| |
| |
| <!DOCTYPE html> |
| <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>apache_beam.io.azure.blobstorageio — Apache Beam 2.47.0 documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../../_static/language_data.js"></script> |
| <script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| |
| <script type="text/javascript" src="../../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../search.html" /> |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../../index.html" class="icon icon-home"> Apache Beam |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 2.47.0 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.runners.html">apache_beam.runners package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.testing.html">apache_beam.testing package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.transforms.html">apache_beam.transforms package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.yaml.html">apache_beam.yaml package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../index.html">Apache Beam</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.io.azure.blobstorageio</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <h1>Source code for apache_beam.io.azure.blobstorageio</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="sd">"""Azure Blob Storage client.</span> |
| <span class="sd">"""</span> |
| |
| <span class="c1"># pytype: skip-file</span> |
| |
| <span class="kn">import</span> <span class="nn">errno</span> |
| <span class="kn">import</span> <span class="nn">io</span> |
| <span class="kn">import</span> <span class="nn">logging</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">re</span> |
| <span class="kn">import</span> <span class="nn">tempfile</span> |
| <span class="kn">import</span> <span class="nn">time</span> |
| |
| <span class="kn">from</span> <span class="nn">apache_beam.internal.azure</span> <span class="kn">import</span> <span class="n">auth</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.filesystemio</span> <span class="kn">import</span> <span class="n">Downloader</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.filesystemio</span> <span class="kn">import</span> <span class="n">DownloaderStream</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.filesystemio</span> <span class="kn">import</span> <span class="n">Uploader</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.filesystemio</span> <span class="kn">import</span> <span class="n">UploaderStream</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">AzureOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.utils</span> <span class="kn">import</span> <span class="n">retry</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.utils.annotations</span> <span class="kn">import</span> <span class="n">deprecated</span> |
| |
| <span class="n">_LOGGER</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="vm">__name__</span><span class="p">)</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="c1"># pylint: disable=wrong-import-order, wrong-import-position</span> |
| <span class="c1"># pylint: disable=ungrouped-imports</span> |
| <span class="kn">from</span> <span class="nn">azure.core.exceptions</span> <span class="kn">import</span> <span class="n">ResourceNotFoundError</span> |
| <span class="kn">from</span> <span class="nn">azure.storage.blob</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">BlobServiceClient</span><span class="p">,</span> |
| <span class="n">ContentSettings</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="n">AZURE_DEPS_INSTALLED</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="n">AZURE_DEPS_INSTALLED</span> <span class="o">=</span> <span class="kc">False</span> |
| |
| <span class="n">DEFAULT_READ_BUFFER_SIZE</span> <span class="o">=</span> <span class="mi">16</span> <span class="o">*</span> <span class="mi">1024</span> <span class="o">*</span> <span class="mi">1024</span> |
| |
| <span class="n">MAX_BATCH_OPERATION_SIZE</span> <span class="o">=</span> <span class="mi">100</span> |
| |
| |
| <div class="viewcode-block" id="parse_azfs_path"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.parse_azfs_path">[docs]</a><span class="k">def</span> <span class="nf">parse_azfs_path</span><span class="p">(</span><span class="n">azfs_path</span><span class="p">,</span> <span class="n">blob_optional</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">get_account</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Return the storage account, the container and</span> |
| <span class="sd"> blob names of the given azfs:// path.</span> |
| <span class="sd"> """</span> |
| <span class="n">match</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">match</span><span class="p">(</span> |
| <span class="s1">'^azfs://([a-z0-9]{3,24})/([a-z0-9](?![a-z0-9-]*--[a-z0-9-]*)'</span> |
| <span class="s1">'[a-z0-9-]{1,61}[a-z0-9])/(.*)$'</span><span class="p">,</span> |
| <span class="n">azfs_path</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">match</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="p">(</span><span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span> <span class="o">==</span> <span class="s1">''</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">blob_optional</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Azure Blob Storage path must be in the form '</span> |
| <span class="s1">'azfs://<storage-account>/<container>/<path>.'</span><span class="p">)</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">if</span> <span class="n">get_account</span><span class="p">:</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">),</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">),</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">),</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">result</span></div> |
| |
| |
| <div class="viewcode-block" id="get_azfs_url"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.get_azfs_url">[docs]</a><span class="k">def</span> <span class="nf">get_azfs_url</span><span class="p">(</span><span class="n">storage_account</span><span class="p">,</span> <span class="n">container</span><span class="p">,</span> <span class="n">blob</span><span class="o">=</span><span class="s1">''</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Returns the url in the form of</span> |
| <span class="sd"> https://account.blob.core.windows.net/container/blob-name</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="s1">'https://'</span> <span class="o">+</span> <span class="n">storage_account</span> <span class="o">+</span> <span class="s1">'.blob.core.windows.net/'</span> <span class="o">+</span> \ |
| <span class="n">container</span> <span class="o">+</span> <span class="s1">'/'</span> <span class="o">+</span> <span class="n">blob</span></div> |
| |
| |
| <div class="viewcode-block" id="Blob"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.Blob">[docs]</a><span class="k">class</span> <span class="nc">Blob</span><span class="p">():</span> |
| <span class="w"> </span><span class="sd">"""A Blob in Azure Blob Storage."""</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">etag</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">last_updated</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">mime_type</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">etag</span> <span class="o">=</span> <span class="n">etag</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">last_updated</span> <span class="o">=</span> <span class="n">last_updated</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">size</span> <span class="o">=</span> <span class="n">size</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mime_type</span> <span class="o">=</span> <span class="n">mime_type</span></div> |
| |
| |
| <div class="viewcode-block" id="BlobStorageIOError"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIOError">[docs]</a><span class="k">class</span> <span class="nc">BlobStorageIOError</span><span class="p">(</span><span class="ne">IOError</span><span class="p">,</span> <span class="n">retry</span><span class="o">.</span><span class="n">PermanentException</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Blob Strorage IO error that should not be retried."""</span> |
| <span class="k">pass</span></div> |
| |
| |
| <div class="viewcode-block" id="BlobStorageError"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageError">[docs]</a><span class="k">class</span> <span class="nc">BlobStorageError</span><span class="p">(</span><span class="ne">Exception</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Blob Storage client error."""</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">message</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">code</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">message</span> <span class="o">=</span> <span class="n">message</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">code</span> <span class="o">=</span> <span class="n">code</span></div> |
| |
| |
| <div class="viewcode-block" id="BlobStorageIO"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO">[docs]</a><span class="k">class</span> <span class="nc">BlobStorageIO</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Azure Blob Storage I/O client."""</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">client</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">pipeline_options</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">client</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">azure_options</span> <span class="o">=</span> <span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">AzureOptions</span><span class="p">)</span> |
| <span class="n">connect_str</span> <span class="o">=</span> <span class="n">azure_options</span><span class="o">.</span><span class="n">azure_connection_string</span> <span class="ow">or</span> \ |
| <span class="n">os</span><span class="o">.</span><span class="n">getenv</span><span class="p">(</span><span class="s1">'AZURE_STORAGE_CONNECTION_STRING'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">connect_str</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">client</span> <span class="o">=</span> <span class="n">BlobServiceClient</span><span class="o">.</span><span class="n">from_connection_string</span><span class="p">(</span> |
| <span class="n">conn_str</span><span class="o">=</span><span class="n">connect_str</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">credential</span> <span class="o">=</span> <span class="n">auth</span><span class="o">.</span><span class="n">get_service_credentials</span><span class="p">(</span><span class="n">pipeline_options</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">client</span> <span class="o">=</span> <span class="n">BlobServiceClient</span><span class="p">(</span> |
| <span class="n">account_url</span><span class="o">=</span><span class="n">azure_options</span><span class="o">.</span><span class="n">blob_service_endpoint</span><span class="p">,</span> |
| <span class="n">credential</span><span class="o">=</span><span class="n">credential</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">client</span> <span class="o">=</span> <span class="n">client</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">AZURE_DEPS_INSTALLED</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s1">'Azure dependencies are not installed. Unable to run.'</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="BlobStorageIO.open"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.open">[docs]</a> <span class="k">def</span> <span class="nf">open</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">filename</span><span class="p">,</span> |
| <span class="n">mode</span><span class="o">=</span><span class="s1">'r'</span><span class="p">,</span> |
| <span class="n">read_buffer_size</span><span class="o">=</span><span class="n">DEFAULT_READ_BUFFER_SIZE</span><span class="p">,</span> |
| <span class="n">mime_type</span><span class="o">=</span><span class="s1">'application/octet-stream'</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Open an Azure Blob Storage file path for reading or writing.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> filename (str): Azure Blob Storage file path in the form</span> |
| <span class="sd"> ``azfs://<storage-account>/<container>/<path>``.</span> |
| <span class="sd"> mode (str): ``'r'`` for reading or ``'w'`` for writing.</span> |
| <span class="sd"> read_buffer_size (int): Buffer size to use during read operations.</span> |
| <span class="sd"> mime_type (str): Mime type to set for write operations.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> Azure Blob Storage file object.</span> |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ValueError: Invalid open file mode.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">'r'</span> <span class="ow">or</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">'rb'</span><span class="p">:</span> |
| <span class="n">downloader</span> <span class="o">=</span> <span class="n">BlobStorageDownloader</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="p">,</span> <span class="n">filename</span><span class="p">,</span> <span class="n">buffer_size</span><span class="o">=</span><span class="n">read_buffer_size</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">io</span><span class="o">.</span><span class="n">BufferedReader</span><span class="p">(</span> |
| <span class="n">DownloaderStream</span><span class="p">(</span> |
| <span class="n">downloader</span><span class="p">,</span> <span class="n">read_buffer_size</span><span class="o">=</span><span class="n">read_buffer_size</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="n">mode</span><span class="p">),</span> |
| <span class="n">buffer_size</span><span class="o">=</span><span class="n">read_buffer_size</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">'w'</span> <span class="ow">or</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">'wb'</span><span class="p">:</span> |
| <span class="n">uploader</span> <span class="o">=</span> <span class="n">BlobStorageUploader</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="p">,</span> <span class="n">filename</span><span class="p">,</span> <span class="n">mime_type</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">io</span><span class="o">.</span><span class="n">BufferedWriter</span><span class="p">(</span> |
| <span class="n">UploaderStream</span><span class="p">(</span><span class="n">uploader</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="n">mode</span><span class="p">),</span> <span class="n">buffer_size</span><span class="o">=</span><span class="mi">128</span> <span class="o">*</span> <span class="mi">1024</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Invalid file open mode: </span><span class="si">%s</span><span class="s1">.'</span> <span class="o">%</span> <span class="n">mode</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="BlobStorageIO.copy"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.copy">[docs]</a> <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span> |
| <span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_beam_io_error_filter</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">copy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Copies a single Azure Blob Storage blob from src to dest.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> src: Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| <span class="sd"> dest: Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> TimeoutError: on timeout.</span> |
| <span class="sd"> """</span> |
| <span class="n">src_storage_account</span><span class="p">,</span> <span class="n">src_container</span><span class="p">,</span> <span class="n">src_blob</span> <span class="o">=</span> <span class="n">parse_azfs_path</span><span class="p">(</span> |
| <span class="n">src</span><span class="p">,</span> <span class="n">get_account</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="n">dest_container</span><span class="p">,</span> <span class="n">dest_blob</span> <span class="o">=</span> <span class="n">parse_azfs_path</span><span class="p">(</span><span class="n">dest</span><span class="p">)</span> |
| |
| <span class="n">source_blob</span> <span class="o">=</span> <span class="n">get_azfs_url</span><span class="p">(</span><span class="n">src_storage_account</span><span class="p">,</span> <span class="n">src_container</span><span class="p">,</span> <span class="n">src_blob</span><span class="p">)</span> |
| <span class="n">copied_blob</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">get_blob_client</span><span class="p">(</span><span class="n">dest_container</span><span class="p">,</span> <span class="n">dest_blob</span><span class="p">)</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">copied_blob</span><span class="o">.</span><span class="n">start_copy_from_url</span><span class="p">(</span><span class="n">source_blob</span><span class="p">)</span> |
| <span class="k">except</span> <span class="n">ResourceNotFoundError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="n">message</span> <span class="o">=</span> <span class="n">e</span><span class="o">.</span><span class="n">reason</span> |
| <span class="n">code</span> <span class="o">=</span> <span class="n">e</span><span class="o">.</span><span class="n">status_code</span> |
| <span class="k">raise</span> <span class="n">BlobStorageError</span><span class="p">(</span><span class="n">message</span><span class="p">,</span> <span class="n">code</span><span class="p">)</span></div> |
| |
| <span class="c1"># We intentionally do not decorate this method with a retry, since the</span> |
| <span class="c1"># underlying copy operation is already an idempotent operation protected</span> |
| <span class="c1"># by retry decorators.</span> |
| <div class="viewcode-block" id="BlobStorageIO.copy_tree"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.copy_tree">[docs]</a> <span class="k">def</span> <span class="nf">copy_tree</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Renames the given Azure Blob storage directory and its contents</span> |
| <span class="sd"> recursively from src to dest.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> src: Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| <span class="sd"> dest: Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> List of tuples of (src, dest, exception) where exception is None if the</span> |
| <span class="sd"> operation succeeded or the relevant exception if the operation failed.</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="n">src</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="n">dest</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)</span> |
| |
| <span class="n">results</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">entry</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">list_prefix</span><span class="p">(</span><span class="n">src</span><span class="p">):</span> |
| <span class="n">rel_path</span> <span class="o">=</span> <span class="n">entry</span><span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">src</span><span class="p">):]</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">entry</span><span class="p">,</span> <span class="n">dest</span> <span class="o">+</span> <span class="n">rel_path</span><span class="p">)</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">entry</span><span class="p">,</span> <span class="n">dest</span> <span class="o">+</span> <span class="n">rel_path</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span> |
| <span class="k">except</span> <span class="n">BlobStorageError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">entry</span><span class="p">,</span> <span class="n">dest</span> <span class="o">+</span> <span class="n">rel_path</span><span class="p">,</span> <span class="n">e</span><span class="p">))</span> |
| |
| <span class="k">return</span> <span class="n">results</span></div> |
| |
| <span class="c1"># We intentionally do not decorate this method with a retry, since the</span> |
| <span class="c1"># underlying copy operation is already an idempotent operation protected</span> |
| <span class="c1"># by retry decorators.</span> |
| <div class="viewcode-block" id="BlobStorageIO.copy_paths"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.copy_paths">[docs]</a> <span class="k">def</span> <span class="nf">copy_paths</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src_dest_pairs</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Copies the given Azure Blob Storage blobs from src to dest. This can</span> |
| <span class="sd"> handle directory or file paths.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> src_dest_pairs: List of (src, dest) tuples of</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name] file paths</span> |
| <span class="sd"> to copy from src to dest.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> List of tuples of (src, dest, exception) in the same order as the</span> |
| <span class="sd"> src_dest_pairs argument, where exception is None if the operation</span> |
| <span class="sd"> succeeded or the relevant exception if the operation failed.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">src_dest_pairs</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">[]</span> |
| |
| <span class="n">results</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="k">for</span> <span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span> <span class="ow">in</span> <span class="n">src_dest_pairs</span><span class="p">:</span> |
| <span class="c1"># Case 1. They are directories.</span> |
| <span class="k">if</span> <span class="n">src_path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)</span> <span class="ow">and</span> <span class="n">dest_path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">):</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">results</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy_tree</span><span class="p">(</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">)</span> |
| <span class="k">except</span> <span class="n">BlobStorageError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">,</span> <span class="n">e</span><span class="p">))</span> |
| |
| <span class="c1"># Case 2. They are individual blobs.</span> |
| <span class="k">elif</span> <span class="ow">not</span> <span class="n">src_path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">dest_path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">):</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">)</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span> |
| <span class="k">except</span> <span class="n">BlobStorageError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">,</span> <span class="n">e</span><span class="p">))</span> |
| |
| <span class="c1"># Mismatched paths (one directory, one non-directory) get an error.</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">e</span> <span class="o">=</span> <span class="n">BlobStorageError</span><span class="p">(</span> |
| <span class="s2">"Unable to copy mismatched paths"</span> <span class="o">+</span> |
| <span class="s2">"(directory, non-directory): </span><span class="si">%s</span><span class="s2">, </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">),</span> |
| <span class="mi">400</span><span class="p">)</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">,</span> <span class="n">e</span><span class="p">))</span> |
| |
| <span class="k">return</span> <span class="n">results</span></div> |
| |
| <span class="c1"># We intentionally do not decorate this method with a retry, since the</span> |
| <span class="c1"># underlying copy and delete operations are already idempotent operations</span> |
| <span class="c1"># protected by retry decorators.</span> |
| <div class="viewcode-block" id="BlobStorageIO.rename"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.rename">[docs]</a> <span class="k">def</span> <span class="nf">rename</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Renames the given Azure Blob Storage blob from src to dest.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> src: Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| <span class="sd"> dest: Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="n">src</span><span class="p">)</span></div> |
| |
| <span class="c1"># We intentionally do not decorate this method with a retry, since the</span> |
| <span class="c1"># underlying copy and delete operations are already idempotent operations</span> |
| <span class="c1"># protected by retry decorators.</span> |
| <div class="viewcode-block" id="BlobStorageIO.rename_files"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.rename_files">[docs]</a> <span class="k">def</span> <span class="nf">rename_files</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src_dest_pairs</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Renames the given Azure Blob Storage blobs from src to dest.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> src_dest_pairs: List of (src, dest) tuples of</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name]</span> |
| <span class="sd"> file paths to rename from src to dest.</span> |
| <span class="sd"> Returns: List of tuples of (src, dest, exception) in the same order as the</span> |
| <span class="sd"> src_dest_pairs argument, where exception is None if the operation</span> |
| <span class="sd"> succeeded or the relevant exception if the operation failed.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">src_dest_pairs</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">[]</span> |
| |
| <span class="k">for</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span> <span class="ow">in</span> <span class="n">src_dest_pairs</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">src</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)</span> <span class="ow">or</span> <span class="n">dest</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Unable to rename a directory.'</span><span class="p">)</span> |
| |
| <span class="c1"># Results from copy operation.</span> |
| <span class="n">copy_results</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy_paths</span><span class="p">(</span><span class="n">src_dest_pairs</span><span class="p">)</span> |
| <span class="n">paths_to_delete</span> <span class="o">=</span> \ |
| <span class="p">[</span><span class="n">src</span> <span class="k">for</span> <span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">error</span><span class="p">)</span> <span class="ow">in</span> <span class="n">copy_results</span> <span class="k">if</span> <span class="n">error</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">]</span> |
| <span class="c1"># Results from delete operation.</span> |
| <span class="n">delete_results</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">delete_files</span><span class="p">(</span><span class="n">paths_to_delete</span><span class="p">)</span> |
| |
| <span class="c1"># Get rename file results (list of tuples).</span> |
| <span class="n">results</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="c1"># Using a dictionary will make the operation faster.</span> |
| <span class="n">delete_results_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">src</span><span class="p">:</span> <span class="n">error</span> <span class="k">for</span> <span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">error</span><span class="p">)</span> <span class="ow">in</span> <span class="n">delete_results</span><span class="p">}</span> |
| |
| <span class="k">for</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">,</span> <span class="n">error</span> <span class="ow">in</span> <span class="n">copy_results</span><span class="p">:</span> |
| <span class="c1"># If there was an error in the copy operation.</span> |
| <span class="k">if</span> <span class="n">error</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">,</span> <span class="n">error</span><span class="p">))</span> |
| <span class="c1"># If there was an error in the delete operation.</span> |
| <span class="k">elif</span> <span class="n">delete_results_dict</span><span class="p">[</span><span class="n">src</span><span class="p">]</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">,</span> <span class="n">delete_results_dict</span><span class="p">[</span><span class="n">src</span><span class="p">]))</span> |
| <span class="c1"># If there was no error in the operations.</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span> |
| |
| <span class="k">return</span> <span class="n">results</span></div> |
| |
| <div class="viewcode-block" id="BlobStorageIO.exists"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.exists">[docs]</a> <span class="k">def</span> <span class="nf">exists</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Returns whether the given Azure Blob Storage blob exists.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: Azure Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| <span class="sd"> """</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_blob_properties</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| <span class="k">except</span> <span class="n">ResourceNotFoundError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">status_code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span> |
| <span class="c1"># HTTP 404 indicates that the file did not exist.</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># We re-raise all other exceptions.</span> |
| <span class="k">raise</span></div> |
| |
| <div class="viewcode-block" id="BlobStorageIO.size"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.size">[docs]</a> <span class="k">def</span> <span class="nf">size</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Returns the size of a single Blob Storage blob.</span> |
| |
| <span class="sd"> This method does not perform glob expansion. Hence the</span> |
| <span class="sd"> given path must be for a single Blob Storage blob.</span> |
| |
| <span class="sd"> Returns: size of the Blob Storage blob in bytes.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_blob_properties</span><span class="p">(</span><span class="n">path</span><span class="p">)</span><span class="o">.</span><span class="n">size</span></div> |
| |
| <div class="viewcode-block" id="BlobStorageIO.last_updated"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.last_updated">[docs]</a> <span class="k">def</span> <span class="nf">last_updated</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Returns the last updated epoch time of a single</span> |
| <span class="sd"> Azure Blob Storage blob.</span> |
| |
| <span class="sd"> This method does not perform glob expansion. Hence the</span> |
| <span class="sd"> given path must be for a single Azure Blob Storage blob.</span> |
| |
| <span class="sd"> Returns: last updated time of the Azure Blob Storage blob</span> |
| <span class="sd"> in seconds.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_updated_to_seconds</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_blob_properties</span><span class="p">(</span><span class="n">path</span><span class="p">)</span><span class="o">.</span><span class="n">last_modified</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="BlobStorageIO.checksum"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.checksum">[docs]</a> <span class="k">def</span> <span class="nf">checksum</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Looks up the checksum of an Azure Blob Storage blob.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: Azure Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_blob_properties</span><span class="p">(</span><span class="n">path</span><span class="p">)</span><span class="o">.</span><span class="n">etag</span></div> |
| |
| <span class="k">def</span> <span class="nf">_status</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""For internal use only; no backwards-compatibility guarantees.</span> |
| |
| <span class="sd"> Returns supported fields (checksum, last_updated, size) of a single object</span> |
| <span class="sd"> as a dict at once.</span> |
| |
| <span class="sd"> This method does not perform glob expansion. Hence the given path must be</span> |
| <span class="sd"> for a single blob property.</span> |
| |
| <span class="sd"> Returns: dict of fields of the blob property.</span> |
| <span class="sd"> """</span> |
| <span class="n">properties</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_blob_properties</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="n">file_status</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">properties</span><span class="p">,</span> <span class="s1">'etag'</span><span class="p">):</span> |
| <span class="n">file_status</span><span class="p">[</span><span class="s1">'checksum'</span><span class="p">]</span> <span class="o">=</span> <span class="n">properties</span><span class="o">.</span><span class="n">etag</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">properties</span><span class="p">,</span> <span class="s1">'last_modified'</span><span class="p">):</span> |
| <span class="n">file_status</span><span class="p">[</span><span class="s1">'last_updated'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_updated_to_seconds</span><span class="p">(</span> |
| <span class="n">properties</span><span class="o">.</span><span class="n">last_modified</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">properties</span><span class="p">,</span> <span class="s1">'size'</span><span class="p">):</span> |
| <span class="n">file_status</span><span class="p">[</span><span class="s1">'size'</span><span class="p">]</span> <span class="o">=</span> <span class="n">properties</span><span class="o">.</span><span class="n">size</span> |
| <span class="k">return</span> <span class="n">file_status</span> |
| |
| <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span> |
| <span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_beam_io_error_filter</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">_blob_properties</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Returns a blob properties object for the given path</span> |
| |
| <span class="sd"> This method does not perform glob expansion. Hence the given path must be</span> |
| <span class="sd"> for a single blob properties object.</span> |
| |
| <span class="sd"> Returns: blob properties.</span> |
| <span class="sd"> """</span> |
| <span class="n">container</span><span class="p">,</span> <span class="n">blob</span> <span class="o">=</span> <span class="n">parse_azfs_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="n">blob_to_check</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">get_blob_client</span><span class="p">(</span><span class="n">container</span><span class="p">,</span> <span class="n">blob</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">properties</span> <span class="o">=</span> <span class="n">blob_to_check</span><span class="o">.</span><span class="n">get_blob_properties</span><span class="p">()</span> |
| <span class="k">except</span> <span class="n">ResourceNotFoundError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="n">message</span> <span class="o">=</span> <span class="n">e</span><span class="o">.</span><span class="n">reason</span> |
| <span class="n">code</span> <span class="o">=</span> <span class="n">e</span><span class="o">.</span><span class="n">status_code</span> |
| <span class="k">raise</span> <span class="n">BlobStorageError</span><span class="p">(</span><span class="n">message</span><span class="p">,</span> <span class="n">code</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">properties</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_updated_to_seconds</span><span class="p">(</span><span class="n">updated</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Helper function transform the updated field of response to seconds"""</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="n">time</span><span class="o">.</span><span class="n">mktime</span><span class="p">(</span><span class="n">updated</span><span class="o">.</span><span class="n">timetuple</span><span class="p">())</span> <span class="o">-</span> <span class="n">time</span><span class="o">.</span><span class="n">timezone</span> <span class="o">+</span> |
| <span class="n">updated</span><span class="o">.</span><span class="n">microsecond</span> <span class="o">/</span> <span class="mf">1000000.0</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="BlobStorageIO.delete"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.delete">[docs]</a> <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span> |
| <span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_beam_io_error_filter</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">delete</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Deletes a single blob at the given Azure Blob Storage path.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: Azure Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| <span class="sd"> """</span> |
| <span class="n">container</span><span class="p">,</span> <span class="n">blob</span> <span class="o">=</span> <span class="n">parse_azfs_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="n">blob_to_delete</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">get_blob_client</span><span class="p">(</span><span class="n">container</span><span class="p">,</span> <span class="n">blob</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">blob_to_delete</span><span class="o">.</span><span class="n">delete_blob</span><span class="p">()</span> |
| <span class="k">except</span> <span class="n">ResourceNotFoundError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">status_code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span> |
| <span class="c1"># Return success when the file doesn't exist anymore for idempotency.</span> |
| <span class="k">return</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s1">'HTTP error while deleting file </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span> |
| <span class="k">raise</span> <span class="n">e</span></div> |
| |
| <span class="c1"># We intentionally do not decorate this method with a retry, since the</span> |
| <span class="c1"># underlying copy and delete operations are already idempotent operations</span> |
| <span class="c1"># protected by retry decorators.</span> |
| <div class="viewcode-block" id="BlobStorageIO.delete_paths"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.delete_paths">[docs]</a> <span class="k">def</span> <span class="nf">delete_paths</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">paths</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Deletes the given Azure Blob Storage blobs from src to dest.</span> |
| <span class="sd"> This can handle directory or file paths.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> paths: list of Azure Blob Storage paths in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name] that give the</span> |
| <span class="sd"> file blobs to be deleted.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> List of tuples of (src, dest, exception) in the same order as the</span> |
| <span class="sd"> src_dest_pairs argument, where exception is None if the operation</span> |
| <span class="sd"> succeeded or the relevant exception if the operation failed.</span> |
| <span class="sd"> """</span> |
| <span class="n">directories</span><span class="p">,</span> <span class="n">blobs</span> <span class="o">=</span> <span class="p">[],</span> <span class="p">[]</span> |
| |
| <span class="c1"># Retrieve directories and not directories.</span> |
| <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">paths</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">):</span> |
| <span class="n">directories</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">blobs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| |
| <span class="n">results</span> <span class="o">=</span> <span class="p">{}</span> |
| |
| <span class="k">for</span> <span class="n">directory</span> <span class="ow">in</span> <span class="n">directories</span><span class="p">:</span> |
| <span class="n">directory_result</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">delete_tree</span><span class="p">(</span><span class="n">directory</span><span class="p">))</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">directory_result</span><span class="p">)</span> |
| |
| <span class="n">blobs_results</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">delete_files</span><span class="p">(</span><span class="n">blobs</span><span class="p">))</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">blobs_results</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">results</span></div> |
| |
| <span class="c1"># We intentionally do not decorate this method with a retry, since the</span> |
| <span class="c1"># underlying copy and delete operations are already idempotent operations</span> |
| <span class="c1"># protected by retry decorators.</span> |
| <div class="viewcode-block" id="BlobStorageIO.delete_tree"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.delete_tree">[docs]</a> <span class="k">def</span> <span class="nf">delete_tree</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">root</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Deletes all blobs under the given Azure BlobStorage virtual</span> |
| <span class="sd"> directory.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: Azure Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name]</span> |
| <span class="sd"> (ending with a "/").</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> List of tuples of (path, exception), where each path is a blob</span> |
| <span class="sd"> under the given root. exception is None if the operation succeeded</span> |
| <span class="sd"> or the relevant exception if the operation failed.</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="n">root</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)</span> |
| |
| <span class="c1"># Get the blob under the root directory.</span> |
| <span class="n">paths_to_delete</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">list_prefix</span><span class="p">(</span><span class="n">root</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">delete_files</span><span class="p">(</span><span class="n">paths_to_delete</span><span class="p">)</span></div> |
| |
| <span class="c1"># We intentionally do not decorate this method with a retry, since the</span> |
| <span class="c1"># underlying copy and delete operations are already idempotent operations</span> |
| <span class="c1"># protected by retry decorators.</span> |
| <div class="viewcode-block" id="BlobStorageIO.delete_files"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.delete_files">[docs]</a> <span class="k">def</span> <span class="nf">delete_files</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">paths</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Deletes the given Azure Blob Storage blobs from src to dest.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> paths: list of Azure Blob Storage paths in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name] that give the</span> |
| <span class="sd"> file blobs to be deleted.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> List of tuples of (src, dest, exception) in the same order as the</span> |
| <span class="sd"> src_dest_pairs argument, where exception is None if the operation</span> |
| <span class="sd"> succeeded or the relevant exception if the operation failed.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">paths</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">[]</span> |
| |
| <span class="c1"># Group blobs into containers.</span> |
| <span class="n">containers</span><span class="p">,</span> <span class="n">blobs</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="p">[</span><span class="n">parse_azfs_path</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">get_account</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> \ |
| <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">paths</span><span class="p">])</span> |
| |
| <span class="n">grouped_blobs</span> <span class="o">=</span> <span class="p">{</span><span class="n">container</span><span class="p">:</span> <span class="p">[]</span> <span class="k">for</span> <span class="n">container</span> <span class="ow">in</span> <span class="n">containers</span><span class="p">}</span> |
| |
| <span class="c1"># Fill dictionary.</span> |
| <span class="k">for</span> <span class="n">container</span><span class="p">,</span> <span class="n">blob</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">containers</span><span class="p">,</span> <span class="n">blobs</span><span class="p">):</span> |
| <span class="n">grouped_blobs</span><span class="p">[</span><span class="n">container</span><span class="p">]</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">blob</span><span class="p">)</span> |
| |
| <span class="n">results</span> <span class="o">=</span> <span class="p">{}</span> |
| |
| <span class="c1"># Delete minibatches of blobs for each container.</span> |
| <span class="k">for</span> <span class="n">container</span><span class="p">,</span> <span class="n">blobs</span> <span class="ow">in</span> <span class="n">grouped_blobs</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">blobs</span><span class="p">),</span> <span class="n">MAX_BATCH_OPERATION_SIZE</span><span class="p">):</span> |
| <span class="n">blobs_to_delete</span> <span class="o">=</span> <span class="n">blobs</span><span class="p">[</span><span class="n">i</span><span class="p">:</span><span class="n">i</span> <span class="o">+</span> <span class="n">MAX_BATCH_OPERATION_SIZE</span><span class="p">]</span> |
| <span class="n">results</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_delete_batch</span><span class="p">(</span><span class="n">container</span><span class="p">,</span> <span class="n">blobs_to_delete</span><span class="p">))</span> |
| |
| <span class="n">final_results</span> <span class="o">=</span> \ |
| <span class="p">[(</span><span class="n">path</span><span class="p">,</span> <span class="n">results</span><span class="p">[</span><span class="n">parse_azfs_path</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">get_account</span><span class="o">=</span><span class="kc">False</span><span class="p">)])</span> \ |
| <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">paths</span><span class="p">]</span> |
| |
| <span class="k">return</span> <span class="n">final_results</span></div> |
| |
| <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span> |
| <span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_beam_io_error_filter</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">_delete_batch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">container</span><span class="p">,</span> <span class="n">blobs</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""A helper method. Azure Blob Storage Python Client allows batch</span> |
| <span class="sd"> deletions for blobs within the same container.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> container: container name.</span> |
| <span class="sd"> blobs: list of blobs to be deleted.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> Dictionary of the form {(container, blob): error}, where error is</span> |
| <span class="sd"> None if the operation succeeded.</span> |
| <span class="sd"> """</span> |
| <span class="n">container_client</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">get_container_client</span><span class="p">(</span><span class="n">container</span><span class="p">)</span> |
| <span class="n">results</span> <span class="o">=</span> <span class="p">{}</span> |
| |
| <span class="k">for</span> <span class="n">blob</span> <span class="ow">in</span> <span class="n">blobs</span><span class="p">:</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="n">container_client</span><span class="o">.</span><span class="n">delete_blob</span><span class="p">(</span><span class="n">blob</span><span class="p">)</span> |
| <span class="n">results</span><span class="p">[(</span><span class="n">container</span><span class="p">,</span> <span class="n">blob</span><span class="p">)]</span> <span class="o">=</span> <span class="n">response</span> |
| <span class="k">except</span> <span class="n">ResourceNotFoundError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="n">results</span><span class="p">[(</span><span class="n">container</span><span class="p">,</span> <span class="n">blob</span><span class="p">)]</span> <span class="o">=</span> <span class="n">e</span><span class="o">.</span><span class="n">status_code</span> |
| |
| <span class="k">return</span> <span class="n">results</span> |
| |
| <div class="viewcode-block" id="BlobStorageIO.list_prefix"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.list_prefix">[docs]</a> <span class="nd">@deprecated</span><span class="p">(</span><span class="n">since</span><span class="o">=</span><span class="s1">'2.45.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s1">'list_files'</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">list_prefix</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">with_metadata</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Lists files matching the prefix.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: Azure Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| <span class="sd"> with_metadata: Experimental. Specify whether returns file metadata.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> If ``with_metadata`` is False: dict of file name -> size; if</span> |
| <span class="sd"> ``with_metadata`` is True: dict of file name -> tuple(size, timestamp).</span> |
| <span class="sd"> """</span> |
| <span class="n">file_info</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">file_metadata</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">list_files</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">with_metadata</span><span class="p">):</span> |
| <span class="n">file_info</span><span class="p">[</span><span class="n">file_metadata</span><span class="p">[</span><span class="mi">0</span><span class="p">]]</span> <span class="o">=</span> <span class="n">file_metadata</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> |
| |
| <span class="k">return</span> <span class="n">file_info</span></div> |
| |
| <div class="viewcode-block" id="BlobStorageIO.list_files"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageIO.list_files">[docs]</a> <span class="k">def</span> <span class="nf">list_files</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">with_metadata</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Lists files matching the prefix.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: Azure Blob Storage file path pattern in the form</span> |
| <span class="sd"> azfs://<storage-account>/<container>/[name].</span> |
| <span class="sd"> with_metadata: Experimental. Specify whether returns file metadata.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> If ``with_metadata`` is False: generator of tuple(file name, size); if</span> |
| <span class="sd"> ``with_metadata`` is True: generator of</span> |
| <span class="sd"> tuple(file name, tuple(size, timestamp)).</span> |
| <span class="sd"> """</span> |
| <span class="n">storage_account</span><span class="p">,</span> <span class="n">container</span><span class="p">,</span> <span class="n">blob</span> <span class="o">=</span> <span class="n">parse_azfs_path</span><span class="p">(</span> |
| <span class="n">path</span><span class="p">,</span> <span class="n">blob_optional</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">get_account</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="n">file_info</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span> |
| <span class="n">counter</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">start_time</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> |
| |
| <span class="k">if</span> <span class="n">with_metadata</span><span class="p">:</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Starting the file information of the input"</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Starting the size estimation of the input"</span><span class="p">)</span> |
| <span class="n">container_client</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">get_container_client</span><span class="p">(</span><span class="n">container</span><span class="p">)</span> |
| |
| <span class="n">response</span> <span class="o">=</span> <span class="n">retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span> |
| <span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_beam_io_error_filter</span><span class="p">)(</span> |
| <span class="n">container_client</span><span class="o">.</span><span class="n">list_blobs</span><span class="p">)(</span> |
| <span class="n">name_starts_with</span><span class="o">=</span><span class="n">blob</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">response</span><span class="p">:</span> |
| <span class="n">file_name</span> <span class="o">=</span> <span class="s2">"azfs://</span><span class="si">%s</span><span class="s2">/</span><span class="si">%s</span><span class="s2">/</span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">storage_account</span><span class="p">,</span> <span class="n">container</span><span class="p">,</span> <span class="n">item</span><span class="o">.</span><span class="n">name</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">file_name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">file_info</span><span class="p">:</span> |
| <span class="n">file_info</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">file_name</span><span class="p">)</span> |
| <span class="n">counter</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">if</span> <span class="n">counter</span> <span class="o">%</span> <span class="mi">10000</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">with_metadata</span><span class="p">:</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s2">"Finished computing file information of: </span><span class="si">%s</span><span class="s2"> files"</span><span class="p">,</span> |
| <span class="nb">len</span><span class="p">(</span><span class="n">file_info</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Finished computing size of: </span><span class="si">%s</span><span class="s2"> files"</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">file_info</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">with_metadata</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="n">file_name</span><span class="p">,</span> <span class="p">(</span> |
| <span class="n">item</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_updated_to_seconds</span><span class="p">(</span><span class="n">item</span><span class="o">.</span><span class="n">last_modified</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="n">file_name</span><span class="p">,</span> <span class="n">item</span><span class="o">.</span><span class="n">size</span> |
| |
| <span class="n">logging</span><span class="o">.</span><span class="n">log</span><span class="p">(</span> |
| <span class="c1"># do not spam logs when list_prefix is likely used to check empty folder</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">INFO</span> <span class="k">if</span> <span class="n">counter</span> <span class="o">></span> <span class="mi">0</span> <span class="k">else</span> <span class="n">logging</span><span class="o">.</span><span class="n">DEBUG</span><span class="p">,</span> |
| <span class="s2">"Finished listing </span><span class="si">%s</span><span class="s2"> files in </span><span class="si">%s</span><span class="s2"> seconds."</span><span class="p">,</span> |
| <span class="n">counter</span><span class="p">,</span> |
| <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">start_time</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="BlobStorageDownloader"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageDownloader">[docs]</a><span class="k">class</span> <span class="nc">BlobStorageDownloader</span><span class="p">(</span><span class="n">Downloader</span><span class="p">):</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">client</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">buffer_size</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_client</span> <span class="o">=</span> <span class="n">client</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_path</span> <span class="o">=</span> <span class="n">path</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_container</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_blob</span> <span class="o">=</span> <span class="n">parse_azfs_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_buffer_size</span> <span class="o">=</span> <span class="n">buffer_size</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_blob_to_download</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_client</span><span class="o">.</span><span class="n">get_blob_client</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_container</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_blob</span><span class="p">)</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">properties</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_object_properties</span><span class="p">()</span> |
| <span class="k">except</span> <span class="n">ResourceNotFoundError</span> <span class="k">as</span> <span class="n">http_error</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">http_error</span><span class="o">.</span><span class="n">status_code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">IOError</span><span class="p">(</span><span class="n">errno</span><span class="o">.</span><span class="n">ENOENT</span><span class="p">,</span> <span class="s1">'Not found: </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">_path</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span> |
| <span class="s1">'HTTP error while requesting file </span><span class="si">%s</span><span class="s1">: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_path</span><span class="p">,</span> <span class="n">http_error</span><span class="p">)</span> |
| <span class="k">raise</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_size</span> <span class="o">=</span> <span class="n">properties</span><span class="o">.</span><span class="n">size</span> |
| |
| <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span> |
| <span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_beam_io_error_filter</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">_get_object_properties</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_blob_to_download</span><span class="o">.</span><span class="n">get_blob_properties</span><span class="p">()</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">size</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_size</span> |
| |
| <div class="viewcode-block" id="BlobStorageDownloader.get_range"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageDownloader.get_range">[docs]</a> <span class="k">def</span> <span class="nf">get_range</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">start</span><span class="p">,</span> <span class="n">end</span><span class="p">):</span> |
| <span class="c1"># Download_blob first parameter is offset and second is length (exclusive).</span> |
| <span class="n">blob_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_blob_to_download</span><span class="o">.</span><span class="n">download_blob</span><span class="p">(</span><span class="n">start</span><span class="p">,</span> <span class="n">end</span> <span class="o">-</span> <span class="n">start</span><span class="p">)</span> |
| <span class="c1"># Returns the content as bytes.</span> |
| <span class="k">return</span> <span class="n">blob_data</span><span class="o">.</span><span class="n">readall</span><span class="p">()</span></div></div> |
| |
| |
| <div class="viewcode-block" id="BlobStorageUploader"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageUploader">[docs]</a><span class="k">class</span> <span class="nc">BlobStorageUploader</span><span class="p">(</span><span class="n">Uploader</span><span class="p">):</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">client</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">mime_type</span><span class="o">=</span><span class="s1">'application/octet-stream'</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_client</span> <span class="o">=</span> <span class="n">client</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_path</span> <span class="o">=</span> <span class="n">path</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_container</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_blob</span> <span class="o">=</span> <span class="n">parse_azfs_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_content_settings</span> <span class="o">=</span> <span class="n">ContentSettings</span><span class="p">(</span><span class="n">mime_type</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_blob_to_upload</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_client</span><span class="o">.</span><span class="n">get_blob_client</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_container</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_blob</span><span class="p">)</span> |
| |
| <span class="c1"># Temporary file.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_temporary_file</span> <span class="o">=</span> <span class="n">tempfile</span><span class="o">.</span><span class="n">NamedTemporaryFile</span><span class="p">()</span> |
| |
| <div class="viewcode-block" id="BlobStorageUploader.put"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageUploader.put">[docs]</a> <span class="k">def</span> <span class="nf">put</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_temporary_file</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">tobytes</span><span class="p">())</span></div> |
| |
| <div class="viewcode-block" id="BlobStorageUploader.finish"><a class="viewcode-back" href="../../../../apache_beam.io.azure.blobstorageio.html#apache_beam.io.azure.blobstorageio.BlobStorageUploader.finish">[docs]</a> <span class="k">def</span> <span class="nf">finish</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_temporary_file</span><span class="o">.</span><span class="n">seek</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> |
| <span class="c1"># The temporary file is deleted immediately after the operation.</span> |
| <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_temporary_file</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="s2">"rb"</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_blob_to_upload</span><span class="o">.</span><span class="n">upload_blob</span><span class="p">(</span> |
| <span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">(),</span> <span class="n">overwrite</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">content_settings</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_content_settings</span><span class="p">)</span></div></div> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |