Releases v0.12.4 (#290)

Author: wjsi

License

@@ -1,4 +1,4 @@
-Copyright 1999-2022 Alibaba Group Holding Ltd.
+Copyright 1999-2025 Alibaba Group Holding Ltd.
 
 
                                  Apache License

README.md

@@ -1,10 +1,5 @@
-# ODPS Python SDK and data analysis framework
+# ODPS Python SDK
 
-[![PyPI version](https://img.shields.io/pypi/v/pyodps.svg?style=flat-square)](https://pypi.python.org/pypi/pyodps) [![Docs](https://img.shields.io/badge/docs-latest-brightgreen.svg?style=flat-square)](http://pyodps.readthedocs.org/) [![License](https://img.shields.io/pypi/l/pyodps.svg?style=flat-square)](https://github.com/aliyun/aliyun-odps-python-sdk/blob/master/License) ![Implementation](https://img.shields.io/pypi/implementation/pyodps.svg?style=flat-square)
-
-<div align="center">
-  <img src="http://pyodps.readthedocs.org/zh_CN/latest/_static/PyODPS.png"><br><br>
-</div>
 -----------------
 
 Elegent way to access ODPS API. [Documentation](http://pyodps.readthedocs.org/)
@@ -49,12 +44,12 @@ $ pip install git+https://github.com/aliyun/aliyun-odps-python-sdk.git
 ```python
 >>> import os
 >>> from odps import ODPS
->>> # Make sure environment variable ALIBABA_CLOUD_ACCESS_KEY_ID already set to Access Key ID of user
->>> # while environment variable ALIBABA_CLOUD_ACCESS_KEY_SECRET set to Access Key Secret of user.
+>>> # Make sure environment variable CLOUD_ACCESS_KEY_ID already set to Access Key ID of user
+>>> # while environment variable CLOUD_ACCESS_KEY_SECRET set to Access Key Secret of user.
 >>> # Not recommended to hardcode Access Key ID or Access Key Secret in your code.
 >>> o = ODPS(
->>>     os.getenv('ALIBABA_CLOUD_ACCESS_KEY_ID'),
->>>     os.getenv('ALIBABA_CLOUD_ACCESS_KEY_SECRET'),
+>>>     os.getenv('CLOUD_ACCESS_KEY_ID'),
+>>>     os.getenv('CLOUD_ACCESS_KEY_SECRET'),
 >>>     project='**your-project**',
 >>>     endpoint='**your-endpoint**',
 >>> )
@@ -93,37 +88,6 @@ False
  <column c_datetime_b, type datetime>]
 ```
 
-## DataFrame API
-
-```python
->>> from odps.df import DataFrame
->>> df = DataFrame(o.get_table('pyodps_iris'))
->>> df.dtypes
-odps.Schema {
-  sepallength           float64
-  sepalwidth            float64
-  petallength           float64
-  petalwidth            float64
-  name                  string
-}
->>> df.head(5)
-|==========================================|   1 /  1  (100.00%)         0s
-   sepallength  sepalwidth  petallength  petalwidth         name
-0          5.1         3.5          1.4         0.2  Iris-setosa
-1          4.9         3.0          1.4         0.2  Iris-setosa
-2          4.7         3.2          1.3         0.2  Iris-setosa
-3          4.6         3.1          1.5         0.2  Iris-setosa
-4          5.0         3.6          1.4         0.2  Iris-setosa
->>> df[df.sepalwidth > 3]['name', 'sepalwidth'].head(5)
-|==========================================|   1 /  1  (100.00%)        12s
-          name  sepalwidth
-0  Iris-setosa         3.5
-1  Iris-setosa         3.2
-2  Iris-setosa         3.1
-3  Iris-setosa         3.6
-4  Iris-setosa         3.9
-```
-
 ## Command-line and IPython enhancement
 
 ```
@@ -174,14 +138,6 @@ cd pyodps
 pip install -r requirements.txt -e .
 ```
 
-If you need to modify the frontend code, you need to install [nodejs/npm](https://www.npmjs.com/). To build and
-install your frontend code, use
-
-```
-python setup.py build_js
-python setup.py install_js
-```
-
 ## License
 
 Licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0.html)

README.rst

@@ -1,7 +1,7 @@
-ODPS Python SDK and data analysis framework
-===========================================
+ODPS Python SDK
+===============
 
-|PyPI version| |Docs| |License| |Implementation|
+--------------
 
 Elegent way to access ODPS API.
 `Documentation <http://pyodps.readthedocs.org/>`__
@@ -52,12 +52,12 @@ Usage
 
    >>> import os
    >>> from odps import ODPS
-   >>> # Make sure environment variable ALIBABA_CLOUD_ACCESS_KEY_ID already set to Access Key ID of user
-   >>> # while environment variable ALIBABA_CLOUD_ACCESS_KEY_SECRET set to Access Key Secret of user.
+   >>> # Make sure environment variable CLOUD_ACCESS_KEY_ID already set to Access Key ID of user
+   >>> # while environment variable CLOUD_ACCESS_KEY_SECRET set to Access Key Secret of user.
    >>> # Not recommended to hardcode Access Key ID or Access Key Secret in your code.
    >>> o = ODPS(
-   >>>     os.getenv('ALIBABA_CLOUD_ACCESS_KEY_ID'),
-   >>>     os.getenv('ALIBABA_CLOUD_ACCESS_KEY_SECRET'),
+   >>>     os.getenv('CLOUD_ACCESS_KEY_ID'),
+   >>>     os.getenv('CLOUD_ACCESS_KEY_SECRET'),
    >>>     project='**your-project**',
    >>>     endpoint='**your-endpoint**',
    >>> )
@@ -95,38 +95,6 @@ Usage
     <column c_datetime_a, type datetime>,
     <column c_datetime_b, type datetime>]
 
-DataFrame API
--------------
-
-.. code:: python
-
-   >>> from odps.df import DataFrame
-   >>> df = DataFrame(o.get_table('pyodps_iris'))
-   >>> df.dtypes
-   odps.Schema {
-     sepallength           float64
-     sepalwidth            float64
-     petallength           float64
-     petalwidth            float64
-     name                  string
-   }
-   >>> df.head(5)
-   |==========================================|   1 /  1  (100.00%)         0s
-      sepallength  sepalwidth  petallength  petalwidth         name
-   0          5.1         3.5          1.4         0.2  Iris-setosa
-   1          4.9         3.0          1.4         0.2  Iris-setosa
-   2          4.7         3.2          1.3         0.2  Iris-setosa
-   3          4.6         3.1          1.5         0.2  Iris-setosa
-   4          5.0         3.6          1.4         0.2  Iris-setosa
-   >>> df[df.sepalwidth > 3]['name', 'sepalwidth'].head(5)
-   |==========================================|   1 /  1  (100.00%)        12s
-             name  sepalwidth
-   0  Iris-setosa         3.5
-   1  Iris-setosa         3.2
-   2  Iris-setosa         3.1
-   3  Iris-setosa         3.6
-   4  Iris-setosa         3.9
-
 Command-line and IPython enhancement
 ------------------------------------
 
@@ -181,25 +149,8 @@ source:
    cd pyodps
    pip install -r requirements.txt -e .
 
-If you need to modify the frontend code, you need to install
-`nodejs/npm <https://www.npmjs.com/>`__. To build and install your
-frontend code, use
-
-::
-
-   python setup.py build_js
-   python setup.py install_js
-
 License
 -------
 
 Licensed under the `Apache License
 2.0 <https://www.apache.org/licenses/LICENSE-2.0.html>`__
-
-.. |PyPI version| image:: https://img.shields.io/pypi/v/pyodps.svg?style=flat-square
-   :target: https://pypi.python.org/pypi/pyodps
-.. |Docs| image:: https://img.shields.io/badge/docs-latest-brightgreen.svg?style=flat-square
-   :target: http://pyodps.readthedocs.org/
-.. |License| image:: https://img.shields.io/pypi/l/pyodps.svg?style=flat-square
-   :target: https://github.com/aliyun/aliyun-odps-python-sdk/blob/master/License
-.. |Implementation| image:: https://img.shields.io/pypi/implementation/pyodps.svg?style=flat-square

examples/storage_api/util.py

@@ -1,4 +1,4 @@
-# Copyright 1999-2022 Alibaba Group Holding Ltd.
+# Copyright 1999-2025 Alibaba Group Holding Ltd.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -18,8 +18,8 @@
 from odps.apis.storage_api import *
 
 o = ODPS(
-    os.getenv("ALIBABA_CLOUD_ACCESS_KEY_ID"),
-    os.getenv("ALIBABA_CLOUD_ACCESS_KEY_SECRET"),
+    os.getenv("CLOUD_ACCESS_KEY_ID"),
+    os.getenv("CLOUD_ACCESS_KEY_SECRET"),
     project="your-default-project",
     endpoint="your-end-point",
 )

odps/_version.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-version_info = (0, 12, 4, "b1")
+version_info = (0, 12, 4)
 _num_index = max(idx if isinstance(v, int) else 0 for idx, v in enumerate(version_info))
 __version__ = ".".join(map(str, version_info[: _num_index + 1])) + "".join(
     version_info[_num_index + 1 :]

odps/accounts.py

@@ -116,7 +116,7 @@ def _get_v4_signature_key(self, date_str, region_name):
 
         sig_prefix = _get_v4_signature_prefix()
 
-        k_secret = utils.to_binary(sig_prefix + self.secret_access_key)
+        k_secret = utils.to_binary(sig_prefix + utils.to_str(self.secret_access_key))
         k_date = hmac.new(k_secret, utils.to_binary(date_str), hashlib.sha256).digest()
         k_region = hmac.new(
             k_date, utils.to_binary(region_name), hashlib.sha256
@@ -184,9 +184,10 @@ def sign_request(self, req, endpoint, region_name=None):
                 hashlib.sha1,
             ).digest()
         )
+        provider = _get_v4_signature_prefix().rsplit("_", 1)[0]
         app_auth_str = (
             "account_provider:%s,signature_method:%s,access_id:%s,signature:%s"
-            % ("aliyun", "hmac-sha1", self.access_id, utils.to_str(signature))
+            % (provider, "hmac-sha1", self.access_id, utils.to_str(signature))
         )
         req.headers["application-authentication"] = app_auth_str
         logger.debug("headers after app signing: %r", req.headers)

odps/compat.py

@@ -334,11 +334,9 @@ def dst(self, dt):
 
 
 try:
-    import zoneinfo
-
-    utc = zoneinfo.ZoneInfo("UTC")
+    utc = datetime.timezone.utc
     FixedOffset = _FixedOffset
-except ImportError:
+except AttributeError:
     try:
         import pytz
 

odps/core.py

@@ -29,7 +29,6 @@
 DEFAULT_ENDPOINT = "http://service.odps.aliyun.com/api"
 DEFAULT_REGION_NAME = "cn"
 LOGVIEW_HOST_DEFAULT = "http://logview.aliyun.com"
-JOB_INSIGHT_HOST_DEFAULT = "https://maxcompute.console.aliyun.com"
 
 _ALTER_TABLE_REGEX = re.compile(
     r"^\s*(drop|alter)\s+table\s*(|if\s+exists)\s+(?P<table_name>[^\s;]+)", re.I
@@ -2164,22 +2163,22 @@ def get_job_insight_host(self):
 
         job_insight_released = utils.is_job_insight_released(self.endpoint)
         # when use_legacy_logview is enforced as False, we still use job insight
-        if job_insight_released is False and options.use_legacy_logview is not False:
+        if not job_insight_released and options.use_legacy_logview is not False:
             return None
 
+        jobinsight_host = self._get_job_insight_from_request()
+        if jobinsight_host:
+            _jobinsight_host_cache[self.endpoint] = jobinsight_host
+        return jobinsight_host
+
+    def _get_job_insight_from_request(self):
         try:
             jobinsight_host = utils.to_str(
                 self.rest.get(self.endpoint + "/webconsole/host").content
             )
-            jobinsight_host = jobinsight_host.strip() or None
+            return jobinsight_host.strip() or None
         except:
-            jobinsight_host = None
-        if not jobinsight_host and job_insight_released is True:
-            jobinsight_host = JOB_INSIGHT_HOST_DEFAULT
-
-        if jobinsight_host:
-            _jobinsight_host_cache[self.endpoint] = jobinsight_host
-        return jobinsight_host
+            return None
 
     def get_logview_address(
         self, instance_id, hours=None, project=None, use_legacy=None

odps/dbapi.py

@@ -14,6 +14,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import base64
 import functools
 import warnings
 
@@ -40,6 +41,14 @@ class State(enum.Enum):
     FINISHED = 2
 
 
+class Binary(object):
+    def __init__(self, value):
+        self.value = value
+
+    def __str__(self):
+        return "unbase64('%s')" % base64.b64encode(self.value).decode()
+
+
 def connect(*args, **kwargs):
     """Constructor for creating a connection to the database. See class :py:class:`Connection` for
     arguments.

odps/df/backends/pd/tests/test_engine.py

@@ -2677,6 +2677,7 @@ def persist_with_dyna_part_test(table_name):
     base_table_name = tn('pyodps_test_pd_engine_persist_table')
     try:
         options.tunnel.write_row_batch_size = 1
+        options.df.writer_count_limit = 2
         run_sub_tests_in_parallel(
             10,
             [
@@ -2686,6 +2687,7 @@ def persist_with_dyna_part_test(table_name):
         )
     finally:
         options.tunnel.write_row_batch_size = 1024
+        options.df.writer_count_limit = 50
 
 
 def test_append_id(odps, setup):