:
-                raise Exception('Full path must be of the format: '
-                                '"vault_name:/object_path" or '
-                                '"account_domain:vault_name:/object_path"')
-
-        if object_path[0] != '/':
-            object_path = '/' + object_path
-
-        # Strip trailing slash
+            raise Exception(
+                'Cannot find a valid object path in "{0}". '
+                'Full path must be in one of the following formats: '
+                '"vault:/path", "domain:vault:/path", or "~/path"'
+                .format(full_path))
+
+        # Remove double slashes
+        object_path = re.sub('//+', '/', object_path)
         if object_path != '/':
+            # Remove trailing slash
             object_path = object_path.rstrip('/')
 
-        full_path = ':'.join([account_domain, vault_name, object_path])
-        return full_path, dict(domain=account_domain,
-                               vault=vault_name,
-                               path=object_path)
+        path_dict['path'] = object_path
+        # TODO: parent_path and filename
+        full_path = '{domain}:{vault}:{path}'.format(**path_dict)
+        path_dict['full_path'] = full_path
+        return full_path, path_dict
 
     @classmethod
     def get_by_full_path(cls, full_path, **params):
diff --git a/solvebio/resource/vault.py b/solvebio/resource/vault.py
index 3de835d8..fb64e95f 100644
--- a/solvebio/resource/vault.py
+++ b/solvebio/resource/vault.py
@@ -8,6 +8,8 @@
 from .apiresource import UpdateableAPIResource
 from .apiresource import DeletableAPIResource
 
+import re
+
 
 class Vault(CreateableAPIResource,
             ListableAPIResource,
@@ -31,6 +33,14 @@ class Vault(CreateableAPIResource,
         ('description', 'Description'),
     )
 
+    # Regex describing Vault full path.
+    # NOTE: Not valid for object full paths.
+    VAULT_PATH_RE = re.compile(
+        # Non-greedy wildcard match for domain
+        r'^(?:(?P<domain>[a-zA-Z0-9\-]+)\:)??'
+        # Match vault or vault:/ or vault/
+        r'(?P<vault>[^\/:]+)(?:\:?\/.*)?$')
+
     def __init__(self, vault_id, **kwargs):
         super(Vault, self).__init__(vault_id, **kwargs)
 
@@ -45,34 +55,65 @@ def _object_list_helper(self, **params):
         return items
 
     @classmethod
-    def validate_path(cls, path, **kwargs):
-        """ Helper method to return a full path
+    def validate_full_path(cls, full_path, **kwargs):
+        """Helper method to return a full path from a full or partial path.
+
+            If no domain, assumes user's account domain
+            If the vault is "~", assumes personal vault.
+
+        Valid vault paths include:
+
+            domain:vault
+            domain:vault:/path
+            domain:vault/path
+            vault:/path
+            vault
+            ~/
+
+        Invalid vault paths include:
+
+            /vault/
+            /path
+            /
+            :/
 
-            If no account_domain, assumes user's account domain
-            If no vault, uses personal vault.
+        Does not allow overrides for any vault path components.
         """
         _client = kwargs.pop('client', None) or cls._client or client
-        parts = path.split(':')
 
-        if not path or len(parts) > 2:
+        full_path = full_path.strip()
+        if not full_path:
             raise Exception(
-                'Vault path "{}" invalid. Must be of the format: '
-                '"account_domain:vault_name".'.format(path)
+                'Vault path "{0}" is invalid. Path must be in the format: '
+                '"domain:vault:/path" or "vault:/path".'.format(full_path)
             )
-        elif len(parts) == 2:
-            account_domain, vault_name = parts
-        else:
-            user = _client.get('/v1/user', {})
-            account_domain = user['account']['domain']
-            vault_name = path
 
-        # Strip any paths from the vault_name
-        if '/' in vault_name:
-            vault_name = vault_name.split('/', 1)[0]
+        match = cls.VAULT_PATH_RE.match(full_path)
+        if not match:
+            raise Exception(
+                'Vault path "{0}" is invalid. Path must be in the format: '
+                '"domain:vault:/path" or "vault:/path".'.format(full_path)
+            )
+        path_parts = match.groupdict()
+
+        # Handle the special case where "~" means personal vault
+        if path_parts.get('vault') == '~':
+            path_parts = dict(domain=None, vault=None)
 
-        full_path = ':'.join([account_domain, vault_name])
-        return full_path, dict(domain=account_domain,
-                               vault=vault_name)
+        # If any values are None, set defaults from the user.
+        if None in path_parts.values():
+            user = _client.get('/v1/user', {})
+            defaults = {
+                'domain': user['account']['domain'],
+                'vault': 'user-{0}'.format(user['id'])
+            }
+            path_parts = dict((k, v or defaults.get(k))
+                              for k, v in path_parts.items())
+
+        # Rebuild the full path
+        full_path = '{domain}:{vault}'.format(**path_parts)
+        path_parts['vault_full_path'] = full_path
+        return full_path, path_parts
 
     def files(self, **params):
         return self._object_list_helper(object_type='file', **params)
@@ -129,7 +170,7 @@ def search(self, query, **params):
     @classmethod
     def get_by_full_path(cls, full_path, **kwargs):
         _client = kwargs.pop('client', None) or cls._client or client
-        full_path, parts = cls.validate_path(full_path)
+        full_path, parts = cls.validate_full_path(full_path)
         return Vault._retrieve_helper(
             'vault', 'name', full_path,
             account_domain=parts['domain'],
diff --git a/solvebio/test/test_object.py b/solvebio/test/test_object.py
index 2595df87..869da634 100644
--- a/solvebio/test/test_object.py
+++ b/solvebio/test/test_object.py
@@ -10,7 +10,8 @@ def test_object_paths(self):
         vaults = self.client.Vault.all()
         for vault in vaults:
             for file_ in list(vault.ls().solve_objects())[:5]:
-                o_path, _ = self.client.Object.validate_path(file_.full_path)
+                o_path, _ = self.client.Object.validate_full_path(
+                    file_.full_path)
                 self.assertEqual(o_path, file_.full_path)
 
     def test_object_path_cases(self):
@@ -19,24 +20,72 @@ def test_object_path_cases(self):
         domain = user.account.domain
         user_vault = '{0}:user-{1}'.format(domain, user.id)
         test_cases = [
-            ['{0}:myVault'.format(domain), '{0}:myVault:/'.format(domain)],
-            ['acme:myVault', 'acme:myVault:/'],
             ['acme:myVault:/uploads_folder', 'acme:myVault:/uploads_folder'],
+            ['acme:myVault/folder1/project: ABCD',
+             'acme:myVault:/folder1/project: ABCD'],
+            ['myVault/folder1/project: ABCD',
+             '{0}:myVault:/folder1/project: ABCD'.format(domain)],
             ['myVault:/uploads_folder', '{0}:myVault:/uploads_folder'.format(domain)],  # noqa
-            ['/uploads_folder', '{0}:/uploads_folder'.format(user_vault)],
-            [':/uploads_folder', '{0}:/uploads_folder'.format(user_vault)],
-            ['myVault/uploads_folder', '{0}:/myVault/uploads_folder'.format(user_vault)],  # noqa
-            ['oops:myDomain:myVault', 'oops:myDomain:/myVault'],
+            # New full path formats
+            ['~/uploads_folder', '{0}:/uploads_folder'.format(user_vault)],
+            ['~/', '{0}:/'.format(user_vault)],
+            ['myVault/uploads_folder', '{0}:myVault:/uploads_folder'.format(domain)],  # noqa
+            ['acme:myVault/uploads_folder', 'acme:myVault:/uploads_folder'],
         ]
         for case, expected in test_cases:
-            p, _ = self.client.Object.validate_path(case)
+            p, _ = self.client.Object.validate_full_path(case)
             self.assertEqual(p, expected)
 
         error_test_cases = [
             '',
+            '/hello',
             'myVault',
-            'acme:myVault/uploads_folder'
+            'oops:myDomain:myVault',
+            '{0}:myVault'.format(domain),
+            'acme:myVault'
         ]
         for case in error_test_cases:
             with self.assertRaises(Exception):
-                v, v_paths = self.client.Object.validate_path(case)
+                v, v_paths = self.client.Object.validate_full_path(case)
+
+    def test_object_path_cases_with_overrides(self):
+        user = self.client.User.retrieve()
+        domain = user.account.domain
+        user_vault = '{0}:user-{1}'.format(domain, user.id)
+
+        test_cases = [
+            'acme:myVault:/folder',
+            'myVault:/folder',
+            'myVault/folder',
+            '/folder',
+        ]
+
+        for case in test_cases:
+            p, _ = self.client.Object.validate_full_path(case, vault='foobar')
+            expected = '{0}:foobar:/folder'.format(domain)
+            self.assertEqual(p, expected)
+
+            p, _ = self.client.Object.validate_full_path(case, vault='foo:bar')
+            expected = 'foo:bar:/folder'
+            self.assertEqual(p, expected)
+
+            p, _ = self.client.Object.validate_full_path(
+                case, vault='foo:bar', path='/baz')
+            expected = 'foo:bar:/baz'
+            self.assertEqual(p, expected)
+
+            p, _ = self.client.Object.validate_full_path(
+                case, vault='foo:bar', path='/baz/bon')
+            expected = 'foo:bar:/baz/bon'
+            self.assertEqual(p, expected)
+
+        # Test cases where just the path changes
+        case = 'acme:myVault:/folder'
+        p, _ = self.client.Object.validate_full_path(case, path='foo/bar/baz')
+        expected = 'acme:myVault:/foo/bar/baz'
+        self.assertEqual(p, expected)
+
+        case = '~/folder'
+        p, _ = self.client.Object.validate_full_path(case, path='foo/bar/baz')
+        expected = '{0}:/foo/bar/baz'.format(user_vault)
+        self.assertEqual(p, expected)
diff --git a/solvebio/test/test_shortcuts.py b/solvebio/test/test_shortcuts.py
index 30639038..e60d54df 100644
--- a/solvebio/test/test_shortcuts.py
+++ b/solvebio/test/test_shortcuts.py
@@ -35,7 +35,7 @@ def test_create_dataset(self, DatasetCreate, ObjectAll, VaultAll):
         ObjectAll.side_effect = fake_object_all
         VaultAll.side_effect = fake_vault_all
         args = ['create-dataset', 'solvebio:test_vault:/test-dataset',
-                   '--capacity', 'small']  # noqa
+                '--capacity', 'small']
         ds = main.main(args)
         self.assertEqual(ds.name, 'test-dataset')
         self.assertEqual(ds.path, '/test-dataset')
diff --git a/solvebio/test/test_vault.py b/solvebio/test/test_vault.py
index d5c0c6c3..6d1564e8 100644
--- a/solvebio/test/test_vault.py
+++ b/solvebio/test/test_vault.py
@@ -28,29 +28,47 @@ def test_vaults(self):
             self.assertTrue(f in vault, '{0} field is present'.format(f))
 
     def test_vault_paths(self):
+        user = self.client.User.retrieve()
+        domain = user.account.domain
+        user_vault = 'user-{0}'.format(user.id)
+
         vaults = self.client.Vault.all()
         for vault in vaults:
-            v, v_paths = self.client.Vault.validate_path(vault.full_path)
+            v, v_paths = self.client.Vault.validate_full_path(vault.full_path)
             self.assertEqual(v, vault.full_path)
 
-        domain = self.client.User.retrieve().account.domain
         test_cases = [
+            ['myVault/', '{0}:myVault'.format(domain, user_vault)],
             ['myVault', '{0}:myVault'.format(domain)],
             ['{0}:myVault'.format(domain), '{0}:myVault'.format(domain)],
             ['acme:myVault', 'acme:myVault'],
-            # this assumes user f-ed and forgot the semi-colon for path
+            ['myVault/folder1/folder2: xyz', '{0}:myVault'.format(domain)],
+            ['acme:myVault/folder1/folder2: xyz', 'acme:myVault'],
+            ['acme:myVault:/folder1/folder2: xyz', 'acme:myVault'],
+            # The following are the "new" vault/path formats:
+            ['~/', '{0}:{1}'.format(domain, user_vault)],
             ['acme:myVault/uploads_folder', 'acme:myVault'],
             ['myVault/uploads_folder', '{0}:myVault'.format(domain)],
         ]
         for case, expected in test_cases:
-            v, v_paths = self.client.Vault.validate_path(case)
+            v, v_paths = self.client.Vault.validate_full_path(case)
             self.assertEqual(v, expected)
 
         error_test_cases = [
             '',
-            'myDomain:myVault:/the/heack',
+            '/',
+            ':',
+            ':/',
+            '::/',
+            'x:',
+            # Underscore in domain
+            'my_Domain:myVault:/the/heack',
+            # Space in domain
+            'my Domain:my:Vault:/the/heack',
+            # Too many colons
+            'myDomain:my:Vault:/the/heack',
             'oops:myDomain:myVault',
         ]
         for case in error_test_cases:
             with self.assertRaises(Exception):
-                v, v_paths = self.client.Vault.validate_path(case)
+                v, v_paths = self.client.Vault.validate_full_path(case)

From 26abed742d8ef21eca03659bcb455c4ff1211375 Mon Sep 17 00:00:00 2001
From: David Caplan <dcaplan@gmail.com>
Date: Thu, 11 Jan 2018 10:23:34 -0500
Subject: [PATCH 19/20] update readme

---
 README.md | 332 +++++-------------------------------------------------
 1 file changed, 27 insertions(+), 305 deletions(-)

diff --git a/README.md b/README.md
index 72e674ab..6d27f4b5 100644
--- a/README.md
+++ b/README.md
@@ -7,15 +7,11 @@ SolveBio Python Client
 This is the SolveBio Python package and command-line interface (CLI).
 This module has been tested on Python 2.6+, Python 3.1+ and PyPy.
 
-For more information about SolveBio visit [solvebio.com](https://www.solvebio.com).
-
-
-Compatibility
--------------
-
 This version of the Python Client is compatible with Vault-based datasets
 only (released on July 28th, 2017).
 
+Developer documentation is available at [docs.solvebio.com](https://docs.solvebio.com). For more information about SolveBio visit [www.solvebio.com](https://www.solvebio.com).
+
 
 Dependencies (Ubuntu)
 --------------------
@@ -31,46 +27,44 @@ To install them, run:
     sudo apt-get install libcurl4-gnutls-dev libgnutls-dev
 
 
-Guided Installation
--------------------
+Installation & Setup
+--------------------
 
-To use our guided installer, open up your terminal paste this:
+Install `solvebio` using `pip`:
 
-    curl -skL install.solvebio.com/python | bash
+    pip install solvebio
 
 
+For interactive use, we recommend installing `IPython` and `gnureadline`:
 
-Manual Installation
--------------------
+    pip install ipython
+    pip install gnureadline
 
-You may want to first install `gnureadline` and `IPython`:
 
-    pip install gnureadline
-    pip install ipython
+To log in, type:
 
+    solvebio login
 
-Install `solvebio` using `pip`:
 
-    pip install solvebio
+Enter your SolveBio credentials and you should be good to go!
 
 
-To log in, type:
+Automatic Installer (Python 2.x only)
+-------------------------------------
 
-    solvebio login
+NOTE: The following installer works for Python 2.x only.
 
-Enter your credentials and you should be good to go!
+Open your terminal and paste the following command:
 
-Just type `solvebio` to enter the SolveBio Python shell or `solvebio tutorial`
-for a quick guide on using SolveBio.
+    curl -skL install.solvebio.com/python | bash
 
 
-Installing from Git
--------------------
+Install from Git
+----------------
 
     pip install -e git+https://github.com/solvebio/solvebio-python.git#egg=solve
 
 
-
 Development
 -----------
 
@@ -78,294 +72,22 @@ Development
     cd solve-python/
     python setup.py develop
 
-To run tests use nosetest
+To run tests use `nosetest`:
 
     nosetests solvebio.test.test_dataset
 
-Or install tox and run that:
+
+Or install `tox` and run:
 
     pip install tox
     tox
 
-To tag new versions:
-
-    git tag `cat solvebio/version.py | cut -d "'" -f 2`
-    git push --tags origin master
-
-
-Migrating to Version 2
-----------------------
-
-Version 2 of the Python client removes support for the `Depository` and
-`DepositoryVersion` classes, and adds support for the `Vault` and `Object`
-classes.
-
-A vault is similar to a filesystem in that it provides a folder-based
-hierarchy in which additional folders, files, and SolveBio Datasets can be
-stored.  The folders, files, and SolveBio Datasets in a vault are
-collectively referred to as "objects" and can be accessed using the
-`Vault` or `Object` classes.
-
-Vaults have an advanced permission model that provides for three different
-levels of access: read, write, and admin.  Permissions are settable through
-the SolveBio UI.  For detailed information on the permission model, please
-visit this link:
-
-https://support.solvebio.com/hc/en-us/articles/227732207
-
-As part of the migration onto Version 2, SolveBio has automatically applied
-the permissions set on Depositories to the new Vaults which we have created to
-replace them.
-
-It is likely that any scripts you have written which utilize the
-Python client will need to be modified to be compatible with Version 2.
-Below is an exhaustive list of all the things that have changed in the
-user-facing methods of the client.  If you encounter any issues migrating
-your code, please submit a support ticket and we would be happy to assist you.
-
-### Naming Conventions
-
-It is useful to know the different names for the various entities (or combined
-entities) that are available via the Client.  The naming conventions are
-as follows:
-
-```
-
-solvebio:public:/ClinVar/3.7.0-2015-12-06/Variants-GRCh37
-+------+
-(1)
-         +----+
-         (2)
-+-------------+
-(3)
-                +---------------------------------------+
-                (4)
-                                          +-------------+
-                                          (5)
-+-------------------------------------------------------+
-(6)
-```
-```
-(1) - Account Domain
-(2) - Vault Name
-(3) - Vault Full Path
-(4) - Object Path
-(5) - Object Filename
-(6) - Object Full Path
-
-```
-
-### Changes in V2
-
-1. Dataset creation changes
-
-```
-Old: Dataset.get_or_create_by_full_name(full_name)
-New: Dataset.get_or_create_by_full_path(account_domain:vault_name:/parent/path/dataset_name)
-```
-
-For example, if you belong to the "acme" domain, then to create a dataset
-named named "EGFR_analysis" in the "/July-2017" folder of the "Research" vault,
-make the following call:
-
-```
-Dataset.get_or_create_by_full_path('Research:/July_2017/EGFR_analysis')
-Dataset.get_or_create_by_full_path('Acme:Research:/July_2017/EGFR_analysis')
-```
 
-If you wish to auto-create the vault, add the `create_vault=True` flag.
-If you wish to auto-create the folder(s), add the `create_folders=True` flag.
+Support
+-------
 
-You can optionally leave off the account domain in front, but note that this
-will not work if your object path includes a colon:
+Developer documentation is available at [docs.solvebio.com](https://docs.solvebio.com).
 
-```
-Dataset.get_or_create_by_full_path('Research:/July_2017/EGFR_analysis')
-```
+If you experience problems with this package, please [create a GitHub Issue](https://github.com/solvebio/solvebio-python/issues).
 
-If you wish to automatically create the vault if it does not exist, add the
-`create_vault=True` flag.
-
-2.  Dataset retrieval changes
-
-A dataset's "full_path" is a triplet consisting of account domain, vault
-name, and the dataset's path in the vault (see above).  Retrieval of a dataset
-by its full path can be performed in a single call:
-
-```
-Dataset.get_by_full_path("account_domain:vault_name:object_path")
-Dataset.get_by_full_path("solvebio:public:/ICGC/3.0.0-23/Donor")
-```
-
-In order to get the full path of an existing dataset, search for datasets
-within a vault.
-
-```
-# Get all of the Clinvar datasets that are version 3 and above
-v = Vault.get_by_full_path('solvebio:public')
-v.datasets(query='Clinvar/3')
-```
-
-3.  Removal of `genome_build` filter
-
-The `genome_build` field on the Dataset entity is no longer a supported
-filter.  The genome build of public datasets is now indicated in the dataset
-name, e.g. `Variants-GRCh38`.
-
-```
-Dataset.get_by_full_path("solvebio:public:/ClinVar/3.7.0-2015-12-06/Variants-GRCh38")
-```
-
-4.  Removal of `Depository` and `DepositoryVersion` classes.
-
-`Depository` has been replaced by the `Vault` class.
-
-`DepositoryVersion` was functionality is now provided by the `Object` class.
-Objects are files, folders, or SolveBio
-Datasets that exist inside a vault.  As part of your account's migration onto
-Version 2 of SolveBio, we have automatically moved datasets located in
-Depository "X" and DepositoryVersion "Y" to a Vault named "X" and a folder named
-"Y".  If the dataset being migrated had the `genome_build` property set, the
-dataset was renamed to `$original_name-$genome_build`.  Otherwise, the name
-remained unchanged.
-
-5.  Renaming of "objects" to "solve_objects"
-
-The `objects` property of a resource has been renamed `solve_objects`.
-
-6.  The `import` and `create-dataset` command-line utilities now require
-`--full-path` arguments.  The `dataset` argument (`test-dataset`
-below) no longer can contain slashes.
-
-```
-create-dataset --capacity=small --full-path=acme:test:/examples test-dataset
-```
-
-7. Removal of DatasetCommit approval. The `auto_approve`, `is_approved` and
-`approved_by` attributes have been removed. The `/approve` endpoint has also
-been removed. All commits will be approved automatically.
-
-
-Vault Browsing
---------------
-### Browse
-
-List all the vaults you currently have access to.
-
-
-```
-Vault.all()
-```
-
-### Your Personal Vault
-
-Each user has a personal vault that is accessible to that user only.  Other
-users cannot list the contents of this vault, cannot access the objects
-contained in it, and cannot modify it in any way.  To provide access to
-objects stored in your personal vault, you must copy the objects into a
-different vault.
-
-Your personal dataset can be retrieved using the following method:
-
-```
-Vault.get_personal_vault()
-```
-
-
-### Shortcuts
-Browsing the contents of a vault can be easily performed using the following
-shortcuts.
-
-First, retrieve a vault:
-
-```
-vault = Vault.get_personal_vault()
-vault = Vault.get_by_full_path('solvebio:public')
-vault = Vault.get_by_full_path('your_account_domain:vault_name')
-vault = Vault.get_by_full_path('vault_name')  # Searches inside your account domain
-```
-
-
-Then, call the appropriate method:
-
-```
-vault.files()
-vault.folders()
-vault.datasets()
-vault.objects()                 # Includes files, folders, and datasets
-
-vault.files(filename='hello.txt')   # Can pass filters to all of these methods
-```
-
-
-Search for files, folders, and datasets in a vault using the `search` method:
-
-```
-vault.search('hello')
-vault.search('hello', object_type='folder')
-vault.search('hello', object_type='file')
-vault.search('hello', object_type='dataset')
-```
-
-Creation
---------
-```
-Vault.get_or_create_by_full_path('acme:test1')
-Vault.get_or_create_by_full_path('test1')
-```
-
-File Upload
------------
-```
-v = Vault.get_personal_vault()
-v.upload_file('analysis.tsv', '/')
->>> Notice: Successfully uploaded analysis.tsv to /analysis.tsv
-```
-
-Re-uploading the same file to the same path auto-increments the filename on
-the server.  This is required because no two objects can have the same full
-path.
-
-```
-v = Vault.get_personal_vault()
-v.upload_file('analysis.tsv', '/')
->>> Notice: Successfully uploaded analysis.tsv to /analysis-1.tsv
-```
-
-
-Deletion
---------
-
-Deletion of any object requires a confirmation from the user.
-You can disable this confirmation by passing the `force=True` flag.
-
-```
-folder = Object.retrieve(504311238004931284)
-folder.delete()
->>> Are you sure you want to delete this object? [y/N] n
->>> Not performing deletion.
-```
-```
-folder.delete(force=True)
-```
-
-Enhanced Command-Line File Uploading
-------------------------------------
-
-A new command-line method called "upload" has been added.  This method
-allows users to upload a file or folder to a vault.  If a folder is
-uploaded, calling the "upload" method again will result in a cross-checking
-of the local folder and SolveBio folder, and upload/create only the
-local files and folders that do not already exist on SolveBio.
-
-```
-solvebio upload --vault analysis --path=/july_2017  local/foo/bar
-```
-
-This command will create a folder named `/july_2017/bar` in the `analysis`
-vault, and upload everything inside `local/foo/bar` on the local machine to
-`/july_2017/bar` in that vault.
-
-Note that comparison is performed by filename, not by file content.  Thus, the
-"upload" command will never replace a remote file with a local file of the same
-name but with updated contents.
+For all other requests, please [email SolveBio Support](mailto:support@solvebio.com).

From a6e4fd7d69b45f65834e089a86ac0a8f9f0f50d3 Mon Sep 17 00:00:00 2001
From: David Caplan <dcaplan@gmail.com>
Date: Thu, 11 Jan 2018 10:45:08 -0500
Subject: [PATCH 20/20] support backwards compatible create-dataset command

---
 solvebio/cli/data.py            | 18 +++++++++++-------
 solvebio/test/test_shortcuts.py | 16 ++++++++++++++++
 2 files changed, 27 insertions(+), 7 deletions(-)

diff --git a/solvebio/cli/data.py b/solvebio/cli/data.py
index 3d897a8e..f7cd3668 100644
--- a/solvebio/cli/data.py
+++ b/solvebio/cli/data.py
@@ -132,9 +132,17 @@ def create_dataset(args):
     NOTE: genome_build has been deprecated and is no longer used.
 
     """
-    # TODO: Support for a parent object path argument?
-    full_path, path_dict = Object.validate_full_path(
-        args.full_path, vault=args.vault, path=args.path)
+    # For backwards compatibility, the "full_path" argument
+    # can be a dataset filename, but only if vault and path
+    # are set. If vault/path are both provided and there
+    # are no forward-slashes in the "full_path", assume
+    # the user has provided a dataset filename.
+    if '/' not in args.full_path and args.vault and args.path:
+        full_path, path_dict = Object.validate_full_path(
+            '{0}:/{1}/{2}'.format(args.vault, args.path, args.full_path))
+    else:
+        full_path, path_dict = Object.validate_full_path(
+            args.full_path, vault=args.vault, path=args.path)
 
     # Accept a template_id or a template_file
     if args.template_id:
@@ -236,10 +244,6 @@ def import_file(args):
         * follow (default: False)
 
     """
-    # FIXME: Does this need to be here? What about other commands?
-    if not solvebio.api_key:
-        solvebio.login()
-
     full_path, path_dict = Object.validate_full_path(
         args.full_path, vault=args.vault, path=args.path)
 
diff --git a/solvebio/test/test_shortcuts.py b/solvebio/test/test_shortcuts.py
index e60d54df..7bb29bea 100644
--- a/solvebio/test/test_shortcuts.py
+++ b/solvebio/test/test_shortcuts.py
@@ -40,6 +40,22 @@ def test_create_dataset(self, DatasetCreate, ObjectAll, VaultAll):
         self.assertEqual(ds.name, 'test-dataset')
         self.assertEqual(ds.path, '/test-dataset')
 
+    @mock.patch('solvebio.resource.Vault.all')
+    @mock.patch('solvebio.resource.Object.all')
+    @mock.patch('solvebio.resource.Dataset.create')
+    def test_create_dataset_by_filename(self, DatasetCreate, ObjectAll,
+                                        VaultAll):
+        DatasetCreate.side_effect = fake_dataset_create
+        ObjectAll.side_effect = fake_object_all
+        VaultAll.side_effect = fake_vault_all
+        args = ['create-dataset', 'test-dataset-filename',
+                '--vault', 'solvebio:test_vault',
+                '--path', '/',
+                '--capacity', 'small']
+        ds = main.main(args)
+        self.assertEqual(ds.name, 'test-dataset-filename')
+        self.assertEqual(ds.path, '/test-dataset-filename')
+
     def _validate_tmpl_fields(self, fields):
         for f in fields:
             if f.name == 'name':