blob: 2c924a85dd9dd6a6bc208c161d05b612082f12e8 [file] [log] [blame]
<!DOCTYPE html>
<!-- Generated by pkgdown: do not edit by hand --><html lang="en-US"><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8"><meta charset="utf-8"><meta http-equiv="X-UA-Compatible" content="IE=edge"><meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"><title>Add the data filename as a column — add_filename • Arrow R Package</title><!-- favicons --><link rel="icon" type="image/png" sizes="96x96" href="../favicon-96x96.png"><link rel="icon" type="”image/svg+xml”" href="../favicon.svg"><link rel="apple-touch-icon" sizes="180x180" href="../apple-touch-icon.png"><link rel="icon" sizes="any" href="../favicon.ico"><link rel="manifest" href="../site.webmanifest"><script src="../deps/jquery-3.6.0/jquery-3.6.0.min.js"></script><meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"><link href="../deps/bootstrap-5.3.1/bootstrap.min.css" rel="stylesheet"><script src="../deps/bootstrap-5.3.1/bootstrap.bundle.min.js"></script><link href="../deps/font-awesome-6.5.2/css/all.min.css" rel="stylesheet"><link href="../deps/font-awesome-6.5.2/css/v4-shims.min.css" rel="stylesheet"><script src="../deps/headroom-0.11.0/headroom.min.js"></script><script src="../deps/headroom-0.11.0/jQuery.headroom.min.js"></script><script src="../deps/bootstrap-toc-1.0.1/bootstrap-toc.min.js"></script><script src="../deps/clipboard.js-2.0.11/clipboard.min.js"></script><script src="../deps/search-1.0.0/autocomplete.jquery.min.js"></script><script src="../deps/search-1.0.0/fuse.min.js"></script><script src="../deps/search-1.0.0/mark.min.js"></script><!-- pkgdown --><script src="../pkgdown.js"></script><link href="../extra.css" rel="stylesheet"><meta property="og:title" content="Add the data filename as a column — add_filename"><meta name="description" content="This function only exists inside arrow dplyr queries, and it only is
valid when querying on a FileSystemDataset."><meta property="og:description" content="This function only exists inside arrow dplyr queries, and it only is
valid when querying on a FileSystemDataset."><meta property="og:image" content="https://arrow.apache.org/img/arrow-logo_horizontal_black-txt_white-bg.png"><meta property="og:image:alt" content="Apache Arrow logo, displaying the triple chevron image adjacent to the text"><!-- Matomo --><script>
var _paq = window._paq = window._paq || [];
/* tracker methods like "setCustomDimension" should be called before "trackPageView" */
/* We explicitly disable cookie tracking to avoid privacy issues */
_paq.push(['disableCookies']);
_paq.push(['trackPageView']);
_paq.push(['enableLinkTracking']);
(function() {
var u="https://analytics.apache.org/";
_paq.push(['setTrackerUrl', u+'matomo.php']);
_paq.push(['setSiteId', '20']);
var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0];
g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s);
})();
</script><!-- End Matomo Code --><!-- Kapa AI --><script async src="https://widget.kapa.ai/kapa-widget.bundle.js" data-website-id="9db461d5-ac77-4b3f-a5c5-75efa78339d2" data-project-name="Apache Arrow" data-project-color="#000000" data-project-logo="https://arrow.apache.org/img/arrow-logo_chevrons_white-txt_black-bg.png" data-modal-disclaimer="This is a custom LLM with access to all of [Arrow documentation](https://arrow.apache.org/docs/). If you want an R-specific answer, please mention this in your question." data-consent-required="true" data-user-analytics-cookie-enabled="false" data-consent-screen-disclaimer="By clicking &quot;I agree, let's chat&quot;, you consent to the use of the AI assistant in accordance with kapa.ai's [Privacy Policy](https://www.kapa.ai/content/privacy-policy). This service uses reCAPTCHA, which requires your consent to Google's [Privacy Policy](https://policies.google.com/privacy) and [Terms of Service](https://policies.google.com/terms). By proceeding, you explicitly agree to both kapa.ai's and Google's privacy policies."></script><!-- End Kapa AI --></head><body>
<a href="#main" class="visually-hidden-focusable">Skip to contents</a>
<nav class="navbar fixed-top navbar-dark navbar-expand-lg bg-black"><div class="container">
<a class="navbar-brand me-2" href="../index.html">Arrow R Package</a>
<span class="version">
<small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">22.0.0.9000</small>
</span>
<button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>
<div id="navbar" class="collapse navbar-collapse ms-3">
<ul class="navbar-nav me-auto"><li class="nav-item"><a class="nav-link" href="../articles/arrow.html">Get started</a></li>
<li class="active nav-item"><a class="nav-link" href="../reference/index.html">Reference</a></li>
<li class="nav-item dropdown">
<button class="nav-link dropdown-toggle" type="button" id="dropdown-articles" data-bs-toggle="dropdown" aria-expanded="false" aria-haspopup="true">Articles</button>
<ul class="dropdown-menu" aria-labelledby="dropdown-articles"><li><hr class="dropdown-divider"></li>
<li><h6 class="dropdown-header" data-toc-skip>Using the package</h6></li>
<li><a class="dropdown-item" href="../articles/read_write.html">Reading and writing data files</a></li>
<li><a class="dropdown-item" href="../articles/data_wrangling.html">Data analysis with dplyr syntax</a></li>
<li><a class="dropdown-item" href="../articles/dataset.html">Working with multi-file data sets</a></li>
<li><a class="dropdown-item" href="../articles/python.html">Integrating Arrow, Python, and R</a></li>
<li><a class="dropdown-item" href="../articles/fs.html">Using cloud storage (S3, GCS)</a></li>
<li><a class="dropdown-item" href="../articles/flight.html">Connecting to a Flight server</a></li>
<li><hr class="dropdown-divider"></li>
<li><h6 class="dropdown-header" data-toc-skip>Arrow concepts</h6></li>
<li><a class="dropdown-item" href="../articles/data_objects.html">Data objects</a></li>
<li><a class="dropdown-item" href="../articles/data_types.html">Data types</a></li>
<li><a class="dropdown-item" href="../articles/metadata.html">Metadata</a></li>
<li><hr class="dropdown-divider"></li>
<li><h6 class="dropdown-header" data-toc-skip>Installation</h6></li>
<li><a class="dropdown-item" href="../articles/install.html">Installing on Linux</a></li>
<li><a class="dropdown-item" href="../articles/install_nightly.html">Installing development versions</a></li>
<li><hr class="dropdown-divider"></li>
<li><a class="dropdown-item" href="../articles/index.html">More articles...</a></li>
</ul></li>
<li class="nav-item"><a class="nav-link" href="../news/index.html">Changelog</a></li>
</ul><form class="form-inline my-2 my-lg-0" role="search">
<input type="search" class="form-control me-sm-2" aria-label="Toggle navigation" name="search-input" data-search-index="../search.json" id="search-input" placeholder="" autocomplete="off"></form>
<ul class="navbar-nav"><li class="nav-item"><a class="external-link nav-link" href="https://github.com/apache/arrow/" aria-label="GitHub"><span class="fa fab fa-github fa-lg"></span></a></li>
</ul></div>
</div>
</nav><div class="container template-reference-topic">
<div class="row">
<main id="main" class="col-md-9"><div class="page-header">
<h1>Add the data filename as a column</h1>
<small class="dont-index">Source: <a href="https://github.com/apache/arrow/blob/main/r/R/dplyr-funcs-augmented.R" class="external-link"><code>R/dplyr-funcs-augmented.R</code></a></small>
<div class="d-none name"><code>add_filename.Rd</code></div>
</div>
<div class="ref-description section level2">
<p>This function only exists inside <code>arrow</code> <code>dplyr</code> queries, and it only is
valid when querying on a <code>FileSystemDataset</code>.</p>
</div>
<div class="section level2">
<h2 id="ref-usage">Usage<a class="anchor" aria-label="anchor" href="#ref-usage"></a></h2>
<div class="sourceCode"><pre class="sourceCode r"><code><span><span class="fu">add_filename</span><span class="op">(</span><span class="op">)</span></span></code></pre></div>
</div>
<div class="section level2">
<h2 id="value">Value<a class="anchor" aria-label="anchor" href="#value"></a></h2>
<p>A <code>FieldRef</code> <code><a href="Expression.html">Expression</a></code> that refers to the filename
augmented column.</p>
</div>
<div class="section level2">
<h2 id="details">Details<a class="anchor" aria-label="anchor" href="#details"></a></h2>
<p>To use filenames generated by this function in subsequent pipeline steps, you
must either call <code><a href="https://dplyr.tidyverse.org/reference/compute.html" class="external-link">compute()</a></code> or
<code><a href="https://dplyr.tidyverse.org/reference/compute.html" class="external-link">collect()</a></code> first. See Examples.</p>
</div>
<div class="section level2">
<h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-examples"></a></h2>
<div class="sourceCode"><pre class="sourceCode r"><code><span class="r-in"><span><span class="kw">if</span> <span class="op">(</span><span class="cn">FALSE</span><span class="op">)</span> <span class="op">{</span> <span class="co"># \dontrun{</span></span></span>
<span class="r-in"><span><span class="fu"><a href="open_dataset.html">open_dataset</a></span><span class="op">(</span><span class="st">"nyc-taxi"</span><span class="op">)</span> <span class="op">|&gt;</span> <span class="fu">mutate</span><span class="op">(</span></span></span>
<span class="r-in"><span> file <span class="op">=</span></span></span>
<span class="r-in"><span> <span class="fu">add_filename</span><span class="op">(</span><span class="op">)</span></span></span>
<span class="r-in"><span><span class="op">)</span></span></span>
<span class="r-in"><span></span></span>
<span class="r-in"><span><span class="co"># To use a verb like mutate() with add_filename() we need to first call</span></span></span>
<span class="r-in"><span><span class="co"># compute()</span></span></span>
<span class="r-in"><span><span class="fu"><a href="open_dataset.html">open_dataset</a></span><span class="op">(</span><span class="st">"nyc-taxi"</span><span class="op">)</span> <span class="op">|&gt;</span></span></span>
<span class="r-in"><span> <span class="fu">mutate</span><span class="op">(</span>file <span class="op">=</span> <span class="fu">add_filename</span><span class="op">(</span><span class="op">)</span><span class="op">)</span> <span class="op">|&gt;</span></span></span>
<span class="r-in"><span> <span class="fu">compute</span><span class="op">(</span><span class="op">)</span> <span class="op">|&gt;</span></span></span>
<span class="r-in"><span> <span class="fu">mutate</span><span class="op">(</span>filename_length <span class="op">=</span> <span class="fu"><a href="https://rdrr.io/r/base/nchar.html" class="external-link">nchar</a></span><span class="op">(</span><span class="va">file</span><span class="op">)</span><span class="op">)</span></span></span>
<span class="r-in"><span><span class="op">}</span> <span class="co"># }</span></span></span>
<span class="r-in"><span></span></span>
</code></pre></div>
</div>
</main><aside class="col-md-3"><nav id="toc" aria-label="Table of contents"><h2>On this page</h2>
</nav></aside></div>
<footer><div class="pkgdown-footer-left">
<p><a href="https://arrow.apache.org/docs/r/versions.html">Older versions of these docs</a></p>
</div>
<div class="pkgdown-footer-right">
<p>Site built with <a href="https://pkgdown.r-lib.org/" class="external-link">pkgdown</a> 2.1.3.</p>
</div>
</footer></div>
</body></html>