| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.util — PySpark 3.3.3 documentation</title> |
| |
| <link rel="stylesheet" href="../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css"> |
| |
| |
| <link rel="stylesheet" |
| href="../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| <link rel="stylesheet" |
| href="../../_static/vendor/open-sans_all/1.44.1/index.css"> |
| <link rel="stylesheet" |
| href="../../_static/vendor/lato_latin-ext/1.44.1/index.css"> |
| |
| |
| <link rel="stylesheet" href="../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../_static/js/index.3da636dd464baa7582d2.js"> |
| |
| <script id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script> |
| <script src="../../_static/jquery.js"></script> |
| <script src="../../_static/underscore.js"></script> |
| <script src="../../_static/doctools.js"></script> |
| <script src="../../_static/language_data.js"></script> |
| <script src="../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="search" title="Search" href="../../search.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="en" /> |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"> |
| <div class="container-xl"> |
| |
| <a class="navbar-brand" href="../../index.html"> |
| |
| <img src="../../_static/spark-logo-reverse.png" class="logo" alt="logo" /> |
| |
| </a> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-menu" aria-controls="navbar-menu" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| <div id="navbar-menu" class="col-lg-9 collapse navbar-collapse"> |
| <ul id="navbar-main-elements" class="navbar-nav mr-auto"> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../getting_started/index.html">Getting Started</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../user_guide/index.html">User Guide</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../reference/index.html">API Reference</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../development/index.html">Development</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../migration_guide/index.html">Migration Guide</a> |
| </li> |
| |
| |
| </ul> |
| |
| |
| |
| |
| <ul class="navbar-nav"> |
| |
| |
| </ul> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| <div class="col-12 col-md-3 bd-sidebar"><form class="bd-search d-flex align-items-center" action="../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form> |
| <nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| |
| <div class="bd-toc-item active"> |
| |
| |
| <ul class="nav bd-sidenav"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| </ul> |
| |
| </nav> |
| </div> |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| |
| <nav id="bd-toc-nav"> |
| <ul class="nav section-nav flex-column"> |
| |
| </ul> |
| </nav> |
| |
| |
| |
| </div> |
| |
| |
| |
| <main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main"> |
| |
| <div> |
| |
| <h1>Source code for pyspark.util</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># -*- coding: utf-8 -*-</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="kn">import</span> <span class="nn">functools</span> |
| <span class="kn">import</span> <span class="nn">itertools</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">platform</span> |
| <span class="kn">import</span> <span class="nn">re</span> |
| <span class="kn">import</span> <span class="nn">sys</span> |
| <span class="kn">import</span> <span class="nn">threading</span> |
| <span class="kn">import</span> <span class="nn">traceback</span> |
| <span class="kn">from</span> <span class="nn">types</span> <span class="kn">import</span> <span class="n">TracebackType</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Callable</span><span class="p">,</span> <span class="n">Iterator</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">TextIO</span><span class="p">,</span> <span class="n">Tuple</span> |
| |
| <span class="kn">from</span> <span class="nn">py4j.clientserver</span> <span class="kn">import</span> <span class="n">ClientServer</span> |
| |
| <span class="n">__all__</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="kn">from</span> <span class="nn">py4j.java_gateway</span> <span class="kn">import</span> <span class="n">JavaObject</span> |
| |
| |
| <span class="k">def</span> <span class="nf">print_exec</span><span class="p">(</span><span class="n">stream</span><span class="p">:</span> <span class="n">TextIO</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">ei</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">exc_info</span><span class="p">()</span> |
| <span class="n">traceback</span><span class="o">.</span><span class="n">print_exception</span><span class="p">(</span><span class="n">ei</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">ei</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">ei</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="kc">None</span><span class="p">,</span> <span class="n">stream</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="VersionUtils"><a class="viewcode-back" href="../../reference/api/pyspark.util.VersionUtils.html#pyspark.VersionUtils">[docs]</a><span class="k">class</span> <span class="nc">VersionUtils</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Provides utility method to determine Spark versions with given input string.</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="VersionUtils.majorMinorVersion"><a class="viewcode-back" href="../../reference/api/pyspark.util.VersionUtils.majorMinorVersion.html#pyspark.VersionUtils.majorMinorVersion">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">majorMinorVersion</span><span class="p">(</span><span class="n">sparkVersion</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Given a Spark version string, return the (major version number, minor version number).</span> |
| <span class="sd"> E.g., for 2.0.1-SNAPSHOT, return (2, 0).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> sparkVersion = "2.4.0"</span> |
| <span class="sd"> >>> VersionUtils.majorMinorVersion(sparkVersion)</span> |
| <span class="sd"> (2, 4)</span> |
| <span class="sd"> >>> sparkVersion = "2.3.0-SNAPSHOT"</span> |
| <span class="sd"> >>> VersionUtils.majorMinorVersion(sparkVersion)</span> |
| <span class="sd"> (2, 3)</span> |
| <span class="sd"> """</span> |
| <span class="n">m</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="sa">r</span><span class="s2">"^(\d+)\.(\d+)(\..*)?$"</span><span class="p">,</span> <span class="n">sparkVersion</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">m</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">m</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="nb">int</span><span class="p">(</span><span class="n">m</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="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s2">"Spark tried to parse '</span><span class="si">%s</span><span class="s2">' as a Spark"</span> <span class="o">%</span> <span class="n">sparkVersion</span> |
| <span class="o">+</span> <span class="s2">" version string, but it could not find the major and minor"</span> |
| <span class="o">+</span> <span class="s2">" version numbers."</span> |
| <span class="p">)</span></div></div> |
| |
| |
| <span class="k">def</span> <span class="nf">fail_on_stopiteration</span><span class="p">(</span><span class="n">f</span><span class="p">:</span> <span class="n">Callable</span><span class="p">)</span> <span class="o">-></span> <span class="n">Callable</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Wraps the input function to fail on 'StopIteration' by raising a 'RuntimeError'</span> |
| <span class="sd"> prevents silent loss of data when 'f' is used in a for loop in Spark code</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">wrapper</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">f</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">StopIteration</span> <span class="k">as</span> <span class="n">exc</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span> |
| <span class="s2">"Caught StopIteration thrown from user's code; failing the task"</span><span class="p">,</span> <span class="n">exc</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">wrapper</span> |
| |
| |
| <span class="k">def</span> <span class="nf">walk_tb</span><span class="p">(</span><span class="n">tb</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">TracebackType</span><span class="p">])</span> <span class="o">-></span> <span class="n">Iterator</span><span class="p">[</span><span class="n">TracebackType</span><span class="p">]:</span> |
| <span class="k">while</span> <span class="n">tb</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="n">tb</span> |
| <span class="n">tb</span> <span class="o">=</span> <span class="n">tb</span><span class="o">.</span><span class="n">tb_next</span> |
| |
| |
| <span class="k">def</span> <span class="nf">try_simplify_traceback</span><span class="p">(</span><span class="n">tb</span><span class="p">:</span> <span class="n">TracebackType</span><span class="p">)</span> <span class="o">-></span> <span class="n">Optional</span><span class="p">[</span><span class="n">TracebackType</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Simplify the traceback. It removes the tracebacks in the current package, and only</span> |
| <span class="sd"> shows the traceback that is related to the thirdparty and user-specified codes.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> TracebackType or None</span> |
| <span class="sd"> Simplified traceback instance. It returns None if it fails to simplify.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> This keeps the tracebacks once it sees they are from a different file even</span> |
| <span class="sd"> though the following tracebacks are from the current package.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import importlib</span> |
| <span class="sd"> >>> import sys</span> |
| <span class="sd"> >>> import traceback</span> |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as tmp_dir:</span> |
| <span class="sd"> ... with open("%s/dummy_module.py" % tmp_dir, "w") as f:</span> |
| <span class="sd"> ... _ = f.write(</span> |
| <span class="sd"> ... 'def raise_stop_iteration():\\n'</span> |
| <span class="sd"> ... ' raise StopIteration()\\n\\n'</span> |
| <span class="sd"> ... 'def simple_wrapper(f):\\n'</span> |
| <span class="sd"> ... ' def wrapper(*a, **k):\\n'</span> |
| <span class="sd"> ... ' return f(*a, **k)\\n'</span> |
| <span class="sd"> ... ' return wrapper\\n')</span> |
| <span class="sd"> ... f.flush()</span> |
| <span class="sd"> ... spec = importlib.util.spec_from_file_location(</span> |
| <span class="sd"> ... "dummy_module", "%s/dummy_module.py" % tmp_dir)</span> |
| <span class="sd"> ... dummy_module = importlib.util.module_from_spec(spec)</span> |
| <span class="sd"> ... spec.loader.exec_module(dummy_module)</span> |
| <span class="sd"> >>> def skip_doctest_traceback(tb):</span> |
| <span class="sd"> ... import pyspark</span> |
| <span class="sd"> ... root = os.path.dirname(pyspark.__file__)</span> |
| <span class="sd"> ... pairs = zip(walk_tb(tb), traceback.extract_tb(tb))</span> |
| <span class="sd"> ... for cur_tb, cur_frame in pairs:</span> |
| <span class="sd"> ... if cur_frame.filename.startswith(root):</span> |
| <span class="sd"> ... return cur_tb</span> |
| |
| <span class="sd"> Regular exceptions should show the file name of the current package as below.</span> |
| |
| <span class="sd"> >>> exc_info = None</span> |
| <span class="sd"> >>> try:</span> |
| <span class="sd"> ... fail_on_stopiteration(dummy_module.raise_stop_iteration)()</span> |
| <span class="sd"> ... except Exception as e:</span> |
| <span class="sd"> ... tb = sys.exc_info()[-1]</span> |
| <span class="sd"> ... e.__cause__ = None</span> |
| <span class="sd"> ... exc_info = "".join(</span> |
| <span class="sd"> ... traceback.format_exception(type(e), e, tb))</span> |
| <span class="sd"> >>> print(exc_info) # doctest: +NORMALIZE_WHITESPACE, +ELLIPSIS</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> File ...</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> File "/.../pyspark/util.py", line ...</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> RuntimeError: ...</span> |
| <span class="sd"> >>> "pyspark/util.py" in exc_info</span> |
| <span class="sd"> True</span> |
| |
| <span class="sd"> If the traceback is simplified with this method, it hides the current package file name:</span> |
| |
| <span class="sd"> >>> exc_info = None</span> |
| <span class="sd"> >>> try:</span> |
| <span class="sd"> ... fail_on_stopiteration(dummy_module.raise_stop_iteration)()</span> |
| <span class="sd"> ... except Exception as e:</span> |
| <span class="sd"> ... tb = try_simplify_traceback(sys.exc_info()[-1])</span> |
| <span class="sd"> ... e.__cause__ = None</span> |
| <span class="sd"> ... exc_info = "".join(</span> |
| <span class="sd"> ... traceback.format_exception(</span> |
| <span class="sd"> ... type(e), e, try_simplify_traceback(skip_doctest_traceback(tb))))</span> |
| <span class="sd"> >>> print(exc_info) # doctest: +NORMALIZE_WHITESPACE, +ELLIPSIS</span> |
| <span class="sd"> RuntimeError: ...</span> |
| <span class="sd"> >>> "pyspark/util.py" in exc_info</span> |
| <span class="sd"> False</span> |
| |
| <span class="sd"> In the case below, the traceback contains the current package in the middle.</span> |
| <span class="sd"> In this case, it just hides the top occurrence only.</span> |
| |
| <span class="sd"> >>> exc_info = None</span> |
| <span class="sd"> >>> try:</span> |
| <span class="sd"> ... fail_on_stopiteration(dummy_module.simple_wrapper(</span> |
| <span class="sd"> ... fail_on_stopiteration(dummy_module.raise_stop_iteration)))()</span> |
| <span class="sd"> ... except Exception as e:</span> |
| <span class="sd"> ... tb = sys.exc_info()[-1]</span> |
| <span class="sd"> ... e.__cause__ = None</span> |
| <span class="sd"> ... exc_info_a = "".join(</span> |
| <span class="sd"> ... traceback.format_exception(type(e), e, tb))</span> |
| <span class="sd"> ... exc_info_b = "".join(</span> |
| <span class="sd"> ... traceback.format_exception(</span> |
| <span class="sd"> ... type(e), e, try_simplify_traceback(skip_doctest_traceback(tb))))</span> |
| <span class="sd"> >>> exc_info_a.count("pyspark/util.py")</span> |
| <span class="sd"> 2</span> |
| <span class="sd"> >>> exc_info_b.count("pyspark/util.py")</span> |
| <span class="sd"> 1</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="s2">"pypy"</span> <span class="ow">in</span> <span class="n">platform</span><span class="o">.</span><span class="n">python_implementation</span><span class="p">()</span><span class="o">.</span><span class="n">lower</span><span class="p">():</span> |
| <span class="c1"># Traceback modification is not supported with PyPy in PySpark.</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| <span class="k">if</span> <span class="n">sys</span><span class="o">.</span><span class="n">version_info</span><span class="p">[:</span><span class="mi">2</span><span class="p">]</span> <span class="o"><</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">7</span><span class="p">):</span> |
| <span class="c1"># Traceback creation is not supported Python < 3.7.</span> |
| <span class="c1"># See https://bugs.python.org/issue30579.</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| <span class="kn">import</span> <span class="nn">pyspark</span> |
| |
| <span class="n">root</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">pyspark</span><span class="o">.</span><span class="vm">__file__</span><span class="p">)</span> |
| <span class="n">tb_next</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="n">new_tb</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="n">pairs</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="n">walk_tb</span><span class="p">(</span><span class="n">tb</span><span class="p">),</span> <span class="n">traceback</span><span class="o">.</span><span class="n">extract_tb</span><span class="p">(</span><span class="n">tb</span><span class="p">))</span> |
| <span class="n">last_seen</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="k">for</span> <span class="n">cur_tb</span><span class="p">,</span> <span class="n">cur_frame</span> <span class="ow">in</span> <span class="n">pairs</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">cur_frame</span><span class="o">.</span><span class="n">filename</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="n">root</span><span class="p">):</span> |
| <span class="c1"># Filter the stacktrace from the PySpark source itself.</span> |
| <span class="n">last_seen</span> <span class="o">=</span> <span class="p">[(</span><span class="n">cur_tb</span><span class="p">,</span> <span class="n">cur_frame</span><span class="p">)]</span> |
| <span class="k">break</span> |
| |
| <span class="k">for</span> <span class="n">cur_tb</span><span class="p">,</span> <span class="n">cur_frame</span> <span class="ow">in</span> <span class="nb">reversed</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">itertools</span><span class="o">.</span><span class="n">chain</span><span class="p">(</span><span class="n">last_seen</span><span class="p">,</span> <span class="n">pairs</span><span class="p">))):</span> |
| <span class="c1"># Once we have seen the file names outside, don't skip.</span> |
| <span class="n">new_tb</span> <span class="o">=</span> <span class="n">TracebackType</span><span class="p">(</span> |
| <span class="n">tb_next</span><span class="o">=</span><span class="n">tb_next</span><span class="p">,</span> |
| <span class="n">tb_frame</span><span class="o">=</span><span class="n">cur_tb</span><span class="o">.</span><span class="n">tb_frame</span><span class="p">,</span> |
| <span class="n">tb_lasti</span><span class="o">=</span><span class="n">cur_tb</span><span class="o">.</span><span class="n">tb_frame</span><span class="o">.</span><span class="n">f_lasti</span><span class="p">,</span> |
| <span class="n">tb_lineno</span><span class="o">=</span><span class="n">cur_tb</span><span class="o">.</span><span class="n">tb_frame</span><span class="o">.</span><span class="n">f_lineno</span> <span class="k">if</span> <span class="n">cur_tb</span><span class="o">.</span><span class="n">tb_frame</span><span class="o">.</span><span class="n">f_lineno</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="k">else</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="n">tb_next</span> <span class="o">=</span> <span class="n">new_tb</span> |
| <span class="k">return</span> <span class="n">new_tb</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_print_missing_jar</span><span class="p">(</span><span class="n">lib_name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">pkg_name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">jar_name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">spark_version</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="nb">print</span><span class="p">(</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd">________________________________________________________________________________________________</span> |
| |
| <span class="sd"> Spark %(lib_name)s libraries not found in class path. Try one of the following.</span> |
| |
| <span class="sd"> 1. Include the %(lib_name)s library and its dependencies with in the</span> |
| <span class="sd"> spark-submit command as</span> |
| |
| <span class="sd"> $ bin/spark-submit --packages org.apache.spark:spark-%(pkg_name)s:%(spark_version)s ...</span> |
| |
| <span class="sd"> 2. Download the JAR of the artifact from Maven Central http://search.maven.org/,</span> |
| <span class="sd"> Group Id = org.apache.spark, Artifact Id = spark-%(jar_name)s, Version = %(spark_version)s.</span> |
| <span class="sd"> Then, include the jar in the spark-submit command as</span> |
| |
| <span class="sd"> $ bin/spark-submit --jars <spark-%(jar_name)s.jar> ...</span> |
| |
| <span class="sd">________________________________________________________________________________________________</span> |
| |
| <span class="sd">"""</span> |
| <span class="o">%</span> <span class="p">{</span> |
| <span class="s2">"lib_name"</span><span class="p">:</span> <span class="n">lib_name</span><span class="p">,</span> |
| <span class="s2">"pkg_name"</span><span class="p">:</span> <span class="n">pkg_name</span><span class="p">,</span> |
| <span class="s2">"jar_name"</span><span class="p">:</span> <span class="n">jar_name</span><span class="p">,</span> |
| <span class="s2">"spark_version"</span><span class="p">:</span> <span class="n">spark_version</span><span class="p">,</span> |
| <span class="p">}</span> |
| <span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_parse_memory</span><span class="p">(</span><span class="n">s</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Parse a memory string in the format supported by Java (e.g. 1g, 200m) and</span> |
| <span class="sd"> return the value in MiB</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> _parse_memory("256m")</span> |
| <span class="sd"> 256</span> |
| <span class="sd"> >>> _parse_memory("2g")</span> |
| <span class="sd"> 2048</span> |
| <span class="sd"> """</span> |
| <span class="n">units</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"g"</span><span class="p">:</span> <span class="mi">1024</span><span class="p">,</span> <span class="s2">"m"</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"t"</span><span class="p">:</span> <span class="mi">1</span> <span class="o"><<</span> <span class="mi">20</span><span class="p">,</span> <span class="s2">"k"</span><span class="p">:</span> <span class="mf">1.0</span> <span class="o">/</span> <span class="mi">1024</span><span class="p">}</span> |
| <span class="k">if</span> <span class="n">s</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">units</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"invalid format: "</span> <span class="o">+</span> <span class="n">s</span><span class="p">)</span> |
| <span class="k">return</span> <span class="nb">int</span><span class="p">(</span><span class="nb">float</span><span class="p">(</span><span class="n">s</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span> <span class="o">*</span> <span class="n">units</span><span class="p">[</span><span class="n">s</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()])</span> |
| |
| |
| <div class="viewcode-block" id="inheritable_thread_target"><a class="viewcode-back" href="../../reference/api/pyspark.inheritable_thread_target.html#pyspark.inheritable_thread_target">[docs]</a><span class="k">def</span> <span class="nf">inheritable_thread_target</span><span class="p">(</span><span class="n">f</span><span class="p">:</span> <span class="n">Callable</span><span class="p">)</span> <span class="o">-></span> <span class="n">Callable</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Return thread target wrapper which is recommended to be used in PySpark when the</span> |
| <span class="sd"> pinned thread mode is enabled. The wrapper function, before calling original</span> |
| <span class="sd"> thread target, it inherits the inheritable properties specific</span> |
| <span class="sd"> to JVM thread such as ``InheritableThreadLocal``.</span> |
| |
| <span class="sd"> Also, note that pinned thread mode does not close the connection from Python</span> |
| <span class="sd"> to JVM when the thread is finished in the Python side. With this wrapper, Python</span> |
| <span class="sd"> garbage-collects the Python thread instance and also closes the connection</span> |
| <span class="sd"> which finishes JVM thread correctly.</span> |
| |
| <span class="sd"> When the pinned thread mode is off, it return the original ``f``.</span> |
| |
| <span class="sd"> .. versionadded:: 3.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> f : function</span> |
| <span class="sd"> the original thread target.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> This API is experimental.</span> |
| |
| <span class="sd"> It is important to know that it captures the local properties when you decorate it</span> |
| <span class="sd"> whereas :class:`InheritableThread` captures when the thread is started.</span> |
| <span class="sd"> Therefore, it is encouraged to decorate it when you want to capture the local</span> |
| <span class="sd"> properties.</span> |
| |
| <span class="sd"> For example, the local properties from the current Spark context is captured</span> |
| <span class="sd"> when you define a function here instead of the invocation:</span> |
| |
| <span class="sd"> >>> @inheritable_thread_target</span> |
| <span class="sd"> ... def target_func():</span> |
| <span class="sd"> ... pass # your codes.</span> |
| |
| <span class="sd"> If you have any updates on local properties afterwards, it would not be reflected to</span> |
| <span class="sd"> the Spark context in ``target_func()``.</span> |
| |
| <span class="sd"> The example below mimics the behavior of JVM threads as close as possible:</span> |
| |
| <span class="sd"> >>> Thread(target=inheritable_thread_target(target_func)).start() # doctest: +SKIP</span> |
| <span class="sd"> """</span> |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">SparkContext</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">SparkContext</span><span class="o">.</span><span class="n">_gateway</span><span class="p">,</span> <span class="n">ClientServer</span><span class="p">):</span> |
| <span class="c1"># Here's when the pinned-thread mode (PYSPARK_PIN_THREAD) is on.</span> |
| |
| <span class="c1"># NOTICE the internal difference vs `InheritableThread`. `InheritableThread`</span> |
| <span class="c1"># copies local properties when the thread starts but `inheritable_thread_target`</span> |
| <span class="c1"># copies when the function is wrapped.</span> |
| <span class="k">assert</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">properties</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">()</span><span class="o">.</span><span class="n">getLocalProperties</span><span class="p">()</span><span class="o">.</span><span class="n">clone</span><span class="p">()</span> |
| |
| <span class="nd">@functools</span><span class="o">.</span><span class="n">wraps</span><span class="p">(</span><span class="n">f</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">wrapped</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span> |
| <span class="c1"># Set local properties in child thread.</span> |
| <span class="k">assert</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">()</span><span class="o">.</span><span class="n">setLocalProperties</span><span class="p">(</span><span class="n">properties</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">f</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">wrapped</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">f</span></div> |
| |
| |
| <div class="viewcode-block" id="InheritableThread"><a class="viewcode-back" href="../../reference/api/pyspark.InheritableThread.html#pyspark.InheritableThread">[docs]</a><span class="k">class</span> <span class="nc">InheritableThread</span><span class="p">(</span><span class="n">threading</span><span class="o">.</span><span class="n">Thread</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Thread that is recommended to be used in PySpark instead of :class:`threading.Thread`</span> |
| <span class="sd"> when the pinned thread mode is enabled. The usage of this class is exactly same as</span> |
| <span class="sd"> :class:`threading.Thread` but correctly inherits the inheritable properties specific</span> |
| <span class="sd"> to JVM thread such as ``InheritableThreadLocal``.</span> |
| |
| <span class="sd"> Also, note that pinned thread mode does not close the connection from Python</span> |
| <span class="sd"> to JVM when the thread is finished in the Python side. With this class, Python</span> |
| <span class="sd"> garbage-collects the Python thread instance and also closes the connection</span> |
| <span class="sd"> which finishes JVM thread correctly.</span> |
| |
| <span class="sd"> When the pinned thread mode is off, this works as :class:`threading.Thread`.</span> |
| |
| <span class="sd"> .. versionadded:: 3.1.0</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> This API is experimental.</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">_props</span><span class="p">:</span> <span class="n">JavaObject</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">target</span><span class="p">:</span> <span class="n">Callable</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">Any</span><span class="p">):</span> |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">SparkContext</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">SparkContext</span><span class="o">.</span><span class="n">_gateway</span><span class="p">,</span> <span class="n">ClientServer</span><span class="p">):</span> |
| <span class="c1"># Here's when the pinned-thread mode (PYSPARK_PIN_THREAD) is on.</span> |
| <span class="k">def</span> <span class="nf">copy_local_properties</span><span class="p">(</span><span class="o">*</span><span class="n">a</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="o">**</span><span class="n">k</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span> |
| <span class="c1"># self._props is set before starting the thread to match the behavior with JVM.</span> |
| <span class="k">assert</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s2">"_props"</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">()</span><span class="o">.</span><span class="n">setLocalProperties</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_props</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">target</span><span class="p">(</span><span class="o">*</span><span class="n">a</span><span class="p">,</span> <span class="o">**</span><span class="n">k</span><span class="p">)</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">InheritableThread</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">target</span><span class="o">=</span><span class="n">copy_local_properties</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span> <span class="c1"># type: ignore[misc]</span> |
| <span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">InheritableThread</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">target</span><span class="o">=</span><span class="n">target</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span> <span class="c1"># type: ignore[misc]</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">start</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">SparkContext</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">SparkContext</span><span class="o">.</span><span class="n">_gateway</span><span class="p">,</span> <span class="n">ClientServer</span><span class="p">):</span> |
| <span class="c1"># Here's when the pinned-thread mode (PYSPARK_PIN_THREAD) is on.</span> |
| |
| <span class="c1"># Local property copy should happen in Thread.start to mimic JVM's behavior.</span> |
| <span class="k">assert</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_props</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">()</span><span class="o">.</span><span class="n">getLocalProperties</span><span class="p">()</span><span class="o">.</span><span class="n">clone</span><span class="p">()</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">InheritableThread</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">start</span><span class="p">()</span></div> |
| |
| |
| <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span> |
| <span class="k">if</span> <span class="s2">"pypy"</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">platform</span><span class="o">.</span><span class="n">python_implementation</span><span class="p">()</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="ow">and</span> <span class="n">sys</span><span class="o">.</span><span class="n">version_info</span><span class="p">[:</span><span class="mi">2</span><span class="p">]</span> <span class="o">>=</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">7</span><span class="p">):</span> |
| <span class="kn">import</span> <span class="nn">doctest</span> |
| <span class="kn">import</span> <span class="nn">pyspark.util</span> |
| <span class="kn">from</span> <span class="nn">pyspark.context</span> <span class="kn">import</span> <span class="n">SparkContext</span> |
| |
| <span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">util</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"sc"</span><span class="p">]</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="s2">"local[4]"</span><span class="p">,</span> <span class="s2">"PythonTest"</span><span class="p">)</span> |
| <span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span><span class="n">pyspark</span><span class="o">.</span><span class="n">util</span><span class="p">,</span> <span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">)</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"sc"</span><span class="p">]</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span> |
| |
| <span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| </pre></div> |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| |
| <script src="../../_static/js/index.3da636dd464baa7582d2.js"></script> |
| |
| |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| <p> |
| © Copyright .<br/> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/> |
| </p> |
| </div> |
| </footer> |
| </body> |
| </html> |
