http://git-wip-us.apache.org/repos/asf/arrow-site/blob/679f060e/docs/python/_modules/pyarrow/parquet.html
----------------------------------------------------------------------
diff --git a/docs/python/_modules/pyarrow/parquet.html
b/docs/python/_modules/pyarrow/parquet.html
new file mode 100644
index 0000000..ab582d2
--- /dev/null
+++ b/docs/python/_modules/pyarrow/parquet.html
@@ -0,0 +1,891 @@
+
+
+<!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.parquet — pyarrow documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css"
/>
+
+
+
+
+
+ <link rel="index" title="Index"
+ href="../../genindex.html"/>
+ <link rel="search" title="Search" href="../../search.html"/>
+ <link rel="top" title="pyarrow documentation" href="../../index.html"/>
+ <link rel="up" title="pyarrow" href="../pyarrow.html"/>
+
+
+ <script src="../../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+
+ <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"> pyarrow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<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">Getting
Started</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal"
href="../../install.html">Install PyArrow</a></li>
+<li class="toctree-l1"><a class="reference internal"
href="../../pandas.html">Pandas Interface</a></li>
+<li class="toctree-l1"><a class="reference internal"
href="../../filesystems.html">File interfaces and Memory Maps</a></li>
+<li class="toctree-l1"><a class="reference internal"
href="../../parquet.html">Reading/Writing Parquet files</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../api.html">API
Reference</a></li>
+<li class="toctree-l1"><a class="reference internal"
href="../../getting_involved.html">Getting Involved</a></li>
+</ul>
+<p class="caption"><span class="caption-text">Additional Features</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal"
href="../../jemalloc.html">jemalloc MemoryPool</a></li>
+</ul>
+
+
+
+ </div>
+ </div>
+ </nav>
+
+ <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
+
+
+ <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
+
+ <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+ <a href="../../index.html">pyarrow</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.parquet</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.parquet</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">six</span>
+
+<span class="kn">import</span> <span class="nn">numpy</span> <span
class="k">as</span> <span class="nn">np</span>
+
+<span class="kn">from</span> <span class="nn">pyarrow.filesystem</span> <span
class="k">import</span> <span class="n">LocalFilesystem</span>
+<span class="kn">from</span> <span class="nn">pyarrow._parquet</span> <span
class="k">import</span> <span class="p">(</span><span
class="n">ParquetReader</span><span class="p">,</span> <span
class="n">FileMetaData</span><span class="p">,</span> <span class="c1">#
noqa</span>
+ <span class="n">RowGroupMetaData</span><span
class="p">,</span> <span class="n">ParquetSchema</span><span class="p">,</span>
+ <span class="n">ParquetWriter</span><span
class="p">)</span>
+<span class="kn">import</span> <span class="nn">pyarrow._parquet</span> <span
class="k">as</span> <span class="nn">_parquet</span> <span class="c1">#
noqa</span>
+<span class="kn">import</span> <span class="nn">pyarrow._array</span> <span
class="k">as</span> <span class="nn">_array</span>
+<span class="kn">import</span> <span class="nn">pyarrow._table</span> <span
class="k">as</span> <span class="nn">_table</span>
+
+
+<span class="c1">#
----------------------------------------------------------------------</span>
+<span class="c1"># Reading a single Parquet file</span>
+
+
+<div class="viewcode-block" id="ParquetFile"><a class="viewcode-back"
href="../../generated/pyarrow.parquet.ParquetFile.html#pyarrow.parquet.ParquetFile">[docs]</a><span
class="k">class</span> <span class="nc">ParquetFile</span><span
class="p">(</span><span class="nb">object</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Reader interface for a single Parquet file</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> source : str or pyarrow.io.NativeFile</span>
+<span class="sd"> Readable source. For passing Python file objects or
byte buffers,</span>
+<span class="sd"> see pyarrow.io.PythonFileInterface or
pyarrow.io.BufferReader.</span>
+<span class="sd"> metadata : ParquetFileMetadata, default None</span>
+<span class="sd"> Use existing metadata object, rather than reading
from file.</span>
+<span class="sd"> """</span>
+<div class="viewcode-block" id="ParquetFile.__init__"><a class="viewcode-back"
href="../../generated/pyarrow.parquet.ParquetFile.html#pyarrow.parquet.ParquetFile.__init__">[docs]</a>
<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">source</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="bp">self</span><span class="o">.</span><span
class="n">reader</span> <span class="o">=</span> <span
class="n">ParquetReader</span><span class="p">()</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">reader</span><span class="o">.</span><span class="n">open</span><span
class="p">(</span><span class="n">source</span><span class="p">,</span> <span
class="n">metadata</span><span class="o">=</span><span
class="n">metadata</span><span class="p">)</span></div>
+
+ <span class="nd">@property</span>
+ <span class="k">def</span> <span class="nf">metadata</span><span
class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="bp">self</span><span
class="o">.</span><span class="n">reader</span><span class="o">.</span><span
class="n">metadata</span>
+
+ <span class="nd">@property</span>
+ <span class="k">def</span> <span class="nf">schema</span><span
class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="bp">self</span><span
class="o">.</span><span class="n">metadata</span><span class="o">.</span><span
class="n">schema</span>
+
+ <span class="nd">@property</span>
+ <span class="k">def</span> <span class="nf">num_row_groups</span><span
class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="bp">self</span><span
class="o">.</span><span class="n">reader</span><span class="o">.</span><span
class="n">num_row_groups</span>
+
+ <span class="k">def</span> <span class="nf">read_row_group</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">i</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">nthreads</span><span class="o">=</span><span class="mi">1</span><span
class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Read a single row group from a Parquet file</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> columns: list</span>
+<span class="sd"> If not None, only these columns will be read from
the row group.</span>
+<span class="sd"> nthreads : int, default 1</span>
+<span class="sd"> Number of columns to read in parallel. If > 1,
requires that the</span>
+<span class="sd"> underlying file source is threadsafe</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> pyarrow.table.Table</span>
+<span class="sd"> Content of the row group as a table (of
columns)</span>
+<span class="sd"> """</span>
+ <span class="n">column_indices</span> <span class="o">=</span> <span
class="bp">self</span><span class="o">.</span><span
class="n">_get_column_indices</span><span class="p">(</span><span
class="n">columns</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">nthreads</span> <span
class="ow">is</span> <span class="ow">not</span> <span
class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">reader</span><span class="o">.</span><span
class="n">set_num_threads</span><span class="p">(</span><span
class="n">nthreads</span><span class="p">)</span>
+ <span class="k">return</span> <span class="bp">self</span><span
class="o">.</span><span class="n">reader</span><span class="o">.</span><span
class="n">read_row_group</span><span class="p">(</span><span
class="n">i</span><span class="p">,</span> <span
class="n">column_indices</span><span class="o">=</span><span
class="n">column_indices</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">read</span><span
class="p">(</span><span class="bp">self</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">nthreads</span><span class="o">=</span><span class="mi">1</span><span
class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Read a Table from Parquet format</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> columns: list</span>
+<span class="sd"> If not None, only these columns will be read from
the file.</span>
+<span class="sd"> nthreads : int, default 1</span>
+<span class="sd"> Number of columns to read in parallel. If > 1,
requires that the</span>
+<span class="sd"> underlying file source is threadsafe</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> pyarrow.table.Table</span>
+<span class="sd"> Content of the file as a table (of columns)</span>
+<span class="sd"> """</span>
+ <span class="n">column_indices</span> <span class="o">=</span> <span
class="bp">self</span><span class="o">.</span><span
class="n">_get_column_indices</span><span class="p">(</span><span
class="n">columns</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">nthreads</span> <span
class="ow">is</span> <span class="ow">not</span> <span
class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">reader</span><span class="o">.</span><span
class="n">set_num_threads</span><span class="p">(</span><span
class="n">nthreads</span><span class="p">)</span>
+ <span class="k">return</span> <span class="bp">self</span><span
class="o">.</span><span class="n">reader</span><span class="o">.</span><span
class="n">read_all</span><span class="p">(</span><span
class="n">column_indices</span><span class="o">=</span><span
class="n">column_indices</span><span class="p">)</span>
+
+ <span class="k">def</span> <span
class="nf">_get_column_indices</span><span class="p">(</span><span
class="bp">self</span><span class="p">,</span> <span
class="n">column_names</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">column_names</span> <span
class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="k">return</span> <span class="kc">None</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">return</span> <span class="p">[</span><span
class="bp">self</span><span class="o">.</span><span
class="n">reader</span><span class="o">.</span><span
class="n">column_name_idx</span><span class="p">(</span><span
class="n">column</span><span class="p">)</span>
+ <span class="k">for</span> <span class="n">column</span>
<span class="ow">in</span> <span class="n">column_names</span><span
class="p">]</span></div>
+
+
+<span class="c1">#
----------------------------------------------------------------------</span>
+<span class="c1"># Metadata container providing instructions about reading a
single Parquet</span>
+<span class="c1"># file, possibly part of a partitioned dataset</span>
+
+
+<span class="k">class</span> <span class="nc">ParquetDatasetPiece</span><span
class="p">(</span><span class="nb">object</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> A single chunk of a potentially larger Parquet dataset to
read. The</span>
+<span class="sd"> arguments will indicate to read either a single row group
or all row</span>
+<span class="sd"> groups, and whether to add partition keys to the
resulting pyarrow.Table</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> path : str</span>
+<span class="sd"> Path to file in the file system where this piece is
located</span>
+<span class="sd"> partition_keys : list of tuples</span>
+<span class="sd"> [(column name, ordinal index)]</span>
+<span class="sd"> row_group : int, default None</span>
+<span class="sd"> Row group to load. By default, reads all row
groups</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">path</span><span class="p">,</span> <span
class="n">row_group</span><span class="o">=</span><span
class="kc">None</span><span class="p">,</span> <span
class="n">partition_keys</span><span class="o">=</span><span
class="kc">None</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">path</span> <span class="o">=</span> <span class="n">path</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">row_group</span> <span class="o">=</span> <span
class="n">row_group</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">partition_keys</span> <span class="o">=</span> <span
class="n">partition_keys</span> <span class="ow">or</span> <span
class="p">[]</span>
+
+ <span class="k">def</span> <span class="nf">__eq__</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">other</span><span class="p">):</span>
+ <span class="k">if</span> <span class="ow">not</span> <span
class="nb">isinstance</span><span class="p">(</span><span
class="n">other</span><span class="p">,</span> <span
class="n">ParquetDatasetPiece</span><span class="p">):</span>
+ <span class="k">return</span> <span class="kc">False</span>
+ <span class="k">return</span> <span class="p">(</span><span
class="bp">self</span><span class="o">.</span><span class="n">path</span> <span
class="o">==</span> <span class="n">other</span><span class="o">.</span><span
class="n">path</span> <span class="ow">and</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">row_group</span> <span class="o">==</span> <span
class="n">other</span><span class="o">.</span><span class="n">row_group</span>
<span class="ow">and</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">partition_keys</span> <span class="o">==</span> <span
class="n">other</span><span class="o">.</span><span
class="n">partition_keys</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">__ne__</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">other</span><span class="p">):</span>
+ <span class="k">return</span> <span class="ow">not</span> <span
class="p">(</span><span class="bp">self</span> <span class="o">==</span> <span
class="n">other</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">__repr__</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="s1">'</span><span class="si">{0}</span><span
class="s1">(</span><span class="si">{1!r}</span><span class="s1">,
row_group=</span><span class="si">{2!r}</span><span class="s1">,
partition_keys=</span><span class="si">{3!r}</span><span
class="s1">)'</span>
+ <span class="o">.</span><span class="n">format</span><span
class="p">(</span><span class="nb">type</span><span class="p">(</span><span
class="bp">self</span><span class="p">)</span><span class="o">.</span><span
class="n">__name__</span><span class="p">,</span> <span
class="bp">self</span><span class="o">.</span><span class="n">path</span><span
class="p">,</span>
+ <span class="bp">self</span><span
class="o">.</span><span class="n">row_group</span><span class="p">,</span>
+ <span class="bp">self</span><span
class="o">.</span><span class="n">partition_keys</span><span class="p">))</span>
+
+ <span class="k">def</span> <span class="nf">__str__</span><span
class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="n">result</span> <span class="o">=</span> <span
class="s1">''</span>
+
+ <span class="k">if</span> <span class="nb">len</span><span
class="p">(</span><span class="bp">self</span><span class="o">.</span><span
class="n">partition_keys</span><span class="p">)</span> <span
class="o">></span> <span class="mi">0</span><span class="p">:</span>
+ <span class="n">partition_str</span> <span class="o">=</span>
<span class="s1">', '</span><span class="o">.</span><span
class="n">join</span><span class="p">(</span><span class="s1">'</span><span
class="si">{0}</span><span class="s1">=</span><span class="si">{1}</span><span
class="s1">'</span><span class="o">.</span><span
class="n">format</span><span class="p">(</span><span class="n">name</span><span
class="p">,</span> <span class="n">index</span><span class="p">)</span>
+ <span class="k">for</span> <span
class="n">name</span><span class="p">,</span> <span class="n">index</span>
<span class="ow">in</span> <span class="bp">self</span><span
class="o">.</span><span class="n">partition_keys</span><span class="p">)</span>
+ <span class="n">result</span> <span class="o">+=</span> <span
class="s1">'partition[</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">partition_str</span><span class="p">)</span>
+
+ <span class="n">result</span> <span class="o">+=</span> <span
class="bp">self</span><span class="o">.</span><span class="n">path</span>
+
+ <span class="k">if</span> <span class="bp">self</span><span
class="o">.</span><span class="n">row_group</span> <span class="ow">is</span>
<span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="n">result</span> <span class="o">+=</span> <span
class="s1">' | row_group=</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="bp">self</span><span class="o">.</span><span
class="n">row_group</span><span class="p">)</span>
+
+ <span class="k">return</span> <span class="n">result</span>
+
+ <span class="k">def</span> <span class="nf">get_metadata</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">open_file_func</span><span class="o">=</span><span
class="kc">None</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Given a function that can create an open ParquetFile
object, return the</span>
+<span class="sd"> file's metadata</span>
+<span class="sd"> """</span>
+ <span class="k">return</span> <span class="bp">self</span><span
class="o">.</span><span class="n">_open</span><span class="p">(</span><span
class="n">open_file_func</span><span class="p">)</span><span
class="o">.</span><span class="n">metadata</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">open_file_func</span><span class="o">=</span><span
class="kc">None</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Returns instance of ParquetFile</span>
+<span class="sd"> """</span>
+ <span class="n">reader</span> <span class="o">=</span> <span
class="n">open_file_func</span><span class="p">(</span><span
class="bp">self</span><span class="o">.</span><span class="n">path</span><span
class="p">)</span>
+ <span class="k">if</span> <span class="ow">not</span> <span
class="nb">isinstance</span><span class="p">(</span><span
class="n">reader</span><span class="p">,</span> <span
class="n">ParquetFile</span><span class="p">):</span>
+ <span class="n">reader</span> <span class="o">=</span> <span
class="n">ParquetFile</span><span class="p">(</span><span
class="n">reader</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">reader</span>
+
+ <span class="k">def</span> <span class="nf">read</span><span
class="p">(</span><span class="bp">self</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">nthreads</span><span class="o">=</span><span class="mi">1</span><span
class="p">,</span> <span class="n">partitions</span><span
class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">open_file_func</span><span
class="o">=</span><span class="kc">None</span><span class="p">,</span> <span
class="n">file</span><span class="o">=</span><span class="kc">None</span><span
class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Read this piece as a pyarrow.Table</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> columns : list of column names, default None</span>
+<span class="sd"> nthreads : int, default 1</span>
+<span class="sd"> For multithreaded file reads</span>
+<span class="sd"> partitions : ParquetPartitions, default None</span>
+<span class="sd"> open_file_func : function, default None</span>
+<span class="sd"> A function that knows how to construct a
ParquetFile object given</span>
+<span class="sd"> the file path in this piece</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> table : pyarrow.Table</span>
+<span class="sd"> """</span>
+ <span class="k">if</span> <span class="n">open_file_func</span> <span
class="ow">is</span> <span class="ow">not</span> <span
class="kc">None</span><span class="p">:</span>
+ <span class="n">reader</span> <span class="o">=</span> <span
class="bp">self</span><span class="o">.</span><span class="n">_open</span><span
class="p">(</span><span class="n">open_file_func</span><span class="p">)</span>
+ <span class="k">elif</span> <span class="n">file</span> <span
class="ow">is</span> <span class="ow">not</span> <span
class="kc">None</span><span class="p">:</span>
+ <span class="n">reader</span> <span class="o">=</span> <span
class="n">ParquetFile</span><span class="p">(</span><span
class="n">file</span><span class="p">)</span>
+
+ <span class="k">if</span> <span class="bp">self</span><span
class="o">.</span><span class="n">row_group</span> <span class="ow">is</span>
<span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="n">table</span> <span class="o">=</span> <span
class="n">reader</span><span class="o">.</span><span
class="n">read_row_group</span><span class="p">(</span><span
class="bp">self</span><span class="o">.</span><span
class="n">row_group</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">nthreads</span><span
class="o">=</span><span class="n">nthreads</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">table</span> <span class="o">=</span> <span
class="n">reader</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">nthreads</span><span class="o">=</span><span
class="n">nthreads</span><span class="p">)</span>
+
+ <span class="k">if</span> <span class="nb">len</span><span
class="p">(</span><span class="bp">self</span><span class="o">.</span><span
class="n">partition_keys</span><span class="p">)</span> <span
class="o">></span> <span class="mi">0</span><span class="p">:</span>
+ <span class="k">if</span> <span class="n">partitions</span> <span
class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="k">raise</span> <span
class="ne">ValueError</span><span class="p">(</span><span class="s1">'Must
pass partition sets'</span><span class="p">)</span>
+
+ <span class="c1"># Here, the index is the categorical code of the
partition where</span>
+ <span class="c1"># this piece is located. Suppose we had</span>
+ <span class="c1">#</span>
+ <span class="c1"># /foo=a/0.parq</span>
+ <span class="c1"># /foo=b/0.parq</span>
+ <span class="c1"># /foo=c/0.parq</span>
+ <span class="c1">#</span>
+ <span class="c1"># Then we assign a=0, b=1, c=2. And the resulting
Table pieces will</span>
+ <span class="c1"># have a DictionaryArray column named foo having
the constant index</span>
+ <span class="c1"># value as indicated. The distinct categories of
the partition have</span>
+ <span class="c1"># been computed in the ParquetManifest</span>
+ <span class="k">for</span> <span class="n">i</span><span
class="p">,</span> <span class="p">(</span><span class="n">name</span><span
class="p">,</span> <span class="n">index</span><span class="p">)</span> <span
class="ow">in</span> <span class="nb">enumerate</span><span
class="p">(</span><span class="bp">self</span><span class="o">.</span><span
class="n">partition_keys</span><span class="p">):</span>
+ <span class="c1"># The partition code is the same for all
values in this piece</span>
+ <span class="n">indices</span> <span class="o">=</span> <span
class="n">np</span><span class="o">.</span><span class="n">array</span><span
class="p">([</span><span class="n">index</span><span class="p">],</span> <span
class="n">dtype</span><span class="o">=</span><span
class="s1">'i4'</span><span class="p">)</span><span
class="o">.</span><span class="n">repeat</span><span class="p">(</span><span
class="nb">len</span><span class="p">(</span><span class="n">table</span><span
class="p">))</span>
+
+ <span class="c1"># This is set of all partition values,
computed as part of the</span>
+ <span class="c1"># manifest, so ['a', 'b',
'c'] as in our example above.</span>
+ <span class="n">dictionary</span> <span class="o">=</span>
<span class="n">partitions</span><span class="o">.</span><span
class="n">levels</span><span class="p">[</span><span class="n">i</span><span
class="p">]</span><span class="o">.</span><span class="n">dictionary</span>
+
+ <span class="n">arr</span> <span class="o">=</span> <span
class="n">_array</span><span class="o">.</span><span
class="n">DictionaryArray</span><span class="o">.</span><span
class="n">from_arrays</span><span class="p">(</span><span
class="n">indices</span><span class="p">,</span> <span
class="n">dictionary</span><span class="p">)</span>
+ <span class="n">col</span> <span class="o">=</span> <span
class="n">_table</span><span class="o">.</span><span
class="n">Column</span><span class="o">.</span><span
class="n">from_array</span><span class="p">(</span><span
class="n">name</span><span class="p">,</span> <span class="n">arr</span><span
class="p">)</span>
+ <span class="n">table</span> <span class="o">=</span> <span
class="n">table</span><span class="o">.</span><span
class="n">append_column</span><span class="p">(</span><span
class="n">col</span><span class="p">)</span>
+
+ <span class="k">return</span> <span class="n">table</span>
+
+
+<span class="k">def</span> <span class="nf">_is_parquet_file</span><span
class="p">(</span><span class="n">path</span><span class="p">):</span>
+ <span class="k">return</span> <span class="n">path</span><span
class="o">.</span><span class="n">endswith</span><span class="p">(</span><span
class="s1">'parq'</span><span class="p">)</span> <span
class="ow">or</span> <span class="n">path</span><span class="o">.</span><span
class="n">endswith</span><span class="p">(</span><span
class="s1">'parquet'</span><span class="p">)</span>
+
+
+<span class="k">class</span> <span class="nc">PartitionSet</span><span
class="p">(</span><span class="nb">object</span><span class="p">):</span>
+ <span class="sd">"""A data structure for cataloguing the
observed Parquet partitions at a</span>
+<span class="sd"> particular level. So if we have</span>
+
+<span class="sd"> /foo=a/bar=0</span>
+<span class="sd"> /foo=a/bar=1</span>
+<span class="sd"> /foo=a/bar=2</span>
+<span class="sd"> /foo=b/bar=0</span>
+<span class="sd"> /foo=b/bar=1</span>
+<span class="sd"> /foo=b/bar=2</span>
+
+<span class="sd"> Then we have two partition sets, one for foo, another for
bar. As we visit</span>
+<span class="sd"> levels of the partition hierarchy, a PartitionSet tracks
the distinct</span>
+<span class="sd"> values and assigns categorical codes to use when reading
the pieces</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">name</span><span class="p">,</span> <span class="n">keys</span><span
class="o">=</span><span class="kc">None</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">name</span> <span class="o">=</span> <span class="n">name</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">keys</span> <span class="o">=</span> <span class="n">keys</span>
<span class="ow">or</span> <span class="p">[]</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">key_indices</span> <span class="o">=</span> <span
class="p">{</span><span class="n">k</span><span class="p">:</span> <span
class="n">i</span> <span class="k">for</span> <span class="n">i</span><span
class="p">,</span> <span class="n">k</span> <span class="ow">in</span> <span
class="nb">enumerate</span><span class="p">(</span><span
class="bp">self</span><span class="o">.</span><span class="n">keys</span><span
class="p">)}</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">_dictionary</span> <span class="o">=</span> <span
class="kc">None</span>
+
+ <span class="k">def</span> <span class="nf">get_index</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">key</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Get the index of the partition value if it is known,
otherwise assign</span>
+<span class="sd"> one</span>
+<span class="sd"> """</span>
+ <span class="k">if</span> <span class="n">key</span> <span
class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span
class="n">key_indices</span><span class="p">:</span>
+ <span class="k">return</span> <span class="bp">self</span><span
class="o">.</span><span class="n">key_indices</span><span
class="p">[</span><span class="n">key</span><span class="p">]</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">index</span> <span class="o">=</span> <span
class="nb">len</span><span class="p">(</span><span class="bp">self</span><span
class="o">.</span><span class="n">key_indices</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">keys</span><span class="o">.</span><span class="n">append</span><span
class="p">(</span><span class="n">key</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">key_indices</span><span class="p">[</span><span
class="n">key</span><span class="p">]</span> <span class="o">=</span> <span
class="n">index</span>
+ <span class="k">return</span> <span class="n">index</span>
+
+ <span class="nd">@property</span>
+ <span class="k">def</span> <span class="nf">dictionary</span><span
class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">if</span> <span class="bp">self</span><span
class="o">.</span><span class="n">_dictionary</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="bp">self</span><span
class="o">.</span><span class="n">_dictionary</span>
+
+ <span class="k">if</span> <span class="nb">len</span><span
class="p">(</span><span class="bp">self</span><span class="o">.</span><span
class="n">keys</span><span class="p">)</span> <span class="o">==</span> <span
class="mi">0</span><span class="p">:</span>
+ <span class="k">raise</span> <span
class="ne">ValueError</span><span class="p">(</span><span class="s1">'No
known partition keys'</span><span class="p">)</span>
+
+ <span class="c1"># Only integer and string partition types are
supported right now</span>
+ <span class="k">try</span><span class="p">:</span>
+ <span class="n">integer_keys</span> <span class="o">=</span> <span
class="p">[</span><span class="nb">int</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="bp">self</span><span
class="o">.</span><span class="n">keys</span><span class="p">]</span>
+ <span class="n">dictionary</span> <span class="o">=</span> <span
class="n">_array</span><span class="o">.</span><span
class="n">array</span><span class="p">(</span><span
class="n">integer_keys</span><span class="p">)</span>
+ <span class="k">except</span> <span class="ne">ValueError</span><span
class="p">:</span>
+ <span class="n">dictionary</span> <span class="o">=</span> <span
class="n">_array</span><span class="o">.</span><span
class="n">array</span><span class="p">(</span><span class="bp">self</span><span
class="o">.</span><span class="n">keys</span><span class="p">)</span>
+
+ <span class="bp">self</span><span class="o">.</span><span
class="n">_dictionary</span> <span class="o">=</span> <span
class="n">dictionary</span>
+ <span class="k">return</span> <span class="n">dictionary</span>
+
+ <span class="nd">@property</span>
+ <span class="k">def</span> <span class="nf">is_sorted</span><span
class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="nb">list</span><span
class="p">(</span><span class="bp">self</span><span class="o">.</span><span
class="n">keys</span><span class="p">)</span> <span class="o">==</span> <span
class="nb">sorted</span><span class="p">(</span><span
class="bp">self</span><span class="o">.</span><span class="n">keys</span><span
class="p">)</span>
+
+
+<span class="k">class</span> <span class="nc">ParquetPartitions</span><span
class="p">(</span><span class="nb">object</span><span class="p">):</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="bp">self</span><span class="o">.</span><span
class="n">levels</span> <span class="o">=</span> <span class="p">[]</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">partition_names</span> <span class="o">=</span> <span
class="nb">set</span><span class="p">()</span>
+
+ <span class="k">def</span> <span class="nf">__len__</span><span
class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="nb">len</span><span
class="p">(</span><span class="bp">self</span><span class="o">.</span><span
class="n">levels</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">__getitem__</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">i</span><span class="p">):</span>
+ <span class="k">return</span> <span class="bp">self</span><span
class="o">.</span><span class="n">levels</span><span class="p">[</span><span
class="n">i</span><span class="p">]</span>
+
+ <span class="k">def</span> <span class="nf">get_index</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">level</span><span class="p">,</span> <span class="n">name</span><span
class="p">,</span> <span class="n">key</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Record a partition value at a particular level,
returning the distinct</span>
+<span class="sd"> code for that value at that level. Example:</span>
+
+<span class="sd"> partitions.get_index(1, 'foo', 'a')
returns 0</span>
+<span class="sd"> partitions.get_index(1, 'foo', 'b')
returns 1</span>
+<span class="sd"> partitions.get_index(1, 'foo', 'c')
returns 2</span>
+<span class="sd"> partitions.get_index(1, 'foo', 'a')
returns 0</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> level : int</span>
+<span class="sd"> The nesting level of the partition we are
observing</span>
+<span class="sd"> name : string</span>
+<span class="sd"> The partition name</span>
+<span class="sd"> key : string or int</span>
+<span class="sd"> The partition value</span>
+<span class="sd"> """</span>
+ <span class="k">if</span> <span class="n">level</span> <span
class="o">==</span> <span class="nb">len</span><span class="p">(</span><span
class="bp">self</span><span class="o">.</span><span
class="n">levels</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">name</span> <span
class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span
class="n">partition_names</span><span class="p">:</span>
+ <span class="k">raise</span> <span
class="ne">ValueError</span><span class="p">(</span><span
class="s1">'</span><span class="si">{0}</span><span class="s1"> was the
name of the partition in '</span>
+ <span class="s1">'another
level'</span><span class="o">.</span><span class="n">format</span><span
class="p">(</span><span class="n">name</span><span class="p">))</span>
+
+ <span class="n">part_set</span> <span class="o">=</span> <span
class="n">PartitionSet</span><span class="p">(</span><span
class="n">name</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">levels</span><span class="o">.</span><span
class="n">append</span><span class="p">(</span><span
class="n">part_set</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">partition_names</span><span class="o">.</span><span
class="n">add</span><span class="p">(</span><span class="n">name</span><span
class="p">)</span>
+
+ <span class="k">return</span> <span class="bp">self</span><span
class="o">.</span><span class="n">levels</span><span class="p">[</span><span
class="n">level</span><span class="p">]</span><span class="o">.</span><span
class="n">get_index</span><span class="p">(</span><span
class="n">key</span><span class="p">)</span>
+
+
+<span class="k">def</span> <span class="nf">is_string</span><span
class="p">(</span><span class="n">x</span><span class="p">):</span>
+ <span class="k">return</span> <span class="nb">isinstance</span><span
class="p">(</span><span class="n">x</span><span class="p">,</span> <span
class="n">six</span><span class="o">.</span><span
class="n">string_types</span><span class="p">)</span>
+
+
+<span class="k">class</span> <span class="nc">ParquetManifest</span><span
class="p">(</span><span class="nb">object</span><span class="p">):</span>
+ <span class="sd">"""</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">dirpath</span><span class="p">,</span> <span
class="n">filesystem</span><span class="o">=</span><span
class="kc">None</span><span class="p">,</span> <span
class="n">pathsep</span><span class="o">=</span><span
class="s1">'/'</span><span class="p">,</span>
+ <span class="n">partition_scheme</span><span
class="o">=</span><span class="s1">'hive'</span><span
class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">filesystem</span> <span class="o">=</span> <span
class="n">filesystem</span> <span class="ow">or</span> <span
class="n">LocalFilesystem</span><span class="o">.</span><span
class="n">get_instance</span><span class="p">()</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">pathsep</span> <span class="o">=</span> <span class="n">pathsep</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">dirpath</span> <span class="o">=</span> <span class="n">dirpath</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">partition_scheme</span> <span class="o">=</span> <span
class="n">partition_scheme</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">partitions</span> <span class="o">=</span> <span
class="n">ParquetPartitions</span><span class="p">()</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">pieces</span> <span class="o">=</span> <span class="p">[]</span>
+
+ <span class="bp">self</span><span class="o">.</span><span
class="n">common_metadata_path</span> <span class="o">=</span> <span
class="kc">None</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">metadata_path</span> <span class="o">=</span> <span
class="kc">None</span>
+
+ <span class="bp">self</span><span class="o">.</span><span
class="n">_visit_level</span><span class="p">(</span><span
class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span
class="o">.</span><span class="n">dirpath</span><span class="p">,</span> <span
class="p">[])</span>
+
+ <span class="k">def</span> <span class="nf">_visit_level</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">level</span><span class="p">,</span> <span
class="n">base_path</span><span class="p">,</span> <span
class="n">part_keys</span><span class="p">):</span>
+ <span class="n">directories</span> <span class="o">=</span> <span
class="p">[]</span>
+ <span class="n">files</span> <span class="o">=</span> <span
class="p">[]</span>
+ <span class="n">fs</span> <span class="o">=</span> <span
class="bp">self</span><span class="o">.</span><span class="n">filesystem</span>
+
+ <span class="k">if</span> <span class="ow">not</span> <span
class="n">fs</span><span class="o">.</span><span class="n">isdir</span><span
class="p">(</span><span class="n">base_path</span><span class="p">):</span>
+ <span class="k">raise</span> <span
class="ne">ValueError</span><span class="p">(</span><span
class="s1">'"</span><span class="si">{0}</span><span class="s1">"
is not a directory'</span><span class="o">.</span><span
class="n">format</span><span class="p">(</span><span
class="n">base_path</span><span class="p">))</span>
+
+ <span class="k">for</span> <span class="n">path</span> <span
class="ow">in</span> <span class="nb">sorted</span><span
class="p">(</span><span class="n">fs</span><span class="o">.</span><span
class="n">ls</span><span class="p">(</span><span
class="n">base_path</span><span class="p">)):</span>
+ <span class="k">if</span> <span class="n">fs</span><span
class="o">.</span><span class="n">isfile</span><span class="p">(</span><span
class="n">path</span><span class="p">):</span>
+ <span class="k">if</span> <span
class="n">_is_parquet_file</span><span class="p">(</span><span
class="n">path</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">path</span><span
class="p">)</span>
+ <span class="k">elif</span> <span class="n">path</span><span
class="o">.</span><span class="n">endswith</span><span class="p">(</span><span
class="s1">'_common_metadata'</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">common_metadata_path</span> <span class="o">=</span> <span
class="n">path</span>
+ <span class="k">elif</span> <span class="n">path</span><span
class="o">.</span><span class="n">endswith</span><span class="p">(</span><span
class="s1">'_metadata'</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">metadata_path</span> <span class="o">=</span> <span
class="n">path</span>
+ <span class="k">elif</span> <span class="ow">not</span> <span
class="bp">self</span><span class="o">.</span><span
class="n">_should_silently_exclude</span><span class="p">(</span><span
class="n">path</span><span class="p">):</span>
+ <span class="nb">print</span><span class="p">(</span><span
class="s1">'Ignoring path: </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">path</span><span
class="p">))</span>
+ <span class="k">elif</span> <span class="n">fs</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="n">directories</span><span
class="o">.</span><span class="n">append</span><span class="p">(</span><span
class="n">path</span><span class="p">)</span>
+
+ <span class="k">if</span> <span class="nb">len</span><span
class="p">(</span><span class="n">files</span><span class="p">)</span> <span
class="o">></span> <span class="mi">0</span> <span class="ow">and</span>
<span class="nb">len</span><span class="p">(</span><span
class="n">directories</span><span class="p">)</span> <span
class="o">></span> <span class="mi">0</span><span class="p">:</span>
+ <span class="k">raise</span> <span
class="ne">ValueError</span><span class="p">(</span><span class="s1">'Found
files in an intermediate '</span>
+ <span class="s1">'directory: </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">base_path</span><span class="p">))</span>
+ <span class="k">elif</span> <span class="nb">len</span><span
class="p">(</span><span class="n">directories</span><span class="p">)</span>
<span class="o">></span> <span class="mi">0</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">_visit_directories</span><span class="p">(</span><span
class="n">level</span><span class="p">,</span> <span
class="n">directories</span><span class="p">,</span> <span
class="n">part_keys</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">_push_pieces</span><span class="p">(</span><span
class="n">files</span><span class="p">,</span> <span
class="n">part_keys</span><span class="p">)</span>
+
+ <span class="k">def</span> <span
class="nf">_should_silently_exclude</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">_</span><span class="p">,</span> <span
class="n">tail</span> <span class="o">=</span> <span class="n">path</span><span
class="o">.</span><span class="n">rsplit</span><span class="p">(</span><span
class="bp">self</span><span class="o">.</span><span
class="n">pathsep</span><span class="p">,</span> <span class="mi">1</span><span
class="p">)</span>
+ <span class="k">return</span> <span class="n">tail</span><span
class="o">.</span><span class="n">endswith</span><span class="p">(</span><span
class="s1">'.crc'</span><span class="p">)</span> <span
class="ow">or</span> <span class="n">tail</span> <span class="ow">in</span>
<span class="n">EXCLUDED_PARQUET_PATHS</span>
+
+ <span class="k">def</span> <span class="nf">_visit_directories</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">level</span><span class="p">,</span> <span
class="n">directories</span><span class="p">,</span> <span
class="n">part_keys</span><span class="p">):</span>
+ <span class="k">for</span> <span class="n">path</span> <span
class="ow">in</span> <span class="n">directories</span><span class="p">:</span>
+ <span class="n">head</span><span class="p">,</span> <span
class="n">tail</span> <span class="o">=</span> <span
class="n">_path_split</span><span class="p">(</span><span
class="n">path</span><span class="p">,</span> <span class="bp">self</span><span
class="o">.</span><span class="n">pathsep</span><span class="p">)</span>
+ <span class="n">name</span><span class="p">,</span> <span
class="n">key</span> <span class="o">=</span> <span
class="n">_parse_hive_partition</span><span class="p">(</span><span
class="n">tail</span><span class="p">)</span>
+
+ <span class="n">index</span> <span class="o">=</span> <span
class="bp">self</span><span class="o">.</span><span
class="n">partitions</span><span class="o">.</span><span
class="n">get_index</span><span class="p">(</span><span
class="n">level</span><span class="p">,</span> <span class="n">name</span><span
class="p">,</span> <span class="n">key</span><span class="p">)</span>
+ <span class="n">dir_part_keys</span> <span class="o">=</span>
<span class="n">part_keys</span> <span class="o">+</span> <span
class="p">[(</span><span class="n">name</span><span class="p">,</span> <span
class="n">index</span><span class="p">)]</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">_visit_level</span><span class="p">(</span><span
class="n">level</span> <span class="o">+</span> <span class="mi">1</span><span
class="p">,</span> <span class="n">path</span><span class="p">,</span> <span
class="n">dir_part_keys</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">_parse_partition</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">dirname</span><span class="p">):</span>
+ <span class="k">if</span> <span class="bp">self</span><span
class="o">.</span><span class="n">partition_scheme</span> <span
class="o">==</span> <span class="s1">'hive'</span><span
class="p">:</span>
+ <span class="k">return</span> <span
class="n">_parse_hive_partition</span><span class="p">(</span><span
class="n">dirname</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">raise</span> <span
class="ne">NotImplementedError</span><span class="p">(</span><span
class="s1">'partition schema: </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="bp">self</span><span class="o">.</span><span
class="n">partition_scheme</span><span class="p">))</span>
+
+ <span class="k">def</span> <span class="nf">_push_pieces</span><span
class="p">(</span><span class="bp">self</span><span class="p">,</span> <span
class="n">files</span><span class="p">,</span> <span
class="n">part_keys</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">pieces</span><span class="o">.</span><span
class="n">extend</span><span class="p">([</span>
+ <span class="n">ParquetDatasetPiece</span><span
class="p">(</span><span class="n">path</span><span class="p">,</span> <span
class="n">partition_keys</span><span class="o">=</span><span
class="n">part_keys</span><span class="p">)</span>
+ <span class="k">for</span> <span class="n">path</span> <span
class="ow">in</span> <span class="n">files</span>
+ <span class="p">])</span>
+
+
+<span class="k">def</span> <span class="nf">_parse_hive_partition</span><span
class="p">(</span><span class="n">value</span><span class="p">):</span>
+ <span class="k">if</span> <span class="s1">'='</span> <span
class="ow">not</span> <span class="ow">in</span> <span
class="n">value</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="ne">ValueError</span><span
class="p">(</span><span class="s1">'Directory name did not appear to be a
'</span>
+ <span class="s1">'partition: </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">value</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">value</span><span
class="o">.</span><span class="n">split</span><span class="p">(</span><span
class="s1">'='</span><span class="p">,</span> <span
class="mi">1</span><span class="p">)</span>
+
+
+<span class="k">def</span> <span class="nf">_path_split</span><span
class="p">(</span><span class="n">path</span><span class="p">,</span> <span
class="n">sep</span><span class="p">):</span>
+ <span class="n">i</span> <span class="o">=</span> <span
class="n">path</span><span class="o">.</span><span class="n">rfind</span><span
class="p">(</span><span class="n">sep</span><span class="p">)</span> <span
class="o">+</span> <span class="mi">1</span>
+ <span class="n">head</span><span class="p">,</span> <span
class="n">tail</span> <span class="o">=</span> <span class="n">path</span><span
class="p">[:</span><span class="n">i</span><span class="p">],</span> <span
class="n">path</span><span class="p">[</span><span class="n">i</span><span
class="p">:]</span>
+ <span class="n">head</span> <span class="o">=</span> <span
class="n">head</span><span class="o">.</span><span class="n">rstrip</span><span
class="p">(</span><span class="n">sep</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">head</span><span
class="p">,</span> <span class="n">tail</span>
+
+
+<span class="n">EXCLUDED_PARQUET_PATHS</span> <span class="o">=</span> <span
class="p">{</span><span class="s1">'_SUCCESS'</span><span
class="p">}</span>
+
+
+<div class="viewcode-block" id="ParquetDataset"><a class="viewcode-back"
href="../../generated/pyarrow.parquet.ParquetDataset.html#pyarrow.parquet.ParquetDataset">[docs]</a><span
class="k">class</span> <span class="nc">ParquetDataset</span><span
class="p">(</span><span class="nb">object</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Encapsulates details of reading a complete Parquet
dataset possibly</span>
+<span class="sd"> consisting of multiple files and partitions in
subdirectories</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> path_or_paths : str or List[str]</span>
+<span class="sd"> A directory name, single file name, or list of file
names</span>
+<span class="sd"> filesystem : Filesystem, default None</span>
+<span class="sd"> If nothing passed, paths assumed to be found in the
local on-disk</span>
+<span class="sd"> filesystem</span>
+<span class="sd"> metadata : pyarrow.parquet.FileMetaData</span>
+<span class="sd"> Use metadata obtained elsewhere to validate file
schemas</span>
+<span class="sd"> schema : pyarrow.parquet.Schema</span>
+<span class="sd"> Use schema obtained elsewhere to validate file
schemas. Alternative to</span>
+<span class="sd"> metadata parameter</span>
+<span class="sd"> split_row_groups : boolean, default False</span>
+<span class="sd"> Divide files into pieces for each row group in the
file</span>
+<span class="sd"> validate_schema : boolean, default True</span>
+<span class="sd"> Check that individual file schemas are all the same /
compatible</span>
+<span class="sd"> """</span>
+<div class="viewcode-block" id="ParquetDataset.__init__"><a
class="viewcode-back"
href="../../generated/pyarrow.parquet.ParquetDataset.html#pyarrow.parquet.ParquetDataset.__init__">[docs]</a>
<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">path_or_paths</span><span class="p">,</span> <span
class="n">filesystem</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">metadata</span><span class="o">=</span><span
class="kc">None</span><span class="p">,</span> <span
class="n">split_row_groups</span><span class="o">=</span><span
class="kc">False</span><span class="p">,</span> <span
class="n">validate_schema</span><span class="o">=</span><span
class="kc">True</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">filesystem</span> <span
class="ow">is</span> <span class="kc">None</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">LocalFilesystem</span><span class="o">.</span><span
class="n">get_instance</span><span class="p">()</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">fs</span> <span class="o">=</span> <span class="n">filesystem</span>
+
+ <span class="bp">self</span><span class="o">.</span><span
class="n">paths</span> <span class="o">=</span> <span
class="n">path_or_paths</span>
+
+ <span class="p">(</span><span class="bp">self</span><span
class="o">.</span><span class="n">pieces</span><span class="p">,</span> <span
class="bp">self</span><span class="o">.</span><span
class="n">partitions</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">metadata_path</span><span class="p">)</span> <span class="o">=</span>
<span class="n">_make_manifest</span><span class="p">(</span><span
class="n">path_or_paths</span><span class="p">,</span> <span
class="bp">self</span><span class="o">.</span><span class="n">fs</span><span
class="p">)</span>
+
+ <span class="bp">self</span><span class="o">.</span><span
class="n">metadata</span> <span class="o">=</span> <span
class="n">metadata</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">schema</span> <span class="o">=</span> <span class="n">schema</span>
+
+ <span class="bp">self</span><span class="o">.</span><span
class="n">split_row_groups</span> <span class="o">=</span> <span
class="n">split_row_groups</span>
+
+ <span class="k">if</span> <span class="n">split_row_groups</span><span
class="p">:</span>
+ <span class="k">raise</span> <span
class="ne">NotImplementedError</span><span class="p">(</span><span
class="s2">"split_row_groups not yet implemented"</span><span
class="p">)</span>
+
+ <span class="k">if</span> <span class="n">validate_schema</span><span
class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">validate_schemas</span><span class="p">()</span></div>
+
+ <span class="k">def</span> <span class="nf">validate_schemas</span><span
class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="n">open_file</span> <span class="o">=</span> <span
class="bp">self</span><span class="o">.</span><span
class="n">_get_open_file_func</span><span class="p">()</span>
+
+ <span class="k">if</span> <span class="bp">self</span><span
class="o">.</span><span class="n">metadata</span> <span class="ow">is</span>
<span class="kc">None</span> <span class="ow">and</span> <span
class="bp">self</span><span class="o">.</span><span class="n">schema</span>
<span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="k">if</span> <span class="bp">self</span><span
class="o">.</span><span class="n">metadata_path</span> <span
class="ow">is</span> <span class="ow">not</span> <span
class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">schema</span> <span class="o">=</span> <span
class="n">open_file</span><span class="p">(</span><span
class="bp">self</span><span class="o">.</span><span
class="n">metadata_path</span><span class="p">)</span><span
class="o">.</span><span class="n">schema</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">schema</span> <span class="o">=</span> <span
class="bp">self</span><span class="o">.</span><span
class="n">pieces</span><span class="p">[</span><span class="mi">0</span><span
class="p">]</span><span class="o">.</span><span
class="n">get_metadata</span><span class="p">(</span><span
class="n">open_file</span><span class="p">)</span><span class="o">.</span><span
class="n">schema</span>
+ <span class="k">elif</span> <span class="bp">self</span><span
class="o">.</span><span class="n">schema</span> <span class="ow">is</span>
<span class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span
class="n">schema</span> <span class="o">=</span> <span
class="bp">self</span><span class="o">.</span><span
class="n">metadata</span><span class="o">.</span><span class="n">schema</span>
+
+ <span class="c1"># Verify schemas are all equal</span>
+ <span class="k">for</span> <span class="n">piece</span> <span
class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span
class="n">pieces</span><span class="p">:</span>
+ <span class="n">file_metadata</span> <span class="o">=</span>
<span class="n">piece</span><span class="o">.</span><span
class="n">get_metadata</span><span class="p">(</span><span
class="n">open_file</span><span class="p">)</span>
+ <span class="k">if</span> <span class="ow">not</span> <span
class="bp">self</span><span class="o">.</span><span
class="n">schema</span><span class="o">.</span><span
class="n">equals</span><span class="p">(</span><span
class="n">file_metadata</span><span class="o">.</span><span
class="n">schema</span><span class="p">):</span>
+ <span class="k">raise</span> <span
class="ne">ValueError</span><span class="p">(</span><span
class="s1">'Schema in </span><span class="si">{0!s}</span><span class="s1">
was different. '</span>
+ <span class="s1">'</span><span
class="si">{1!s}</span><span class="s1"> vs </span><span
class="si">{2!s}</span><span class="s1">'</span>
+ <span class="o">.</span><span
class="n">format</span><span class="p">(</span><span
class="n">piece</span><span class="p">,</span> <span
class="n">file_metadata</span><span class="o">.</span><span
class="n">schema</span><span class="p">,</span>
+ <span class="bp">self</span><span
class="o">.</span><span class="n">schema</span><span class="p">))</span>
+
+ <span class="k">def</span> <span class="nf">read</span><span
class="p">(</span><span class="bp">self</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">nthreads</span><span class="o">=</span><span class="mi">1</span><span
class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Read multiple Parquet files as a single
pyarrow.Table</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> columns : List[str]</span>
+<span class="sd"> Names of columns to read from the file</span>
+<span class="sd"> nthreads : int, default 1</span>
+<span class="sd"> Number of columns to read in parallel. Requires
that the underlying</span>
+<span class="sd"> file source is threadsafe</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> pyarrow.Table</span>
+<span class="sd"> Content of the file as a table (of columns)</span>
+<span class="sd"> """</span>
+ <span class="n">open_file</span> <span class="o">=</span> <span
class="bp">self</span><span class="o">.</span><span
class="n">_get_open_file_func</span><span class="p">()</span>
+
+ <span class="n">tables</span> <span class="o">=</span> <span
class="p">[]</span>
+ <span class="k">for</span> <span class="n">piece</span> <span
class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span
class="n">pieces</span><span class="p">:</span>
+ <span class="n">table</span> <span class="o">=</span> <span
class="n">piece</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">nthreads</span><span class="o">=</span><span
class="n">nthreads</span><span class="p">,</span>
+ <span class="n">partitions</span><span
class="o">=</span><span class="bp">self</span><span class="o">.</span><span
class="n">partitions</span><span class="p">,</span>
+ <span class="n">open_file_func</span><span
class="o">=</span><span class="n">open_file</span><span class="p">)</span>
+ <span class="n">tables</span><span class="o">.</span><span
class="n">append</span><span class="p">(</span><span
class="n">table</span><span class="p">)</span>
+
+ <span class="n">all_data</span> <span class="o">=</span> <span
class="n">_table</span><span class="o">.</span><span
class="n">concat_tables</span><span class="p">(</span><span
class="n">tables</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">all_data</span>
+
+ <span class="k">def</span> <span
class="nf">_get_open_file_func</span><span class="p">(</span><span
class="bp">self</span><span class="p">):</span>
+ <span class="k">if</span> <span class="bp">self</span><span
class="o">.</span><span class="n">fs</span> <span class="ow">is</span> <span
class="kc">None</span> <span class="ow">or</span> <span
class="nb">isinstance</span><span class="p">(</span><span
class="bp">self</span><span class="o">.</span><span class="n">fs</span><span
class="p">,</span> <span class="n">LocalFilesystem</span><span
class="p">):</span>
+ <span class="k">def</span> <span class="nf">open_file</span><span
class="p">(</span><span class="n">path</span><span class="p">,</span> <span
class="n">meta</span><span class="o">=</span><span class="kc">None</span><span
class="p">):</span>
+ <span class="k">return</span> <span
class="n">ParquetFile</span><span class="p">(</span><span
class="n">path</span><span class="p">,</span> <span
class="n">metadata</span><span class="o">=</span><span
class="n">meta</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">def</span> <span class="nf">open_file</span><span
class="p">(</span><span class="n">path</span><span class="p">,</span> <span
class="n">meta</span><span class="o">=</span><span class="kc">None</span><span
class="p">):</span>
+ <span class="k">return</span> <span
class="n">ParquetFile</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">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="s1">'rb'</span><span class="p">),</span>
+ <span class="n">metadata</span><span
class="o">=</span><span class="n">meta</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">open_file</span></div>
+
+
+<span class="k">def</span> <span class="nf">_make_manifest</span><span
class="p">(</span><span class="n">path_or_paths</span><span class="p">,</span>
<span class="n">fs</span><span class="p">,</span> <span
class="n">pathsep</span><span class="o">=</span><span
class="s1">'/'</span><span class="p">):</span>
+ <span class="n">partitions</span> <span class="o">=</span> <span
class="kc">None</span>
+ <span class="n">metadata_path</span> <span class="o">=</span> <span
class="kc">None</span>
+
+ <span class="k">if</span> <span class="nb">len</span><span
class="p">(</span><span class="n">path_or_paths</span><span class="p">)</span>
<span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
+ <span class="c1"># Dask passes a directory as a list of length 1</span>
+ <span class="n">path_or_paths</span> <span class="o">=</span> <span
class="n">path_or_paths</span><span class="p">[</span><span
class="mi">0</span><span class="p">]</span>
+
+ <span class="k">if</span> <span class="n">is_string</span><span
class="p">(</span><span class="n">path_or_paths</span><span class="p">)</span>
<span class="ow">and</span> <span class="n">fs</span><span
class="o">.</span><span class="n">isdir</span><span class="p">(</span><span
class="n">path_or_paths</span><span class="p">):</span>
+ <span class="n">manifest</span> <span class="o">=</span> <span
class="n">ParquetManifest</span><span class="p">(</span><span
class="n">path_or_paths</span><span class="p">,</span> <span
class="n">filesystem</span><span class="o">=</span><span
class="n">fs</span><span class="p">,</span>
+ <span class="n">pathsep</span><span
class="o">=</span><span class="n">pathsep</span><span class="p">)</span>
+ <span class="n">metadata_path</span> <span class="o">=</span> <span
class="n">manifest</span><span class="o">.</span><span
class="n">metadata_path</span>
+ <span class="n">pieces</span> <span class="o">=</span> <span
class="n">manifest</span><span class="o">.</span><span class="n">pieces</span>
+ <span class="n">partitions</span> <span class="o">=</span> <span
class="n">manifest</span><span class="o">.</span><span
class="n">partitions</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">if</span> <span class="ow">not</span> <span
class="nb">isinstance</span><span class="p">(</span><span
class="n">path_or_paths</span><span class="p">,</span> <span
class="nb">list</span><span class="p">):</span>
+ <span class="n">path_or_paths</span> <span class="o">=</span>
<span class="p">[</span><span class="n">path_or_paths</span><span
class="p">]</span>
+
+ <span class="c1"># List of paths</span>
+ <span class="k">if</span> <span class="nb">len</span><span
class="p">(</span><span class="n">path_or_paths</span><span class="p">)</span>
<span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
+ <span class="k">raise</span> <span
class="ne">ValueError</span><span class="p">(</span><span class="s1">'Must
pass at least one file path'</span><span class="p">)</span>
+
+ <span class="n">pieces</span> <span class="o">=</span> <span
class="p">[]</span>
+ <span class="k">for</span> <span class="n">path</span> <span
class="ow">in</span> <span class="n">path_or_paths</span><span
class="p">:</span>
+ <span class="k">if</span> <span class="ow">not</span> <span
class="n">fs</span><span class="o">.</span><span class="n">isfile</span><span
class="p">(</span><span class="n">path</span><span class="p">):</span>
+ <span class="k">raise</span> <span
class="ne">IOError</span><span class="p">(</span><span class="s1">'Passed
non-file path: </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">path</span><span
class="p">))</span>
+ <span class="n">piece</span> <span class="o">=</span> <span
class="n">ParquetDatasetPiece</span><span class="p">(</span><span
class="n">path</span><span class="p">)</span>
+ <span class="n">pieces</span><span class="o">.</span><span
class="n">append</span><span class="p">(</span><span
class="n">piece</span><span class="p">)</span>
+
+ <span class="k">return</span> <span class="n">pieces</span><span
class="p">,</span> <span class="n">partitions</span><span class="p">,</span>
<span class="n">metadata_path</span>
+
+
+<div class="viewcode-block" id="read_table"><a class="viewcode-back"
href="../../generated/pyarrow.parquet.read_table.html#pyarrow.parquet.read_table">[docs]</a><span
class="k">def</span> <span class="nf">read_table</span><span
class="p">(</span><span class="n">source</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">nthreads</span><span class="o">=</span><span class="mi">1</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="sd">"""</span>
+<span class="sd"> Read a Table from Parquet format</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> source: str or pyarrow.io.NativeFile</span>
+<span class="sd"> Location of Parquet dataset. If a string passed, can
be a single file</span>
+<span class="sd"> name or directory name. For passing Python file
objects or byte</span>
+<span class="sd"> buffers, see pyarrow.io.PythonFileInterface or
pyarrow.io.BufferReader.</span>
+<span class="sd"> columns: list</span>
+<span class="sd"> If not None, only these columns will be read from the
file.</span>
+<span class="sd"> nthreads : int, default 1</span>
+<span class="sd"> Number of columns to read in parallel. Requires that
the underlying</span>
+<span class="sd"> file source is threadsafe</span>
+<span class="sd"> metadata : FileMetaData</span>
+<span class="sd"> If separately computed</span>
+
+<span class="sd"> Returns</span>
+<span class="sd"> -------</span>
+<span class="sd"> pyarrow.Table</span>
+<span class="sd"> Content of the file as a table (of columns)</span>
+<span class="sd"> """</span>
+ <span class="k">if</span> <span class="n">is_string</span><span
class="p">(</span><span class="n">source</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">if</span> <span class="n">fs</span><span
class="o">.</span><span class="n">isdir</span><span class="p">(</span><span
class="n">source</span><span class="p">):</span>
+ <span class="k">return</span> <span class="n">fs</span><span
class="o">.</span><span class="n">read_parquet</span><span
class="p">(</span><span class="n">source</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">metadata</span><span
class="o">=</span><span class="n">metadata</span><span class="p">)</span>
+
+ <span class="n">pf</span> <span class="o">=</span> <span
class="n">ParquetFile</span><span class="p">(</span><span
class="n">source</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="k">return</span> <span class="n">pf</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">nthreads</span><span class="o">=</span><span
class="n">nthreads</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="write_table"><a class="viewcode-back"
href="../../generated/pyarrow.parquet.write_table.html#pyarrow.parquet.write_table">[docs]</a><span
class="k">def</span> <span class="nf">write_table</span><span
class="p">(</span><span class="n">table</span><span class="p">,</span> <span
class="n">where</span><span class="p">,</span> <span
class="n">row_group_size</span><span class="o">=</span><span
class="kc">None</span><span class="p">,</span> <span
class="n">version</span><span class="o">=</span><span
class="s1">'1.0'</span><span class="p">,</span>
+ <span class="n">use_dictionary</span><span
class="o">=</span><span class="kc">True</span><span class="p">,</span> <span
class="n">compression</span><span class="o">=</span><span
class="s1">'snappy'</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"> Write a Table to Parquet format</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> table : pyarrow.Table</span>
+<span class="sd"> where: string or pyarrow.io.NativeFile</span>
+<span class="sd"> row_group_size : int, default None</span>
+<span class="sd"> The maximum number of rows in each Parquet RowGroup.
As a default,</span>
+<span class="sd"> we will write a single RowGroup per file.</span>
+<span class="sd"> version : {"1.0", "2.0"}, default
"1.0"</span>
+<span class="sd"> The Parquet format version, defaults to 1.0</span>
+<span class="sd"> use_dictionary : bool or list</span>
+<span class="sd"> Specify if we should use dictionary encoding in
general or only for</span>
+<span class="sd"> some columns.</span>
+<span class="sd"> compression : str or dict</span>
+<span class="sd"> Specify the compression codec, either on a general
basis or per-column.</span>
+<span class="sd"> """</span>
+ <span class="n">row_group_size</span> <span class="o">=</span> <span
class="n">kwargs</span><span class="o">.</span><span class="n">get</span><span
class="p">(</span><span class="s1">'chunk_size'</span><span
class="p">,</span> <span class="n">row_group_size</span><span class="p">)</span>
+ <span class="n">writer</span> <span class="o">=</span> <span
class="n">ParquetWriter</span><span class="p">(</span><span
class="n">where</span><span class="p">,</span> <span
class="n">table</span><span class="o">.</span><span
class="n">schema</span><span class="p">,</span>
+ <span class="n">use_dictionary</span><span
class="o">=</span><span class="n">use_dictionary</span><span class="p">,</span>
+ <span class="n">compression</span><span
class="o">=</span><span class="n">compression</span><span class="p">,</span>
+ <span class="n">version</span><span
class="o">=</span><span class="n">version</span><span class="p">)</span>
+ <span class="n">writer</span><span class="o">.</span><span
class="n">write_table</span><span class="p">(</span><span
class="n">table</span><span class="p">,</span> <span
class="n">row_group_size</span><span class="o">=</span><span
class="n">row_group_size</span><span class="p">)</span>
+ <span class="n">writer</span><span class="o">.</span><span
class="n">close</span><span class="p">()</span></div>
+
+
+<div class="viewcode-block" id="write_metadata"><a class="viewcode-back"
href="../../generated/pyarrow.parquet.write_metadata.html#pyarrow.parquet.write_metadata">[docs]</a><span
class="k">def</span> <span class="nf">write_metadata</span><span
class="p">(</span><span class="n">schema</span><span class="p">,</span> <span
class="n">where</span><span class="p">,</span> <span
class="n">version</span><span class="o">=</span><span
class="s1">'1.0'</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Write metadata-only Parquet file from schema</span>
+
+<span class="sd"> Parameters</span>
+<span class="sd"> ----------</span>
+<span class="sd"> schema : pyarrow.Schema</span>
+<span class="sd"> where: string or pyarrow.io.NativeFile</span>
+<span class="sd"> version : {"1.0", "2.0"}, default
"1.0"</span>
+<span class="sd"> The Parquet format version, defaults to 1.0</span>
+<span class="sd"> """</span>
+ <span class="n">writer</span> <span class="o">=</span> <span
class="n">ParquetWriter</span><span class="p">(</span><span
class="n">where</span><span class="p">,</span> <span
class="n">schema</span><span class="p">,</span> <span
class="n">version</span><span class="o">=</span><span
class="n">version</span><span class="p">)</span>
+ <span class="n">writer</span><span class="o">.</span><span
class="n">close</span><span class="p">()</span></div>
+</pre></div>
+
+ </div>
+ <div class="articleComments">
+
+ </div>
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+ © Copyright 2016 Apache Software Foundation.
+
+ </p>
+ </div>
+ Built with <a href="http://sphinx-doc.org/";>Sphinx</a> using a <a
href="https://github.com/snide/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">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT:'../../',
+ VERSION:'',
+ COLLAPSE_INDEX:false,
+ FILE_SUFFIX:'.html',
+ HAS_SOURCE: true,
+ SOURCELINK_SUFFIX: '.txt'
+ };
+ </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="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML";></script>
+
+
+
+
+
+ <script type="text/javascript" src="../../_static/js/theme.js"></script>
+
+
+
+
+ <script type="text/javascript">
+ jQuery(function () {
+ SphinxRtdTheme.StickyNav.enable();
+ });
+ </script>
+
+
+</body>
+</html>
\ No newline at end of file
