Use PyHive pure-sasl import (#818) (#945)

* Use PyHive pure-sasl import * Test PyHive pure-sasl import * update requirements.txt * use github fix for >3.11 * use github fix for >3.11 * fix pyhive spec * remove unnecessary requests extra * remove unnecessary sasl install * add changie * specify no-binary for pyodbc install * conditionally import sasl vs puresasl * conditionally import sasl vs pure-sasl * experiment with pure sasl SASLClient * file formatting * test using only puresasl * test using only puresasl * update requirements.txt * remove sasl from req * remove unused sys dependency * test spark-session * fix pure-sasl * allow pre-release installs * allow pre-release installs * use pyhive 0.7.0 * add pyhive back to reqs * fix setup.py and remove sasl from dev-requirements.txt * Update Dependencies-20230628-121341.yaml * remove unnecessary pip_pre arg from tox.ini --------- Co-authored-by: Mike Alfare <[email protected]> (cherry picked from commit 07383d9) Co-authored-by: colin-rogers-dbt <[email protected]>
dbt-labs · Nov 9, 2023 · ddbfea7 · ddbfea7
1 parent 838cedc
commit ddbfea7
Show file tree

Hide file tree

Showing 6 changed files with 19 additions and 16 deletions.
diff --git a/.changes/unreleased/Dependencies-20230628-121341.yaml b/.changes/unreleased/Dependencies-20230628-121341.yaml
@@ -0,0 +1,6 @@
+kind: Dependencies
+body: Replace sasl with pure-sasl for PyHive
+time: 2023-06-28T12:13:41.141588-07:00
+custom:
+  Author: colin-rogers-dbt
+  PR: "818"
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
@@ -79,7 +79,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.7", "3.8", "3.9", "3.10"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
 
     env:
       TOXENV: "unit"
@@ -177,7 +177,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ["3.7", "3.8", "3.9", "3.10"]
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
 
     steps:
       - name: Set up Python ${{ matrix.python-version }}

diff --git a/dbt/adapters/spark/connections.py b/dbt/adapters/spark/connections.py
@@ -31,8 +31,8 @@
     from thrift.transport.TSSLSocket import TSSLSocket
     import thrift
     import ssl
-    import sasl
     import thrift_sasl
+    from puresasl.client import SASLClient
 except ImportError:
     pass  # done deliberately: setting modules to None explicitly violates MyPy contracts by degrading type semantics
 
@@ -530,17 +530,15 @@ def build_ssl_transport(host, port, username, auth, kerberos_service_name, passw
                 # to be nonempty.
                 password = "x"
 
-        def sasl_factory():
-            sasl_client = sasl.Client()
-            sasl_client.setAttr("host", host)
+        def sasl_factory() -> SASLClient:
             if sasl_auth == "GSSAPI":
-                sasl_client.setAttr("service", kerberos_service_name)
+                sasl_client = SASLClient(host, kerberos_service_name, mechanism=sasl_auth)
             elif sasl_auth == "PLAIN":
-                sasl_client.setAttr("username", username)
-                sasl_client.setAttr("password", password)
+                sasl_client = SASLClient(
+                    host, mechanism=sasl_auth, username=username, password=password
+                )
             else:
                 raise AssertionError
-            sasl_client.init()
             return sasl_client
 
         transport = thrift_sasl.TSaslClientTransport(sasl_factory, sasl_auth, socket)

diff --git a/dev-requirements.txt b/dev-requirements.txt
@@ -33,5 +33,4 @@ wheel~=0.40
 
 # Adapter specific dependencies
 mock~=5.0
-sasl~=0.3.1
 thrift_sasl~=0.4.3
diff --git a/requirements.txt b/requirements.txt
@@ -1,5 +1,5 @@
-PyHive[hive]>=0.6.0,<0.7.0
-requests[python]>=2.28.1
+pyhive[hive_pure_sasl]~=0.7.0
+requests>=2.28.1
 
 pyodbc==4.0.34
 sqlparams>=3.0.0

diff --git a/setup.py b/setup.py
@@ -9,7 +9,6 @@
     print("Please upgrade to Python 3.7 or higher.")
     sys.exit(1)
 
-
 # require version of setuptools that supports find_namespace_packages
 from setuptools import setup
 
@@ -54,9 +53,9 @@ def _get_dbt_core_version():
 dbt_core_version = _get_dbt_core_version()
 description = """The Apache Spark adapter plugin for dbt"""
 
-odbc_extras = ["pyodbc>=4.0.30"]
+odbc_extras = ["pyodbc>=4.0.39"]
 pyhive_extras = [
-    "PyHive[hive]>=0.6.0,<0.7.0",
+    "PyHive[hive_pure_sasl]~=0.7.0",
     "thrift>=0.11.0,<0.17.0",
 ]
 session_extras = ["pyspark>=3.0.0,<4.0.0"]
@@ -94,6 +93,7 @@ def _get_dbt_core_version():
         "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
     ],
     python_requires=">=3.7",
 )