You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@arrow.apache.org by uw...@apache.org on 2018/12/23 16:31:55 UTC
[48/51] [partial] arrow-site git commit: Upload nightly docs
http://git-wip-us.apache.org/repos/asf/arrow-site/blob/62ef7145/docs/latest/_modules/pyarrow/filesystem.html
----------------------------------------------------------------------
diff --git a/docs/latest/_modules/pyarrow/filesystem.html b/docs/latest/_modules/pyarrow/filesystem.html
new file mode 100644
index 0000000..29ee84c
--- /dev/null
+++ b/docs/latest/_modules/pyarrow/filesystem.html
@@ -0,0 +1,634 @@
+
+
+
+<!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>pyarrow.filesystem — Apache Arrow v0.11.1.dev473+g6ed02454</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <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" />
+
+
+ <script src="../../_static/js/modernizr.min.js"></script>
+
+</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 Arrow
+
+
+
+ </a>
+
+
+
+
+ <div class="version">
+ 0.11.1.dev473+g6ed02454
+ </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">
+
+
+
+
+
+
+ <p class="caption"><span class="caption-text">Memory Format</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="../../format/README.html">Arrow specification documents</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../format/Guidelines.html">Implementation guidelines</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../format/Layout.html">Physical memory layout</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../format/Metadata.html">Metadata: Logical types, schemas, data headers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../format/IPC.html">Interprocess messaging / communication (IPC)</a></li>
+</ul>
+<p class="caption"><span class="caption-text">Languages</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="../../cpp/index.html">C++ Implementation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../python/index.html">Python bindings</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 Arrow</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><a href="../pyarrow.html">pyarrow</a> »</li>
+
+ <li>pyarrow.filesystem</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 pyarrow.filesystem</h1><div class="highlight"><pre>
+<span></span><span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
+<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
+<span class="c1"># distributed with this work for additional information</span>
+<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
+<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
+<span class="c1"># "License"); you may not use this file except in compliance</span>
+<span class="c1"># with 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,</span>
+<span class="c1"># software distributed under the License is distributed on an</span>
+<span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
+<span class="c1"># KIND, either express or implied. See the License for the</span>
+<span class="c1"># specific language governing permissions and limitations</span>
+<span class="c1"># under the License.</span>
+
+<span class="kn">import</span> <span class="nn">os</span>
+<span class="kn">import</span> <span class="nn">inspect</span>
+<span class="kn">import</span> <span class="nn">posixpath</span>
+
+<span class="kn">from</span> <span class="nn">os.path</span> <span class="k">import</span> <span class="n">join</span> <span class="k">as</span> <span class="n">pjoin</span>
+<span class="kn">from</span> <span class="nn">six.moves.urllib.parse</span> <span class="k">import</span> <span class="n">urlparse</span>
+
+<span class="kn">import</span> <span class="nn">pyarrow</span> <span class="k">as</span> <span class="nn">pa</span>
+<span class="kn">from</span> <span class="nn">pyarrow.util</span> <span class="k">import</span> <span class="n">implements</span><span class="p">,</span> <span class="n">_stringify_path</span>
+
+
+<span class="k">class</span> <span class="nc">FileSystem</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Abstract filesystem interface</span>
+<span class="sd"> """</span>
+ <span class="k">def</span> <span class="nf">cat</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="sd">"""</span>
+<span class="sd"> Return contents of file as a bytes object</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> contents : bytes</span>
+<span class="sd"> """</span>
+ <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
+ <span class="k">return</span> <span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">()</span>
+
+ <span class="k">def</span> <span class="nf">ls</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="sd">"""</span>
+<span class="sd"> Return list of file paths</span>
+<span class="sd"> """</span>
+ <span class="k">raise</span> <span class="ne">NotImplementedError</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="n">recursive</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Delete the indicated file or directory</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> path : string</span>
+<span class="sd"> recursive : boolean, default False</span>
+<span class="sd"> If True, also delete child paths for directories</span>
+<span class="sd"> """</span>
+ <span class="k">raise</span> <span class="ne">NotImplementedError</span>
+
+ <span class="k">def</span> <span class="nf">disk_usage</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="sd">"""</span>
+<span class="sd"> Compute bytes used by all contents under indicated path in file tree</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> path : string</span>
+<span class="sd"> Can be a file path or directory</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> usage : int</span>
+<span class="sd"> """</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="n">path_info</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">stat</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">path_info</span><span class="p">[</span><span class="s1">'kind'</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'file'</span><span class="p">:</span>
+ <span class="k">return</span> <span class="n">path_info</span><span class="p">[</span><span class="s1">'size'</span><span class="p">]</span>
+
+ <span class="n">total</span> <span class="o">=</span> <span class="mi">0</span>
+ <span class="k">for</span> <span class="n">root</span><span class="p">,</span> <span class="n">directories</span><span class="p">,</span> <span class="n">files</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">walk</span><span class="p">(</span><span class="n">path</span><span class="p">):</span>
+ <span class="k">for</span> <span class="n">child_path</span> <span class="ow">in</span> <span class="n">files</span><span class="p">:</span>
+ <span class="n">abspath</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_path_join</span><span class="p">(</span><span class="n">root</span><span class="p">,</span> <span class="n">child_path</span><span class="p">)</span>
+ <span class="n">total</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">stat</span><span class="p">(</span><span class="n">abspath</span><span class="p">)[</span><span class="s1">'size'</span><span class="p">]</span>
+
+ <span class="k">return</span> <span class="n">total</span>
+
+ <span class="k">def</span> <span class="nf">_path_join</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">):</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">pathsep</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">args</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">stat</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="sd">"""</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> stat : dict</span>
+<span class="sd"> """</span>
+ <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s1">'FileSystem.stat'</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">rm</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">recursive</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Alias for FileSystem.delete</span>
+<span class="sd"> """</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">recursive</span><span class="o">=</span><span class="n">recursive</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">mv</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">new_path</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Alias for FileSystem.rename</span>
+<span class="sd"> """</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">rename</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">new_path</span><span class="p">)</span>
+
+ <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">path</span><span class="p">,</span> <span class="n">new_path</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Rename file, like UNIX mv command</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> path : string</span>
+<span class="sd"> Path to alter</span>
+<span class="sd"> new_path : string</span>
+<span class="sd"> Path to move to</span>
+<span class="sd"> """</span>
+ <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s1">'FileSystem.rename'</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">mkdir</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">create_parents</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
+ <span class="k">raise</span> <span class="ne">NotImplementedError</span>
+
+ <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="k">raise</span> <span class="ne">NotImplementedError</span>
+
+ <span class="k">def</span> <span class="nf">isdir</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="sd">"""</span>
+<span class="sd"> Return True if path is a directory</span>
+<span class="sd"> """</span>
+ <span class="k">raise</span> <span class="ne">NotImplementedError</span>
+
+ <span class="k">def</span> <span class="nf">isfile</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="sd">"""</span>
+<span class="sd"> Return True if path is a file</span>
+<span class="sd"> """</span>
+ <span class="k">raise</span> <span class="ne">NotImplementedError</span>
+
+ <span class="k">def</span> <span class="nf">_isfilestore</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Returns True if this FileSystem is a unix-style file store with</span>
+<span class="sd"> directories.</span>
+<span class="sd"> """</span>
+ <span class="k">raise</span> <span class="ne">NotImplementedError</span>
+
+ <span class="k">def</span> <span class="nf">read_parquet</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">columns</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">metadata</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">use_threads</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">use_pandas_metadata</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Read Parquet data from path in file system. Can read from a single file</span>
+<span class="sd"> or a directory of files</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> path : str</span>
+<span class="sd"> Single file path or directory</span>
+<span class="sd"> columns : List[str], optional</span>
+<span class="sd"> Subset of columns to read</span>
+<span class="sd"> metadata : pyarrow.parquet.FileMetaData</span>
+<span class="sd"> Known metadata to validate files against</span>
+<span class="sd"> schema : pyarrow.parquet.Schema</span>
+<span class="sd"> Known schema to validate files against. Alternative to metadata</span>
+<span class="sd"> argument</span>
+<span class="sd"> use_threads : boolean, default True</span>
+<span class="sd"> Perform multi-threaded column reads</span>
+<span class="sd"> use_pandas_metadata : boolean, default False</span>
+<span class="sd"> If True and file has custom pandas schema metadata, ensure that</span>
+<span class="sd"> index columns are also loaded</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> table : pyarrow.Table</span>
+<span class="sd"> """</span>
+ <span class="kn">from</span> <span class="nn">pyarrow.parquet</span> <span class="k">import</span> <span class="n">ParquetDataset</span>
+ <span class="n">dataset</span> <span class="o">=</span> <span class="n">ParquetDataset</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">schema</span><span class="p">,</span> <span class="n">metadata</span><span class="o">=</span><span class="n">metadata</span><span class="p">,</span>
+ <span class="n">filesystem</span><span class="o">=</span><span class="bp">self</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">dataset</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">columns</span><span class="o">=</span><span class="n">columns</span><span class="p">,</span> <span class="n">use_threads</span><span class="o">=</span><span class="n">use_threads</span><span class="p">,</span>
+ <span class="n">use_pandas_metadata</span><span class="o">=</span><span class="n">use_pandas_metadata</span><span class="p">)</span>
+
+ <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">path</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="s1">'rb'</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Open file for reading or writing</span>
+<span class="sd"> """</span>
+ <span class="k">raise</span> <span class="ne">NotImplementedError</span>
+
+ <span class="nd">@property</span>
+ <span class="k">def</span> <span class="nf">pathsep</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="s1">'/'</span>
+
+
+<div class="viewcode-block" id="LocalFileSystem"><a class="viewcode-back" href="../../python/generated/pyarrow.LocalFileSystem.html#pyarrow.LocalFileSystem">[docs]</a><span class="k">class</span> <span class="nc">LocalFileSystem</span><span class="p">(</span><span class="n">FileSystem</span><span class="p">):</span>
+
+ <span class="n">_instance</span> <span class="o">=</span> <span class="kc">None</span>
+
+<div class="viewcode-block" id="LocalFileSystem.get_instance"><a class="viewcode-back" href="../../python/generated/pyarrow.LocalFileSystem.html#pyarrow.LocalFileSystem.get_instance">[docs]</a> <span class="nd">@classmethod</span>
+ <span class="k">def</span> <span class="nf">get_instance</span><span class="p">(</span><span class="bp">cls</span><span class="p">):</span>
+ <span class="k">if</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_instance</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="bp">cls</span><span class="o">.</span><span class="n">_instance</span> <span class="o">=</span> <span class="n">LocalFileSystem</span><span class="p">()</span>
+ <span class="k">return</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_instance</span></div>
+
+<div class="viewcode-block" id="LocalFileSystem.ls"><a class="viewcode-back" href="../../python/generated/pyarrow.LocalFileSystem.html#pyarrow.LocalFileSystem.ls">[docs]</a> <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">ls</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">ls</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">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">pjoin</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">x</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">os</span><span class="o">.</span><span class="n">listdir</span><span class="p">(</span><span class="n">path</span><span class="p">))</span></div>
+
+<div class="viewcode-block" id="LocalFileSystem.mkdir"><a class="viewcode-back" href="../../python/generated/pyarrow.LocalFileSystem.html#pyarrow.LocalFileSystem.mkdir">[docs]</a> <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">mkdir</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">mkdir</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">create_parents</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">create_parents</span><span class="p">:</span>
+ <span class="n">os</span><span class="o">.</span><span class="n">makedirs</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">os</span><span class="o">.</span><span class="n">mkdir</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div>
+
+<div class="viewcode-block" id="LocalFileSystem.isdir"><a class="viewcode-back" href="../../python/generated/pyarrow.LocalFileSystem.html#pyarrow.LocalFileSystem.isdir">[docs]</a> <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">isdir</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">isdir</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">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isdir</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div>
+
+<div class="viewcode-block" id="LocalFileSystem.isfile"><a class="viewcode-back" href="../../python/generated/pyarrow.LocalFileSystem.html#pyarrow.LocalFileSystem.isfile">[docs]</a> <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">isfile</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">isfile</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">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">_isfilestore</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">_isfilestore</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="kc">True</span>
+
+<div class="viewcode-block" id="LocalFileSystem.exists"><a class="viewcode-back" href="../../python/generated/pyarrow.LocalFileSystem.html#pyarrow.LocalFileSystem.exists">[docs]</a> <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">exists</span><span class="p">)</span>
+ <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="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div>
+
+<div class="viewcode-block" id="LocalFileSystem.open"><a class="viewcode-back" href="../../python/generated/pyarrow.LocalFileSystem.html#pyarrow.LocalFileSystem.open">[docs]</a> <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">open</span><span class="p">)</span>
+ <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">path</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="s1">'rb'</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Open file for reading or writing</span>
+<span class="sd"> """</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="nb">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="n">mode</span><span class="p">)</span></div>
+
+ <span class="nd">@property</span>
+ <span class="k">def</span> <span class="nf">pathsep</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">sep</span>
+
+<div class="viewcode-block" id="LocalFileSystem.walk"><a class="viewcode-back" href="../../python/generated/pyarrow.LocalFileSystem.html#pyarrow.LocalFileSystem.walk">[docs]</a> <span class="k">def</span> <span class="nf">walk</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="sd">"""</span>
+<span class="sd"> Directory tree generator, see os.walk</span>
+<span class="sd"> """</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">os</span><span class="o">.</span><span class="n">walk</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div></div>
+
+
+<span class="k">class</span> <span class="nc">DaskFileSystem</span><span class="p">(</span><span class="n">FileSystem</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Wraps s3fs Dask filesystem implementation like s3fs, gcsfs, etc.</span>
+<span class="sd"> """</span>
+
+ <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fs</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">fs</span> <span class="o">=</span> <span class="n">fs</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">isdir</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">isdir</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="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s2">"Unsupported file system API"</span><span class="p">)</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">isfile</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">isfile</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="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s2">"Unsupported file system API"</span><span class="p">)</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">_isfilestore</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">_isfilestore</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Object Stores like S3 and GCSFS are based on key lookups, not true</span>
+<span class="sd"> file-paths</span>
+<span class="sd"> """</span>
+ <span class="k">return</span> <span class="kc">False</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">delete</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="n">recursive</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fs</span><span class="o">.</span><span class="n">rm</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">recursive</span><span class="o">=</span><span class="n">recursive</span><span class="p">)</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">exists</span><span class="p">)</span>
+ <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="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fs</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">mkdir</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">mkdir</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">create_parents</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">create_parents</span><span class="p">:</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fs</span><span class="o">.</span><span class="n">mkdirs</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="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fs</span><span class="o">.</span><span class="n">mkdir</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">open</span><span class="p">)</span>
+ <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">path</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="s1">'rb'</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Open file for reading or writing</span>
+<span class="sd"> """</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fs</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">path</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="k">def</span> <span class="nf">ls</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">detail</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fs</span><span class="o">.</span><span class="n">ls</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">detail</span><span class="o">=</span><span class="n">detail</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">walk</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="sd">"""</span>
+<span class="sd"> Directory tree generator, like os.walk</span>
+<span class="sd"> """</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fs</span><span class="o">.</span><span class="n">walk</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+
+
+<span class="k">class</span> <span class="nc">S3FSWrapper</span><span class="p">(</span><span class="n">DaskFileSystem</span><span class="p">):</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">isdir</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">isdir</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">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">try</span><span class="p">:</span>
+ <span class="n">contents</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fs</span><span class="o">.</span><span class="n">ls</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">contents</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="n">contents</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="n">path</span><span class="p">:</span>
+ <span class="k">return</span> <span class="kc">False</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">return</span> <span class="kc">True</span>
+ <span class="k">except</span> <span class="ne">OSError</span><span class="p">:</span>
+ <span class="k">return</span> <span class="kc">False</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">isfile</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">isfile</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">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">try</span><span class="p">:</span>
+ <span class="n">contents</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fs</span><span class="o">.</span><span class="n">ls</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="n">contents</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="n">contents</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="n">path</span>
+ <span class="k">except</span> <span class="ne">OSError</span><span class="p">:</span>
+ <span class="k">return</span> <span class="kc">False</span>
+
+ <span class="k">def</span> <span class="nf">walk</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">refresh</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Directory tree generator, like os.walk</span>
+
+<span class="sd"> Generator version of what is in s3fs, which yields a flattened list of</span>
+<span class="sd"> files</span>
+<span class="sd"> """</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">'s3://'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span>
+ <span class="n">directories</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
+ <span class="n">files</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
+
+ <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fs</span><span class="o">.</span><span class="n">_ls</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">refresh</span><span class="o">=</span><span class="n">refresh</span><span class="p">)):</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">key</span><span class="p">[</span><span class="s1">'Key'</span><span class="p">]</span>
+ <span class="k">if</span> <span class="n">key</span><span class="p">[</span><span class="s1">'StorageClass'</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'DIRECTORY'</span><span class="p">:</span>
+ <span class="n">directories</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">elif</span> <span class="n">key</span><span class="p">[</span><span class="s1">'StorageClass'</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'BUCKET'</span><span class="p">:</span>
+ <span class="k">pass</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">files</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+
+ <span class="c1"># s3fs creates duplicate 'DIRECTORY' entries</span>
+ <span class="n">files</span> <span class="o">=</span> <span class="nb">sorted</span><span class="p">([</span><span class="n">posixpath</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">f</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">files</span>
+ <span class="k">if</span> <span class="n">f</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">directories</span><span class="p">])</span>
+ <span class="n">directories</span> <span class="o">=</span> <span class="nb">sorted</span><span class="p">([</span><span class="n">posixpath</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">x</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span>
+ <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">directories</span><span class="p">])</span>
+
+ <span class="k">yield</span> <span class="n">path</span><span class="p">,</span> <span class="n">directories</span><span class="p">,</span> <span class="n">files</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="k">for</span> <span class="n">tup</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">walk</span><span class="p">(</span><span class="n">directory</span><span class="p">,</span> <span class="n">refresh</span><span class="o">=</span><span class="n">refresh</span><span class="p">):</span>
+ <span class="k">yield</span> <span class="n">tup</span>
+
+
+<span class="k">def</span> <span class="nf">_ensure_filesystem</span><span class="p">(</span><span class="n">fs</span><span class="p">):</span>
+ <span class="n">fs_type</span> <span class="o">=</span> <span class="nb">type</span><span class="p">(</span><span class="n">fs</span><span class="p">)</span>
+
+ <span class="c1"># If the arrow filesystem was subclassed, assume it supports the full</span>
+ <span class="c1"># interface and return it</span>
+ <span class="k">if</span> <span class="ow">not</span> <span class="nb">issubclass</span><span class="p">(</span><span class="n">fs_type</span><span class="p">,</span> <span class="n">FileSystem</span><span class="p">):</span>
+ <span class="k">for</span> <span class="n">mro</span> <span class="ow">in</span> <span class="n">inspect</span><span class="o">.</span><span class="n">getmro</span><span class="p">(</span><span class="n">fs_type</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">mro</span><span class="o">.</span><span class="vm">__name__</span> <span class="ow">is</span> <span class="s1">'S3FileSystem'</span><span class="p">:</span>
+ <span class="k">return</span> <span class="n">S3FSWrapper</span><span class="p">(</span><span class="n">fs</span><span class="p">)</span>
+ <span class="c1"># In case its a simple LocalFileSystem (e.g. dask) use native arrow</span>
+ <span class="c1"># FS</span>
+ <span class="k">elif</span> <span class="n">mro</span><span class="o">.</span><span class="vm">__name__</span> <span class="ow">is</span> <span class="s1">'LocalFileSystem'</span><span class="p">:</span>
+ <span class="k">return</span> <span class="n">LocalFileSystem</span><span class="o">.</span><span class="n">get_instance</span><span class="p">()</span>
+
+ <span class="k">raise</span> <span class="ne">IOError</span><span class="p">(</span><span class="s1">'Unrecognized filesystem: </span><span class="si">{0}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">fs_type</span><span class="p">))</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">return</span> <span class="n">fs</span>
+
+
+<span class="k">def</span> <span class="nf">get_filesystem_from_uri</span><span class="p">(</span><span class="n">path</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> return filesystem from path which could be an HDFS URI</span>
+<span class="sd"> """</span>
+ <span class="c1"># input can be hdfs URI such as hdfs://host:port/myfile.parquet</span>
+ <span class="n">path</span> <span class="o">=</span> <span class="n">_stringify_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="c1"># if _has_pathlib and isinstance(path, pathlib.Path):</span>
+ <span class="c1"># path = str(path)</span>
+ <span class="n">parsed_uri</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">parsed_uri</span><span class="o">.</span><span class="n">scheme</span> <span class="o">==</span> <span class="s1">'hdfs'</span><span class="p">:</span>
+ <span class="n">netloc_split</span> <span class="o">=</span> <span class="n">parsed_uri</span><span class="o">.</span><span class="n">netloc</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">':'</span><span class="p">)</span>
+ <span class="n">host</span> <span class="o">=</span> <span class="n">netloc_split</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
+ <span class="k">if</span> <span class="n">host</span> <span class="o">==</span> <span class="s1">''</span><span class="p">:</span>
+ <span class="n">host</span> <span class="o">=</span> <span class="s1">'default'</span>
+ <span class="n">port</span> <span class="o">=</span> <span class="mi">0</span>
+ <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">netloc_split</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span> <span class="ow">and</span> <span class="n">netloc_split</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">isnumeric</span><span class="p">():</span>
+ <span class="n">port</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">netloc_split</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
+ <span class="n">fs</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">hdfs</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span><span class="n">host</span><span class="o">=</span><span class="n">host</span><span class="p">,</span> <span class="n">port</span><span class="o">=</span><span class="n">port</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">fs</span> <span class="o">=</span> <span class="n">LocalFileSystem</span><span class="o">.</span><span class="n">get_instance</span><span class="p">()</span>
+
+ <span class="k">return</span> <span class="n">fs</span><span class="p">,</span> <span class="n">parsed_uri</span><span class="o">.</span><span class="n">path</span>
+</pre></div>
+
+ </div>
+
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+ © Copyright 2016-2018 Apache Software Foundation
+
+ </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" 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/js/theme.js"></script>
+
+ <script type="text/javascript">
+ jQuery(function () {
+ SphinxRtdTheme.Navigation.enable(true);
+ });
+ </script>
+<script async src="https://www.googletagmanager.com/gtag/js?id=UA-107500873-1"></script>
+<script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+
+ gtag('config', 'UA-107500873-1');
+</script>
+
+
+</body>
+</html>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/arrow-site/blob/62ef7145/docs/latest/_modules/pyarrow/hdfs.html
----------------------------------------------------------------------
diff --git a/docs/latest/_modules/pyarrow/hdfs.html b/docs/latest/_modules/pyarrow/hdfs.html
new file mode 100644
index 0000000..589b4cc
--- /dev/null
+++ b/docs/latest/_modules/pyarrow/hdfs.html
@@ -0,0 +1,428 @@
+
+
+
+<!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>pyarrow.hdfs — Apache Arrow v0.11.1.dev473+g6ed02454</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <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" />
+
+
+ <script src="../../_static/js/modernizr.min.js"></script>
+
+</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 Arrow
+
+
+
+ </a>
+
+
+
+
+ <div class="version">
+ 0.11.1.dev473+g6ed02454
+ </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">
+
+
+
+
+
+
+ <p class="caption"><span class="caption-text">Memory Format</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="../../format/README.html">Arrow specification documents</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../format/Guidelines.html">Implementation guidelines</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../format/Layout.html">Physical memory layout</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../format/Metadata.html">Metadata: Logical types, schemas, data headers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../format/IPC.html">Interprocess messaging / communication (IPC)</a></li>
+</ul>
+<p class="caption"><span class="caption-text">Languages</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="../../cpp/index.html">C++ Implementation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../python/index.html">Python bindings</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 Arrow</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><a href="../pyarrow.html">pyarrow</a> »</li>
+
+ <li>pyarrow.hdfs</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 pyarrow.hdfs</h1><div class="highlight"><pre>
+<span></span><span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
+<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
+<span class="c1"># distributed with this work for additional information</span>
+<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
+<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
+<span class="c1"># "License"); you may not use this file except in compliance</span>
+<span class="c1"># with 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,</span>
+<span class="c1"># software distributed under the License is distributed on an</span>
+<span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
+<span class="c1"># KIND, either express or implied. See the License for the</span>
+<span class="c1"># specific language governing permissions and limitations</span>
+<span class="c1"># under the License.</span>
+
+<span class="kn">import</span> <span class="nn">os</span>
+<span class="kn">import</span> <span class="nn">posixpath</span>
+<span class="kn">import</span> <span class="nn">sys</span>
+
+<span class="kn">from</span> <span class="nn">pyarrow.util</span> <span class="k">import</span> <span class="n">implements</span>
+<span class="kn">from</span> <span class="nn">pyarrow.filesystem</span> <span class="k">import</span> <span class="n">FileSystem</span>
+<span class="kn">import</span> <span class="nn">pyarrow.lib</span> <span class="k">as</span> <span class="nn">lib</span>
+
+
+<div class="viewcode-block" id="HadoopFileSystem"><a class="viewcode-back" href="../../python/api.html#pyarrow.HadoopFileSystem">[docs]</a><span class="k">class</span> <span class="nc">HadoopFileSystem</span><span class="p">(</span><span class="n">lib</span><span class="o">.</span><span class="n">HadoopFileSystem</span><span class="p">,</span> <span class="n">FileSystem</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> FileSystem interface for HDFS cluster. See pyarrow.hdfs.connect for full</span>
+<span class="sd"> connection details</span>
+<span class="sd"> """</span>
+
+ <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">host</span><span class="o">=</span><span class="s2">"default"</span><span class="p">,</span> <span class="n">port</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">user</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">kerb_ticket</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">driver</span><span class="o">=</span><span class="s1">'libhdfs'</span><span class="p">,</span> <span class="n">extra_conf</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">driver</span> <span class="o">==</span> <span class="s1">'libhdfs'</span><span class="p">:</span>
+ <span class="n">_maybe_set_hadoop_classpath</span><span class="p">()</span>
+
+ <span class="bp">self</span><span class="o">.</span><span class="n">_connect</span><span class="p">(</span><span class="n">host</span><span class="p">,</span> <span class="n">port</span><span class="p">,</span> <span class="n">user</span><span class="p">,</span> <span class="n">kerb_ticket</span><span class="p">,</span> <span class="n">driver</span><span class="p">,</span> <span class="n">extra_conf</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">__reduce__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="p">(</span><span class="n">HadoopFileSystem</span><span class="p">,</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">host</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">port</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">user</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">kerb_ticket</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">driver</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">extra_conf</span><span class="p">))</span>
+
+ <span class="k">def</span> <span class="nf">_isfilestore</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Returns True if this FileSystem is a unix-style file store with</span>
+<span class="sd"> directories.</span>
+<span class="sd"> """</span>
+ <span class="k">return</span> <span class="kc">True</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">isdir</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">isdir</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="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">HadoopFileSystem</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">isdir</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+
+ <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">isfile</span><span class="p">)</span>
+ <span class="k">def</span> <span class="nf">isfile</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="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">HadoopFileSystem</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
+
+<div class="viewcode-block" id="HadoopFileSystem.delete"><a class="viewcode-back" href="../../python/generated/pyarrow.HadoopFileSystem.delete.html#pyarrow.HadoopFileSystem.delete">[docs]</a> <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">delete</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="n">recursive</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+ <span class="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">HadoopFileSystem</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">recursive</span><span class="p">)</span></div>
+
+<div class="viewcode-block" id="HadoopFileSystem.mkdir"><a class="viewcode-back" href="../../python/generated/pyarrow.HadoopFileSystem.mkdir.html#pyarrow.HadoopFileSystem.mkdir">[docs]</a> <span class="k">def</span> <span class="nf">mkdir</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="o">**</span><span class="n">kwargs</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Create directory in HDFS</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> path : string</span>
+<span class="sd"> Directory path to create, including any parent directories</span>
+
+<span class="sd"> Notes</span>
+<span class="sd"> -----</span>
+<span class="sd"> libhdfs does not support create_parents=False, so we ignore this here</span>
+<span class="sd"> """</span>
+ <span class="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">HadoopFileSystem</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">mkdir</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div>
+
+<div class="viewcode-block" id="HadoopFileSystem.rename"><a class="viewcode-back" href="../../python/generated/pyarrow.HadoopFileSystem.rename.html#pyarrow.HadoopFileSystem.rename">[docs]</a> <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">rename</span><span class="p">)</span>
+ <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">path</span><span class="p">,</span> <span class="n">new_path</span><span class="p">):</span>
+ <span class="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">HadoopFileSystem</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">rename</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">new_path</span><span class="p">)</span></div>
+
+<div class="viewcode-block" id="HadoopFileSystem.exists"><a class="viewcode-back" href="../../python/generated/pyarrow.HadoopFileSystem.exists.html#pyarrow.HadoopFileSystem.exists">[docs]</a> <span class="nd">@implements</span><span class="p">(</span><span class="n">FileSystem</span><span class="o">.</span><span class="n">exists</span><span class="p">)</span>
+ <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="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">HadoopFileSystem</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div>
+
+<div class="viewcode-block" id="HadoopFileSystem.ls"><a class="viewcode-back" href="../../python/generated/pyarrow.HadoopFileSystem.ls.html#pyarrow.HadoopFileSystem.ls">[docs]</a> <span class="k">def</span> <span class="nf">ls</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">detail</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Retrieve directory contents and metadata, if requested.</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> path : HDFS path</span>
+<span class="sd"> detail : boolean, default False</span>
+<span class="sd"> If False, only return list of paths</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> result : list of dicts (detail=True) or strings (detail=False)</span>
+<span class="sd"> """</span>
+ <span class="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">HadoopFileSystem</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">ls</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">detail</span><span class="p">)</span></div>
+
+ <span class="k">def</span> <span class="nf">walk</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">top_path</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Directory tree generator for HDFS, like os.walk</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> top_path : string</span>
+<span class="sd"> Root directory for tree traversal</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> Generator yielding 3-tuple (dirpath, dirnames, filename)</span>
+<span class="sd"> """</span>
+ <span class="n">contents</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">ls</span><span class="p">(</span><span class="n">top_path</span><span class="p">,</span> <span class="n">detail</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+
+ <span class="n">directories</span><span class="p">,</span> <span class="n">files</span> <span class="o">=</span> <span class="n">_libhdfs_walk_files_dirs</span><span class="p">(</span><span class="n">top_path</span><span class="p">,</span> <span class="n">contents</span><span class="p">)</span>
+ <span class="k">yield</span> <span class="n">top_path</span><span class="p">,</span> <span class="n">directories</span><span class="p">,</span> <span class="n">files</span>
+ <span class="k">for</span> <span class="n">dirname</span> <span class="ow">in</span> <span class="n">directories</span><span class="p">:</span>
+ <span class="k">for</span> <span class="n">tup</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">walk</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_path_join</span><span class="p">(</span><span class="n">top_path</span><span class="p">,</span> <span class="n">dirname</span><span class="p">)):</span>
+ <span class="k">yield</span> <span class="n">tup</span></div>
+
+
+<span class="k">def</span> <span class="nf">_maybe_set_hadoop_classpath</span><span class="p">():</span>
+ <span class="k">if</span> <span class="s1">'hadoop'</span> <span class="ow">in</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'CLASSPATH'</span><span class="p">,</span> <span class="s1">''</span><span class="p">):</span>
+ <span class="k">return</span>
+
+ <span class="k">if</span> <span class="s1">'HADOOP_HOME'</span> <span class="ow">in</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">:</span>
+ <span class="k">if</span> <span class="n">sys</span><span class="o">.</span><span class="n">platform</span> <span class="o">!=</span> <span class="s1">'win32'</span><span class="p">:</span>
+ <span class="n">classpath</span> <span class="o">=</span> <span class="n">_derive_hadoop_classpath</span><span class="p">()</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">hadoop_bin</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{0}</span><span class="s1">/bin/hadoop'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'HADOOP_HOME'</span><span class="p">])</span>
+ <span class="n">classpath</span> <span class="o">=</span> <span class="n">_hadoop_classpath_glob</span><span class="p">(</span><span class="n">hadoop_bin</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">classpath</span> <span class="o">=</span> <span class="n">_hadoop_classpath_glob</span><span class="p">(</span><span class="s1">'hadoop'</span><span class="p">)</span>
+
+ <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'CLASSPATH'</span><span class="p">]</span> <span class="o">=</span> <span class="n">classpath</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)</span>
+
+
+<span class="k">def</span> <span class="nf">_derive_hadoop_classpath</span><span class="p">():</span>
+ <span class="kn">import</span> <span class="nn">subprocess</span>
+
+ <span class="n">find_args</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'find'</span><span class="p">,</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'HADOOP_HOME'</span><span class="p">],</span> <span class="s1">'-name'</span><span class="p">,</span> <span class="s1">'*.jar'</span><span class="p">)</span>
+ <span class="n">find</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span><span class="n">find_args</span><span class="p">,</span> <span class="n">stdout</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">)</span>
+ <span class="n">xargs_echo</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">((</span><span class="s1">'xargs'</span><span class="p">,</span> <span class="s1">'echo'</span><span class="p">),</span>
+ <span class="n">stdin</span><span class="o">=</span><span class="n">find</span><span class="o">.</span><span class="n">stdout</span><span class="p">,</span>
+ <span class="n">stdout</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">check_output</span><span class="p">((</span><span class="s1">'tr'</span><span class="p">,</span> <span class="s2">"' '"</span><span class="p">,</span> <span class="s2">"':'"</span><span class="p">),</span>
+ <span class="n">stdin</span><span class="o">=</span><span class="n">xargs_echo</span><span class="o">.</span><span class="n">stdout</span><span class="p">)</span>
+
+
+<span class="k">def</span> <span class="nf">_hadoop_classpath_glob</span><span class="p">(</span><span class="n">hadoop_bin</span><span class="p">):</span>
+ <span class="kn">import</span> <span class="nn">subprocess</span>
+
+ <span class="n">hadoop_classpath_args</span> <span class="o">=</span> <span class="p">(</span><span class="n">hadoop_bin</span><span class="p">,</span> <span class="s1">'classpath'</span><span class="p">,</span> <span class="s1">'--glob'</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">check_output</span><span class="p">(</span><span class="n">hadoop_classpath_args</span><span class="p">)</span>
+
+
+<span class="k">def</span> <span class="nf">_libhdfs_walk_files_dirs</span><span class="p">(</span><span class="n">top_path</span><span class="p">,</span> <span class="n">contents</span><span class="p">):</span>
+ <span class="n">files</span> <span class="o">=</span> <span class="p">[]</span>
+ <span class="n">directories</span> <span class="o">=</span> <span class="p">[]</span>
+ <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">contents</span><span class="p">:</span>
+ <span class="n">scrubbed_name</span> <span class="o">=</span> <span class="n">posixpath</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">c</span><span class="p">[</span><span class="s1">'name'</span><span class="p">])[</span><span class="mi">1</span><span class="p">]</span>
+ <span class="k">if</span> <span class="n">c</span><span class="p">[</span><span class="s1">'kind'</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'file'</span><span class="p">:</span>
+ <span class="n">files</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">scrubbed_name</span><span class="p">)</span>
+ <span class="k">else</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">scrubbed_name</span><span class="p">)</span>
+
+ <span class="k">return</span> <span class="n">directories</span><span class="p">,</span> <span class="n">files</span>
+
+
+<div class="viewcode-block" id="connect"><a class="viewcode-back" href="../../python/generated/pyarrow.hdfs.connect.html#pyarrow.connect">[docs]</a><span class="k">def</span> <span class="nf">connect</span><span class="p">(</span><span class="n">host</span><span class="o">=</span><span class="s2">"default"</span><span class="p">,</span> <span class="n">port</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">user</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">kerb_ticket</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">driver</span><span class="o">=</span><span class="s1">'libhdfs'</span><span class="p">,</span> <span class="n">extra_conf</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Connect to an HDFS cluster. All parameters are optional and should</span>
+<span class="sd"> only be set if the defaults need to be overridden.</span>
+
+<span class="sd"> Authentication should be automatic if the HDFS cluster uses Kerberos.</span>
+<span class="sd"> However, if a username is specified, then the ticket cache will likely</span>
+<span class="sd"> be required.</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> host : NameNode. Set to "default" for fs.defaultFS from core-site.xml.</span>
+<span class="sd"> port : NameNode's port. Set to 0 for default or logical (HA) nodes.</span>
+<span class="sd"> user : Username when connecting to HDFS; None implies login user.</span>
+<span class="sd"> kerb_ticket : Path to Kerberos ticket cache.</span>
+<span class="sd"> driver : {'libhdfs', 'libhdfs3'}, default 'libhdfs'</span>
+<span class="sd"> Connect using libhdfs (JNI-based) or libhdfs3 (3rd-party C++</span>
+<span class="sd"> library from Apache HAWQ (incubating) )</span>
+<span class="sd"> extra_conf : dict, default None</span>
+<span class="sd"> extra Key/Value pairs for config; Will override any</span>
+<span class="sd"> hdfs-site.xml properties</span>
+
+<span class="sd"> Notes</span>
+<span class="sd"> -----</span>
+<span class="sd"> The first time you call this method, it will take longer than usual due</span>
+<span class="sd"> to JNI spin-up time.</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> filesystem : HadoopFileSystem</span>
+<span class="sd"> """</span>
+ <span class="n">fs</span> <span class="o">=</span> <span class="n">HadoopFileSystem</span><span class="p">(</span><span class="n">host</span><span class="o">=</span><span class="n">host</span><span class="p">,</span> <span class="n">port</span><span class="o">=</span><span class="n">port</span><span class="p">,</span> <span class="n">user</span><span class="o">=</span><span class="n">user</span><span class="p">,</span>
+ <span class="n">kerb_ticket</span><span class="o">=</span><span class="n">kerb_ticket</span><span class="p">,</span> <span class="n">driver</span><span class="o">=</span><span class="n">driver</span><span class="p">,</span>
+ <span class="n">extra_conf</span><span class="o">=</span><span class="n">extra_conf</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">fs</span></div>
+</pre></div>
+
+ </div>
+
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+ © Copyright 2016-2018 Apache Software Foundation
+
+ </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" 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/js/theme.js"></script>
+
+ <script type="text/javascript">
+ jQuery(function () {
+ SphinxRtdTheme.Navigation.enable(true);
+ });
+ </script>
+<script async src="https://www.googletagmanager.com/gtag/js?id=UA-107500873-1"></script>
+<script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+
+ gtag('config', 'UA-107500873-1');
+</script>
+
+
+</body>
+</html>
\ No newline at end of file