diff --git a/404.html b/404.html
index 288f57b..31e3372 100644
--- a/404.html
+++ b/404.html
@@ -23,7 +23,7 @@
 
     <a class="navbar-brand me-2" href="https://nanoparquet.r-lib.org/index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/LICENSE-text.html b/LICENSE-text.html
index a67ef3c..3d7221a 100644
--- a/LICENSE-text.html
+++ b/LICENSE-text.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/articles/benchmarks.html b/articles/benchmarks.html
index ec2b0f0..756dbb5 100644
--- a/articles/benchmarks.html
+++ b/articles/benchmarks.html
@@ -25,7 +25,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -117,23 +117,23 @@ <h1>Benchmarks</h1>
 <span>  <span class="fu"><a href="https://gt.rstudio.com/reference/fmt_integer.html" class="external-link">fmt_integer</a></span><span class="op">(</span><span class="op">)</span> <span class="op">|&gt;</span></span>
 <span>  <span class="fu"><a href="https://gt.rstudio.com/reference/fmt_bytes.html" class="external-link">fmt_bytes</a></span><span class="op">(</span>columns <span class="op">=</span> <span class="st">"size in memory"</span><span class="op">)</span></span></code></pre></div>
 </details><div class="cell-output-display">
-<div id="feueueehtr" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
-<style>#feueueehtr table {
+<div id="mwcjfaymaz" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
+<style>#mwcjfaymaz table {
   font-family: system-ui, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
   -webkit-font-smoothing: antialiased;
   -moz-osx-font-smoothing: grayscale;
 }
 
-#feueueehtr thead, #feueueehtr tbody, #feueueehtr tfoot, #feueueehtr tr, #feueueehtr td, #feueueehtr th {
+#mwcjfaymaz thead, #mwcjfaymaz tbody, #mwcjfaymaz tfoot, #mwcjfaymaz tr, #mwcjfaymaz td, #mwcjfaymaz th {
   border-style: none;
 }
 
-#feueueehtr p {
+#mwcjfaymaz p {
   margin: 0;
   padding: 0;
 }
 
-#feueueehtr .gt_table {
+#mwcjfaymaz .gt_table {
   display: table;
   border-collapse: collapse;
   line-height: normal;
@@ -159,12 +159,12 @@ <h1>Benchmarks</h1>
   border-left-color: #D3D3D3;
 }
 
-#feueueehtr .gt_caption {
+#mwcjfaymaz .gt_caption {
   padding-top: 4px;
   padding-bottom: 4px;
 }
 
-#feueueehtr .gt_title {
+#mwcjfaymaz .gt_title {
   color: #333333;
   font-size: 125%;
   font-weight: initial;
@@ -176,7 +176,7 @@ <h1>Benchmarks</h1>
   border-bottom-width: 0;
 }
 
-#feueueehtr .gt_subtitle {
+#mwcjfaymaz .gt_subtitle {
   color: #333333;
   font-size: 85%;
   font-weight: initial;
@@ -188,7 +188,7 @@ <h1>Benchmarks</h1>
   border-top-width: 0;
 }
 
-#feueueehtr .gt_heading {
+#mwcjfaymaz .gt_heading {
   background-color: #FFFFFF;
   text-align: center;
   border-bottom-color: #FFFFFF;
@@ -200,13 +200,13 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#feueueehtr .gt_bottom_border {
+#mwcjfaymaz .gt_bottom_border {
   border-bottom-style: solid;
   border-bottom-width: 2px;
   border-bottom-color: #D3D3D3;
 }
 
-#feueueehtr .gt_col_headings {
+#mwcjfaymaz .gt_col_headings {
   border-top-style: solid;
   border-top-width: 2px;
   border-top-color: #D3D3D3;
@@ -221,7 +221,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#feueueehtr .gt_col_heading {
+#mwcjfaymaz .gt_col_heading {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -241,7 +241,7 @@ <h1>Benchmarks</h1>
   overflow-x: hidden;
 }
 
-#feueueehtr .gt_column_spanner_outer {
+#mwcjfaymaz .gt_column_spanner_outer {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -253,15 +253,15 @@ <h1>Benchmarks</h1>
   padding-right: 4px;
 }
 
-#feueueehtr .gt_column_spanner_outer:first-child {
+#mwcjfaymaz .gt_column_spanner_outer:first-child {
   padding-left: 0;
 }
 
-#feueueehtr .gt_column_spanner_outer:last-child {
+#mwcjfaymaz .gt_column_spanner_outer:last-child {
   padding-right: 0;
 }
 
-#feueueehtr .gt_column_spanner {
+#mwcjfaymaz .gt_column_spanner {
   border-bottom-style: solid;
   border-bottom-width: 2px;
   border-bottom-color: #D3D3D3;
@@ -273,11 +273,11 @@ <h1>Benchmarks</h1>
   width: 100%;
 }
 
-#feueueehtr .gt_spanner_row {
+#mwcjfaymaz .gt_spanner_row {
   border-bottom-style: hidden;
 }
 
-#feueueehtr .gt_group_heading {
+#mwcjfaymaz .gt_group_heading {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -303,7 +303,7 @@ <h1>Benchmarks</h1>
   text-align: left;
 }
 
-#feueueehtr .gt_empty_group_heading {
+#mwcjfaymaz .gt_empty_group_heading {
   padding: 0.5px;
   color: #333333;
   background-color: #FFFFFF;
@@ -318,15 +318,15 @@ <h1>Benchmarks</h1>
   vertical-align: middle;
 }
 
-#feueueehtr .gt_from_md > :first-child {
+#mwcjfaymaz .gt_from_md > :first-child {
   margin-top: 0;
 }
 
-#feueueehtr .gt_from_md > :last-child {
+#mwcjfaymaz .gt_from_md > :last-child {
   margin-bottom: 0;
 }
 
-#feueueehtr .gt_row {
+#mwcjfaymaz .gt_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -345,7 +345,7 @@ <h1>Benchmarks</h1>
   overflow-x: hidden;
 }
 
-#feueueehtr .gt_stub {
+#mwcjfaymaz .gt_stub {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -358,7 +358,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#feueueehtr .gt_stub_row_group {
+#mwcjfaymaz .gt_stub_row_group {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -372,15 +372,15 @@ <h1>Benchmarks</h1>
   vertical-align: top;
 }
 
-#feueueehtr .gt_row_group_first td {
+#mwcjfaymaz .gt_row_group_first td {
   border-top-width: 2px;
 }
 
-#feueueehtr .gt_row_group_first th {
+#mwcjfaymaz .gt_row_group_first th {
   border-top-width: 2px;
 }
 
-#feueueehtr .gt_summary_row {
+#mwcjfaymaz .gt_summary_row {
   color: #333333;
   background-color: #FFFFFF;
   text-transform: inherit;
@@ -390,16 +390,16 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#feueueehtr .gt_first_summary_row {
+#mwcjfaymaz .gt_first_summary_row {
   border-top-style: solid;
   border-top-color: #D3D3D3;
 }
 
-#feueueehtr .gt_first_summary_row.thick {
+#mwcjfaymaz .gt_first_summary_row.thick {
   border-top-width: 2px;
 }
 
-#feueueehtr .gt_last_summary_row {
+#mwcjfaymaz .gt_last_summary_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -409,7 +409,7 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#feueueehtr .gt_grand_summary_row {
+#mwcjfaymaz .gt_grand_summary_row {
   color: #333333;
   background-color: #FFFFFF;
   text-transform: inherit;
@@ -419,7 +419,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#feueueehtr .gt_first_grand_summary_row {
+#mwcjfaymaz .gt_first_grand_summary_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -429,7 +429,7 @@ <h1>Benchmarks</h1>
   border-top-color: #D3D3D3;
 }
 
-#feueueehtr .gt_last_grand_summary_row_top {
+#mwcjfaymaz .gt_last_grand_summary_row_top {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -439,11 +439,11 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#feueueehtr .gt_striped {
+#mwcjfaymaz .gt_striped {
   background-color: rgba(128, 128, 128, 0.05);
 }
 
-#feueueehtr .gt_table_body {
+#mwcjfaymaz .gt_table_body {
   border-top-style: solid;
   border-top-width: 2px;
   border-top-color: #D3D3D3;
@@ -452,7 +452,7 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#feueueehtr .gt_footnotes {
+#mwcjfaymaz .gt_footnotes {
   color: #333333;
   background-color: #FFFFFF;
   border-bottom-style: none;
@@ -466,7 +466,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#feueueehtr .gt_footnote {
+#mwcjfaymaz .gt_footnote {
   margin: 0px;
   font-size: 90%;
   padding-top: 4px;
@@ -475,7 +475,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#feueueehtr .gt_sourcenotes {
+#mwcjfaymaz .gt_sourcenotes {
   color: #333333;
   background-color: #FFFFFF;
   border-bottom-style: none;
@@ -489,7 +489,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#feueueehtr .gt_sourcenote {
+#mwcjfaymaz .gt_sourcenote {
   font-size: 90%;
   padding-top: 4px;
   padding-bottom: 4px;
@@ -497,72 +497,72 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#feueueehtr .gt_left {
+#mwcjfaymaz .gt_left {
   text-align: left;
 }
 
-#feueueehtr .gt_center {
+#mwcjfaymaz .gt_center {
   text-align: center;
 }
 
-#feueueehtr .gt_right {
+#mwcjfaymaz .gt_right {
   text-align: right;
   font-variant-numeric: tabular-nums;
 }
 
-#feueueehtr .gt_font_normal {
+#mwcjfaymaz .gt_font_normal {
   font-weight: normal;
 }
 
-#feueueehtr .gt_font_bold {
+#mwcjfaymaz .gt_font_bold {
   font-weight: bold;
 }
 
-#feueueehtr .gt_font_italic {
+#mwcjfaymaz .gt_font_italic {
   font-style: italic;
 }
 
-#feueueehtr .gt_super {
+#mwcjfaymaz .gt_super {
   font-size: 65%;
 }
 
-#feueueehtr .gt_footnote_marks {
+#mwcjfaymaz .gt_footnote_marks {
   font-size: 75%;
   vertical-align: 0.4em;
   position: initial;
 }
 
-#feueueehtr .gt_asterisk {
+#mwcjfaymaz .gt_asterisk {
   font-size: 100%;
   vertical-align: 0;
 }
 
-#feueueehtr .gt_indent_1 {
+#mwcjfaymaz .gt_indent_1 {
   text-indent: 5px;
 }
 
-#feueueehtr .gt_indent_2 {
+#mwcjfaymaz .gt_indent_2 {
   text-indent: 10px;
 }
 
-#feueueehtr .gt_indent_3 {
+#mwcjfaymaz .gt_indent_3 {
   text-indent: 15px;
 }
 
-#feueueehtr .gt_indent_4 {
+#mwcjfaymaz .gt_indent_4 {
   text-indent: 20px;
 }
 
-#feueueehtr .gt_indent_5 {
+#mwcjfaymaz .gt_indent_5 {
   text-indent: 25px;
 }
 
-#feueueehtr .katex-display {
+#mwcjfaymaz .katex-display {
   display: inline-flex !important;
   margin-bottom: 0.75em !important;
 }
 
-#feueueehtr div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
+#mwcjfaymaz div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
   height: 0px !important;
 }
 </style>
@@ -721,23 +721,23 @@ <h1>Benchmarks</h1>
 <span>  <span class="fu"><a href="https://gt.rstudio.com/reference/fmt_bytes.html" class="external-link">fmt_bytes</a></span><span class="op">(</span>columns <span class="op">=</span> <span class="va">memory</span><span class="op">)</span> <span class="op">|&gt;</span></span>
 <span>  <span class="fu"><a href="https://jthomasmock.github.io/gtExtras/reference/gt_plt_bar.html" class="external-link">gt_plt_bar</a></span><span class="op">(</span>column <span class="op">=</span> <span class="va">`speedup from CSV`</span><span class="op">)</span></span></code></pre></div>
 </details><div class="cell-output-display">
-<div id="sefsotesmt" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
-<style>#sefsotesmt table {
+<div id="qsayfcwvmn" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
+<style>#qsayfcwvmn table {
   font-family: system-ui, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
   -webkit-font-smoothing: antialiased;
   -moz-osx-font-smoothing: grayscale;
 }
 
-#sefsotesmt thead, #sefsotesmt tbody, #sefsotesmt tfoot, #sefsotesmt tr, #sefsotesmt td, #sefsotesmt th {
+#qsayfcwvmn thead, #qsayfcwvmn tbody, #qsayfcwvmn tfoot, #qsayfcwvmn tr, #qsayfcwvmn td, #qsayfcwvmn th {
   border-style: none;
 }
 
-#sefsotesmt p {
+#qsayfcwvmn p {
   margin: 0;
   padding: 0;
 }
 
-#sefsotesmt .gt_table {
+#qsayfcwvmn .gt_table {
   display: table;
   border-collapse: collapse;
   line-height: normal;
@@ -763,12 +763,12 @@ <h1>Benchmarks</h1>
   border-left-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_caption {
+#qsayfcwvmn .gt_caption {
   padding-top: 4px;
   padding-bottom: 4px;
 }
 
-#sefsotesmt .gt_title {
+#qsayfcwvmn .gt_title {
   color: #333333;
   font-size: 125%;
   font-weight: initial;
@@ -780,7 +780,7 @@ <h1>Benchmarks</h1>
   border-bottom-width: 0;
 }
 
-#sefsotesmt .gt_subtitle {
+#qsayfcwvmn .gt_subtitle {
   color: #333333;
   font-size: 85%;
   font-weight: initial;
@@ -792,7 +792,7 @@ <h1>Benchmarks</h1>
   border-top-width: 0;
 }
 
-#sefsotesmt .gt_heading {
+#qsayfcwvmn .gt_heading {
   background-color: #FFFFFF;
   text-align: center;
   border-bottom-color: #FFFFFF;
@@ -804,13 +804,13 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_bottom_border {
+#qsayfcwvmn .gt_bottom_border {
   border-bottom-style: solid;
   border-bottom-width: 2px;
   border-bottom-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_col_headings {
+#qsayfcwvmn .gt_col_headings {
   border-top-style: solid;
   border-top-width: 2px;
   border-top-color: #D3D3D3;
@@ -825,7 +825,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_col_heading {
+#qsayfcwvmn .gt_col_heading {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -845,7 +845,7 @@ <h1>Benchmarks</h1>
   overflow-x: hidden;
 }
 
-#sefsotesmt .gt_column_spanner_outer {
+#qsayfcwvmn .gt_column_spanner_outer {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -857,15 +857,15 @@ <h1>Benchmarks</h1>
   padding-right: 4px;
 }
 
-#sefsotesmt .gt_column_spanner_outer:first-child {
+#qsayfcwvmn .gt_column_spanner_outer:first-child {
   padding-left: 0;
 }
 
-#sefsotesmt .gt_column_spanner_outer:last-child {
+#qsayfcwvmn .gt_column_spanner_outer:last-child {
   padding-right: 0;
 }
 
-#sefsotesmt .gt_column_spanner {
+#qsayfcwvmn .gt_column_spanner {
   border-bottom-style: solid;
   border-bottom-width: 2px;
   border-bottom-color: #D3D3D3;
@@ -877,11 +877,11 @@ <h1>Benchmarks</h1>
   width: 100%;
 }
 
-#sefsotesmt .gt_spanner_row {
+#qsayfcwvmn .gt_spanner_row {
   border-bottom-style: hidden;
 }
 
-#sefsotesmt .gt_group_heading {
+#qsayfcwvmn .gt_group_heading {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -907,7 +907,7 @@ <h1>Benchmarks</h1>
   text-align: left;
 }
 
-#sefsotesmt .gt_empty_group_heading {
+#qsayfcwvmn .gt_empty_group_heading {
   padding: 0.5px;
   color: #333333;
   background-color: #FFFFFF;
@@ -922,15 +922,15 @@ <h1>Benchmarks</h1>
   vertical-align: middle;
 }
 
-#sefsotesmt .gt_from_md > :first-child {
+#qsayfcwvmn .gt_from_md > :first-child {
   margin-top: 0;
 }
 
-#sefsotesmt .gt_from_md > :last-child {
+#qsayfcwvmn .gt_from_md > :last-child {
   margin-bottom: 0;
 }
 
-#sefsotesmt .gt_row {
+#qsayfcwvmn .gt_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -949,7 +949,7 @@ <h1>Benchmarks</h1>
   overflow-x: hidden;
 }
 
-#sefsotesmt .gt_stub {
+#qsayfcwvmn .gt_stub {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -962,7 +962,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#sefsotesmt .gt_stub_row_group {
+#qsayfcwvmn .gt_stub_row_group {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -976,15 +976,15 @@ <h1>Benchmarks</h1>
   vertical-align: top;
 }
 
-#sefsotesmt .gt_row_group_first td {
+#qsayfcwvmn .gt_row_group_first td {
   border-top-width: 2px;
 }
 
-#sefsotesmt .gt_row_group_first th {
+#qsayfcwvmn .gt_row_group_first th {
   border-top-width: 2px;
 }
 
-#sefsotesmt .gt_summary_row {
+#qsayfcwvmn .gt_summary_row {
   color: #333333;
   background-color: #FFFFFF;
   text-transform: inherit;
@@ -994,16 +994,16 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#sefsotesmt .gt_first_summary_row {
+#qsayfcwvmn .gt_first_summary_row {
   border-top-style: solid;
   border-top-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_first_summary_row.thick {
+#qsayfcwvmn .gt_first_summary_row.thick {
   border-top-width: 2px;
 }
 
-#sefsotesmt .gt_last_summary_row {
+#qsayfcwvmn .gt_last_summary_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -1013,7 +1013,7 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_grand_summary_row {
+#qsayfcwvmn .gt_grand_summary_row {
   color: #333333;
   background-color: #FFFFFF;
   text-transform: inherit;
@@ -1023,7 +1023,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#sefsotesmt .gt_first_grand_summary_row {
+#qsayfcwvmn .gt_first_grand_summary_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -1033,7 +1033,7 @@ <h1>Benchmarks</h1>
   border-top-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_last_grand_summary_row_top {
+#qsayfcwvmn .gt_last_grand_summary_row_top {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -1043,11 +1043,11 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_striped {
+#qsayfcwvmn .gt_striped {
   background-color: rgba(128, 128, 128, 0.05);
 }
 
-#sefsotesmt .gt_table_body {
+#qsayfcwvmn .gt_table_body {
   border-top-style: solid;
   border-top-width: 2px;
   border-top-color: #D3D3D3;
@@ -1056,7 +1056,7 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_footnotes {
+#qsayfcwvmn .gt_footnotes {
   color: #333333;
   background-color: #FFFFFF;
   border-bottom-style: none;
@@ -1070,7 +1070,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_footnote {
+#qsayfcwvmn .gt_footnote {
   margin: 0px;
   font-size: 90%;
   padding-top: 4px;
@@ -1079,7 +1079,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#sefsotesmt .gt_sourcenotes {
+#qsayfcwvmn .gt_sourcenotes {
   color: #333333;
   background-color: #FFFFFF;
   border-bottom-style: none;
@@ -1093,7 +1093,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#sefsotesmt .gt_sourcenote {
+#qsayfcwvmn .gt_sourcenote {
   font-size: 90%;
   padding-top: 4px;
   padding-bottom: 4px;
@@ -1101,72 +1101,72 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#sefsotesmt .gt_left {
+#qsayfcwvmn .gt_left {
   text-align: left;
 }
 
-#sefsotesmt .gt_center {
+#qsayfcwvmn .gt_center {
   text-align: center;
 }
 
-#sefsotesmt .gt_right {
+#qsayfcwvmn .gt_right {
   text-align: right;
   font-variant-numeric: tabular-nums;
 }
 
-#sefsotesmt .gt_font_normal {
+#qsayfcwvmn .gt_font_normal {
   font-weight: normal;
 }
 
-#sefsotesmt .gt_font_bold {
+#qsayfcwvmn .gt_font_bold {
   font-weight: bold;
 }
 
-#sefsotesmt .gt_font_italic {
+#qsayfcwvmn .gt_font_italic {
   font-style: italic;
 }
 
-#sefsotesmt .gt_super {
+#qsayfcwvmn .gt_super {
   font-size: 65%;
 }
 
-#sefsotesmt .gt_footnote_marks {
+#qsayfcwvmn .gt_footnote_marks {
   font-size: 75%;
   vertical-align: 0.4em;
   position: initial;
 }
 
-#sefsotesmt .gt_asterisk {
+#qsayfcwvmn .gt_asterisk {
   font-size: 100%;
   vertical-align: 0;
 }
 
-#sefsotesmt .gt_indent_1 {
+#qsayfcwvmn .gt_indent_1 {
   text-indent: 5px;
 }
 
-#sefsotesmt .gt_indent_2 {
+#qsayfcwvmn .gt_indent_2 {
   text-indent: 10px;
 }
 
-#sefsotesmt .gt_indent_3 {
+#qsayfcwvmn .gt_indent_3 {
   text-indent: 15px;
 }
 
-#sefsotesmt .gt_indent_4 {
+#qsayfcwvmn .gt_indent_4 {
   text-indent: 20px;
 }
 
-#sefsotesmt .gt_indent_5 {
+#qsayfcwvmn .gt_indent_5 {
   text-indent: 25px;
 }
 
-#sefsotesmt .katex-display {
+#qsayfcwvmn .katex-display {
   display: inline-flex !important;
   margin-bottom: 0.75em !important;
 }
 
-#sefsotesmt div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
+#qsayfcwvmn div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
   height: 0px !important;
 }
 </style>
@@ -1324,23 +1324,23 @@ <h1>Benchmarks</h1>
 <span>  <span class="fu"><a href="https://gt.rstudio.com/reference/fmt_bytes.html" class="external-link">fmt_bytes</a></span><span class="op">(</span>columns <span class="op">=</span> <span class="fu"><a href="https://rdrr.io/r/base/c.html" class="external-link">c</a></span><span class="op">(</span><span class="va">memory</span>, <span class="va">`file size`</span><span class="op">)</span><span class="op">)</span> <span class="op">|&gt;</span></span>
 <span>  <span class="fu"><a href="https://jthomasmock.github.io/gtExtras/reference/gt_plt_bar.html" class="external-link">gt_plt_bar</a></span><span class="op">(</span>column <span class="op">=</span> <span class="va">`speedup from CSV`</span><span class="op">)</span></span></code></pre></div>
 </details><div class="cell-output-display">
-<div id="rryaeqvzab" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
-<style>#rryaeqvzab table {
+<div id="wqzdyxlcam" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
+<style>#wqzdyxlcam table {
   font-family: system-ui, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
   -webkit-font-smoothing: antialiased;
   -moz-osx-font-smoothing: grayscale;
 }
 
-#rryaeqvzab thead, #rryaeqvzab tbody, #rryaeqvzab tfoot, #rryaeqvzab tr, #rryaeqvzab td, #rryaeqvzab th {
+#wqzdyxlcam thead, #wqzdyxlcam tbody, #wqzdyxlcam tfoot, #wqzdyxlcam tr, #wqzdyxlcam td, #wqzdyxlcam th {
   border-style: none;
 }
 
-#rryaeqvzab p {
+#wqzdyxlcam p {
   margin: 0;
   padding: 0;
 }
 
-#rryaeqvzab .gt_table {
+#wqzdyxlcam .gt_table {
   display: table;
   border-collapse: collapse;
   line-height: normal;
@@ -1366,12 +1366,12 @@ <h1>Benchmarks</h1>
   border-left-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_caption {
+#wqzdyxlcam .gt_caption {
   padding-top: 4px;
   padding-bottom: 4px;
 }
 
-#rryaeqvzab .gt_title {
+#wqzdyxlcam .gt_title {
   color: #333333;
   font-size: 125%;
   font-weight: initial;
@@ -1383,7 +1383,7 @@ <h1>Benchmarks</h1>
   border-bottom-width: 0;
 }
 
-#rryaeqvzab .gt_subtitle {
+#wqzdyxlcam .gt_subtitle {
   color: #333333;
   font-size: 85%;
   font-weight: initial;
@@ -1395,7 +1395,7 @@ <h1>Benchmarks</h1>
   border-top-width: 0;
 }
 
-#rryaeqvzab .gt_heading {
+#wqzdyxlcam .gt_heading {
   background-color: #FFFFFF;
   text-align: center;
   border-bottom-color: #FFFFFF;
@@ -1407,13 +1407,13 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_bottom_border {
+#wqzdyxlcam .gt_bottom_border {
   border-bottom-style: solid;
   border-bottom-width: 2px;
   border-bottom-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_col_headings {
+#wqzdyxlcam .gt_col_headings {
   border-top-style: solid;
   border-top-width: 2px;
   border-top-color: #D3D3D3;
@@ -1428,7 +1428,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_col_heading {
+#wqzdyxlcam .gt_col_heading {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -1448,7 +1448,7 @@ <h1>Benchmarks</h1>
   overflow-x: hidden;
 }
 
-#rryaeqvzab .gt_column_spanner_outer {
+#wqzdyxlcam .gt_column_spanner_outer {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -1460,15 +1460,15 @@ <h1>Benchmarks</h1>
   padding-right: 4px;
 }
 
-#rryaeqvzab .gt_column_spanner_outer:first-child {
+#wqzdyxlcam .gt_column_spanner_outer:first-child {
   padding-left: 0;
 }
 
-#rryaeqvzab .gt_column_spanner_outer:last-child {
+#wqzdyxlcam .gt_column_spanner_outer:last-child {
   padding-right: 0;
 }
 
-#rryaeqvzab .gt_column_spanner {
+#wqzdyxlcam .gt_column_spanner {
   border-bottom-style: solid;
   border-bottom-width: 2px;
   border-bottom-color: #D3D3D3;
@@ -1480,11 +1480,11 @@ <h1>Benchmarks</h1>
   width: 100%;
 }
 
-#rryaeqvzab .gt_spanner_row {
+#wqzdyxlcam .gt_spanner_row {
   border-bottom-style: hidden;
 }
 
-#rryaeqvzab .gt_group_heading {
+#wqzdyxlcam .gt_group_heading {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -1510,7 +1510,7 @@ <h1>Benchmarks</h1>
   text-align: left;
 }
 
-#rryaeqvzab .gt_empty_group_heading {
+#wqzdyxlcam .gt_empty_group_heading {
   padding: 0.5px;
   color: #333333;
   background-color: #FFFFFF;
@@ -1525,15 +1525,15 @@ <h1>Benchmarks</h1>
   vertical-align: middle;
 }
 
-#rryaeqvzab .gt_from_md > :first-child {
+#wqzdyxlcam .gt_from_md > :first-child {
   margin-top: 0;
 }
 
-#rryaeqvzab .gt_from_md > :last-child {
+#wqzdyxlcam .gt_from_md > :last-child {
   margin-bottom: 0;
 }
 
-#rryaeqvzab .gt_row {
+#wqzdyxlcam .gt_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -1552,7 +1552,7 @@ <h1>Benchmarks</h1>
   overflow-x: hidden;
 }
 
-#rryaeqvzab .gt_stub {
+#wqzdyxlcam .gt_stub {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -1565,7 +1565,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#rryaeqvzab .gt_stub_row_group {
+#wqzdyxlcam .gt_stub_row_group {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -1579,15 +1579,15 @@ <h1>Benchmarks</h1>
   vertical-align: top;
 }
 
-#rryaeqvzab .gt_row_group_first td {
+#wqzdyxlcam .gt_row_group_first td {
   border-top-width: 2px;
 }
 
-#rryaeqvzab .gt_row_group_first th {
+#wqzdyxlcam .gt_row_group_first th {
   border-top-width: 2px;
 }
 
-#rryaeqvzab .gt_summary_row {
+#wqzdyxlcam .gt_summary_row {
   color: #333333;
   background-color: #FFFFFF;
   text-transform: inherit;
@@ -1597,16 +1597,16 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#rryaeqvzab .gt_first_summary_row {
+#wqzdyxlcam .gt_first_summary_row {
   border-top-style: solid;
   border-top-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_first_summary_row.thick {
+#wqzdyxlcam .gt_first_summary_row.thick {
   border-top-width: 2px;
 }
 
-#rryaeqvzab .gt_last_summary_row {
+#wqzdyxlcam .gt_last_summary_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -1616,7 +1616,7 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_grand_summary_row {
+#wqzdyxlcam .gt_grand_summary_row {
   color: #333333;
   background-color: #FFFFFF;
   text-transform: inherit;
@@ -1626,7 +1626,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#rryaeqvzab .gt_first_grand_summary_row {
+#wqzdyxlcam .gt_first_grand_summary_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -1636,7 +1636,7 @@ <h1>Benchmarks</h1>
   border-top-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_last_grand_summary_row_top {
+#wqzdyxlcam .gt_last_grand_summary_row_top {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -1646,11 +1646,11 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_striped {
+#wqzdyxlcam .gt_striped {
   background-color: rgba(128, 128, 128, 0.05);
 }
 
-#rryaeqvzab .gt_table_body {
+#wqzdyxlcam .gt_table_body {
   border-top-style: solid;
   border-top-width: 2px;
   border-top-color: #D3D3D3;
@@ -1659,7 +1659,7 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_footnotes {
+#wqzdyxlcam .gt_footnotes {
   color: #333333;
   background-color: #FFFFFF;
   border-bottom-style: none;
@@ -1673,7 +1673,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_footnote {
+#wqzdyxlcam .gt_footnote {
   margin: 0px;
   font-size: 90%;
   padding-top: 4px;
@@ -1682,7 +1682,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#rryaeqvzab .gt_sourcenotes {
+#wqzdyxlcam .gt_sourcenotes {
   color: #333333;
   background-color: #FFFFFF;
   border-bottom-style: none;
@@ -1696,7 +1696,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#rryaeqvzab .gt_sourcenote {
+#wqzdyxlcam .gt_sourcenote {
   font-size: 90%;
   padding-top: 4px;
   padding-bottom: 4px;
@@ -1704,72 +1704,72 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#rryaeqvzab .gt_left {
+#wqzdyxlcam .gt_left {
   text-align: left;
 }
 
-#rryaeqvzab .gt_center {
+#wqzdyxlcam .gt_center {
   text-align: center;
 }
 
-#rryaeqvzab .gt_right {
+#wqzdyxlcam .gt_right {
   text-align: right;
   font-variant-numeric: tabular-nums;
 }
 
-#rryaeqvzab .gt_font_normal {
+#wqzdyxlcam .gt_font_normal {
   font-weight: normal;
 }
 
-#rryaeqvzab .gt_font_bold {
+#wqzdyxlcam .gt_font_bold {
   font-weight: bold;
 }
 
-#rryaeqvzab .gt_font_italic {
+#wqzdyxlcam .gt_font_italic {
   font-style: italic;
 }
 
-#rryaeqvzab .gt_super {
+#wqzdyxlcam .gt_super {
   font-size: 65%;
 }
 
-#rryaeqvzab .gt_footnote_marks {
+#wqzdyxlcam .gt_footnote_marks {
   font-size: 75%;
   vertical-align: 0.4em;
   position: initial;
 }
 
-#rryaeqvzab .gt_asterisk {
+#wqzdyxlcam .gt_asterisk {
   font-size: 100%;
   vertical-align: 0;
 }
 
-#rryaeqvzab .gt_indent_1 {
+#wqzdyxlcam .gt_indent_1 {
   text-indent: 5px;
 }
 
-#rryaeqvzab .gt_indent_2 {
+#wqzdyxlcam .gt_indent_2 {
   text-indent: 10px;
 }
 
-#rryaeqvzab .gt_indent_3 {
+#wqzdyxlcam .gt_indent_3 {
   text-indent: 15px;
 }
 
-#rryaeqvzab .gt_indent_4 {
+#wqzdyxlcam .gt_indent_4 {
   text-indent: 20px;
 }
 
-#rryaeqvzab .gt_indent_5 {
+#wqzdyxlcam .gt_indent_5 {
   text-indent: 25px;
 }
 
-#rryaeqvzab .katex-display {
+#wqzdyxlcam .katex-display {
   display: inline-flex !important;
   margin-bottom: 0.75em !important;
 }
 
-#rryaeqvzab div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
+#wqzdyxlcam div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
   height: 0px !important;
 }
 </style>
@@ -1946,23 +1946,23 @@ <h1>Benchmarks</h1>
 <span>  <span class="fu"><a href="https://gt.rstudio.com/reference/fmt_bytes.html" class="external-link">fmt_bytes</a></span><span class="op">(</span>columns <span class="op">=</span> <span class="va">memory</span><span class="op">)</span> <span class="op">|&gt;</span></span>
 <span>  <span class="fu"><a href="https://jthomasmock.github.io/gtExtras/reference/gt_plt_bar.html" class="external-link">gt_plt_bar</a></span><span class="op">(</span>column <span class="op">=</span> <span class="va">`speedup from CSV`</span><span class="op">)</span></span></code></pre></div>
 </details><div class="cell-output-display">
-<div id="vtqbtqhcko" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
-<style>#vtqbtqhcko table {
+<div id="stfmyywzuw" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
+<style>#stfmyywzuw table {
   font-family: system-ui, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
   -webkit-font-smoothing: antialiased;
   -moz-osx-font-smoothing: grayscale;
 }
 
-#vtqbtqhcko thead, #vtqbtqhcko tbody, #vtqbtqhcko tfoot, #vtqbtqhcko tr, #vtqbtqhcko td, #vtqbtqhcko th {
+#stfmyywzuw thead, #stfmyywzuw tbody, #stfmyywzuw tfoot, #stfmyywzuw tr, #stfmyywzuw td, #stfmyywzuw th {
   border-style: none;
 }
 
-#vtqbtqhcko p {
+#stfmyywzuw p {
   margin: 0;
   padding: 0;
 }
 
-#vtqbtqhcko .gt_table {
+#stfmyywzuw .gt_table {
   display: table;
   border-collapse: collapse;
   line-height: normal;
@@ -1988,12 +1988,12 @@ <h1>Benchmarks</h1>
   border-left-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_caption {
+#stfmyywzuw .gt_caption {
   padding-top: 4px;
   padding-bottom: 4px;
 }
 
-#vtqbtqhcko .gt_title {
+#stfmyywzuw .gt_title {
   color: #333333;
   font-size: 125%;
   font-weight: initial;
@@ -2005,7 +2005,7 @@ <h1>Benchmarks</h1>
   border-bottom-width: 0;
 }
 
-#vtqbtqhcko .gt_subtitle {
+#stfmyywzuw .gt_subtitle {
   color: #333333;
   font-size: 85%;
   font-weight: initial;
@@ -2017,7 +2017,7 @@ <h1>Benchmarks</h1>
   border-top-width: 0;
 }
 
-#vtqbtqhcko .gt_heading {
+#stfmyywzuw .gt_heading {
   background-color: #FFFFFF;
   text-align: center;
   border-bottom-color: #FFFFFF;
@@ -2029,13 +2029,13 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_bottom_border {
+#stfmyywzuw .gt_bottom_border {
   border-bottom-style: solid;
   border-bottom-width: 2px;
   border-bottom-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_col_headings {
+#stfmyywzuw .gt_col_headings {
   border-top-style: solid;
   border-top-width: 2px;
   border-top-color: #D3D3D3;
@@ -2050,7 +2050,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_col_heading {
+#stfmyywzuw .gt_col_heading {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -2070,7 +2070,7 @@ <h1>Benchmarks</h1>
   overflow-x: hidden;
 }
 
-#vtqbtqhcko .gt_column_spanner_outer {
+#stfmyywzuw .gt_column_spanner_outer {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -2082,15 +2082,15 @@ <h1>Benchmarks</h1>
   padding-right: 4px;
 }
 
-#vtqbtqhcko .gt_column_spanner_outer:first-child {
+#stfmyywzuw .gt_column_spanner_outer:first-child {
   padding-left: 0;
 }
 
-#vtqbtqhcko .gt_column_spanner_outer:last-child {
+#stfmyywzuw .gt_column_spanner_outer:last-child {
   padding-right: 0;
 }
 
-#vtqbtqhcko .gt_column_spanner {
+#stfmyywzuw .gt_column_spanner {
   border-bottom-style: solid;
   border-bottom-width: 2px;
   border-bottom-color: #D3D3D3;
@@ -2102,11 +2102,11 @@ <h1>Benchmarks</h1>
   width: 100%;
 }
 
-#vtqbtqhcko .gt_spanner_row {
+#stfmyywzuw .gt_spanner_row {
   border-bottom-style: hidden;
 }
 
-#vtqbtqhcko .gt_group_heading {
+#stfmyywzuw .gt_group_heading {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -2132,7 +2132,7 @@ <h1>Benchmarks</h1>
   text-align: left;
 }
 
-#vtqbtqhcko .gt_empty_group_heading {
+#stfmyywzuw .gt_empty_group_heading {
   padding: 0.5px;
   color: #333333;
   background-color: #FFFFFF;
@@ -2147,15 +2147,15 @@ <h1>Benchmarks</h1>
   vertical-align: middle;
 }
 
-#vtqbtqhcko .gt_from_md > :first-child {
+#stfmyywzuw .gt_from_md > :first-child {
   margin-top: 0;
 }
 
-#vtqbtqhcko .gt_from_md > :last-child {
+#stfmyywzuw .gt_from_md > :last-child {
   margin-bottom: 0;
 }
 
-#vtqbtqhcko .gt_row {
+#stfmyywzuw .gt_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -2174,7 +2174,7 @@ <h1>Benchmarks</h1>
   overflow-x: hidden;
 }
 
-#vtqbtqhcko .gt_stub {
+#stfmyywzuw .gt_stub {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -2187,7 +2187,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#vtqbtqhcko .gt_stub_row_group {
+#stfmyywzuw .gt_stub_row_group {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -2201,15 +2201,15 @@ <h1>Benchmarks</h1>
   vertical-align: top;
 }
 
-#vtqbtqhcko .gt_row_group_first td {
+#stfmyywzuw .gt_row_group_first td {
   border-top-width: 2px;
 }
 
-#vtqbtqhcko .gt_row_group_first th {
+#stfmyywzuw .gt_row_group_first th {
   border-top-width: 2px;
 }
 
-#vtqbtqhcko .gt_summary_row {
+#stfmyywzuw .gt_summary_row {
   color: #333333;
   background-color: #FFFFFF;
   text-transform: inherit;
@@ -2219,16 +2219,16 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#vtqbtqhcko .gt_first_summary_row {
+#stfmyywzuw .gt_first_summary_row {
   border-top-style: solid;
   border-top-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_first_summary_row.thick {
+#stfmyywzuw .gt_first_summary_row.thick {
   border-top-width: 2px;
 }
 
-#vtqbtqhcko .gt_last_summary_row {
+#stfmyywzuw .gt_last_summary_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -2238,7 +2238,7 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_grand_summary_row {
+#stfmyywzuw .gt_grand_summary_row {
   color: #333333;
   background-color: #FFFFFF;
   text-transform: inherit;
@@ -2248,7 +2248,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#vtqbtqhcko .gt_first_grand_summary_row {
+#stfmyywzuw .gt_first_grand_summary_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -2258,7 +2258,7 @@ <h1>Benchmarks</h1>
   border-top-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_last_grand_summary_row_top {
+#stfmyywzuw .gt_last_grand_summary_row_top {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -2268,11 +2268,11 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_striped {
+#stfmyywzuw .gt_striped {
   background-color: rgba(128, 128, 128, 0.05);
 }
 
-#vtqbtqhcko .gt_table_body {
+#stfmyywzuw .gt_table_body {
   border-top-style: solid;
   border-top-width: 2px;
   border-top-color: #D3D3D3;
@@ -2281,7 +2281,7 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_footnotes {
+#stfmyywzuw .gt_footnotes {
   color: #333333;
   background-color: #FFFFFF;
   border-bottom-style: none;
@@ -2295,7 +2295,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_footnote {
+#stfmyywzuw .gt_footnote {
   margin: 0px;
   font-size: 90%;
   padding-top: 4px;
@@ -2304,7 +2304,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#vtqbtqhcko .gt_sourcenotes {
+#stfmyywzuw .gt_sourcenotes {
   color: #333333;
   background-color: #FFFFFF;
   border-bottom-style: none;
@@ -2318,7 +2318,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#vtqbtqhcko .gt_sourcenote {
+#stfmyywzuw .gt_sourcenote {
   font-size: 90%;
   padding-top: 4px;
   padding-bottom: 4px;
@@ -2326,72 +2326,72 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#vtqbtqhcko .gt_left {
+#stfmyywzuw .gt_left {
   text-align: left;
 }
 
-#vtqbtqhcko .gt_center {
+#stfmyywzuw .gt_center {
   text-align: center;
 }
 
-#vtqbtqhcko .gt_right {
+#stfmyywzuw .gt_right {
   text-align: right;
   font-variant-numeric: tabular-nums;
 }
 
-#vtqbtqhcko .gt_font_normal {
+#stfmyywzuw .gt_font_normal {
   font-weight: normal;
 }
 
-#vtqbtqhcko .gt_font_bold {
+#stfmyywzuw .gt_font_bold {
   font-weight: bold;
 }
 
-#vtqbtqhcko .gt_font_italic {
+#stfmyywzuw .gt_font_italic {
   font-style: italic;
 }
 
-#vtqbtqhcko .gt_super {
+#stfmyywzuw .gt_super {
   font-size: 65%;
 }
 
-#vtqbtqhcko .gt_footnote_marks {
+#stfmyywzuw .gt_footnote_marks {
   font-size: 75%;
   vertical-align: 0.4em;
   position: initial;
 }
 
-#vtqbtqhcko .gt_asterisk {
+#stfmyywzuw .gt_asterisk {
   font-size: 100%;
   vertical-align: 0;
 }
 
-#vtqbtqhcko .gt_indent_1 {
+#stfmyywzuw .gt_indent_1 {
   text-indent: 5px;
 }
 
-#vtqbtqhcko .gt_indent_2 {
+#stfmyywzuw .gt_indent_2 {
   text-indent: 10px;
 }
 
-#vtqbtqhcko .gt_indent_3 {
+#stfmyywzuw .gt_indent_3 {
   text-indent: 15px;
 }
 
-#vtqbtqhcko .gt_indent_4 {
+#stfmyywzuw .gt_indent_4 {
   text-indent: 20px;
 }
 
-#vtqbtqhcko .gt_indent_5 {
+#stfmyywzuw .gt_indent_5 {
   text-indent: 25px;
 }
 
-#vtqbtqhcko .katex-display {
+#stfmyywzuw .katex-display {
   display: inline-flex !important;
   margin-bottom: 0.75em !important;
 }
 
-#vtqbtqhcko div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
+#stfmyywzuw div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
   height: 0px !important;
 }
 </style>
@@ -2531,23 +2531,23 @@ <h1>Benchmarks</h1>
 <span>  <span class="fu"><a href="https://gt.rstudio.com/reference/fmt_bytes.html" class="external-link">fmt_bytes</a></span><span class="op">(</span>columns <span class="op">=</span> <span class="fu"><a href="https://rdrr.io/r/base/c.html" class="external-link">c</a></span><span class="op">(</span><span class="va">memory</span>, <span class="va">`file size`</span><span class="op">)</span><span class="op">)</span> <span class="op">|&gt;</span></span>
 <span>  <span class="fu"><a href="https://jthomasmock.github.io/gtExtras/reference/gt_plt_bar.html" class="external-link">gt_plt_bar</a></span><span class="op">(</span>column <span class="op">=</span> <span class="va">`speedup from CSV`</span><span class="op">)</span></span></code></pre></div>
 </details><div class="cell-output-display">
-<div id="iohtvmkcow" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
-<style>#iohtvmkcow table {
+<div id="qsggdsbfek" style="padding-left:0px;padding-right:0px;padding-top:10px;padding-bottom:10px;overflow-x:auto;overflow-y:auto;width:auto;height:auto;">
+<style>#qsggdsbfek table {
   font-family: system-ui, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
   -webkit-font-smoothing: antialiased;
   -moz-osx-font-smoothing: grayscale;
 }
 
-#iohtvmkcow thead, #iohtvmkcow tbody, #iohtvmkcow tfoot, #iohtvmkcow tr, #iohtvmkcow td, #iohtvmkcow th {
+#qsggdsbfek thead, #qsggdsbfek tbody, #qsggdsbfek tfoot, #qsggdsbfek tr, #qsggdsbfek td, #qsggdsbfek th {
   border-style: none;
 }
 
-#iohtvmkcow p {
+#qsggdsbfek p {
   margin: 0;
   padding: 0;
 }
 
-#iohtvmkcow .gt_table {
+#qsggdsbfek .gt_table {
   display: table;
   border-collapse: collapse;
   line-height: normal;
@@ -2573,12 +2573,12 @@ <h1>Benchmarks</h1>
   border-left-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_caption {
+#qsggdsbfek .gt_caption {
   padding-top: 4px;
   padding-bottom: 4px;
 }
 
-#iohtvmkcow .gt_title {
+#qsggdsbfek .gt_title {
   color: #333333;
   font-size: 125%;
   font-weight: initial;
@@ -2590,7 +2590,7 @@ <h1>Benchmarks</h1>
   border-bottom-width: 0;
 }
 
-#iohtvmkcow .gt_subtitle {
+#qsggdsbfek .gt_subtitle {
   color: #333333;
   font-size: 85%;
   font-weight: initial;
@@ -2602,7 +2602,7 @@ <h1>Benchmarks</h1>
   border-top-width: 0;
 }
 
-#iohtvmkcow .gt_heading {
+#qsggdsbfek .gt_heading {
   background-color: #FFFFFF;
   text-align: center;
   border-bottom-color: #FFFFFF;
@@ -2614,13 +2614,13 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_bottom_border {
+#qsggdsbfek .gt_bottom_border {
   border-bottom-style: solid;
   border-bottom-width: 2px;
   border-bottom-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_col_headings {
+#qsggdsbfek .gt_col_headings {
   border-top-style: solid;
   border-top-width: 2px;
   border-top-color: #D3D3D3;
@@ -2635,7 +2635,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_col_heading {
+#qsggdsbfek .gt_col_heading {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -2655,7 +2655,7 @@ <h1>Benchmarks</h1>
   overflow-x: hidden;
 }
 
-#iohtvmkcow .gt_column_spanner_outer {
+#qsggdsbfek .gt_column_spanner_outer {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -2667,15 +2667,15 @@ <h1>Benchmarks</h1>
   padding-right: 4px;
 }
 
-#iohtvmkcow .gt_column_spanner_outer:first-child {
+#qsggdsbfek .gt_column_spanner_outer:first-child {
   padding-left: 0;
 }
 
-#iohtvmkcow .gt_column_spanner_outer:last-child {
+#qsggdsbfek .gt_column_spanner_outer:last-child {
   padding-right: 0;
 }
 
-#iohtvmkcow .gt_column_spanner {
+#qsggdsbfek .gt_column_spanner {
   border-bottom-style: solid;
   border-bottom-width: 2px;
   border-bottom-color: #D3D3D3;
@@ -2687,11 +2687,11 @@ <h1>Benchmarks</h1>
   width: 100%;
 }
 
-#iohtvmkcow .gt_spanner_row {
+#qsggdsbfek .gt_spanner_row {
   border-bottom-style: hidden;
 }
 
-#iohtvmkcow .gt_group_heading {
+#qsggdsbfek .gt_group_heading {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -2717,7 +2717,7 @@ <h1>Benchmarks</h1>
   text-align: left;
 }
 
-#iohtvmkcow .gt_empty_group_heading {
+#qsggdsbfek .gt_empty_group_heading {
   padding: 0.5px;
   color: #333333;
   background-color: #FFFFFF;
@@ -2732,15 +2732,15 @@ <h1>Benchmarks</h1>
   vertical-align: middle;
 }
 
-#iohtvmkcow .gt_from_md > :first-child {
+#qsggdsbfek .gt_from_md > :first-child {
   margin-top: 0;
 }
 
-#iohtvmkcow .gt_from_md > :last-child {
+#qsggdsbfek .gt_from_md > :last-child {
   margin-bottom: 0;
 }
 
-#iohtvmkcow .gt_row {
+#qsggdsbfek .gt_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -2759,7 +2759,7 @@ <h1>Benchmarks</h1>
   overflow-x: hidden;
 }
 
-#iohtvmkcow .gt_stub {
+#qsggdsbfek .gt_stub {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -2772,7 +2772,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#iohtvmkcow .gt_stub_row_group {
+#qsggdsbfek .gt_stub_row_group {
   color: #333333;
   background-color: #FFFFFF;
   font-size: 100%;
@@ -2786,15 +2786,15 @@ <h1>Benchmarks</h1>
   vertical-align: top;
 }
 
-#iohtvmkcow .gt_row_group_first td {
+#qsggdsbfek .gt_row_group_first td {
   border-top-width: 2px;
 }
 
-#iohtvmkcow .gt_row_group_first th {
+#qsggdsbfek .gt_row_group_first th {
   border-top-width: 2px;
 }
 
-#iohtvmkcow .gt_summary_row {
+#qsggdsbfek .gt_summary_row {
   color: #333333;
   background-color: #FFFFFF;
   text-transform: inherit;
@@ -2804,16 +2804,16 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#iohtvmkcow .gt_first_summary_row {
+#qsggdsbfek .gt_first_summary_row {
   border-top-style: solid;
   border-top-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_first_summary_row.thick {
+#qsggdsbfek .gt_first_summary_row.thick {
   border-top-width: 2px;
 }
 
-#iohtvmkcow .gt_last_summary_row {
+#qsggdsbfek .gt_last_summary_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -2823,7 +2823,7 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_grand_summary_row {
+#qsggdsbfek .gt_grand_summary_row {
   color: #333333;
   background-color: #FFFFFF;
   text-transform: inherit;
@@ -2833,7 +2833,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#iohtvmkcow .gt_first_grand_summary_row {
+#qsggdsbfek .gt_first_grand_summary_row {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -2843,7 +2843,7 @@ <h1>Benchmarks</h1>
   border-top-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_last_grand_summary_row_top {
+#qsggdsbfek .gt_last_grand_summary_row_top {
   padding-top: 8px;
   padding-bottom: 8px;
   padding-left: 5px;
@@ -2853,11 +2853,11 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_striped {
+#qsggdsbfek .gt_striped {
   background-color: rgba(128, 128, 128, 0.05);
 }
 
-#iohtvmkcow .gt_table_body {
+#qsggdsbfek .gt_table_body {
   border-top-style: solid;
   border-top-width: 2px;
   border-top-color: #D3D3D3;
@@ -2866,7 +2866,7 @@ <h1>Benchmarks</h1>
   border-bottom-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_footnotes {
+#qsggdsbfek .gt_footnotes {
   color: #333333;
   background-color: #FFFFFF;
   border-bottom-style: none;
@@ -2880,7 +2880,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_footnote {
+#qsggdsbfek .gt_footnote {
   margin: 0px;
   font-size: 90%;
   padding-top: 4px;
@@ -2889,7 +2889,7 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#iohtvmkcow .gt_sourcenotes {
+#qsggdsbfek .gt_sourcenotes {
   color: #333333;
   background-color: #FFFFFF;
   border-bottom-style: none;
@@ -2903,7 +2903,7 @@ <h1>Benchmarks</h1>
   border-right-color: #D3D3D3;
 }
 
-#iohtvmkcow .gt_sourcenote {
+#qsggdsbfek .gt_sourcenote {
   font-size: 90%;
   padding-top: 4px;
   padding-bottom: 4px;
@@ -2911,72 +2911,72 @@ <h1>Benchmarks</h1>
   padding-right: 5px;
 }
 
-#iohtvmkcow .gt_left {
+#qsggdsbfek .gt_left {
   text-align: left;
 }
 
-#iohtvmkcow .gt_center {
+#qsggdsbfek .gt_center {
   text-align: center;
 }
 
-#iohtvmkcow .gt_right {
+#qsggdsbfek .gt_right {
   text-align: right;
   font-variant-numeric: tabular-nums;
 }
 
-#iohtvmkcow .gt_font_normal {
+#qsggdsbfek .gt_font_normal {
   font-weight: normal;
 }
 
-#iohtvmkcow .gt_font_bold {
+#qsggdsbfek .gt_font_bold {
   font-weight: bold;
 }
 
-#iohtvmkcow .gt_font_italic {
+#qsggdsbfek .gt_font_italic {
   font-style: italic;
 }
 
-#iohtvmkcow .gt_super {
+#qsggdsbfek .gt_super {
   font-size: 65%;
 }
 
-#iohtvmkcow .gt_footnote_marks {
+#qsggdsbfek .gt_footnote_marks {
   font-size: 75%;
   vertical-align: 0.4em;
   position: initial;
 }
 
-#iohtvmkcow .gt_asterisk {
+#qsggdsbfek .gt_asterisk {
   font-size: 100%;
   vertical-align: 0;
 }
 
-#iohtvmkcow .gt_indent_1 {
+#qsggdsbfek .gt_indent_1 {
   text-indent: 5px;
 }
 
-#iohtvmkcow .gt_indent_2 {
+#qsggdsbfek .gt_indent_2 {
   text-indent: 10px;
 }
 
-#iohtvmkcow .gt_indent_3 {
+#qsggdsbfek .gt_indent_3 {
   text-indent: 15px;
 }
 
-#iohtvmkcow .gt_indent_4 {
+#qsggdsbfek .gt_indent_4 {
   text-indent: 20px;
 }
 
-#iohtvmkcow .gt_indent_5 {
+#qsggdsbfek .gt_indent_5 {
   text-indent: 25px;
 }
 
-#iohtvmkcow .katex-display {
+#qsggdsbfek .katex-display {
   display: inline-flex !important;
   margin-bottom: 0.75em !important;
 }
 
-#iohtvmkcow div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
+#qsggdsbfek div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
   height: 0px !important;
 }
 </style>
@@ -3198,9 +3198,9 @@ <h1>Benchmarks</h1>
 <span><span class="co">#&gt;  collate  C.UTF-8</span></span>
 <span><span class="co">#&gt;  ctype    C.UTF-8</span></span>
 <span><span class="co">#&gt;  tz       UTC</span></span>
-<span><span class="co">#&gt;  date     2025-02-10</span></span>
+<span><span class="co">#&gt;  date     2025-02-22</span></span>
 <span><span class="co">#&gt;  pandoc   3.1.11 @ /opt/hostedtoolcache/pandoc/3.1.11/x64/ (via rmarkdown)</span></span>
-<span><span class="co">#&gt;  quarto   1.6.40 @ /usr/local/bin/quarto</span></span>
+<span><span class="co">#&gt;  quarto   1.6.41 @ /usr/local/bin/quarto</span></span>
 <span><span class="co">#&gt;</span></span>
 <span><span class="co">#&gt; ─ Packages ───────────────────────────────────────────────────────────────────</span></span>
 <span><span class="co">#&gt;  package      * version  date (UTC) lib source</span></span>
@@ -3209,13 +3209,13 @@ <h1>Benchmarks</h1>
 <span><span class="co">#&gt;  base64enc      0.1-3    2015-07-28 [1] RSPM</span></span>
 <span><span class="co">#&gt;  bit            4.5.0.1  2024-12-03 [1] RSPM</span></span>
 <span><span class="co">#&gt;  bit64          4.6.0-1  2025-01-16 [1] RSPM</span></span>
-<span><span class="co">#&gt;  cli            3.6.3    2024-06-21 [1] RSPM</span></span>
+<span><span class="co">#&gt;  cli            3.6.4    2025-02-13 [1] RSPM</span></span>
 <span><span class="co">#&gt;  colorspace     2.1-1    2024-07-26 [1] RSPM</span></span>
 <span><span class="co">#&gt;  commonmark     1.9.2    2024-10-04 [1] RSPM</span></span>
 <span><span class="co">#&gt;  DBI            1.2.3    2024-06-02 [1] RSPM</span></span>
 <span><span class="co">#&gt;  digest         0.6.37   2024-08-19 [1] RSPM</span></span>
 <span><span class="co">#&gt;  dplyr        * 1.1.4    2023-11-17 [1] RSPM</span></span>
-<span><span class="co">#&gt;  duckdb         1.1.3-2  2025-01-24 [1] RSPM</span></span>
+<span><span class="co">#&gt;  duckdb         1.2.0    2025-02-21 [1] RSPM</span></span>
 <span><span class="co">#&gt;  evaluate       1.0.3    2025-01-10 [1] RSPM</span></span>
 <span><span class="co">#&gt;  farver         2.1.2    2024-05-13 [1] RSPM</span></span>
 <span><span class="co">#&gt;  fastmap        1.2.0    2024-05-15 [1] RSPM</span></span>
@@ -3227,21 +3227,21 @@ <h1>Benchmarks</h1>
 <span><span class="co">#&gt;  gtable         0.3.6    2024-10-25 [1] RSPM</span></span>
 <span><span class="co">#&gt;  gtExtras     * 0.5.0    2023-09-15 [1] RSPM</span></span>
 <span><span class="co">#&gt;  htmltools      0.5.8.1  2024-04-04 [1] RSPM</span></span>
-<span><span class="co">#&gt;  jsonlite       1.8.9    2024-09-20 [1] RSPM</span></span>
+<span><span class="co">#&gt;  jsonlite       1.9.0    2025-02-19 [1] RSPM</span></span>
 <span><span class="co">#&gt;  knitr          1.49     2024-11-08 [1] RSPM</span></span>
 <span><span class="co">#&gt;  labeling       0.4.3    2023-08-29 [1] RSPM</span></span>
 <span><span class="co">#&gt;  lifecycle      1.0.4    2023-11-07 [1] RSPM</span></span>
 <span><span class="co">#&gt;  magrittr       2.0.3    2022-03-30 [1] RSPM</span></span>
 <span><span class="co">#&gt;  markdown       1.13     2024-06-04 [1] RSPM</span></span>
 <span><span class="co">#&gt;  munsell        0.5.1    2024-04-01 [1] RSPM</span></span>
-<span><span class="co">#&gt;  nanoparquet    0.4.1    2025-02-10 [1] local</span></span>
+<span><span class="co">#&gt;  nanoparquet    0.4.2    2025-02-22 [1] local</span></span>
 <span><span class="co">#&gt;  nycflights13   1.0.2    2021-04-12 [1] RSPM</span></span>
 <span><span class="co">#&gt;  paletteer      1.6.0    2024-01-21 [1] RSPM</span></span>
 <span><span class="co">#&gt;  pillar         1.10.1   2025-01-07 [1] RSPM</span></span>
 <span><span class="co">#&gt;  pkgconfig      2.0.3    2019-09-22 [1] RSPM</span></span>
 <span><span class="co">#&gt;  prettyunits    1.2.0    2023-09-24 [1] RSPM</span></span>
 <span><span class="co">#&gt;  purrr          1.0.4    2025-02-05 [1] RSPM</span></span>
-<span><span class="co">#&gt;  R6             2.5.1    2021-08-19 [1] RSPM</span></span>
+<span><span class="co">#&gt;  R6             2.6.1    2025-02-15 [1] RSPM</span></span>
 <span><span class="co">#&gt;  ragg           1.3.3    2024-09-11 [1] RSPM</span></span>
 <span><span class="co">#&gt;  rematch2       2.1.2    2020-05-01 [1] RSPM</span></span>
 <span><span class="co">#&gt;  rlang          1.1.5    2025-01-17 [1] RSPM</span></span>
@@ -3257,7 +3257,7 @@ <h1>Benchmarks</h1>
 <span><span class="co">#&gt;  utf8           1.2.4    2023-10-22 [1] RSPM</span></span>
 <span><span class="co">#&gt;  vctrs          0.6.5    2023-12-01 [1] RSPM</span></span>
 <span><span class="co">#&gt;  withr          3.0.2    2024-10-28 [1] RSPM</span></span>
-<span><span class="co">#&gt;  xfun           0.50     2025-01-07 [1] RSPM</span></span>
+<span><span class="co">#&gt;  xfun           0.51     2025-02-19 [1] RSPM</span></span>
 <span><span class="co">#&gt;  xml2           1.3.6    2023-12-04 [1] RSPM</span></span>
 <span><span class="co">#&gt;  yaml           2.3.10   2024-07-26 [1] RSPM</span></span>
 <span><span class="co">#&gt;</span></span>
diff --git a/articles/index.html b/articles/index.html
index 7869f3d..cf9ca32 100644
--- a/articles/index.html
+++ b/articles/index.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/authors.html b/authors.html
index 75cb6b8..818aedd 100644
--- a/authors.html
+++ b/authors.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -89,14 +89,14 @@ <h2 id="citation">Citation</h2>
 
       <p>Csárdi G, Mühleisen H (2025).
 <em>nanoparquet: Read and Write 'Parquet' Files</em>.
-R package version 0.4.1,
+R package version 0.4.2,
 https://nanoparquet.r-lib.org/, <a href="https://github.com/r-lib/nanoparquet" class="external-link">https://github.com/r-lib/nanoparquet</a>.
 </p>
       <pre>@Manual{,
   title = {nanoparquet: Read and Write 'Parquet' Files},
   author = {Gábor Csárdi and Hannes Mühleisen},
   year = {2025},
-  note = {R package version 0.4.1,
+  note = {R package version 0.4.2,
     https://nanoparquet.r-lib.org/},
   url = {https://github.com/r-lib/nanoparquet},
 }</pre>
diff --git a/index.html b/index.html
index af293d7..4e03a91 100644
--- a/index.html
+++ b/index.html
@@ -25,7 +25,7 @@
 
     <a class="navbar-brand me-2" href="index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/news/index.html b/news/index.html
index 95432eb..9f275e1 100644
--- a/news/index.html
+++ b/news/index.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -44,7 +44,12 @@ <h1>Changelog</h1>
     </div>
 
     <div class="section level2">
-<h2 class="pkg-version" data-toc-text="0.4.1" id="nanoparquet-041">nanoparquet 0.4.1<a class="anchor" aria-label="anchor" href="#nanoparquet-041"></a></h2>
+<h2 class="pkg-version" data-toc-text="0.4.2" id="nanoparquet-042">nanoparquet 0.4.2<a class="anchor" aria-label="anchor" href="#nanoparquet-042"></a></h2><p class="text-muted">CRAN release: 2025-02-22</p>
+<ul><li><p><code><a href="../reference/write_parquet.html">write_parquet()</a></code> now does not fail when writing files with a zero-length first page (<a href="https://github.com/r-lib/nanoparquet/issues/122" class="external-link">#122</a>).</p></li>
+<li><p><code><a href="../reference/read_parquet.html">read_parquet()</a></code> can now read Parquet files that do not contain the dictionary page offset in their metadata. Polars creates such files (<a href="https://github.com/r-lib/nanoparquet/issues/132" class="external-link">#132</a>).</p></li>
+</ul></div>
+    <div class="section level2">
+<h2 class="pkg-version" data-toc-text="0.4.1" id="nanoparquet-041">nanoparquet 0.4.1<a class="anchor" aria-label="anchor" href="#nanoparquet-041"></a></h2><p class="text-muted">CRAN release: 2025-02-10</p>
 <ul><li><p><code><a href="../reference/write_parquet.html">write_parquet()</a></code> now correctly converts double <code>Date</code> columns to integer columns (<a href="https://github.com/eitsupi" class="external-link">@eitsupi</a>, <a href="https://github.com/r-lib/nanoparquet/issues/116" class="external-link">#116</a>).</p></li>
 <li><p><code><a href="../reference/read_parquet.html">read_parquet()</a></code> now correctly reads <code>FLOAT</code> columns from files with multiple row groups.</p></li>
 <li><p><code><a href="../reference/read_parquet.html">read_parquet()</a></code> now correctly reads Parquet files that have column chunks with both dictionary encoded and not dictionary encoded pages (<a href="https://github.com/r-lib/nanoparquet/issues/110" class="external-link">#110</a>).</p></li>
diff --git a/pkgdown.yml b/pkgdown.yml
index 8daf331..cafd141 100644
--- a/pkgdown.yml
+++ b/pkgdown.yml
@@ -3,7 +3,7 @@ pkgdown: 2.1.1.9000
 pkgdown_sha: 18cca452d736fea33d47b19b4ef4973db9104a75
 articles:
   articles/benchmarks: benchmarks.html
-last_built: 2025-02-10T12:44Z
+last_built: 2025-02-22T13:51Z
 urls:
   reference: https://nanoparquet.r-lib.org/reference
   article: https://nanoparquet.r-lib.org/articles
diff --git a/reference/append_parquet.html b/reference/append_parquet.html
index 10bea67..4b81c32 100644
--- a/reference/append_parquet.html
+++ b/reference/append_parquet.html
@@ -9,7 +9,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/index.html b/reference/index.html
index d214130..2c98b03 100644
--- a/reference/index.html
+++ b/reference/index.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/infer_parquet_schema.html b/reference/infer_parquet_schema.html
index 3e0c915..a81d74e 100644
--- a/reference/infer_parquet_schema.html
+++ b/reference/infer_parquet_schema.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/nanoparquet-package.html b/reference/nanoparquet-package.html
index 696281e..7d3a1b8 100644
--- a/reference/nanoparquet-package.html
+++ b/reference/nanoparquet-package.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/nanoparquet-types.html b/reference/nanoparquet-types.html
index e5b526b..9786878 100644
--- a/reference/nanoparquet-types.html
+++ b/reference/nanoparquet-types.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/parquet-encodings.html b/reference/parquet-encodings.html
index 6131844..725890f 100644
--- a/reference/parquet-encodings.html
+++ b/reference/parquet-encodings.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/parquet_column_types.html b/reference/parquet_column_types.html
index 1cf9320..9bf1418 100644
--- a/reference/parquet_column_types.html
+++ b/reference/parquet_column_types.html
@@ -11,7 +11,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/parquet_options.html b/reference/parquet_options.html
index 55d2d49..facbc24 100644
--- a/reference/parquet_options.html
+++ b/reference/parquet_options.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/parquet_schema.html b/reference/parquet_schema.html
index 5508dc4..96c777c 100644
--- a/reference/parquet_schema.html
+++ b/reference/parquet_schema.html
@@ -9,7 +9,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -149,13 +149,13 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-in"><span>  c3 <span class="op">=</span> <span class="fu"><a href="https://rdrr.io/r/base/list.html" class="external-link">list</a></span><span class="op">(</span><span class="st">"STRING"</span>, repetition_type <span class="op">=</span> <span class="st">"OPTIONAL"</span><span class="op">)</span></span></span>
 <span class="r-in"><span><span class="op">)</span></span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># A data frame: 3 × 12</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>   file_name name  r_type type   type_length repetition_type converted_type</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">*</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>     <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>  <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>        <span style="color: #949494; font-style: italic;">&lt;int&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>           <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>         </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">1</span> <span style="color: #BB0000;">NA</span>        c1    <span style="color: #BB0000;">NA</span>     INT32           <span style="color: #BB0000;">NA</span> <span style="color: #BB0000;">NA</span>              <span style="color: #BB0000;">NA</span>            </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">2</span> <span style="color: #BB0000;">NA</span>        c2    <span style="color: #BB0000;">NA</span>     INT64           <span style="color: #BB0000;">NA</span> <span style="color: #BB0000;">NA</span>              INT_64        </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">3</span> <span style="color: #BB0000;">NA</span>        c3    <span style="color: #BB0000;">NA</span>     BYTE_…          <span style="color: #BB0000;">NA</span> OPTIONAL        UTF8          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># ℹ 5 more variables: logical_type &lt;I&lt;list&gt;&gt;, num_children &lt;int&gt;,</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;">#   scale &lt;int&gt;, precision &lt;int&gt;, field_id &lt;int&gt;</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>   file_name name  r_type type       type_length repetition_type</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">*</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>     <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>  <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>            <span style="color: #949494; font-style: italic;">&lt;int&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>          </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">1</span> <span style="color: #BB0000;">NA</span>        c1    <span style="color: #BB0000;">NA</span>     INT32               <span style="color: #BB0000;">NA</span> <span style="color: #BB0000;">NA</span>             </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">2</span> <span style="color: #BB0000;">NA</span>        c2    <span style="color: #BB0000;">NA</span>     INT64               <span style="color: #BB0000;">NA</span> <span style="color: #BB0000;">NA</span>             </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">3</span> <span style="color: #BB0000;">NA</span>        c3    <span style="color: #BB0000;">NA</span>     BYTE_ARRAY          <span style="color: #BB0000;">NA</span> OPTIONAL       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># ℹ 6 more variables: converted_type &lt;chr&gt;, logical_type &lt;I&lt;list&gt;&gt;,</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;">#   num_children &lt;int&gt;, scale &lt;int&gt;, precision &lt;int&gt;, field_id &lt;int&gt;</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>
diff --git a/reference/read_parquet.html b/reference/read_parquet.html
index fdd7813..faed2ee 100644
--- a/reference/read_parquet.html
+++ b/reference/read_parquet.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -96,7 +96,7 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-in"><span><span class="va">parquet_df</span> <span class="op">&lt;-</span> <span class="fu">nanoparquet</span><span class="fu">::</span><span class="fu">read_parquet</span><span class="op">(</span><span class="va">file_name</span><span class="op">)</span></span></span>
 <span class="r-in"><span><span class="fu"><a href="https://rdrr.io/r/base/print.html" class="external-link">print</a></span><span class="op">(</span><span class="fu"><a href="https://rdrr.io/r/utils/str.html" class="external-link">str</a></span><span class="op">(</span><span class="va">parquet_df</span><span class="op">)</span><span class="op">)</span></span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> Classes ‘tbl’ and 'data.frame':	1000 obs. of  13 variables:</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>  $ registration: POSIXct, format: "2016-02-03 07:55:29" "2016-02-03 17:04:03" ...</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>  $ registration: POSIXct, format: "2016-02-03 07:55:29" ...</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>  $ id          : int  1 2 3 4 5 6 7 8 9 10 ...</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>  $ first_name  : chr  "Amanda" "Albert" "Evelyn" "Denise" ...</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>  $ last_name   : chr  "Jordan" "Freeman" "Morgan" "Riley" ...</span>
@@ -105,7 +105,7 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-out co"><span class="r-pr">#&gt;</span>  $ ip_address  : chr  "1.197.201.2" "218.111.175.34" "7.161.136.94" "140.35.109.83" ...</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>  $ cc          : chr  "6759521864920116" NA "6767119071901597" "3576031598965625" ...</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>  $ country     : chr  "Indonesia" "Canada" "Russia" "China" ...</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>  $ birthdate   : Date, format: "1971-03-08" "1968-01-16" ...</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>  $ birthdate   : Date, format: "1971-03-08" ...</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>  $ salary      : num  49757 150280 144973 90263 NA ...</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>  $ title       : chr  "Internal Auditor" "Accountant IV" "Structural Engineer" "Senior Cost Accountant" ...</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>  $ comments    : chr  "1E+02" NA NA NA ...</span>
diff --git a/reference/read_parquet_info.html b/reference/read_parquet_info.html
index 56f0b97..a0dfcac 100644
--- a/reference/read_parquet_info.html
+++ b/reference/read_parquet_info.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/read_parquet_metadata.html b/reference/read_parquet_metadata.html
index 87b876f..cda53ca 100644
--- a/reference/read_parquet_metadata.html
+++ b/reference/read_parquet_metadata.html
@@ -11,7 +11,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -177,55 +177,55 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-in"><span><span class="fu">nanoparquet</span><span class="fu">::</span><span class="fu">read_parquet_metadata</span><span class="op">(</span><span class="va">file_name</span><span class="op">)</span></span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> $file_meta_data</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># A data frame: 1 × 5</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>   file_name                 version num_rows key_value_metadata created_by</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>   <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                       <span style="color: #949494; font-style: italic;">&lt;int&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span> <span style="color: #949494; font-style: italic;">&lt;I&lt;list&gt;&gt;</span>          <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>     </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">1</span> /home/runner/work/_temp/…       1     <span style="text-decoration: underline;">1</span>000 <span style="color: #949494;">&lt;tbl [1 × 2]&gt;</span>      https://g…</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>   file_name              version num_rows key_value_metadata created_by</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>   <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                    <span style="color: #949494; font-style: italic;">&lt;int&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span> <span style="color: #949494; font-style: italic;">&lt;I&lt;list&gt;&gt;</span>          <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>     </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">1</span> /home/runner/work/_te…       1     <span style="text-decoration: underline;">1</span>000 <span style="color: #949494;">&lt;tbl [1 × 2]&gt;</span>      https://g…</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> </span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> $schema</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># A data frame: 14 × 12</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>    file_name name  r_type type  type_length repetition_type converted_type</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>     <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>  <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>       <span style="color: #949494; font-style: italic;">&lt;int&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>           <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>         </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 1</span> /home/ru… sche… <span style="color: #BB0000;">NA</span>     <span style="color: #BB0000;">NA</span>             <span style="color: #BB0000;">NA</span> <span style="color: #BB0000;">NA</span>              <span style="color: #BB0000;">NA</span>            </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 2</span> /home/ru… regi… POSIX… INT64          <span style="color: #BB0000;">NA</span> REQUIRED        TIMESTAMP_MIC…</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 3</span> /home/ru… id    integ… INT32          <span style="color: #BB0000;">NA</span> REQUIRED        INT_32        </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 4</span> /home/ru… firs… chara… BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL        UTF8          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 5</span> /home/ru… last… chara… BYTE…          <span style="color: #BB0000;">NA</span> REQUIRED        UTF8          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 6</span> /home/ru… email factor BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL        UTF8          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 7</span> /home/ru… gend… chara… BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL        UTF8          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 8</span> /home/ru… ip_a… chara… BYTE…          <span style="color: #BB0000;">NA</span> REQUIRED        UTF8          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 9</span> /home/ru… cc    chara… BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL        UTF8          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">10</span> /home/ru… coun… chara… BYTE…          <span style="color: #BB0000;">NA</span> REQUIRED        UTF8          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">11</span> /home/ru… birt… Date   INT32          <span style="color: #BB0000;">NA</span> OPTIONAL        DATE          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">12</span> /home/ru… sala… double DOUB…          <span style="color: #BB0000;">NA</span> OPTIONAL        <span style="color: #BB0000;">NA</span>            </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">13</span> /home/ru… title chara… BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL        UTF8          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">14</span> /home/ru… comm… chara… BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL        UTF8          </span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># ℹ 5 more variables: logical_type &lt;I&lt;list&gt;&gt;, num_children &lt;int&gt;,</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;">#   scale &lt;int&gt;, precision &lt;int&gt;, field_id &lt;int&gt;</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>    file_name             name  r_type type  type_length repetition_type</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                 <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>  <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>       <span style="color: #949494; font-style: italic;">&lt;int&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>          </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 1</span> /home/runner/work/_t… sche… <span style="color: #BB0000;">NA</span>     <span style="color: #BB0000;">NA</span>             <span style="color: #BB0000;">NA</span> <span style="color: #BB0000;">NA</span>             </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 2</span> /home/runner/work/_t… regi… POSIX… INT64          <span style="color: #BB0000;">NA</span> REQUIRED       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 3</span> /home/runner/work/_t… id    integ… INT32          <span style="color: #BB0000;">NA</span> REQUIRED       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 4</span> /home/runner/work/_t… firs… chara… BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 5</span> /home/runner/work/_t… last… chara… BYTE…          <span style="color: #BB0000;">NA</span> REQUIRED       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 6</span> /home/runner/work/_t… email factor BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 7</span> /home/runner/work/_t… gend… chara… BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 8</span> /home/runner/work/_t… ip_a… chara… BYTE…          <span style="color: #BB0000;">NA</span> REQUIRED       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 9</span> /home/runner/work/_t… cc    chara… BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">10</span> /home/runner/work/_t… coun… chara… BYTE…          <span style="color: #BB0000;">NA</span> REQUIRED       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">11</span> /home/runner/work/_t… birt… Date   INT32          <span style="color: #BB0000;">NA</span> OPTIONAL       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">12</span> /home/runner/work/_t… sala… double DOUB…          <span style="color: #BB0000;">NA</span> OPTIONAL       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">13</span> /home/runner/work/_t… title chara… BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">14</span> /home/runner/work/_t… comm… chara… BYTE…          <span style="color: #BB0000;">NA</span> OPTIONAL       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># ℹ 6 more variables: converted_type &lt;chr&gt;, logical_type &lt;I&lt;list&gt;&gt;,</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;">#   num_children &lt;int&gt;, scale &lt;int&gt;, precision &lt;int&gt;, field_id &lt;int&gt;</span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> </span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> $row_groups</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># A data frame: 1 × 7</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>   file_name                        id total_byte_size num_rows file_offset</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>   <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                         <span style="color: #949494; font-style: italic;">&lt;int&gt;</span>           <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span>       <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">1</span> /home/runner/work/_temp/Libr…     0           <span style="text-decoration: underline;">71</span>427     <span style="text-decoration: underline;">1</span>000          <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>   file_name                     id total_byte_size num_rows file_offset</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>   <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                      <span style="color: #949494; font-style: italic;">&lt;int&gt;</span>           <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span>       <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">1</span> /home/runner/work/_temp/L…     0           <span style="text-decoration: underline;">71</span>427     <span style="text-decoration: underline;">1</span>000          <span style="color: #BB0000;">NA</span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># ℹ 2 more variables: total_compressed_size &lt;dbl&gt;, ordinal &lt;int&gt;</span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> </span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> $column_chunks</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># A data frame: 13 × 24</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>    file_name    row_group column file_path file_offset offset_index_offset</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>            <span style="color: #949494; font-style: italic;">&lt;int&gt;</span>  <span style="color: #949494; font-style: italic;">&lt;int&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>           <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span>               <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 1</span> /home/runne…         0      0 <span style="color: #BB0000;">NA</span>                  4                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 2</span> /home/runne…         0      1 <span style="color: #BB0000;">NA</span>               <span style="text-decoration: underline;">6</span>741                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 3</span> /home/runne…         0      2 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">12</span>259                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 4</span> /home/runne…         0      3 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">15</span>211                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 5</span> /home/runne…         0      4 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">16</span>239                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 6</span> /home/runne…         0      5 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">31</span>759                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 7</span> /home/runne…         0      6 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">32</span>031                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 8</span> /home/runne…         0      7 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">42</span>952                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 9</span> /home/runne…         0      8 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">55</span>009                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">10</span> /home/runne…         0      9 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">55</span>925                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">11</span> /home/runne…         0     10 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">59</span>312                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">12</span> /home/runne…         0     11 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">67</span>026                  <span style="color: #BB0000;">NA</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">13</span> /home/runne…         0     12 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">71</span>089                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>    file_name row_group column file_path file_offset offset_index_offset</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>         <span style="color: #949494; font-style: italic;">&lt;int&gt;</span>  <span style="color: #949494; font-style: italic;">&lt;int&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>           <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span>               <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 1</span> /home/ru…         0      0 <span style="color: #BB0000;">NA</span>                  4                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 2</span> /home/ru…         0      1 <span style="color: #BB0000;">NA</span>               <span style="text-decoration: underline;">6</span>741                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 3</span> /home/ru…         0      2 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">12</span>259                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 4</span> /home/ru…         0      3 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">15</span>211                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 5</span> /home/ru…         0      4 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">16</span>239                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 6</span> /home/ru…         0      5 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">31</span>759                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 7</span> /home/ru…         0      6 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">32</span>031                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 8</span> /home/ru…         0      7 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">42</span>952                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 9</span> /home/ru…         0      8 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">55</span>009                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">10</span> /home/ru…         0      9 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">55</span>925                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">11</span> /home/ru…         0     10 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">59</span>312                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">12</span> /home/ru…         0     11 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">67</span>026                  <span style="color: #BB0000;">NA</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">13</span> /home/ru…         0     12 <span style="color: #BB0000;">NA</span>              <span style="text-decoration: underline;">71</span>089                  <span style="color: #BB0000;">NA</span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># ℹ 18 more variables: offset_index_length &lt;int&gt;,</span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;">#   column_index_offset &lt;dbl&gt;, column_index_length &lt;int&gt;, type &lt;chr&gt;,</span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;">#   encodings &lt;I&lt;list&gt;&gt;, path_in_schema &lt;I&lt;list&gt;&gt;, codec &lt;chr&gt;,</span></span>
diff --git a/reference/read_parquet_page.html b/reference/read_parquet_page.html
index 41d9151..be5621d 100644
--- a/reference/read_parquet_page.html
+++ b/reference/read_parquet_page.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -99,27 +99,27 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
     <div class="sourceCode"><pre class="sourceCode r"><code><span class="r-in"><span><span class="va">file_name</span> <span class="op">&lt;-</span> <span class="fu"><a href="https://rdrr.io/r/base/system.file.html" class="external-link">system.file</a></span><span class="op">(</span><span class="st">"extdata/userdata1.parquet"</span>, package <span class="op">=</span> <span class="st">"nanoparquet"</span><span class="op">)</span></span></span>
 <span class="r-in"><span><span class="fu">nanoparquet</span><span class="fu">:::</span><span class="fu"><a href="read_parquet_pages.html">read_parquet_pages</a></span><span class="op">(</span><span class="va">file_name</span><span class="op">)</span></span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># A data frame: 19 × 14</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>    file_name                 row_group column page_type page_header_offset</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                         <span style="color: #949494; font-style: italic;">&lt;int&gt;</span>  <span style="color: #949494; font-style: italic;">&lt;int&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                  <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 1</span> /home/runner/work/_temp/…         0      0 DATA_PAGE                  4</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 2</span> /home/runner/work/_temp/…         0      1 DATA_PAGE               <span style="text-decoration: underline;">6</span>741</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 3</span> /home/runner/work/_temp/…         0      2 DICTIONA…              <span style="text-decoration: underline;">10</span>766</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 4</span> /home/runner/work/_temp/…         0      2 DATA_PAGE              <span style="text-decoration: underline;">12</span>259</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 5</span> /home/runner/work/_temp/…         0      3 DICTIONA…              <span style="text-decoration: underline;">13</span>334</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 6</span> /home/runner/work/_temp/…         0      3 DATA_PAGE              <span style="text-decoration: underline;">15</span>211</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 7</span> /home/runner/work/_temp/…         0      4 DATA_PAGE              <span style="text-decoration: underline;">16</span>239</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 8</span> /home/runner/work/_temp/…         0      5 DICTIONA…              <span style="text-decoration: underline;">31</span>726</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 9</span> /home/runner/work/_temp/…         0      5 DATA_PAGE              <span style="text-decoration: underline;">31</span>759</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">10</span> /home/runner/work/_temp/…         0      6 DATA_PAGE              <span style="text-decoration: underline;">32</span>031</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">11</span> /home/runner/work/_temp/…         0      7 DATA_PAGE              <span style="text-decoration: underline;">42</span>952</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">12</span> /home/runner/work/_temp/…         0      8 DICTIONA…              <span style="text-decoration: underline;">53</span>749</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">13</span> /home/runner/work/_temp/…         0      8 DATA_PAGE              <span style="text-decoration: underline;">55</span>009</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">14</span> /home/runner/work/_temp/…         0      9 DATA_PAGE              <span style="text-decoration: underline;">55</span>925</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">15</span> /home/runner/work/_temp/…         0     10 DATA_PAGE              <span style="text-decoration: underline;">59</span>312</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">16</span> /home/runner/work/_temp/…         0     11 DICTIONA…              <span style="text-decoration: underline;">65</span>063</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">17</span> /home/runner/work/_temp/…         0     11 DATA_PAGE              <span style="text-decoration: underline;">67</span>026</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">18</span> /home/runner/work/_temp/…         0     12 DICTIONA…              <span style="text-decoration: underline;">68</span>019</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">19</span> /home/runner/work/_temp/…         0     12 DATA_PAGE              <span style="text-decoration: underline;">71</span>089</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>    file_name              row_group column page_type page_header_offset</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                      <span style="color: #949494; font-style: italic;">&lt;int&gt;</span>  <span style="color: #949494; font-style: italic;">&lt;int&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                  <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 1</span> /home/runner/work/_te…         0      0 DATA_PAGE                  4</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 2</span> /home/runner/work/_te…         0      1 DATA_PAGE               <span style="text-decoration: underline;">6</span>741</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 3</span> /home/runner/work/_te…         0      2 DICTIONA…              <span style="text-decoration: underline;">10</span>766</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 4</span> /home/runner/work/_te…         0      2 DATA_PAGE              <span style="text-decoration: underline;">12</span>259</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 5</span> /home/runner/work/_te…         0      3 DICTIONA…              <span style="text-decoration: underline;">13</span>334</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 6</span> /home/runner/work/_te…         0      3 DATA_PAGE              <span style="text-decoration: underline;">15</span>211</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 7</span> /home/runner/work/_te…         0      4 DATA_PAGE              <span style="text-decoration: underline;">16</span>239</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 8</span> /home/runner/work/_te…         0      5 DICTIONA…              <span style="text-decoration: underline;">31</span>726</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 9</span> /home/runner/work/_te…         0      5 DATA_PAGE              <span style="text-decoration: underline;">31</span>759</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">10</span> /home/runner/work/_te…         0      6 DATA_PAGE              <span style="text-decoration: underline;">32</span>031</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">11</span> /home/runner/work/_te…         0      7 DATA_PAGE              <span style="text-decoration: underline;">42</span>952</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">12</span> /home/runner/work/_te…         0      8 DICTIONA…              <span style="text-decoration: underline;">53</span>749</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">13</span> /home/runner/work/_te…         0      8 DATA_PAGE              <span style="text-decoration: underline;">55</span>009</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">14</span> /home/runner/work/_te…         0      9 DATA_PAGE              <span style="text-decoration: underline;">55</span>925</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">15</span> /home/runner/work/_te…         0     10 DATA_PAGE              <span style="text-decoration: underline;">59</span>312</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">16</span> /home/runner/work/_te…         0     11 DICTIONA…              <span style="text-decoration: underline;">65</span>063</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">17</span> /home/runner/work/_te…         0     11 DATA_PAGE              <span style="text-decoration: underline;">67</span>026</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">18</span> /home/runner/work/_te…         0     12 DICTIONA…              <span style="text-decoration: underline;">68</span>019</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">19</span> /home/runner/work/_te…         0     12 DATA_PAGE              <span style="text-decoration: underline;">71</span>089</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># ℹ 9 more variables: uncompressed_page_size &lt;int&gt;,</span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;">#   compressed_page_size &lt;int&gt;, crc &lt;int&gt;, num_values &lt;int&gt;,</span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;">#   encoding &lt;chr&gt;, definition_level_encoding &lt;chr&gt;,</span></span>
@@ -185,11 +185,11 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-out co"><span class="r-pr">#&gt;</span>  [1] 15 00 15 80 7d 15 fa 68 2c 15 d0 0f 15 00 15 00 15 00 00 00</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> </span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> $data</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>   [1] 40 be 0c f1 d8 2a 05 00 c0 86 e0 9a e0 2a 05 00 c0 28 33 45 d3 2a 05</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>  [24] 00 40 2b 96 ce d2 2a 05 00 c0 9c 33 91 d6 2a 05 00 80 a2 54 7b d8 2a</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>  [47] 05 00 00 59 b2 77 d9 2a 05 00 80 ee 7d fc d7 2a 05 00 40 cf 71 8d d5</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>  [70] 2a 05 00 c0 bc 7b cd e1 2a 05 00 80 e4 da 72 d2 2a 05 00 80 30 4d 73</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>  [93] e1 2a 05 00 40 fe a4 0f</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>   [1] 40 be 0c f1 d8 2a 05 00 c0 86 e0 9a e0 2a 05 00 c0 28 33 45 d3 2a</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>  [23] 05 00 40 2b 96 ce d2 2a 05 00 c0 9c 33 91 d6 2a 05 00 80 a2 54 7b</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>  [45] d8 2a 05 00 00 59 b2 77 d9 2a 05 00 80 ee 7d fc d7 2a 05 00 40 cf</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>  [67] 71 8d d5 2a 05 00 c0 bc 7b cd e1 2a 05 00 80 e4 da 72 d2 2a 05 00</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>  [89] 80 30 4d 73 e1 2a 05 00 40 fe a4 0f</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>  [ reached getOption("max.print") -- omitted 7900 entries ]</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> </span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> $definition_levels_byte_length</span>
@@ -205,11 +205,11 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-out co"><span class="r-pr">#&gt;</span> [1] NA</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> </span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> $compressed_data</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>   [1] c0 3e 30 40 be 0c f1 d8 2a 05 00 c0 86 e0 9a e0 01 08 2c 28 33 45 d3</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>  [24] 2a 05 00 40 2b 96 ce d2 01 10 28 9c 33 91 d6 2a 05 00 80 a2 54 7b 01</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>  [47] 28 10 00 59 b2 77 d9 01 10 0c ee 7d fc d7 01 28 0c cf 71 8d d5 01 28</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>  [70] 0c bc 7b cd e1 01 18 08 e4 da 72 01 38 0c 80 30 4d 73 01 10 30 40 fe</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>  [93] a4 0f e2 2a 05 00 00 eb</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>   [1] c0 3e 30 40 be 0c f1 d8 2a 05 00 c0 86 e0 9a e0 01 08 2c 28 33 45</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>  [23] d3 2a 05 00 40 2b 96 ce d2 01 10 28 9c 33 91 d6 2a 05 00 80 a2 54</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>  [45] 7b 01 28 10 00 59 b2 77 d9 01 10 0c ee 7d fc d7 01 28 0c cf 71 8d</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>  [67] d5 01 28 0c bc 7b cd e1 01 18 08 e4 da 72 01 38 0c 80 30 4d 73 01</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>  [89] 10 30 40 fe a4 0f e2 2a 05 00 00 eb</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>  [ reached getOption("max.print") -- omitted 6617 entries ]</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> </span>
 </code></pre></div>
diff --git a/reference/read_parquet_pages.html b/reference/read_parquet_pages.html
index 006b1b5..f88a740 100644
--- a/reference/read_parquet_pages.html
+++ b/reference/read_parquet_pages.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -107,27 +107,27 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
     <div class="sourceCode"><pre class="sourceCode r"><code><span class="r-in"><span><span class="va">file_name</span> <span class="op">&lt;-</span> <span class="fu"><a href="https://rdrr.io/r/base/system.file.html" class="external-link">system.file</a></span><span class="op">(</span><span class="st">"extdata/userdata1.parquet"</span>, package <span class="op">=</span> <span class="st">"nanoparquet"</span><span class="op">)</span></span></span>
 <span class="r-in"><span><span class="fu">nanoparquet</span><span class="fu">:::</span><span class="fu">read_parquet_pages</span><span class="op">(</span><span class="va">file_name</span><span class="op">)</span></span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># A data frame: 19 × 14</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>    file_name                 row_group column page_type page_header_offset</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                         <span style="color: #949494; font-style: italic;">&lt;int&gt;</span>  <span style="color: #949494; font-style: italic;">&lt;int&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                  <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span></span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 1</span> /home/runner/work/_temp/…         0      0 DATA_PAGE                  4</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 2</span> /home/runner/work/_temp/…         0      1 DATA_PAGE               <span style="text-decoration: underline;">6</span>741</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 3</span> /home/runner/work/_temp/…         0      2 DICTIONA…              <span style="text-decoration: underline;">10</span>766</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 4</span> /home/runner/work/_temp/…         0      2 DATA_PAGE              <span style="text-decoration: underline;">12</span>259</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 5</span> /home/runner/work/_temp/…         0      3 DICTIONA…              <span style="text-decoration: underline;">13</span>334</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 6</span> /home/runner/work/_temp/…         0      3 DATA_PAGE              <span style="text-decoration: underline;">15</span>211</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 7</span> /home/runner/work/_temp/…         0      4 DATA_PAGE              <span style="text-decoration: underline;">16</span>239</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 8</span> /home/runner/work/_temp/…         0      5 DICTIONA…              <span style="text-decoration: underline;">31</span>726</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 9</span> /home/runner/work/_temp/…         0      5 DATA_PAGE              <span style="text-decoration: underline;">31</span>759</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">10</span> /home/runner/work/_temp/…         0      6 DATA_PAGE              <span style="text-decoration: underline;">32</span>031</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">11</span> /home/runner/work/_temp/…         0      7 DATA_PAGE              <span style="text-decoration: underline;">42</span>952</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">12</span> /home/runner/work/_temp/…         0      8 DICTIONA…              <span style="text-decoration: underline;">53</span>749</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">13</span> /home/runner/work/_temp/…         0      8 DATA_PAGE              <span style="text-decoration: underline;">55</span>009</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">14</span> /home/runner/work/_temp/…         0      9 DATA_PAGE              <span style="text-decoration: underline;">55</span>925</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">15</span> /home/runner/work/_temp/…         0     10 DATA_PAGE              <span style="text-decoration: underline;">59</span>312</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">16</span> /home/runner/work/_temp/…         0     11 DICTIONA…              <span style="text-decoration: underline;">65</span>063</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">17</span> /home/runner/work/_temp/…         0     11 DATA_PAGE              <span style="text-decoration: underline;">67</span>026</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">18</span> /home/runner/work/_temp/…         0     12 DICTIONA…              <span style="text-decoration: underline;">68</span>019</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">19</span> /home/runner/work/_temp/…         0     12 DATA_PAGE              <span style="text-decoration: underline;">71</span>089</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>    file_name              row_group column page_type page_header_offset</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span>    <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                      <span style="color: #949494; font-style: italic;">&lt;int&gt;</span>  <span style="color: #949494; font-style: italic;">&lt;int&gt;</span> <span style="color: #949494; font-style: italic;">&lt;chr&gt;</span>                  <span style="color: #949494; font-style: italic;">&lt;dbl&gt;</span></span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 1</span> /home/runner/work/_te…         0      0 DATA_PAGE                  4</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 2</span> /home/runner/work/_te…         0      1 DATA_PAGE               <span style="text-decoration: underline;">6</span>741</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 3</span> /home/runner/work/_te…         0      2 DICTIONA…              <span style="text-decoration: underline;">10</span>766</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 4</span> /home/runner/work/_te…         0      2 DATA_PAGE              <span style="text-decoration: underline;">12</span>259</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 5</span> /home/runner/work/_te…         0      3 DICTIONA…              <span style="text-decoration: underline;">13</span>334</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 6</span> /home/runner/work/_te…         0      3 DATA_PAGE              <span style="text-decoration: underline;">15</span>211</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 7</span> /home/runner/work/_te…         0      4 DATA_PAGE              <span style="text-decoration: underline;">16</span>239</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 8</span> /home/runner/work/_te…         0      5 DICTIONA…              <span style="text-decoration: underline;">31</span>726</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;"> 9</span> /home/runner/work/_te…         0      5 DATA_PAGE              <span style="text-decoration: underline;">31</span>759</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">10</span> /home/runner/work/_te…         0      6 DATA_PAGE              <span style="text-decoration: underline;">32</span>031</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">11</span> /home/runner/work/_te…         0      7 DATA_PAGE              <span style="text-decoration: underline;">42</span>952</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">12</span> /home/runner/work/_te…         0      8 DICTIONA…              <span style="text-decoration: underline;">53</span>749</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">13</span> /home/runner/work/_te…         0      8 DATA_PAGE              <span style="text-decoration: underline;">55</span>009</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">14</span> /home/runner/work/_te…         0      9 DATA_PAGE              <span style="text-decoration: underline;">55</span>925</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">15</span> /home/runner/work/_te…         0     10 DATA_PAGE              <span style="text-decoration: underline;">59</span>312</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">16</span> /home/runner/work/_te…         0     11 DICTIONA…              <span style="text-decoration: underline;">65</span>063</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">17</span> /home/runner/work/_te…         0     11 DATA_PAGE              <span style="text-decoration: underline;">67</span>026</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">18</span> /home/runner/work/_te…         0     12 DICTIONA…              <span style="text-decoration: underline;">68</span>019</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #BCBCBC;">19</span> /home/runner/work/_te…         0     12 DATA_PAGE              <span style="text-decoration: underline;">71</span>089</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;"># ℹ 9 more variables: uncompressed_page_size &lt;int&gt;,</span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;">#   compressed_page_size &lt;int&gt;, crc &lt;int&gt;, num_values &lt;int&gt;,</span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> <span style="color: #949494;">#   encoding &lt;chr&gt;, definition_level_encoding &lt;chr&gt;,</span></span>
diff --git a/reference/read_parquet_schema.html b/reference/read_parquet_schema.html
index b99667d..c4d68fb 100644
--- a/reference/read_parquet_schema.html
+++ b/reference/read_parquet_schema.html
@@ -11,7 +11,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/rle_decode_int.html b/reference/rle_decode_int.html
index d894666..6e9fab9 100644
--- a/reference/rle_decode_int.html
+++ b/reference/rle_decode_int.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/rle_encode_int.html b/reference/rle_encode_int.html
index 1e5f472..cfe6dc7 100644
--- a/reference/rle_encode_int.html
+++ b/reference/rle_encode_int.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/reference/write_parquet.html b/reference/write_parquet.html
index 02e4711..59f442e 100644
--- a/reference/write_parquet.html
+++ b/reference/write_parquet.html
@@ -7,7 +7,7 @@
 
     <a class="navbar-brand me-2" href="../index.html">nanoparquet</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.1</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="Released version">0.4.2</small>
 
 
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/search.json b/search.json
index 1b3c6b0..48538a8 100644
--- a/search.json
+++ b/search.json
@@ -1 +1 @@
-[{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"goals","dir":"Articles","previous_headings":"","what":"Goals","title":"Benchmarks","text":"First, want measure nanoparquet’s speed relative good quality CSV readers writers, also look sizes Parquet CSV files. Second, want see nanoparquet fares relative Parquet implementations available R.","code":"library(dplyr) library(gt) library(gtExtras)"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"data-sets","dir":"Articles","previous_headings":"","what":"Data sets","title":"Benchmarks","text":"used use three data sets: small, medium large. small data set nycflights13::flights data set, . medium data set contains 20 copies small data set. large data set contains 200 copies small data set. See gen_data() function benchmark-funcs.R file nanoparquet GitHub repository. basic information data set: quick look data:","code":"if (file.exists(file.path(me, \"data-info.parquet\"))) {   info_tab <- nanoparquet::read_parquet(file.path(me, \"data-info.parquet\")) } else {   get_data_info <- function(x) {     list(dim = dim(x), size = object.size(x))   }   info <- lapply(data_sizes, function(s) get_data_info(gen_data(s)))   info_tab <- data.frame(     check.names = FALSE,     name = data_sizes,     rows = sapply(info, \"[[\", \"dim\")[1,],     columns = sapply(info, \"[[\", \"dim\")[2,],     \"size in memory\" = sapply(info, \"[[\", \"size\")   )   nanoparquet::write_parquet(info_tab, file.path(me, \"data-info.parquet\")) } info_tab |>   gt() |>   tab_header(title = \"Data sets\") |>   tab_options(table.align = \"left\") |>   fmt_integer() |>   fmt_bytes(columns = \"size in memory\") head(nycflights13::flights) #> # A tibble: 6 × 19 #>    year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time #>   <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int> #> 1  2013     1     1      517            515         2      830            819 #> 2  2013     1     1      533            529         4      850            830 #> 3  2013     1     1      542            540         2      923            850 #> 4  2013     1     1      544            545        -1     1004           1022 #> 5  2013     1     1      554            600        -6      812            837 #> 6  2013     1     1      554            558        -4      740            728 #> # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>, #> #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, #> #   hour <dbl>, minute <dbl>, time_hour <dttm> dplyr::glimpse(nycflights13::flights) #> Rows: 336,776 #> Columns: 19 #> $ year           <int> 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2… #> $ month          <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1… #> $ day            <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1… #> $ dep_time       <int> 517, 533, 542, 544, 554, 554, 555, 557, 557, 558, 558, … #> $ sched_dep_time <int> 515, 529, 540, 545, 600, 558, 600, 600, 600, 600, 600, … #> $ dep_delay      <dbl> 2, 4, 2, -1, -6, -4, -5, -3, -3, -2, -2, -2, -2, -2, -1… #> $ arr_time       <int> 830, 850, 923, 1004, 812, 740, 913, 709, 838, 753, 849,… #> $ sched_arr_time <int> 819, 830, 850, 1022, 837, 728, 854, 723, 846, 745, 851,… #> $ arr_delay      <dbl> 11, 20, 33, -18, -25, 12, 19, -14, -8, 8, -2, -3, 7, -1… #> $ carrier        <chr> \"UA\", \"UA\", \"AA\", \"B6\", \"DL\", \"UA\", \"B6\", \"EV\", \"B6\", \"… #> $ flight         <int> 1545, 1714, 1141, 725, 461, 1696, 507, 5708, 79, 301, 4… #> $ tailnum        <chr> \"N14228\", \"N24211\", \"N619AA\", \"N804JB\", \"N668DN\", \"N394… #> $ origin         <chr> \"EWR\", \"LGA\", \"JFK\", \"JFK\", \"LGA\", \"EWR\", \"EWR\", \"LGA\",… #> $ dest           <chr> \"IAH\", \"IAH\", \"MIA\", \"BQN\", \"ATL\", \"ORD\", \"FLL\", \"IAD\",… #> $ air_time       <dbl> 227, 227, 160, 183, 116, 150, 158, 53, 140, 138, 149, 1… #> $ distance       <dbl> 1400, 1416, 1089, 1576, 762, 719, 1065, 229, 944, 733, … #> $ hour           <dbl> 5, 5, 5, 5, 6, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 6… #> $ minute         <dbl> 15, 29, 40, 45, 0, 58, 0, 0, 0, 0, 0, 0, 0, 0, 0, 59, 0… #> $ time_hour      <dttm> 2013-01-01 05:00:00, 2013-01-01 05:00:00, 2013-01-01 0…"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"parquet-implementations","dir":"Articles","previous_headings":"","what":"Parquet implementations","title":"Benchmarks","text":"ran nanoparquet, Arrow DuckDB. also ran data.table without compression readr, read/write CSV files. used running time readr baseline. ran benchmark three times record results third run. make sure data software swapped OS. (Except readr large data set, take long.) include complete raw results end article.","code":"if (file.exists(file.path(me, \"results.parquet\"))) {   results <- nanoparquet::read_parquet(file.path(me, \"results.parquet\")) } else {   results <- NULL   lapply(data_sizes[1:2], function(s) {     lapply(variants, function(v) {       r <- if (v == \"readr\" && s == \"large\") {         measure(v, s)       } else {         measure(v, s)         measure(v, s)         measure(v, s)       }       results <<- rbind(results, r)     })   })   nanoparquet::write_parquet(results, file.path(me, \"results.parquet\")) }"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"parquet-vs-csv","dir":"Articles","previous_headings":"","what":"Parquet vs CSV","title":"Benchmarks","text":"results, focusing CSV readers nanoparquet: Notes: single-threaded nanoparquet Parquet-reader competitive. can read compressed Parquet file just fast state art uncompressed CSV reader uses least 2 threads. nanoparquet vs CSV results writing Parquet CSV files: Notes: data.table CSV writer 3 times fast nanoparquet Parquet writer, CSV file uncompressed. CSV writer uses least 4 threads, Parquet write single-threaded. nanoparquet Parquet writer 2-5 times faster data.table CSV writer CSV file compressed. Parquet files 5-6 times smaller uncompressed CSV files 30-35% smaller compressed CSV files.","code":"csv_tab_read <- results |>   filter(software %in% c(\"nanoparquet\", \"data.table\", \"data.table.gz\", \"readr\")) |>   filter(direction == \"read\") |>   mutate(software = case_when(     software ==  \"data.table.gz\" ~ \"data.table (compressed)\",     .default = software   )) |>   rename(`data size` = data_size, time = time_elapsed) |>   mutate(memory = mem_max_after - mem_before) |>   mutate(base = tail(time, 1), .by = `data size`) |>   mutate(speedup = base / time, x = round(speedup, digits = 1)) |>   select(`data size`, software, time, x, speedup, memory) |>   mutate(rawtime = time, time = prettyunits::pretty_sec(time)) |>   rename(`speedup from CSV` = speedup)  csv_tab_read |>   gt() |>   tab_header(title = \"Parquet vs CSV, reading\") |>   tab_options(table.align = \"left\") |>   tab_row_group(md(\"**small data**\"), rows = `data size` == \"small\", \"s\") |>   tab_row_group(md(\"**medium data**\"), rows = `data size` == \"medium\", \"m\") |>   tab_row_group(md(\"**large data**\"), rows = `data size` == \"large\", \"l\") |>   row_group_order(c(\"s\", \"m\", \"l\")) |>   cols_hide(columns = c(`data size`, rawtime)) |>   cols_align(columns = time, align = \"right\") |>   fmt_bytes(columns = memory) |>   gt_plt_bar(column = `speedup from CSV`) csv_tab_write <- results |>   filter(software %in% c(\"nanoparquet\", \"data.table\", \"data.table.gz\", \"readr\")) |>   filter(direction == \"write\") |>   mutate(software = case_when(     software ==  \"data.table.gz\" ~ \"data.table (compressed)\",     .default = software   )) |>   rename(`data size` = data_size, time = time_elapsed, `file size` = file_size) |>   mutate(memory = mem_max_after - mem_before) |>   mutate(base = tail(time, 1), .by = `data size`) |>   mutate(speedup = base / time, x = round(speedup, digits = 1)) |>   select(`data size`, software, time, x, speedup, memory, `file size`) |>   mutate(rawtime = time, time = prettyunits::pretty_sec(time)) |>   rename(`speedup from CSV` = speedup)  csv_tab_write |>   gt() |>   tab_header(title = \"Parquet vs CSV, writing\") |>   tab_options(table.align = \"left\") |>   tab_row_group(md(\"**small data**\"), rows = `data size` == \"small\", \"s\") |>   tab_row_group(md(\"**medium data**\"), rows = `data size` == \"medium\", \"m\") |>   tab_row_group(md(\"**large data**\"), rows = `data size` == \"large\", \"l\") |>   row_group_order(c(\"s\", \"m\", \"l\")) |>   cols_hide(columns = c(`data size`, rawtime)) |>   cols_align(columns = time, align = \"right\") |>   fmt_bytes(columns = c(memory, `file size`)) |>   gt_plt_bar(column = `speedup from CSV`)"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"parquet-implementations-1","dir":"Articles","previous_headings":"","what":"Parquet implementations","title":"Benchmarks","text":"summary Parquet readers, three files. Notes: general, three implementations perform similarly. nanoparquet competitive three data sets terms speed also tends use least amount memory. turned ALTREP arrow, reads data memory. summary Parquet writers: Notes: nanoparquet competitive terms speed, slightly faster two implementations, data sets. DuckDB seems waste space writing Parquet files. possibly fine tuned forcing different encoding. behavior improve forthcoming DuckDB 1.2.0 release, see also https://github.com/duckdb/duckdb/issues/3316.","code":"pq_tab_read <- results |>   filter(software %in% c(\"nanoparquet\", \"arrow\", \"duckdb\", \"readr\")) |>   filter(direction == \"read\") |>   rename(`data size` = data_size, time = time_elapsed) |>   mutate(memory = mem_max_after - mem_before) |>   mutate(base = tail(time, 1), .by = `data size`) |>   mutate(speedup = base / time, x = round(speedup, digits = 1)) |>   select(`data size`, software, time, x, speedup, memory) |>   mutate(rawtime = time, time = prettyunits::pretty_sec(time)) |>   filter(software %in% c(\"nanoparquet\", \"arrow\", \"duckdb\")) |>   mutate(software = case_when(     software ==  \"arrow\" ~ \"Arrow\",     software == \"duckdb\" ~ \"DuckDB\",     .default = software   )) |>   rename(`speedup from CSV` = speedup)  pq_tab_read |>   gt() |>   tab_header(title = \"Parquet implementations, reading\") |>   tab_options(table.align = \"left\") |>   tab_row_group(md(\"**small data**\"), rows = `data size` == \"small\", \"s\") |>   tab_row_group(md(\"**medium data**\"), rows = `data size` == \"medium\", \"m\") |>   tab_row_group(md(\"**large data**\"), rows = `data size` == \"large\", \"l\") |>   row_group_order(c(\"s\", \"m\", \"l\")) |>   cols_hide(columns = c(`data size`, rawtime)) |>   cols_align(columns = time, align = \"right\") |>   fmt_bytes(columns = memory) |>   gt_plt_bar(column = `speedup from CSV`) pq_tab_write <- results |>   filter(software %in% c(\"nanoparquet\", \"arrow\", \"duckdb\", \"readr\")) |>   filter(direction == \"write\") |>   rename(`data size` = data_size, time = time_elapsed, `file size` = file_size) |>   mutate(memory = mem_max_after - mem_before) |>   mutate(base = tail(time, 1), .by = `data size`) |>   mutate(speedup = base / time, x = round(speedup, digits = 1)) |>   select(`data size`, software, time, x, speedup, memory, `file size`) |>   mutate(rawtime = time, time = prettyunits::pretty_sec(time)) |>   filter(software %in% c(\"nanoparquet\", \"arrow\", \"duckdb\", \"readr\")) |>   mutate(software = case_when(     software ==  \"arrow\" ~ \"Arrow\",     software == \"duckdb\" ~ \"DuckDB\",     .default = software   )) |>   rename(`speedup from CSV` = speedup)  pq_tab_write |>   gt() |>   tab_header(title = \"Parquet implementations, writing\") |>   tab_options(table.align = \"left\") |>   tab_row_group(md(\"**small data**\"), rows = `data size` == \"small\", \"s\") |>   tab_row_group(md(\"**medium data**\"), rows = `data size` == \"medium\", \"m\") |>   tab_row_group(md(\"**large data**\"), rows = `data size` == \"large\", \"l\") |>   row_group_order(c(\"s\", \"m\", \"l\")) |>   cols_hide(columns = c(`data size`, rawtime)) |>   cols_align(columns = time, align = \"right\") |>   fmt_bytes(columns = c(memory, `file size`)) |>   gt_plt_bar(column = `speedup from CSV`)"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"conclusions","dir":"Articles","previous_headings":"","what":"Conclusions","title":"Benchmarks","text":"results probably change different data sets, different system. particular, Arrow DuckDB probably faster larger systems, data stored multiple physical disks. Arrow DuckDB let run queries data without loading memory first. especially important data fit memory , even columns needed analysis. nanoparquet . However, general, based benchmarks good reasons trust nanoparquet Parquet reader writer competitive implementations available R, terms speed memory use. limitations nanoparquet prohibitive use case, good choice Parquet /O.","code":""},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"raw-benchmark-results","dir":"Articles","previous_headings":"","what":"Raw benchmark results","title":"Benchmarks","text":"raw results. can scroll right screen wide enough whole table. Notes: User time (time_user) plus system time (time_system) can larger elapsed time (time_elapsed) multithreaded implementations indeed tools, except nanoparquet, single-threaded. memory columns bytes. mem_before RSS size reading/writing. mem_max_before maximum RSS size process . mem_max_after maximum RSS size process read/write operation. can calculate (estimate) memory usage tool subtracting mem_before mem_max_after. overestimate memory usage mem_max_after mem_max_before, never happens practice. reading file, mem_max_after includes memory needed store data set . (See data sizes .) arrow, turned ALTREP using options(arrow.use_altrep = FALSE), see benchmarks-funcs.R file. Otherwise arrow actually read data memory.","code":"print(results, n = Inf) #> # A data frame: 36 × 10 #>    software      direction data_size time_user time_system time_elapsed mem_before mem_max_before mem_max_after  file_size #>    <chr>         <chr>     <chr>         <dbl>       <dbl>        <dbl>      <dbl>          <dbl>         <dbl>      <dbl> #>  1 nanoparquet   read      small        0.0220     0.007         0.0290  156909568      156909568     236765184         NA #>  2 nanoparquet   write     small        0.103      0.015         0.117   305168384      305168384     386613248    5687737 #>  3 arrow         read      small        0.06       0.023         0.0400  160317440      160317440     267173888         NA #>  4 arrow         write     small        0.149      0.00700       0.151   306151424      306151424     340574208    5693381 #>  5 duckdb        read      small        0.081      0.018         0.0660  166313984      166313984     286916608         NA #>  6 duckdb        write     small        0.283      0.025         0.207   309510144      309510144     465649664   10684818 #>  7 data.table    read      small        0.137      0.016         0.0590  164282368      164282368     231325696         NA #>  8 data.table    write     small        0.158      0.0100        0.0620  313851904      313851904     314769408   30960660 #>  9 data.table.gz read      small        0.215      0.026         0.15    164986880      164986880     278757376         NA #> 10 data.table.gz write     small        1.45       0.014         0.386   310034432      310034432     311033856    8263176 #> 11 readr         read      small        1.08       0.27          0.415   162152448      162152448     350666752         NA #> 12 readr         write     small        1.78       1.85          0.781   314736640      314736640     359104512   31053850 #> 13 nanoparquet   read      medium       0.84       0.139         0.979   158351360      158351360    1640300544         NA #> 14 nanoparquet   write     medium       1.97       0.227         2.20   1079656448     1079656448    1762787328  111363363 #> 15 arrow         read      medium       1.40       0.265         0.982   168099840      168099840    2229256192         NA #> 16 arrow         write     medium       2.65       0.065         2.60   1090486272     1090486272    1380417536  112167843 #> 17 duckdb        read      medium       1.82       0.331         1.12    160743424      160743424    2224111616         NA #> 18 duckdb        write     medium       7.07       0.353         2.38   1099300864     1099300864    3086221312  213168966 #> 19 data.table    read      medium       2.36       0.135         0.891   159596544      159596544    1453031424         NA #> 20 data.table    write     medium       2.60       0.098         0.744  1086357504     1086357504    1088962560  619210198 #> 21 data.table.gz read      medium       3.26       0.305         1.98    155844608      155844608    1516044288         NA #> 22 data.table.gz write     medium      27.6        0.084         7.01   1092681728     1092681728    1095352320  165249944 #> 23 readr         read      medium      19.1        5.35          5.10    158367744      158367744    3874635776         NA #> 24 readr         write     medium      34.4       39.4          14.0    1090158592     1090158592    1932197888  621073998 #> 25 nanoparquet   read      large        7.25       2.44         10.8      73023488       73023488    8098021376         NA #> 26 nanoparquet   write     large       19.2        4.46         24.8    8158134272     8450293760    8450293760 1113819142 #> 27 arrow         read      large       12.0        7.32         10.8      72941568       72941568    9892495360         NA #> 28 arrow         write     large       27.9        2.31         29.9    8304607232     8573747200    8835842048 1121513329 #> 29 duckdb        read      large       16.2        5.18         14.6      75251712       75251712    8127512576         NA #> 30 duckdb        write     large       54.7       14.2          33.7    8305164288     8574451712    9348841472 2131769619 #> 31 data.table    read      large       21.6        3.87         12.8      78872576       78872576    8691007488         NA #> 32 data.table    write     large       26.3        1.69          8.09   8304033792     8573157376    8573157376 6192100558 #> 33 data.table.gz read      large       30.6        7.16         26.7      72876032       72876032    8018870272         NA #> 34 data.table.gz write     large      279.         1.93         71.6    8303362048     8572665856    8572665856 1652494401 #> 35 readr         read      large      144.       177.          231.       73564160       73564160    8500789248         NA #> 36 readr         write     large      333.       345.          143.     8304148480     8573452288    9224192000 6210738558"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"about","dir":"Articles","previous_headings":"","what":"About","title":"Benchmarks","text":"See benchmark-funcs.R file nanoparquet repository code benchmarks. ran measurement subprocess, make easier measure memory usage. include package loading time benchmarks. nanoparquet dependencies loads quickly. arrow duckdb packages might take 200ms load test system, need load dependencies also bigger.","code":"sessioninfo::session_info() #> ─ Session info ─────────────────────────────────────────────────────────────── #>  setting  value #>  version  R version 4.4.2 (2024-10-31) #>  os       Ubuntu 24.04.1 LTS #>  system   x86_64, linux-gnu #>  ui       X11 #>  language en-US #>  collate  C.UTF-8 #>  ctype    C.UTF-8 #>  tz       UTC #>  date     2025-02-10 #>  pandoc   3.1.11 @ /opt/hostedtoolcache/pandoc/3.1.11/x64/ (via rmarkdown) #>  quarto   1.6.40 @ /usr/local/bin/quarto #> #> ─ Packages ─────────────────────────────────────────────────────────────────── #>  package      * version  date (UTC) lib source #>  arrow          18.1.0.1 2025-01-08 [1] RSPM #>  assertthat     0.2.1    2019-03-21 [1] RSPM #>  base64enc      0.1-3    2015-07-28 [1] RSPM #>  bit            4.5.0.1  2024-12-03 [1] RSPM #>  bit64          4.6.0-1  2025-01-16 [1] RSPM #>  cli            3.6.3    2024-06-21 [1] RSPM #>  colorspace     2.1-1    2024-07-26 [1] RSPM #>  commonmark     1.9.2    2024-10-04 [1] RSPM #>  DBI            1.2.3    2024-06-02 [1] RSPM #>  digest         0.6.37   2024-08-19 [1] RSPM #>  dplyr        * 1.1.4    2023-11-17 [1] RSPM #>  duckdb         1.1.3-2  2025-01-24 [1] RSPM #>  evaluate       1.0.3    2025-01-10 [1] RSPM #>  farver         2.1.2    2024-05-13 [1] RSPM #>  fastmap        1.2.0    2024-05-15 [1] RSPM #>  fontawesome    0.5.3    2024-11-16 [1] RSPM #>  generics       0.1.3    2022-07-05 [1] RSPM #>  ggplot2        3.5.1    2024-04-23 [1] RSPM #>  glue           1.8.0    2024-09-30 [1] RSPM #>  gt           * 0.11.1   2024-10-04 [1] RSPM #>  gtable         0.3.6    2024-10-25 [1] RSPM #>  gtExtras     * 0.5.0    2023-09-15 [1] RSPM #>  htmltools      0.5.8.1  2024-04-04 [1] RSPM #>  jsonlite       1.8.9    2024-09-20 [1] RSPM #>  knitr          1.49     2024-11-08 [1] RSPM #>  labeling       0.4.3    2023-08-29 [1] RSPM #>  lifecycle      1.0.4    2023-11-07 [1] RSPM #>  magrittr       2.0.3    2022-03-30 [1] RSPM #>  markdown       1.13     2024-06-04 [1] RSPM #>  munsell        0.5.1    2024-04-01 [1] RSPM #>  nanoparquet    0.4.1    2025-02-10 [1] local #>  nycflights13   1.0.2    2021-04-12 [1] RSPM #>  paletteer      1.6.0    2024-01-21 [1] RSPM #>  pillar         1.10.1   2025-01-07 [1] RSPM #>  pkgconfig      2.0.3    2019-09-22 [1] RSPM #>  prettyunits    1.2.0    2023-09-24 [1] RSPM #>  purrr          1.0.4    2025-02-05 [1] RSPM #>  R6             2.5.1    2021-08-19 [1] RSPM #>  ragg           1.3.3    2024-09-11 [1] RSPM #>  rematch2       2.1.2    2020-05-01 [1] RSPM #>  rlang          1.1.5    2025-01-17 [1] RSPM #>  rmarkdown      2.29     2024-11-04 [1] RSPM #>  sass           0.4.9    2024-03-15 [1] RSPM #>  scales         1.3.0    2023-11-28 [1] RSPM #>  sessioninfo    1.2.3    2025-02-05 [1] any (@1.2.3) #>  svglite        2.1.3    2023-12-08 [1] RSPM #>  systemfonts    1.2.1    2025-01-20 [1] RSPM #>  textshaping    1.0.0    2025-01-20 [1] RSPM #>  tibble         3.2.1    2023-03-20 [1] RSPM #>  tidyselect     1.2.1    2024-03-11 [1] RSPM #>  utf8           1.2.4    2023-10-22 [1] RSPM #>  vctrs          0.6.5    2023-12-01 [1] RSPM #>  withr          3.0.2    2024-10-28 [1] RSPM #>  xfun           0.50     2025-01-07 [1] RSPM #>  xml2           1.3.6    2023-12-04 [1] RSPM #>  yaml           2.3.10   2024-07-26 [1] RSPM #> #>  [1] /home/runner/work/_temp/Library #>  [2] /opt/R/4.4.2/lib/R/site-library #>  [3] /opt/R/4.4.2/lib/R/library #>  * ── Packages attached to the search path. #> #> ──────────────────────────────────────────────────────────────────────────────"},{"path":"https://nanoparquet.r-lib.org/authors.html","id":null,"dir":"","previous_headings":"","what":"Authors","title":"Authors and Citation","text":"Gábor Csárdi. Author, maintainer. Hannes Mühleisen. Author, copyright holder. Google Inc.. Copyright holder. Apache Software Foundation. Copyright holder. . Copyright holder. RAD Game Tools. Copyright holder. Valve Software. Copyright holder. Tenacious Software LLC. Copyright holder. Facebook, Inc.. Copyright holder.","code":""},{"path":"https://nanoparquet.r-lib.org/authors.html","id":"citation","dir":"","previous_headings":"","what":"Citation","title":"Authors and Citation","text":"Csárdi G, Mühleisen H (2025). nanoparquet: Read Write 'Parquet' Files. R package version 0.4.1, https://nanoparquet.r-lib.org/, https://github.com/r-lib/nanoparquet.","code":"@Manual{,   title = {nanoparquet: Read and Write 'Parquet' Files},   author = {Gábor Csárdi and Hannes Mühleisen},   year = {2025},   note = {R package version 0.4.1,     https://nanoparquet.r-lib.org/},   url = {https://github.com/r-lib/nanoparquet}, }"},{"path":"https://nanoparquet.r-lib.org/index.html","id":"nanoparquet","dir":"","previous_headings":"","what":"Read and Write Parquet Files","title":"Read and Write Parquet Files","text":"nanoparquet reader writer common subset Parquet files.","code":""},{"path":"https://nanoparquet.r-lib.org/index.html","id":"features","dir":"","previous_headings":"","what":"Features:","title":"Read and Write Parquet Files","text":"Read write flat (.e. non-nested) Parquet files. Can read Parquet data types. Can read subset columns Parquet file. Can write many R data types, including factors temporal types Parquet. Can append data frame Parquet file without first reading rewriting whole file. Completely dependency free. Supports Snappy, Gzip Zstd compression. Competitive tools terms speed, memory use file size.","code":""},{"path":"https://nanoparquet.r-lib.org/index.html","id":"limitations","dir":"","previous_headings":"","what":"Limitations:","title":"Read and Write Parquet Files","text":"Nested Parquet types supported. Parquet logical types supported: INTERVAL, UNKNOWN. Snappy, Gzip Zstd compression supported. Encryption supported. Reading files URLs supported. nanoparquet always reads data (selected subset ) memory. work --memory data Parquet files like Apache Arrow DuckDB .","code":""},{"path":"https://nanoparquet.r-lib.org/index.html","id":"installation","dir":"","previous_headings":"","what":"Installation","title":"Read and Write Parquet Files","text":"Install R package CRAN:","code":"install.packages(\"nanoparquet\")"},{"path":[]},{"path":"https://nanoparquet.r-lib.org/index.html","id":"read","dir":"","previous_headings":"Usage","what":"Read","title":"Read and Write Parquet Files","text":"Call read_parquet() read Parquet file: see columns Parquet file types mapped R types read_parquet(), call read_parquet_schema() first: Folders similar-structured Parquet files (e.g. produced Spark) can read like :","code":"df <- nanoparquet::read_parquet(\"example.parquet\") nanoparquet::read_parquet_schema(\"example.parquet\") df <- data.table::rbindlist(lapply(   Sys.glob(\"some-folder/part-*.parquet\"),   nanoparquet::read_parquet ))"},{"path":"https://nanoparquet.r-lib.org/index.html","id":"write","dir":"","previous_headings":"Usage","what":"Write","title":"Read and Write Parquet Files","text":"Call write_parquet() write data frame Parquet file: see columns data frame mapped Parquet types write_parquet(), call infer_parquet_schema() first:","code":"nanoparquet::write_parquet(mtcars, \"mtcars.parquet\") nanoparquet::infer_parquet_schema(mtcars)"},{"path":"https://nanoparquet.r-lib.org/index.html","id":"inspect","dir":"","previous_headings":"Usage","what":"Inspect","title":"Read and Write Parquet Files","text":"Call read_parquet_info(), read_parquet_schema(), read_parquet_metadata() see various kinds metadata Parquet file: read_parquet_info() shows basic summary file. read_parquet_schema() shows columns, including non-leaf columns, mapped R types read_parquet(). read_parquet_metadata() shows complete metadata information: file meta data, schema, row groups column chunks file. find file supported isn’t, please open issue link file.","code":"nanoparquet::read_parquet_info(\"mtcars.parquet\") nanoparquet::read_parquet_schema(\"mtcars.parquet\") nanoparquet::read_parquet_metadata(\"mtcars.parquet\")"},{"path":"https://nanoparquet.r-lib.org/index.html","id":"options","dir":"","previous_headings":"","what":"Options","title":"Read and Write Parquet Files","text":"See also ?parquet_options() details. nanoparquet.class: extra class add data frames returned read_parquet(). defined, default \"tbl\", changes data frame printed pillar package loaded. nanoparquet.compression_level: See ?parquet_options() defaults possible values compression method. Inf selects maximum compression method. nanoparquet.num_rows_per_row_group: number rows put row group write_parquet(), row groups specified explicitly. integer scalar. Defaults 10 million. nanoparquet.use_arrow_metadata: unless set FALSE, read_parquet() make use Arrow metadata Parquet file. Currently used detect factor columns. nanoparquet.write_arrow_metadata: unless set FALSE, write_parquet() add Arrow metadata Parquet file. helps preserving classes columns, e.g. factors read back factors, nanoparquet Arrow. nanoparquet.write_data_page_version: Data version write default. Possible values 1 2. Default 1. nanoparquet.write_minmax_values: Whether write minimum maximum values per row group, data types support write_parquet().","code":""},{"path":"https://nanoparquet.r-lib.org/index.html","id":"license","dir":"","previous_headings":"","what":"License","title":"Read and Write Parquet Files","text":"MIT","code":""},{"path":"https://nanoparquet.r-lib.org/reference/append_parquet.html","id":null,"dir":"Reference","previous_headings":"","what":"Append a data frame to an existing Parquet file — append_parquet","title":"Append a data frame to an existing Parquet file — append_parquet","text":"schema data frame must compatible schema file.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/append_parquet.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Append a data frame to an existing Parquet file — append_parquet","text":"","code":"append_parquet(   x,   file,   compression = c(\"snappy\", \"gzip\", \"zstd\", \"uncompressed\"),   encoding = NULL,   row_groups = NULL,   options = parquet_options() )"},{"path":"https://nanoparquet.r-lib.org/reference/append_parquet.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Append a data frame to an existing Parquet file — append_parquet","text":"x Data frame append. file Path output file. compression Compression algorithm use newly written data. See write_parquet(). encoding Encoding use newly written data. encoding data file. See write_parquet() possible values. row_groups Row groups new, extended Parquet file. append_parquet() can change last existing row group, row_groups specified, respect . .e. existing file n rows, last row group starts k (k <= n), first row group row_groups refers new data must start k n+1. (simpler specify num_rows_per_row_group options, see parquet_options() instead row_groups. use row_groups need complete control.) options Nanoparquet options, new data, see parquet_options(). keep_row_groups option also affects whether append_parquet() overwrites existing row groups file.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/append_parquet.html","id":"warning","dir":"Reference","previous_headings":"","what":"Warning","title":"Append a data frame to an existing Parquet file — append_parquet","text":"function atomic! interrupted, may leave file corrupt state. work around create copy original file, append new data copy, rename new, extended file original one.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/append_parquet.html","id":"about-row-groups","dir":"Reference","previous_headings":"","what":"About row groups","title":"Append a data frame to an existing Parquet file — append_parquet","text":"Parquet file may partitioned multiple row groups, indeed large Parquet files . append_parquet() able update existing file along row group boundaries. two possibilities: append_parquet() keeps existing row groups file, creates new row groups new data. mode can forced keep_row_groups option options, see parquet_options(). Alternatively, write_parquet overwrite last row group file, existing contents plus (beginning ) new data. mode makes sense last row group small, many small row groups inefficient. default append_parquet chooses two modes automatically, aiming create row groups least num_rows_per_row_group (see parquet_options()) rows. can customize behavior keep_row_groups options row_groups argument.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/infer_parquet_schema.html","id":null,"dir":"Reference","previous_headings":"","what":"Infer Parquet schema of a data frame — infer_parquet_schema","title":"Infer Parquet schema of a data frame — infer_parquet_schema","text":"Infer Parquet schema data frame","code":""},{"path":"https://nanoparquet.r-lib.org/reference/infer_parquet_schema.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Infer Parquet schema of a data frame — infer_parquet_schema","text":"","code":"infer_parquet_schema(df, options = parquet_options())"},{"path":"https://nanoparquet.r-lib.org/reference/infer_parquet_schema.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Infer Parquet schema of a data frame — infer_parquet_schema","text":"df Data frame. options Return value parquet_options(), may modify R Parquet type mappings.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/infer_parquet_schema.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Infer Parquet schema of a data frame — infer_parquet_schema","text":"Data frame, inferred schema. columns return value read_parquet_schema(): file_name, name, r_type, type, type_length, repetition_type, converted_type, logical_type, num_children, scale, precision, field_id.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":null,"dir":"Reference","previous_headings":"","what":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Self-sufficient reader writer flat 'Parquet' files. Can read 'Parquet' data types. Can write many 'R' data types, including factors temporal types. See docs limitations.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"nanoparquet reader writer common subset Parquet files.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"features-","dir":"Reference","previous_headings":"","what":"Features:","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Read write flat (.e. non-nested) Parquet files. Can read Parquet data types. Can read subset columns Parquet file. Can write many R data types, including factors temporal types Parquet. Can append data frame Parquet file without first reading rewriting whole file. Completely dependency free. Supports Snappy, Gzip Zstd compression. Competitive tools terms speed, memory use file size.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"limitations-","dir":"Reference","previous_headings":"","what":"Limitations:","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Nested Parquet types supported. Parquet logical types supported: INTERVAL, UNKNOWN. Snappy, Gzip Zstd compression supported. Encryption supported. Reading files URLs supported. nanoparquet always reads data (selected subset ) memory. work --memory data Parquet files like Apache Arrow DuckDB .","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"installation","dir":"Reference","previous_headings":"","what":"Installation","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Install R package CRAN:","code":"install.packages(\"nanoparquet\")"},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"read","dir":"Reference","previous_headings":"","what":"Read","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Call read_parquet() read Parquet file:   see columns Parquet file types mapped R types read_parquet(), call read_parquet_schema() first:   Folders similar-structured Parquet files (e.g. produced Spark) can read like :","code":"df <- nanoparquet::read_parquet(\"example.parquet\") nanoparquet::read_parquet_schema(\"example.parquet\") df <- data.table::rbindlist(lapply(   Sys.glob(\"some-folder/part-*.parquet\"),   nanoparquet::read_parquet ))"},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"write","dir":"Reference","previous_headings":"","what":"Write","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Call write_parquet() write data frame Parquet file:   see columns data frame mapped Parquet types write_parquet(), call infer_parquet_schema() first:","code":"nanoparquet::write_parquet(mtcars, \"mtcars.parquet\") nanoparquet::infer_parquet_schema(mtcars)"},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"inspect","dir":"Reference","previous_headings":"","what":"Inspect","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Call read_parquet_info(), read_parquet_schema(), read_parquet_metadata() see various kinds metadata Parquet file: read_parquet_info() shows basic summary file. read_parquet_schema() shows columns, including non-leaf columns, mapped R types read_parquet(). read_parquet_metadata() shows complete metadata information: file meta data, schema, row groups column chunks file.   find file supported , please open issue link file.","code":"nanoparquet::read_parquet_info(\"mtcars.parquet\") nanoparquet::read_parquet_schema(\"mtcars.parquet\") nanoparquet::read_parquet_metadata(\"mtcars.parquet\")"},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"options","dir":"Reference","previous_headings":"","what":"Options","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"See also ?parquet_options() details. nanoparquet.class: extra class add data frames returned read_parquet(). defined, default \"tbl\", changes data frame printed pillar package loaded. nanoparquet.compression_level: See ?parquet_options() defaults possible values compression method. Inf selects maximum compression method. nanoparquet.num_rows_per_row_group: number rows put row group write_parquet(), row groups specified explicitly. integer scalar. Defaults 10 million. nanoparquet.use_arrow_metadata: unless set FALSE, read_parquet() make use Arrow metadata Parquet file. Currently used detect factor columns. nanoparquet.write_arrow_metadata: unless set FALSE, write_parquet() add Arrow metadata Parquet file. helps preserving classes columns, e.g. factors read back factors, nanoparquet Arrow. nanoparquet.write_data_page_version: Data version write default. Possible values 1 2. Default 1. nanoparquet.write_minmax_values: Whether write minimum maximum values per row group, data types support write_parquet().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"license","dir":"Reference","previous_headings":"","what":"License","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"MIT","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"author","dir":"Reference","previous_headings":"","what":"Author","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Maintainer: Gábor Csárdi csardi.gabor@gmail.com Authors: Hannes Mühleisen (ORCID) [copyright holder] contributors: Google Inc. [copyright holder] Apache Software Foundation [copyright holder] Posit Software, PBC [copyright holder] RAD Game Tools [copyright holder] Valve Software [copyright holder] Tenacious Software LLC [copyright holder] Facebook, Inc. [copyright holder]","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-types.html","id":null,"dir":"Reference","previous_headings":"","what":"nanoparquet's type maps — nanoparquet-types","title":"nanoparquet's type maps — nanoparquet-types","text":"nanoparquet maps R types Parquet types.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-types.html","id":"r-s-data-types","dir":"Reference","previous_headings":"","what":"R's data types","title":"nanoparquet's type maps — nanoparquet-types","text":"writing data frame, nanoparquet maps R's data types Parquet logical types. following table summary mapping. details see . non-default mappings can selected via schema argument. E.g. write factor column called 'name' ENUM, use   detailed mapping rules listed , order preference. rules likely change nanoparquet reaches version 1.0.0. Factors (.e. vectors inherit factor class) converted character vectors using .character(), written STRSXP (character vector) type. fact column factor stored Arrow metadata (see ), unless nanoparquet.write_arrow_metadata option set FALSE. Dates (.e. Date class) written DATE logical type, INT32 type internally. hms objects (hms package) written TIME(true, MILLIS). logical type, internally INT32 Parquet type. Sub-milliseconds precision lost. POSIXct objects written TIMESTAMP(true, MICROS) logical type, internally INT64 Parquet type. Sub-microsecond precision lost. difftime objects (hms objects, see ), written INT64 Parquet type, noting Arrow metadata (see ) column type Duration NANOSECONDS unit. Integer vectors (INTSXP) written INT(32, true) logical type, corresponds INT32 type. Real vectors (REALSXP) written DOUBLE type. Character vectors (STRSXP) written STRING logical type, BYTE_ARRAY type. always converted UTF-8 writing. Logical vectors (LGLSXP) written BOOLEAN type. vectors error currently. can use infer_parquet_schema() data frame map R data types Parquet data types. change default R Parquet mapping, use parquet_schema() schema argument write_parquet(). Currently supported non-default mappings : integer INT64, integer INT96, double INT96, double FLOAT, character BYTE_ARRAY, character FIXED_LEN_BYTE_ARRAY, character ENUM, factor ENUM, integer DECIAML & INT32, integer DECIAML & INT64, double DECIAML & INT32, double DECIAML & INT64, integer INT(8, *), INT(16, *), INT(32, signed), double INT(*, *), character UUID, double FLOAT16, list raw vectors BYTE_ARRAY, list raw vectors FIXED_LEN_BYTE_ARRAY.","code":"write_parquet(..., schema = parquet_schema(name = \"ENUM\"))"},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-types.html","id":"parquet-s-data-types","dir":"Reference","previous_headings":"","what":"Parquet's data types","title":"nanoparquet's type maps — nanoparquet-types","text":"reading Parquet file nanoparquet also relies logical types Arrow metadata (present, see ) addition low level data types. following table summarizes mappings. See details . exact rules . rules likely change nanoparquet reaches version 1.0.0. BOOLEAN type read logical vector (LGLSXP). STRING logical type UTF8 converted type read character vector UTF-8 encoding. DATE logical type DATE converted type read Date R object. TIME logical type TIME_MILLIS TIME_MICROS converted types read hms object, see hms package. TIMESTAMP logical type TIMESTAMP_MILLIS TIMESTAMP_MICROS converted types read POSIXct objects. logical type UTC flag set, time zone POSIXct object set UTC. INT32 read integer vector (INTSXP). INT64, DOUBLE FLOAT read real vectors (REALSXP). INT96 read POSIXct read vector tzone attribute set \"UTC\". old convention store time stamps INT96 objects. DECIMAL converted type (FIXED_LEN_BYTE_ARRAY BYTE_ARRAY type) read real vector (REALSXP), potentially losing precision. ENUM logical type read character vector. UUID logical type read character vector uses 00112233-4455-6677-8899-aabbccddeeff form. FLOAT16 logical type read real vector (REALSXP). BYTE_ARRAY read factor object file written Arrow original data type column factor. (See 'Arrow metadata .) Otherwise BYTE_ARRAY read list raw vectors, missing values denoted NULL. logical converted types read annotated low level types: INT(8, true), INT(16, true) INT(32, true) read integer vectors INT32 internally Parquet. INT(64, true) read real vector (REALSXP). Unsigned integer types INT(8, false), INT(16, false) INT(32, false) read integer vectors (INTSXP). Large positive values may overflow negative values, known issue fix. INT(64, false) read real vector (REALSXP). Large positive values may overflow negative values, known issue fix. INTERVAL fixed length byte array, nanoparquet reads list raw vectors. Missing values denoted NULL. JSON columns read character vectors (STRSXP). BSON columns read raw vectors (RAWSXP). types yet supported: Nested types (LIST, MAP) supported. UNKNOWN logical type supported. can use read_parquet_schema() function see R read columns Parquet file. Look r_type column.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-types.html","id":"the-arrow-metadata","dir":"Reference","previous_headings":"","what":"The Arrow metadata","title":"nanoparquet's type maps — nanoparquet-types","text":"Apache Arrow (.e. arrow R package) adds additional metadata Parquet files writing arrow::write_parquet(). , reading file arrow::read_parquet(), uses metadata recreate Arrow R data types writing. nanoparquet::write_parquet() also adds Arrow metadata Parquet files, unless nanoparquet.write_arrow_metadata option set FALSE. Similarly, nanoparquet::read_parquet() uses Arrow metadata Parquet file (present), unless nanoparquet.use_arrow_metadata option set FALSE. Arrow metadata stored file level key-value metadata, key ARROW:schema. Currently nanoparquet uses Arrow metadata two things: uses detect factors. Without Arrow metadata factors read string vectors. uses detect difftime objects. Without arrow metadata read INT64 columns, containing time difference nanoseconds.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":null,"dir":"Reference","previous_headings":"","what":"Parquet encodings — parquet-encodings","title":"Parquet encodings — parquet-encodings","text":"Various Parquet encodings","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"nanoparquet-defaults","dir":"Reference","previous_headings":"","what":"Nanoparquet defaults","title":"Parquet encodings — parquet-encodings","text":"Currently defaults decided based R types. might change future. general, defaults likely change nanoparquet reaches version 1.0.0. Current encoding defaults: Definition levels always use RLE. (Nanoparquet currently write repetition levels, also use RLE, implemented.) factor columns use RLE_DICTIONARY. logical columns use RLE average run length first 10,000 values least 15. Otherwise use PLAIN encoding. integer, double character columns use RLE_DICTIONARY least two third values repeated. Otherwise use PLAIN encoding. list columns raw vectors always use PLAIN encoding currently.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"parquet-encodings","dir":"Reference","previous_headings":"","what":"Parquet encodings","title":"Parquet encodings — parquet-encodings","text":"See https://github.com/apache/parquet-format/blob/master/Encodings.md details Parquet encodings.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"plain-encoding","dir":"Reference","previous_headings":"","what":"PLAIN encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: . general values written back back: Integer types little endian. Floating point types follow IEEE standard. BYTE_ARRAY: element, little endian 4-byte length bytes . FIXED_LEN_BYTE_ARRAY: bytes written back back. Nanoparquet can read write encoding primitive types.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"rle-dictionary-encoding","dir":"Reference","previous_headings":"","what":"RLE_DICTIONARY encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: dictionary indices data pages. encoding combines run-length encoding bit-packing. Repeated sequences value can run-length encoded, non-repeated parts bit packed. used data pages dictionaries. dictionary pages PLAIN encoded. deprecated PLAIN_DICTIONARY name treated RLE_DICTIONARY. Nanoparquet can read write encoding.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"rle-encoding","dir":"Reference","previous_headings":"","what":"RLE encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: BOOLEAN. Also definition repetition levels. encoding RLE_DICTIONARY, slightly different header. combines run-length encoding bit packing. used BOOLEAN columns, also definition repetition levels. Nanoparquet can read write encoding.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"bit-packed-encoding-deprecated-in-favor-of-rle-","dir":"Reference","previous_headings":"","what":"BIT_PACKED encoding (deprecated in favor of RLE)","title":"Parquet encodings — parquet-encodings","text":"Supported types: none. definition repetition levels, RLE used instead. simple bit packing encoding integers, previously used encoding definition repetition levels. used new Parquet files RLE encoding includes better. Nanoparquet currently read write BIT_PACKED encoding.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"delta-binary-packed-encoding","dir":"Reference","previous_headings":"","what":"DELTA_BINARY_PACKED encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: INT32, INT64. encoding efficiently encodes integer columns differences consecutive elements often , /differences consecutive elements small. extreme case arithmetic sequence can encoded O(1) space. Nanoparquet can read encoding, currently write .","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"delta-length-byte-array-encoding","dir":"Reference","previous_headings":"","what":"DELTA_LENGTH_BYTE_ARRAY encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: BYTE_ARRAY. encoding uses DELTA_BINARY_PACKED encode length byte array elements. especially efficient short byte array elements, .e. column short strings. Nanoparquet can read encoding, currently write .","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"delta-byte-array-encoding","dir":"Reference","previous_headings":"","what":"DELTA_BYTE_ARRAY encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: BYTE_ARRAY, FIXED_LEN_BYTE_ARRAY. encoding efficient consecutive byte array elements share prefix, element can reuse prefix previous element. Nanoparquet can read encoding, currently write .","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"byte-stream-split-encoding","dir":"Reference","previous_headings":"","what":"BYTE_STREAM_SPLIT encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: FLOAT, DOUBLE, INT32, INT64, FIXED_LEN_BYTE_ARRAY. encoding stores first bytes elements first, second bytes, etc. reduce size , may allow efficient compression. Nanoparquet can read encoding, currently write .","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/parquet_column_types.html","id":null,"dir":"Reference","previous_headings":"","what":"Map between R and Parquet data types — parquet_column_types","title":"Map between R and Parquet data types — parquet_column_types","text":"Note function now deprecated. Please use read_parquet_schema() files, infer_parquet_schema() data frames.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_column_types.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Map between R and Parquet data types — parquet_column_types","text":"","code":"parquet_column_types(x, options = parquet_options())"},{"path":"https://nanoparquet.r-lib.org/reference/parquet_column_types.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Map between R and Parquet data types — parquet_column_types","text":"x Path Parquet file, data frame. options Nanoparquet options, see parquet_options().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_column_types.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Map between R and Parquet data types — parquet_column_types","text":"Data frame columns: file_name: file name. name: column name. type: (low level) Parquet data type. r_type: R type corresponds Parquet type. Might NA read_parquet() read column. See nanoparquet-types type mapping rules. repetition_type: whether column REQUIRED (NA) OPTIONAL (may NA). REPEATED columns currently supported nanoparquet. logical_type: Parquet logical type list column. element least entry called type, potentially additional entries, e.g. bit_width, is_signed, etc.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_column_types.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Map between R and Parquet data types — parquet_column_types","text":"function works two ways. can map R types data frame Parquet types, see write_parquet() write data frame. can also map types Parquet file R types, see read_parquet() read file R.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/parquet_options.html","id":null,"dir":"Reference","previous_headings":"","what":"Nanoparquet options — parquet_options","title":"Nanoparquet options — parquet_options","text":"Create list nanoparquet options.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_options.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Nanoparquet options — parquet_options","text":"","code":"parquet_options(   class = getOption(\"nanoparquet.class\", \"tbl\"),   compression_level = getOption(\"nanoparquet.compression_level\", NA_integer_),   keep_row_groups = FALSE,   num_rows_per_row_group = getOption(\"nanoparquet.num_rows_per_row_group\", 10000000L),   use_arrow_metadata = getOption(\"nanoparquet.use_arrow_metadata\", TRUE),   write_arrow_metadata = getOption(\"nanoparquet.write_arrow_metadata\", TRUE),   write_data_page_version = getOption(\"nanoparquet.write_data_page_version\", 1L),   write_minmax_values = getOption(\"nanoparquet.write_minmax_values\", TRUE) )"},{"path":"https://nanoparquet.r-lib.org/reference/parquet_options.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Nanoparquet options — parquet_options","text":"class extra class classes add data frames created read_parquet(). default nanoparquet adds \"tbl\" class, data frames printed differently pillar package loaded. compression_level compression level write_parquet(). NA default, specifies default compression level method. Inf always selects highest possible compression level. details: Snappy support compression levels currently. GZIP supports levels 0 (uncompressed), 1 (fastest), 9 (best). default 6. ZSTD allows positive levels 22 currently. 20 require memory. Negative levels also allowed, lower level, faster speed, cost compression. Currently smallest level -131072. default level 3. keep_row_groups option used appending Parquet file append_parquet(). TRUE existing row groups file always kept nanoparquet creates new row groups new data. FALSE (default), last row group file overwritten smaller default row group size, .e. num_rows_per_row_group. num_rows_per_row_group number rows put row group, row groups specified explicitly. integer scalar. Defaults 10 million. use_arrow_metadata TRUE FALSE. TRUE, read_parquet() read_parquet_schema() make use Apache Arrow metadata assign R classes Parquet columns. currently used detect factor columns, detect \"difftime\" columns. option FALSE: \"factor\" columns read character vectors. \"difftime\" columns read real numbers, meaning one seconds, milliseconds, microseconds nanoseconds. Impossible tell without using Arrow metadata. write_arrow_metadata Whether add Apache Arrow types metadata file write_parquet(). write_data_page_version Data version write default. Possible values 1 2. Default 1. write_minmax_values Whether write minimum maximum values per row group, data types support write_parquet(). However, nanoparquet currently support minimum maximum values DECIMAL, UUID FLOAT16 logical types BOOLEAN, BYTE_ARRAY FIXED_LEN_BYTE_ARRAY primitive types writing without logical type. Currently default TRUE.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_options.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Nanoparquet options — parquet_options","text":"List nanoparquet options.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_options.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Nanoparquet options — parquet_options","text":"","code":"if (FALSE) { # the effect of using Arrow metadata tmp <- tempfile(fileext = \".parquet\") d <- data.frame(   fct = as.factor(\"a\"),   dft = as.difftime(10, units = \"secs\") ) write_parquet(d, tmp) read_parquet(tmp, options = parquet_options(use_arrow_metadata = TRUE)) read_parquet(tmp, options = parquet_options(use_arrow_metadata = FALSE)) }"},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a Parquet schema — parquet_schema","title":"Create a Parquet schema — parquet_schema","text":"can use schema specify write data frame Parquet file write_parquet().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a Parquet schema — parquet_schema","text":"","code":"parquet_schema(...)"},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a Parquet schema — parquet_schema","text":"... Parquet type specifications, see . backwards compatibility, can supply file name , parquet_schema behaves read_parquet_schema().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Create a Parquet schema — parquet_schema","text":"Data frame columns read_parquet_schema(): file_name, name, r_type, type, type_length, repetition_type, converted_type, logical_type, num_children, scale, precision, field_id.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Create a Parquet schema — parquet_schema","text":"schema list potentially named type specifications. schema stored data frame. (potentially named) argument parquet_schema may character scalar, list. Parameterized types need specified list. Primitive Parquet types may specified string list.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"possible-types-","dir":"Reference","previous_headings":"","what":"Possible types:","title":"Create a Parquet schema — parquet_schema","text":"Special type: \"AUTO\": Parquet type, tells write_parquet() map R type Parquet automatically, using default mapping rules. Primitive Parquet types: \"BOOLEAN\" \"INT32\" \"INT64\" \"INT96\" \"FLOAT\" \"DOUBLE\" \"BYTE_ARRAY\" \"FIXED_LEN_BYTE_ARRAY\": fixed-length byte array. needs type_length parameter, integer 0 2^31-1. Parquet logical types: \"STRING\" \"ENUM\" \"UUID\" \"INTEGER\": signed unsigned integer. needs bit_width is_signed parameter. bit_width must 8, 16, 32 64. is_signed must TRUE FALSE. \"INT\": \"INTEGER\". Parquet documentation uses \"INT\", actual specification uses \"INTEGER\". supported nanoparquet. \"DECIMAL\": decimal number specified scale precision. needs precision primitive_type parameters. Also supports scale parameter, defaults zero specified. \"FLOAT16\" \"DATE\" \"TIME\": needs is_adjusted_utc (TRUE FALSE) unit parameter. unit must \"MILLIS\", \"MICROS\" \"NANOS\". \"TIMESTAMP\": needs is_adjusted_utc (TRUE FALSE) unit parameter. unit must \"MILLIS\", \"MICROS\" \"NANOS\". \"JSON\" \"BSON\" Logical types MAP, LIST UNKNOWN supported currently. Converted types deprecated Parquet specification favor logical types, parquet_schema() accepts converted types syntactic shortcut corresponding logical types: INT_8 mean list(\"INT\", bit_width = 8, is_signed = TRUE). INT_16 mean list(\"INT\", bit_width = 16, is_signed = TRUE). INT_32 mean list(\"INT\", bit_width = 32, is_signed = TRUE). INT_64 mean list(\"INT\", bit_width = 64, is_signed = TRUE). TIME_MICROS means list(\"TIME\", is_adjusted_utc = TRUE, unit = \"MICROS\"). TIME_MILLIS means list(\"TIME\", is_adjusted_utc = TRUE, unit = \"MILLIS\"). TIMESTAMP_MICROS means list(\"TIMESTAMP\", is_adjusted_utc = TRUE, unit = \"MICROS\"). TIMESTAMP_MILLIS means list(\"TIMESTAMP\", is_adjusted_utc = TRUE, unit = \"MILLIS\"). UINT_8 means list(\"INT\", bit_width = 8, is_signed = FALSE). UINT_16 means list(\"INT\", bit_width = 16, is_signed = FALSE). UINT_32 means list(\"INT\", bit_width = 32, is_signed = FALSE). UINT_64 means list(\"INT\", bit_width = 64, is_signed = FALSE).","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"missing-values","dir":"Reference","previous_headings":"","what":"Missing values","title":"Create a Parquet schema — parquet_schema","text":"type might also repetition_type parameter, possible values \"REQUIRED\", \"OPTIONAL\" \"REPEATED\". \"REQUIRED\" columns allow missing values. Missing values allowed \"OPTIONAL\" columns. \"REPEATED\" columns currently supported write_parquet().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create a Parquet schema — parquet_schema","text":"","code":"parquet_schema(   c1 = \"INT32\",   c2 = list(\"INT\", bit_width = 64, is_signed = TRUE),   c3 = list(\"STRING\", repetition_type = \"OPTIONAL\") ) #> # A data frame: 3 × 12 #>   file_name name  r_type type   type_length repetition_type converted_type #> * <chr>     <chr> <chr>  <chr>        <int> <chr>           <chr>          #> 1 NA        c1    NA     INT32           NA NA              NA             #> 2 NA        c2    NA     INT64           NA NA              INT_64         #> 3 NA        c3    NA     BYTE_…          NA OPTIONAL        UTF8           #> # ℹ 5 more variables: logical_type <I<list>>, num_children <int>, #> #   scale <int>, precision <int>, field_id <int>"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet.html","id":null,"dir":"Reference","previous_headings":"","what":"Read a Parquet file into a data frame — read_parquet","title":"Read a Parquet file into a data frame — read_parquet","text":"Converts contents named Parquet file R data frame.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Read a Parquet file into a data frame — read_parquet","text":"","code":"read_parquet(file, col_select = NULL, options = parquet_options())"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Read a Parquet file into a data frame — read_parquet","text":"file Path Parquet file. may also R connection, case first reads data connection, writes temporary file, reads temporary file, deletes . connection might open, case must binary connection. open, read_parquet() open also close end. col_select Columns read. can numeric vector column indices, character vector column names. error select column multiple times. order columns result order col_select. options Nanoparquet options, see parquet_options().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Read a Parquet file into a data frame — read_parquet","text":"data.frame file's contents.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Read a Parquet file into a data frame — read_parquet","text":"","code":"file_name <- system.file(\"extdata/userdata1.parquet\", package = \"nanoparquet\") parquet_df <- nanoparquet::read_parquet(file_name) print(str(parquet_df)) #> Classes ‘tbl’ and 'data.frame':\t1000 obs. of  13 variables: #>  $ registration: POSIXct, format: \"2016-02-03 07:55:29\" \"2016-02-03 17:04:03\" ... #>  $ id          : int  1 2 3 4 5 6 7 8 9 10 ... #>  $ first_name  : chr  \"Amanda\" \"Albert\" \"Evelyn\" \"Denise\" ... #>  $ last_name   : chr  \"Jordan\" \"Freeman\" \"Morgan\" \"Riley\" ... #>  $ email       : chr  \"ajordan0@com.com\" \"afreeman1@is.gd\" \"emorgan2@altervista.org\" \"driley3@gmpg.org\" ... #>  $ gender      : Factor w/ 2 levels \"Female\",\"Male\": 1 2 1 1 NA 1 2 2 2 1 ... #>  $ ip_address  : chr  \"1.197.201.2\" \"218.111.175.34\" \"7.161.136.94\" \"140.35.109.83\" ... #>  $ cc          : chr  \"6759521864920116\" NA \"6767119071901597\" \"3576031598965625\" ... #>  $ country     : chr  \"Indonesia\" \"Canada\" \"Russia\" \"China\" ... #>  $ birthdate   : Date, format: \"1971-03-08\" \"1968-01-16\" ... #>  $ salary      : num  49757 150280 144973 90263 NA ... #>  $ title       : chr  \"Internal Auditor\" \"Accountant IV\" \"Structural Engineer\" \"Senior Cost Accountant\" ... #>  $ comments    : chr  \"1E+02\" NA NA NA ... #> NULL"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_info.html","id":null,"dir":"Reference","previous_headings":"","what":"Short summary of a Parquet file — read_parquet_info","title":"Short summary of a Parquet file — read_parquet_info","text":"Short summary Parquet file","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_info.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Short summary of a Parquet file — read_parquet_info","text":"","code":"read_parquet_info(file)  parquet_info(file)"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_info.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Short summary of a Parquet file — read_parquet_info","text":"file Path Parquet file.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_info.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Short summary of a Parquet file — read_parquet_info","text":"Data frame columns: file_name: file name. num_cols: number (leaf) columns. num_rows: number rows. num_row_groups: number row groups. file_size: file size bytes. parquet_version: Parquet version. created_by: string scalar, usually name software created file. NA available.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_metadata.html","id":null,"dir":"Reference","previous_headings":"","what":"Read the metadata of a Parquet file — read_parquet_metadata","title":"Read the metadata of a Parquet file — read_parquet_metadata","text":"function work files, even read_parquet() unable read , unsupported schema, encoding, compression reason.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_metadata.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Read the metadata of a Parquet file — read_parquet_metadata","text":"","code":"read_parquet_metadata(file, options = parquet_options())  parquet_metadata(file)"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_metadata.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Read the metadata of a Parquet file — read_parquet_metadata","text":"file Path Parquet file. options Options potentially alter default Parquet R type mappings, see parquet_options().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_metadata.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Read the metadata of a Parquet file — read_parquet_metadata","text":"named list entries: file_meta_data: data frame file meta data: file_name: file name. version: Parquet version, integer. num_rows: total number rows. key_value_metadata: list column data frames two character columns called key value. key-value metadata file. Arrow stores schema . created_by: string scalar, usually name software created file. schema: data frame, schema file. one row node (inner node leaf node). flat files means one root node (inner node), always first one, one row \"real\" column. nested schemas, rows depth-first search order. important columns : file_name: file name. name: column name. r_type: R type corresponds Parquet type. Might NA read_parquet() read column. See nanoparquet-types type mapping rules. r_type: type: data type. One low level data types. type_length: length fixed length byte arrays. repettion_type: character, one REQUIRED, OPTIONAL REPEATED. logical_type: list column, logical types columns. element least entry called type, potentially additional entries, e.g. bit_width, is_signed, etc. num_children: number child nodes. non-negative integer root node, NA leaf node. $row_groups: data frame, information row groups. important columns: file_name: file name. id: row group id, integer zero number row groups minus one. total_byte_size: total uncompressed size column data. num_rows: number rows. file_offset: row group starts file. optional, might NA. total_compressed_size: total byte size compressed (potentially encrypted) column data row group. optional, might NA. ordinal: ordinal position row group file, starting zero. optional, might NA. NA, order row groups appear metadata. $column_chunks: data frame, information column chunks, across row groups. important columns: file_name: file name. row_group: row group chunk belongs . column: leaf column chunks belongs . order $schema, leaf columns (.e. columns NA children) counted. file_path: file chunk stored . NA means file. file_offset: column chunk begins file. type: low level parquet data type. encodings: encodings used store chunk. list column character vectors encoding names. Current possible encodings: \"PLAIN\", \"GROUP_VAR_INT\", \"PLAIN_DICTIONARY\", \"RLE\", \"BIT_PACKED\", \"DELTA_BINARY_PACKED\", \"DELTA_LENGTH_BYTE_ARRAY\", \"DELTA_BYTE_ARRAY\", \"RLE_DICTIONARY\", \"BYTE_STREAM_SPLIT\". path_in_scema: list column character vectors. simply path root node. simply column name flat schemas. codec: compression codec used column chunk. Possible values : \"UNCOMPRESSED\", \"SNAPPY\", \"GZIP\", \"LZO\", \"BROTLI\", \"LZ4\", \"ZSTD\". num_values: number values column chunk. total_uncompressed_size: total uncompressed size bytes. total_compressed_size: total compressed size bytes. data_page_offset: absolute position first data page column chunk file. index_page_offset: absolute position first index page column chunk file, NA index pages. dictionary_page_offset: absolute position first dictionary page column chunk file, NA dictionary pages. null_count: number missing values column chunk. may NA. min_value: list column raw vectors, minimum value column, binary. NULL, specified. column experimental. max_value: list column raw vectors, maximum value column, binary. NULL, specified. column experimental. is_min_value_exact: whether minimum value actual value column, bound. may NA. is_max_value_exact: whether maximum value actual value column, bound. may NA.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_metadata.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Read the metadata of a Parquet file — read_parquet_metadata","text":"","code":"file_name <- system.file(\"extdata/userdata1.parquet\", package = \"nanoparquet\") nanoparquet::read_parquet_metadata(file_name) #> $file_meta_data #> # A data frame: 1 × 5 #>   file_name                 version num_rows key_value_metadata created_by #>   <chr>                       <int>    <dbl> <I<list>>          <chr>      #> 1 /home/runner/work/_temp/…       1     1000 <tbl [1 × 2]>      https://g… #>  #> $schema #> # A data frame: 14 × 12 #>    file_name name  r_type type  type_length repetition_type converted_type #>    <chr>     <chr> <chr>  <chr>       <int> <chr>           <chr>          #>  1 /home/ru… sche… NA     NA             NA NA              NA             #>  2 /home/ru… regi… POSIX… INT64          NA REQUIRED        TIMESTAMP_MIC… #>  3 /home/ru… id    integ… INT32          NA REQUIRED        INT_32         #>  4 /home/ru… firs… chara… BYTE…          NA OPTIONAL        UTF8           #>  5 /home/ru… last… chara… BYTE…          NA REQUIRED        UTF8           #>  6 /home/ru… email factor BYTE…          NA OPTIONAL        UTF8           #>  7 /home/ru… gend… chara… BYTE…          NA OPTIONAL        UTF8           #>  8 /home/ru… ip_a… chara… BYTE…          NA REQUIRED        UTF8           #>  9 /home/ru… cc    chara… BYTE…          NA OPTIONAL        UTF8           #> 10 /home/ru… coun… chara… BYTE…          NA REQUIRED        UTF8           #> 11 /home/ru… birt… Date   INT32          NA OPTIONAL        DATE           #> 12 /home/ru… sala… double DOUB…          NA OPTIONAL        NA             #> 13 /home/ru… title chara… BYTE…          NA OPTIONAL        UTF8           #> 14 /home/ru… comm… chara… BYTE…          NA OPTIONAL        UTF8           #> # ℹ 5 more variables: logical_type <I<list>>, num_children <int>, #> #   scale <int>, precision <int>, field_id <int> #>  #> $row_groups #> # A data frame: 1 × 7 #>   file_name                        id total_byte_size num_rows file_offset #>   <chr>                         <int>           <dbl>    <dbl>       <dbl> #> 1 /home/runner/work/_temp/Libr…     0           71427     1000          NA #> # ℹ 2 more variables: total_compressed_size <dbl>, ordinal <int> #>  #> $column_chunks #> # A data frame: 13 × 24 #>    file_name    row_group column file_path file_offset offset_index_offset #>    <chr>            <int>  <int> <chr>           <dbl>               <dbl> #>  1 /home/runne…         0      0 NA                  4                  NA #>  2 /home/runne…         0      1 NA               6741                  NA #>  3 /home/runne…         0      2 NA              12259                  NA #>  4 /home/runne…         0      3 NA              15211                  NA #>  5 /home/runne…         0      4 NA              16239                  NA #>  6 /home/runne…         0      5 NA              31759                  NA #>  7 /home/runne…         0      6 NA              32031                  NA #>  8 /home/runne…         0      7 NA              42952                  NA #>  9 /home/runne…         0      8 NA              55009                  NA #> 10 /home/runne…         0      9 NA              55925                  NA #> 11 /home/runne…         0     10 NA              59312                  NA #> 12 /home/runne…         0     11 NA              67026                  NA #> 13 /home/runne…         0     12 NA              71089                  NA #> # ℹ 18 more variables: offset_index_length <int>, #> #   column_index_offset <dbl>, column_index_length <int>, type <chr>, #> #   encodings <I<list>>, path_in_schema <I<list>>, codec <chr>, #> #   num_values <dbl>, total_uncompressed_size <dbl>, #> #   total_compressed_size <dbl>, data_page_offset <dbl>, #> #   index_page_offset <dbl>, dictionary_page_offset <dbl>, #> #   null_count <dbl>, min_value <I<list>>, max_value <I<list>>, … #>"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_page.html","id":null,"dir":"Reference","previous_headings":"","what":"Read a page from a Parquet file — read_parquet_page","title":"Read a page from a Parquet file — read_parquet_page","text":"Read page Parquet file","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_page.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Read a page from a Parquet file — read_parquet_page","text":"","code":"read_parquet_page(file, offset)"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_page.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Read a page from a Parquet file — read_parquet_page","text":"file Path Parquet file. offset Integer offset start page file. See read_parquet_pages() list pages offsets.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_page.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Read a page from a Parquet file — read_parquet_page","text":"Named list. Many entries correspond columns result read_parquet_pages(). Additional entries : codec: compression codec. Possible values: has_repetition_levels: whether page repetition levels. has_definition_levels: whether page definition levels. schema_column: schema column page corresponds . Note leaf columns pages. data_type: low level Parquet data type. Possible values: repetition_type: whether column page belongs REQUIRED, OPTIONAL REPEATED. page_header: bytes page header raw vector. num_null: number missing (NA) values. set V2 data pages. num_rows: num_values flat tables, .e. files without repetition levels. compressed_data: data page raw vector. includes repetition definition levels, . data: uncompressed data, nanoparquet supports compression codec file (GZIP SNAPPY time writing), file compressed. latter case compressed_data.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_page.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Read a page from a Parquet file — read_parquet_page","text":"","code":"file_name <- system.file(\"extdata/userdata1.parquet\", package = \"nanoparquet\") nanoparquet:::read_parquet_pages(file_name) #> # A data frame: 19 × 14 #>    file_name                 row_group column page_type page_header_offset #>    <chr>                         <int>  <int> <chr>                  <dbl> #>  1 /home/runner/work/_temp/…         0      0 DATA_PAGE                  4 #>  2 /home/runner/work/_temp/…         0      1 DATA_PAGE               6741 #>  3 /home/runner/work/_temp/…         0      2 DICTIONA…              10766 #>  4 /home/runner/work/_temp/…         0      2 DATA_PAGE              12259 #>  5 /home/runner/work/_temp/…         0      3 DICTIONA…              13334 #>  6 /home/runner/work/_temp/…         0      3 DATA_PAGE              15211 #>  7 /home/runner/work/_temp/…         0      4 DATA_PAGE              16239 #>  8 /home/runner/work/_temp/…         0      5 DICTIONA…              31726 #>  9 /home/runner/work/_temp/…         0      5 DATA_PAGE              31759 #> 10 /home/runner/work/_temp/…         0      6 DATA_PAGE              32031 #> 11 /home/runner/work/_temp/…         0      7 DATA_PAGE              42952 #> 12 /home/runner/work/_temp/…         0      8 DICTIONA…              53749 #> 13 /home/runner/work/_temp/…         0      8 DATA_PAGE              55009 #> 14 /home/runner/work/_temp/…         0      9 DATA_PAGE              55925 #> 15 /home/runner/work/_temp/…         0     10 DATA_PAGE              59312 #> 16 /home/runner/work/_temp/…         0     11 DICTIONA…              65063 #> 17 /home/runner/work/_temp/…         0     11 DATA_PAGE              67026 #> 18 /home/runner/work/_temp/…         0     12 DICTIONA…              68019 #> 19 /home/runner/work/_temp/…         0     12 DATA_PAGE              71089 #> # ℹ 9 more variables: uncompressed_page_size <int>, #> #   compressed_page_size <int>, crc <int>, num_values <int>, #> #   encoding <chr>, definition_level_encoding <chr>, #> #   repetition_level_encoding <chr>, data_offset <dbl>, #> #   page_header_length <int> options(max.print = 100)  # otherwise long raw vector nanoparquet:::read_parquet_page(file_name, 4L) #> $page_type #> [1] \"DATA_PAGE\" #>  #> $row_group #> [1] 0 #>  #> $column #> [1] 0 #>  #> $page_header_offset #> [1] 4 #>  #> $data_page_offset #> [1] 24 #>  #> $page_header_length #> [1] 20 #>  #> $compressed_page_size #> [1] 6717 #>  #> $uncompressed_page_size #> [1] 8000 #>  #> $codec #> [1] \"SNAPPY\" #>  #> $num_values #> [1] 1000 #>  #> $encoding #> [1] \"PLAIN\" #>  #> $definition_level_encoding #> [1] \"PLAIN\" #>  #> $repetition_level_encoding #> [1] \"PLAIN\" #>  #> $has_repetition_levels #> [1] FALSE #>  #> $has_definition_levels #> [1] FALSE #>  #> $schema_column #> [1] 1 #>  #> $data_type #> [1] \"INT64\" #>  #> $repetition_type #> [1] \"REQUIRED\" #>  #> $page_header #>  [1] 15 00 15 80 7d 15 fa 68 2c 15 d0 0f 15 00 15 00 15 00 00 00 #>  #> $data #>   [1] 40 be 0c f1 d8 2a 05 00 c0 86 e0 9a e0 2a 05 00 c0 28 33 45 d3 2a 05 #>  [24] 00 40 2b 96 ce d2 2a 05 00 c0 9c 33 91 d6 2a 05 00 80 a2 54 7b d8 2a #>  [47] 05 00 00 59 b2 77 d9 2a 05 00 80 ee 7d fc d7 2a 05 00 40 cf 71 8d d5 #>  [70] 2a 05 00 c0 bc 7b cd e1 2a 05 00 80 e4 da 72 d2 2a 05 00 80 30 4d 73 #>  [93] e1 2a 05 00 40 fe a4 0f #>  [ reached getOption(\"max.print\") -- omitted 7900 entries ] #>  #> $definition_levels_byte_length #> [1] NA #>  #> $repetition_levels_byte_length #> [1] NA #>  #> $num_nulls #> [1] NA #>  #> $num_rows #> [1] NA #>  #> $compressed_data #>   [1] c0 3e 30 40 be 0c f1 d8 2a 05 00 c0 86 e0 9a e0 01 08 2c 28 33 45 d3 #>  [24] 2a 05 00 40 2b 96 ce d2 01 10 28 9c 33 91 d6 2a 05 00 80 a2 54 7b 01 #>  [47] 28 10 00 59 b2 77 d9 01 10 0c ee 7d fc d7 01 28 0c cf 71 8d d5 01 28 #>  [70] 0c bc 7b cd e1 01 18 08 e4 da 72 01 38 0c 80 30 4d 73 01 10 30 40 fe #>  [93] a4 0f e2 2a 05 00 00 eb #>  [ reached getOption(\"max.print\") -- omitted 6617 entries ] #>"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":null,"dir":"Reference","previous_headings":"","what":"Metadata of all pages of a Parquet file — read_parquet_pages","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"Metadata pages Parquet file","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"","code":"read_parquet_pages(file)"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"file Path Parquet file.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"Data frame columns: file_name: file name. row_group: id row group page belongs , integer 0 number row groups minus one. column: id column. integer number leaf columns minus one. Note leaf columns considered, non-leaf columns pages. page_type: DATA_PAGE, INDEX_PAGE, DICTIONARY_PAGE DATA_PAGE_V2. page_header_offset: offset data page (header) file. uncompressed_page_size: include page header, per Parquet spec. compressed_page_size: without page header. crc: integer, checksum, present file, can NA. num_values: number data values page, include NULL (NA R) values. encoding: encoding page, current possible encodings: \"PLAIN\", \"GROUP_VAR_INT\", \"PLAIN_DICTIONARY\", \"RLE\", \"BIT_PACKED\", \"DELTA_BINARY_PACKED\", \"DELTA_LENGTH_BYTE_ARRAY\", \"DELTA_BYTE_ARRAY\", \"RLE_DICTIONARY\", \"BYTE_STREAM_SPLIT\". definition_level_encoding: encoding definition levels, see encoding possible values. can missing V2 data pages, always RLE encoded. repetition_level_encoding: encoding repetition levels, see encoding possible values. can missing V2 data pages, always RLE encoded. data_offset: offset actual data file. page_header_length: size page header, bytes.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"Reading page headers might slow large files, especially file many small pages.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"","code":"file_name <- system.file(\"extdata/userdata1.parquet\", package = \"nanoparquet\") nanoparquet:::read_parquet_pages(file_name) #> # A data frame: 19 × 14 #>    file_name                 row_group column page_type page_header_offset #>    <chr>                         <int>  <int> <chr>                  <dbl> #>  1 /home/runner/work/_temp/…         0      0 DATA_PAGE                  4 #>  2 /home/runner/work/_temp/…         0      1 DATA_PAGE               6741 #>  3 /home/runner/work/_temp/…         0      2 DICTIONA…              10766 #>  4 /home/runner/work/_temp/…         0      2 DATA_PAGE              12259 #>  5 /home/runner/work/_temp/…         0      3 DICTIONA…              13334 #>  6 /home/runner/work/_temp/…         0      3 DATA_PAGE              15211 #>  7 /home/runner/work/_temp/…         0      4 DATA_PAGE              16239 #>  8 /home/runner/work/_temp/…         0      5 DICTIONA…              31726 #>  9 /home/runner/work/_temp/…         0      5 DATA_PAGE              31759 #> 10 /home/runner/work/_temp/…         0      6 DATA_PAGE              32031 #> 11 /home/runner/work/_temp/…         0      7 DATA_PAGE              42952 #> 12 /home/runner/work/_temp/…         0      8 DICTIONA…              53749 #> 13 /home/runner/work/_temp/…         0      8 DATA_PAGE              55009 #> 14 /home/runner/work/_temp/…         0      9 DATA_PAGE              55925 #> 15 /home/runner/work/_temp/…         0     10 DATA_PAGE              59312 #> 16 /home/runner/work/_temp/…         0     11 DICTIONA…              65063 #> 17 /home/runner/work/_temp/…         0     11 DATA_PAGE              67026 #> 18 /home/runner/work/_temp/…         0     12 DICTIONA…              68019 #> 19 /home/runner/work/_temp/…         0     12 DATA_PAGE              71089 #> # ℹ 9 more variables: uncompressed_page_size <int>, #> #   compressed_page_size <int>, crc <int>, num_values <int>, #> #   encoding <chr>, definition_level_encoding <chr>, #> #   repetition_level_encoding <chr>, data_offset <dbl>, #> #   page_header_length <int>"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_schema.html","id":null,"dir":"Reference","previous_headings":"","what":"Read the schema of a Parquet file — read_parquet_schema","title":"Read the schema of a Parquet file — read_parquet_schema","text":"function work files, even read_parquet() unable read , unsupported schema, encoding, compression reason.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_schema.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Read the schema of a Parquet file — read_parquet_schema","text":"","code":"read_parquet_schema(file, options = parquet_options())"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_schema.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Read the schema of a Parquet file — read_parquet_schema","text":"file Path Parquet file. options Return value parquet_options(), options potentially modify Parquet R type mappings.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_schema.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Read the schema of a Parquet file — read_parquet_schema","text":"","code":"Data frame, the schema of the file. It has one row for each node (inner node or leaf node). For flat files this means one root node (inner node), always the first one, and then one row for each \"real\" column. For nested schemas, the rows are in depth-first search order. Most important columns are: - `file_name`: file name. - `name`: column name. - `r_type`: the R type that corresponds to the Parquet type.   Might be `NA` if [read_parquet()] cannot read this column. See   [nanoparquet-types] for the type mapping rules. - `type`: data type. One of the low level data types. - `type_length`: length for fixed length byte arrays. - `repettion_type`: character, one of `REQUIRED`, `OPTIONAL` or   `REPEATED`. - `logical_type`: a list column, the logical types of the columns.   An element has at least an entry called `type`, and potentially   additional entries, e.g. `bit_width`, `is_signed`, etc. - `num_children`: number of child nodes. Should be a non-negative   integer for the root node, and `NA` for a leaf node."},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/rle_decode_int.html","id":null,"dir":"Reference","previous_headings":"","what":"RLE decode integers — rle_decode_int","title":"RLE decode integers — rle_decode_int","text":"RLE decode integers","code":""},{"path":"https://nanoparquet.r-lib.org/reference/rle_decode_int.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"RLE decode integers — rle_decode_int","text":"","code":"rle_decode_int(   x,   bit_width = attr(x, \"bit_width\"),   length = attr(x, \"length\") %||% NA )"},{"path":"https://nanoparquet.r-lib.org/reference/rle_decode_int.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"RLE decode integers — rle_decode_int","text":"x Raw vector encoded integers. bit_width Bit width used encoding. length Length output. NA assume x starts length output, encoded 4 byte integer.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/rle_decode_int.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"RLE decode integers — rle_decode_int","text":"decoded integer vector.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/rle_encode_int.html","id":null,"dir":"Reference","previous_headings":"","what":"RLE encode integers — rle_encode_int","title":"RLE encode integers — rle_encode_int","text":"RLE encode integers","code":""},{"path":"https://nanoparquet.r-lib.org/reference/rle_encode_int.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"RLE encode integers — rle_encode_int","text":"","code":"rle_encode_int(x)"},{"path":"https://nanoparquet.r-lib.org/reference/rle_encode_int.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"RLE encode integers — rle_encode_int","text":"x Integer vector.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/rle_encode_int.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"RLE encode integers — rle_encode_int","text":"Raw vector, encoded integers. two attributes: bit_length: number bits needed encode input, length: length original integer input.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":null,"dir":"Reference","previous_headings":"","what":"Write a data frame to a Parquet file — write_parquet","title":"Write a data frame to a Parquet file — write_parquet","text":"Writes contents R data frame Parquet file.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Write a data frame to a Parquet file — write_parquet","text":"","code":"write_parquet(   x,   file,   schema = NULL,   compression = c(\"snappy\", \"gzip\", \"zstd\", \"uncompressed\"),   encoding = NULL,   metadata = NULL,   row_groups = NULL,   options = parquet_options() )"},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Write a data frame to a Parquet file — write_parquet","text":"x Data frame write. file Path output file. string \":raw:\", data frame written memory buffer, memory buffer returned raw vector. schema Parquet schema. Specify schema tweak default nanoparquet R -> Parquet type mappings. Use parquet_schema() create schema can use , read_parquet_schema() use schema Parquet file. compression Compression algorithm use. Currently \"snappy\" (default), \"gzip\", \"zstd\", \"uncompressed\" supported. encoding Encoding use. Possible values: NULL, appropriate encoding selected automatically: RLE PLAIN BOOLEAN columns, RLE_DICTIONARY columns many repeated values, PLAIN otherwise. single (unnamed) character string, 'll used columns. unnamed character vector encoding names length number columns data frame, encodings used column. named character vector, named must unique name must match column name, specify encoding column. special empty name (\"\") applies rest columns. empty name, rest columns use default encoding. NA_character_ specified column, default encoding used column. specified encoding invalid certain column type, nanoparquet implement , write_parquet() throws error. Currently write_parquet() supports following encodings: PLAIN column types, PLAIN_DICTIONARY RLE_DICTIONARY column types, RLE BOOLEAN columns. See parquet-encodings encodings. metadata Additional key-value metadata add file. must named character vector, data frame columns character columns called key value. row_groups Row groups Parquet file. NULL, num_rows_per_row_group option used options argument, see parquet_options(). Otherwise must integer vector, specifying starts row groups. options Nanoparquet options, see parquet_options().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Write a data frame to a Parquet file — write_parquet","text":"NULL, unless file \":raw:\", case Parquet file returned raw vector.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Write a data frame to a Parquet file — write_parquet","text":"write_parquet() converts string columns UTF-8 encoding calling base::enc2utf8(). factor levels.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Write a data frame to a Parquet file — write_parquet","text":"","code":"if (FALSE) { # add row names as a column, because `write_parquet()` ignores them. mtcars2 <- cbind(name = rownames(mtcars), mtcars) write_parquet(mtcars2, \"mtcars.parquet\") }"},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-041","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.4.1","title":"nanoparquet 0.4.1","text":"write_parquet() now correctly converts double Date columns integer columns (@eitsupi, #116). read_parquet() now correctly reads FLOAT columns files multiple row groups. read_parquet() now correctly reads Parquet files column chunks dictionary encoded dictionary encoded pages (#110).","code":""},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-040","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.4.0","title":"nanoparquet 0.4.0","text":"CRAN release: 2025-01-29 API changes: parquet_schema() now called read_parquet_schema(). new parquet_schema() function falls back read_parquet_schema() called single string argument, warning. parquet_info() now called read_parquet_info(). parquet_info( still works now, warning. parquet_metadata() now called read_parquet_metadata(). parquet_metadata() still works, warning. parquet_column_types() now deprecated, issues warning. Use read_parquet_schema() new infer_parquet_schema() function instead. improvements: new parquet_schema() function creates Parquet schema scratch. can use schema new schema argument write_parquet(), specify columns data frame mapped Parquet types. New append_parquet() function append data frame existing Parquet file. New col_select argument read_parquet() read subset columns Parquet file. write_parquet() can now write multiple row groups. default puts 10 million rows single row group. can choose row groups manually row_groups argument. write_parquet() now writes minimum maximum values per row group types. See ?parquet_options() turning . also writes number non-missing values. Newly supported type conversions write_parquet() via schema argument: integer INT64, integer INT96, double INT96, double FLOAT, character BYTE_ARRAY, character FIXED_LEN_BYTE_ARRAY, character ENUM, factor ENUM. integer DECIMAL, INT32, integer DECIMAL, INT64, double DECIMAL, INT32, double DECIMAL, INT64, integer INT(8, *), INT(16, *), INT(32, signed), double INT(*, *), character UUID, double FLOAT16, list raw vectors BYTE_ARRAY, list raw vectors FIXED_LEN_BYTE_ARRAY. write_parquet() can now write version 2 data pages. default still version 1, might change future. write_parquet(file = \":raw:\") now works correctly larger data frames (#77). New compression_level option select compression level manually. See ?parquet_options details. (#91). read_parquet() can now read R connection (#71). read_parquet() now reads DECIMAL values correctly INT32 INT64 columns scale zero. read_parquet() now reads JSON columns character vectors, documented. read_parquet() now reads FLOAT16 logical type real (double) vector. class argument parquet_options() nanoparquet.class option now work (#104).","code":""},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-031","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.3.1","title":"nanoparquet 0.3.1","text":"CRAN release: 2024-07-01 version fixes write_parquet() crash (#73).","code":""},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-030","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.3.0","title":"nanoparquet 0.3.0","text":"CRAN release: 2024-06-17 read_parquet() type mapping changes: STRING logical type UTF8 converted type still read character vector, BYTE_ARRAY types without converted logical types , read list raw vectors. Missing values indicated NULL values. DECIMAL converted type read REALSXP now, even type FIXED_LEN_BYTE_ARRAY. (just BYTE_ARRAY). UUID logical type now read character vector, formatted 00112233-4455-6677-8899-aabbccddeeff. BYTE_ARRAY FIXED_LEN_BYTE_ARRAY types without logical converted types; unsupported ones: FLOAT16, INTERVAL; now read list raw vectors. Missing values denoted NULL. write_parquet() now automatically uses dictionary encoding columns many repeated values. first 10k rows used decide dictionary used . Similarly, logical columns written RLE encoding contain runs repeated values. NA values ignored selecting encoding (#18). write_parquet() can now write data frame memory buffer, returned raw vector, special \":raw:\" filename used (#31). read_parquet() can now read Parquet files V2 data pages (#37). read_parquet() write_parquet() now support GZIP ZSTD compressed Parquet files. read_parquet() now supports RLE encoding BOOLEAN columns also supports DELTA_BINARY_PACKED, DELTA_LENGTH_BYTE_ARRAY, DELTA_BYTE_ARRAY BYTE_STREAM_SPLIT encodings. parquet_columns() function now called parquet_column_types() can now map column types data frame Parquet types. parquet_info(), parquet_metadata() parquet_column_types() now work created_by metadata field unset. New parquet_options() function can use set nanoparquet options single read_parquet() write_parquet() call.","code":""},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-020","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.2.0","title":"nanoparquet 0.2.0","text":"CRAN release: 2024-05-30 First release CRAN. contains Parquet reader https://github.com/hannes/miniparquet, Parquet writer, functions read Parquet metadata, many improvements.","code":""}]
+[{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"goals","dir":"Articles","previous_headings":"","what":"Goals","title":"Benchmarks","text":"First, want measure nanoparquet’s speed relative good quality CSV readers writers, also look sizes Parquet CSV files. Second, want see nanoparquet fares relative Parquet implementations available R.","code":"library(dplyr) library(gt) library(gtExtras)"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"data-sets","dir":"Articles","previous_headings":"","what":"Data sets","title":"Benchmarks","text":"used use three data sets: small, medium large. small data set nycflights13::flights data set, . medium data set contains 20 copies small data set. large data set contains 200 copies small data set. See gen_data() function benchmark-funcs.R file nanoparquet GitHub repository. basic information data set: quick look data:","code":"if (file.exists(file.path(me, \"data-info.parquet\"))) {   info_tab <- nanoparquet::read_parquet(file.path(me, \"data-info.parquet\")) } else {   get_data_info <- function(x) {     list(dim = dim(x), size = object.size(x))   }   info <- lapply(data_sizes, function(s) get_data_info(gen_data(s)))   info_tab <- data.frame(     check.names = FALSE,     name = data_sizes,     rows = sapply(info, \"[[\", \"dim\")[1,],     columns = sapply(info, \"[[\", \"dim\")[2,],     \"size in memory\" = sapply(info, \"[[\", \"size\")   )   nanoparquet::write_parquet(info_tab, file.path(me, \"data-info.parquet\")) } info_tab |>   gt() |>   tab_header(title = \"Data sets\") |>   tab_options(table.align = \"left\") |>   fmt_integer() |>   fmt_bytes(columns = \"size in memory\") head(nycflights13::flights) #> # A tibble: 6 × 19 #>    year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time #>   <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int> #> 1  2013     1     1      517            515         2      830            819 #> 2  2013     1     1      533            529         4      850            830 #> 3  2013     1     1      542            540         2      923            850 #> 4  2013     1     1      544            545        -1     1004           1022 #> 5  2013     1     1      554            600        -6      812            837 #> 6  2013     1     1      554            558        -4      740            728 #> # ℹ 11 more variables: arr_delay <dbl>, carrier <chr>, flight <int>, #> #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, #> #   hour <dbl>, minute <dbl>, time_hour <dttm> dplyr::glimpse(nycflights13::flights) #> Rows: 336,776 #> Columns: 19 #> $ year           <int> 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2… #> $ month          <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1… #> $ day            <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1… #> $ dep_time       <int> 517, 533, 542, 544, 554, 554, 555, 557, 557, 558, 558, … #> $ sched_dep_time <int> 515, 529, 540, 545, 600, 558, 600, 600, 600, 600, 600, … #> $ dep_delay      <dbl> 2, 4, 2, -1, -6, -4, -5, -3, -3, -2, -2, -2, -2, -2, -1… #> $ arr_time       <int> 830, 850, 923, 1004, 812, 740, 913, 709, 838, 753, 849,… #> $ sched_arr_time <int> 819, 830, 850, 1022, 837, 728, 854, 723, 846, 745, 851,… #> $ arr_delay      <dbl> 11, 20, 33, -18, -25, 12, 19, -14, -8, 8, -2, -3, 7, -1… #> $ carrier        <chr> \"UA\", \"UA\", \"AA\", \"B6\", \"DL\", \"UA\", \"B6\", \"EV\", \"B6\", \"… #> $ flight         <int> 1545, 1714, 1141, 725, 461, 1696, 507, 5708, 79, 301, 4… #> $ tailnum        <chr> \"N14228\", \"N24211\", \"N619AA\", \"N804JB\", \"N668DN\", \"N394… #> $ origin         <chr> \"EWR\", \"LGA\", \"JFK\", \"JFK\", \"LGA\", \"EWR\", \"EWR\", \"LGA\",… #> $ dest           <chr> \"IAH\", \"IAH\", \"MIA\", \"BQN\", \"ATL\", \"ORD\", \"FLL\", \"IAD\",… #> $ air_time       <dbl> 227, 227, 160, 183, 116, 150, 158, 53, 140, 138, 149, 1… #> $ distance       <dbl> 1400, 1416, 1089, 1576, 762, 719, 1065, 229, 944, 733, … #> $ hour           <dbl> 5, 5, 5, 5, 6, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 6… #> $ minute         <dbl> 15, 29, 40, 45, 0, 58, 0, 0, 0, 0, 0, 0, 0, 0, 0, 59, 0… #> $ time_hour      <dttm> 2013-01-01 05:00:00, 2013-01-01 05:00:00, 2013-01-01 0…"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"parquet-implementations","dir":"Articles","previous_headings":"","what":"Parquet implementations","title":"Benchmarks","text":"ran nanoparquet, Arrow DuckDB. also ran data.table without compression readr, read/write CSV files. used running time readr baseline. ran benchmark three times record results third run. make sure data software swapped OS. (Except readr large data set, take long.) include complete raw results end article.","code":"if (file.exists(file.path(me, \"results.parquet\"))) {   results <- nanoparquet::read_parquet(file.path(me, \"results.parquet\")) } else {   results <- NULL   lapply(data_sizes[1:2], function(s) {     lapply(variants, function(v) {       r <- if (v == \"readr\" && s == \"large\") {         measure(v, s)       } else {         measure(v, s)         measure(v, s)         measure(v, s)       }       results <<- rbind(results, r)     })   })   nanoparquet::write_parquet(results, file.path(me, \"results.parquet\")) }"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"parquet-vs-csv","dir":"Articles","previous_headings":"","what":"Parquet vs CSV","title":"Benchmarks","text":"results, focusing CSV readers nanoparquet: Notes: single-threaded nanoparquet Parquet-reader competitive. can read compressed Parquet file just fast state art uncompressed CSV reader uses least 2 threads. nanoparquet vs CSV results writing Parquet CSV files: Notes: data.table CSV writer 3 times fast nanoparquet Parquet writer, CSV file uncompressed. CSV writer uses least 4 threads, Parquet write single-threaded. nanoparquet Parquet writer 2-5 times faster data.table CSV writer CSV file compressed. Parquet files 5-6 times smaller uncompressed CSV files 30-35% smaller compressed CSV files.","code":"csv_tab_read <- results |>   filter(software %in% c(\"nanoparquet\", \"data.table\", \"data.table.gz\", \"readr\")) |>   filter(direction == \"read\") |>   mutate(software = case_when(     software ==  \"data.table.gz\" ~ \"data.table (compressed)\",     .default = software   )) |>   rename(`data size` = data_size, time = time_elapsed) |>   mutate(memory = mem_max_after - mem_before) |>   mutate(base = tail(time, 1), .by = `data size`) |>   mutate(speedup = base / time, x = round(speedup, digits = 1)) |>   select(`data size`, software, time, x, speedup, memory) |>   mutate(rawtime = time, time = prettyunits::pretty_sec(time)) |>   rename(`speedup from CSV` = speedup)  csv_tab_read |>   gt() |>   tab_header(title = \"Parquet vs CSV, reading\") |>   tab_options(table.align = \"left\") |>   tab_row_group(md(\"**small data**\"), rows = `data size` == \"small\", \"s\") |>   tab_row_group(md(\"**medium data**\"), rows = `data size` == \"medium\", \"m\") |>   tab_row_group(md(\"**large data**\"), rows = `data size` == \"large\", \"l\") |>   row_group_order(c(\"s\", \"m\", \"l\")) |>   cols_hide(columns = c(`data size`, rawtime)) |>   cols_align(columns = time, align = \"right\") |>   fmt_bytes(columns = memory) |>   gt_plt_bar(column = `speedup from CSV`) csv_tab_write <- results |>   filter(software %in% c(\"nanoparquet\", \"data.table\", \"data.table.gz\", \"readr\")) |>   filter(direction == \"write\") |>   mutate(software = case_when(     software ==  \"data.table.gz\" ~ \"data.table (compressed)\",     .default = software   )) |>   rename(`data size` = data_size, time = time_elapsed, `file size` = file_size) |>   mutate(memory = mem_max_after - mem_before) |>   mutate(base = tail(time, 1), .by = `data size`) |>   mutate(speedup = base / time, x = round(speedup, digits = 1)) |>   select(`data size`, software, time, x, speedup, memory, `file size`) |>   mutate(rawtime = time, time = prettyunits::pretty_sec(time)) |>   rename(`speedup from CSV` = speedup)  csv_tab_write |>   gt() |>   tab_header(title = \"Parquet vs CSV, writing\") |>   tab_options(table.align = \"left\") |>   tab_row_group(md(\"**small data**\"), rows = `data size` == \"small\", \"s\") |>   tab_row_group(md(\"**medium data**\"), rows = `data size` == \"medium\", \"m\") |>   tab_row_group(md(\"**large data**\"), rows = `data size` == \"large\", \"l\") |>   row_group_order(c(\"s\", \"m\", \"l\")) |>   cols_hide(columns = c(`data size`, rawtime)) |>   cols_align(columns = time, align = \"right\") |>   fmt_bytes(columns = c(memory, `file size`)) |>   gt_plt_bar(column = `speedup from CSV`)"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"parquet-implementations-1","dir":"Articles","previous_headings":"","what":"Parquet implementations","title":"Benchmarks","text":"summary Parquet readers, three files. Notes: general, three implementations perform similarly. nanoparquet competitive three data sets terms speed also tends use least amount memory. turned ALTREP arrow, reads data memory. summary Parquet writers: Notes: nanoparquet competitive terms speed, slightly faster two implementations, data sets. DuckDB seems waste space writing Parquet files. possibly fine tuned forcing different encoding. behavior improve forthcoming DuckDB 1.2.0 release, see also https://github.com/duckdb/duckdb/issues/3316.","code":"pq_tab_read <- results |>   filter(software %in% c(\"nanoparquet\", \"arrow\", \"duckdb\", \"readr\")) |>   filter(direction == \"read\") |>   rename(`data size` = data_size, time = time_elapsed) |>   mutate(memory = mem_max_after - mem_before) |>   mutate(base = tail(time, 1), .by = `data size`) |>   mutate(speedup = base / time, x = round(speedup, digits = 1)) |>   select(`data size`, software, time, x, speedup, memory) |>   mutate(rawtime = time, time = prettyunits::pretty_sec(time)) |>   filter(software %in% c(\"nanoparquet\", \"arrow\", \"duckdb\")) |>   mutate(software = case_when(     software ==  \"arrow\" ~ \"Arrow\",     software == \"duckdb\" ~ \"DuckDB\",     .default = software   )) |>   rename(`speedup from CSV` = speedup)  pq_tab_read |>   gt() |>   tab_header(title = \"Parquet implementations, reading\") |>   tab_options(table.align = \"left\") |>   tab_row_group(md(\"**small data**\"), rows = `data size` == \"small\", \"s\") |>   tab_row_group(md(\"**medium data**\"), rows = `data size` == \"medium\", \"m\") |>   tab_row_group(md(\"**large data**\"), rows = `data size` == \"large\", \"l\") |>   row_group_order(c(\"s\", \"m\", \"l\")) |>   cols_hide(columns = c(`data size`, rawtime)) |>   cols_align(columns = time, align = \"right\") |>   fmt_bytes(columns = memory) |>   gt_plt_bar(column = `speedup from CSV`) pq_tab_write <- results |>   filter(software %in% c(\"nanoparquet\", \"arrow\", \"duckdb\", \"readr\")) |>   filter(direction == \"write\") |>   rename(`data size` = data_size, time = time_elapsed, `file size` = file_size) |>   mutate(memory = mem_max_after - mem_before) |>   mutate(base = tail(time, 1), .by = `data size`) |>   mutate(speedup = base / time, x = round(speedup, digits = 1)) |>   select(`data size`, software, time, x, speedup, memory, `file size`) |>   mutate(rawtime = time, time = prettyunits::pretty_sec(time)) |>   filter(software %in% c(\"nanoparquet\", \"arrow\", \"duckdb\", \"readr\")) |>   mutate(software = case_when(     software ==  \"arrow\" ~ \"Arrow\",     software == \"duckdb\" ~ \"DuckDB\",     .default = software   )) |>   rename(`speedup from CSV` = speedup)  pq_tab_write |>   gt() |>   tab_header(title = \"Parquet implementations, writing\") |>   tab_options(table.align = \"left\") |>   tab_row_group(md(\"**small data**\"), rows = `data size` == \"small\", \"s\") |>   tab_row_group(md(\"**medium data**\"), rows = `data size` == \"medium\", \"m\") |>   tab_row_group(md(\"**large data**\"), rows = `data size` == \"large\", \"l\") |>   row_group_order(c(\"s\", \"m\", \"l\")) |>   cols_hide(columns = c(`data size`, rawtime)) |>   cols_align(columns = time, align = \"right\") |>   fmt_bytes(columns = c(memory, `file size`)) |>   gt_plt_bar(column = `speedup from CSV`)"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"conclusions","dir":"Articles","previous_headings":"","what":"Conclusions","title":"Benchmarks","text":"results probably change different data sets, different system. particular, Arrow DuckDB probably faster larger systems, data stored multiple physical disks. Arrow DuckDB let run queries data without loading memory first. especially important data fit memory , even columns needed analysis. nanoparquet . However, general, based benchmarks good reasons trust nanoparquet Parquet reader writer competitive implementations available R, terms speed memory use. limitations nanoparquet prohibitive use case, good choice Parquet /O.","code":""},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"raw-benchmark-results","dir":"Articles","previous_headings":"","what":"Raw benchmark results","title":"Benchmarks","text":"raw results. can scroll right screen wide enough whole table. Notes: User time (time_user) plus system time (time_system) can larger elapsed time (time_elapsed) multithreaded implementations indeed tools, except nanoparquet, single-threaded. memory columns bytes. mem_before RSS size reading/writing. mem_max_before maximum RSS size process . mem_max_after maximum RSS size process read/write operation. can calculate (estimate) memory usage tool subtracting mem_before mem_max_after. overestimate memory usage mem_max_after mem_max_before, never happens practice. reading file, mem_max_after includes memory needed store data set . (See data sizes .) arrow, turned ALTREP using options(arrow.use_altrep = FALSE), see benchmarks-funcs.R file. Otherwise arrow actually read data memory.","code":"print(results, n = Inf) #> # A data frame: 36 × 10 #>    software      direction data_size time_user time_system time_elapsed mem_before mem_max_before mem_max_after  file_size #>    <chr>         <chr>     <chr>         <dbl>       <dbl>        <dbl>      <dbl>          <dbl>         <dbl>      <dbl> #>  1 nanoparquet   read      small        0.0220     0.007         0.0290  156909568      156909568     236765184         NA #>  2 nanoparquet   write     small        0.103      0.015         0.117   305168384      305168384     386613248    5687737 #>  3 arrow         read      small        0.06       0.023         0.0400  160317440      160317440     267173888         NA #>  4 arrow         write     small        0.149      0.00700       0.151   306151424      306151424     340574208    5693381 #>  5 duckdb        read      small        0.081      0.018         0.0660  166313984      166313984     286916608         NA #>  6 duckdb        write     small        0.283      0.025         0.207   309510144      309510144     465649664   10684818 #>  7 data.table    read      small        0.137      0.016         0.0590  164282368      164282368     231325696         NA #>  8 data.table    write     small        0.158      0.0100        0.0620  313851904      313851904     314769408   30960660 #>  9 data.table.gz read      small        0.215      0.026         0.15    164986880      164986880     278757376         NA #> 10 data.table.gz write     small        1.45       0.014         0.386   310034432      310034432     311033856    8263176 #> 11 readr         read      small        1.08       0.27          0.415   162152448      162152448     350666752         NA #> 12 readr         write     small        1.78       1.85          0.781   314736640      314736640     359104512   31053850 #> 13 nanoparquet   read      medium       0.84       0.139         0.979   158351360      158351360    1640300544         NA #> 14 nanoparquet   write     medium       1.97       0.227         2.20   1079656448     1079656448    1762787328  111363363 #> 15 arrow         read      medium       1.40       0.265         0.982   168099840      168099840    2229256192         NA #> 16 arrow         write     medium       2.65       0.065         2.60   1090486272     1090486272    1380417536  112167843 #> 17 duckdb        read      medium       1.82       0.331         1.12    160743424      160743424    2224111616         NA #> 18 duckdb        write     medium       7.07       0.353         2.38   1099300864     1099300864    3086221312  213168966 #> 19 data.table    read      medium       2.36       0.135         0.891   159596544      159596544    1453031424         NA #> 20 data.table    write     medium       2.60       0.098         0.744  1086357504     1086357504    1088962560  619210198 #> 21 data.table.gz read      medium       3.26       0.305         1.98    155844608      155844608    1516044288         NA #> 22 data.table.gz write     medium      27.6        0.084         7.01   1092681728     1092681728    1095352320  165249944 #> 23 readr         read      medium      19.1        5.35          5.10    158367744      158367744    3874635776         NA #> 24 readr         write     medium      34.4       39.4          14.0    1090158592     1090158592    1932197888  621073998 #> 25 nanoparquet   read      large        7.25       2.44         10.8      73023488       73023488    8098021376         NA #> 26 nanoparquet   write     large       19.2        4.46         24.8    8158134272     8450293760    8450293760 1113819142 #> 27 arrow         read      large       12.0        7.32         10.8      72941568       72941568    9892495360         NA #> 28 arrow         write     large       27.9        2.31         29.9    8304607232     8573747200    8835842048 1121513329 #> 29 duckdb        read      large       16.2        5.18         14.6      75251712       75251712    8127512576         NA #> 30 duckdb        write     large       54.7       14.2          33.7    8305164288     8574451712    9348841472 2131769619 #> 31 data.table    read      large       21.6        3.87         12.8      78872576       78872576    8691007488         NA #> 32 data.table    write     large       26.3        1.69          8.09   8304033792     8573157376    8573157376 6192100558 #> 33 data.table.gz read      large       30.6        7.16         26.7      72876032       72876032    8018870272         NA #> 34 data.table.gz write     large      279.         1.93         71.6    8303362048     8572665856    8572665856 1652494401 #> 35 readr         read      large      144.       177.          231.       73564160       73564160    8500789248         NA #> 36 readr         write     large      333.       345.          143.     8304148480     8573452288    9224192000 6210738558"},{"path":"https://nanoparquet.r-lib.org/articles/benchmarks.html","id":"about","dir":"Articles","previous_headings":"","what":"About","title":"Benchmarks","text":"See benchmark-funcs.R file nanoparquet repository code benchmarks. ran measurement subprocess, make easier measure memory usage. include package loading time benchmarks. nanoparquet dependencies loads quickly. arrow duckdb packages might take 200ms load test system, need load dependencies also bigger.","code":"sessioninfo::session_info() #> ─ Session info ─────────────────────────────────────────────────────────────── #>  setting  value #>  version  R version 4.4.2 (2024-10-31) #>  os       Ubuntu 24.04.1 LTS #>  system   x86_64, linux-gnu #>  ui       X11 #>  language en-US #>  collate  C.UTF-8 #>  ctype    C.UTF-8 #>  tz       UTC #>  date     2025-02-22 #>  pandoc   3.1.11 @ /opt/hostedtoolcache/pandoc/3.1.11/x64/ (via rmarkdown) #>  quarto   1.6.41 @ /usr/local/bin/quarto #> #> ─ Packages ─────────────────────────────────────────────────────────────────── #>  package      * version  date (UTC) lib source #>  arrow          18.1.0.1 2025-01-08 [1] RSPM #>  assertthat     0.2.1    2019-03-21 [1] RSPM #>  base64enc      0.1-3    2015-07-28 [1] RSPM #>  bit            4.5.0.1  2024-12-03 [1] RSPM #>  bit64          4.6.0-1  2025-01-16 [1] RSPM #>  cli            3.6.4    2025-02-13 [1] RSPM #>  colorspace     2.1-1    2024-07-26 [1] RSPM #>  commonmark     1.9.2    2024-10-04 [1] RSPM #>  DBI            1.2.3    2024-06-02 [1] RSPM #>  digest         0.6.37   2024-08-19 [1] RSPM #>  dplyr        * 1.1.4    2023-11-17 [1] RSPM #>  duckdb         1.2.0    2025-02-21 [1] RSPM #>  evaluate       1.0.3    2025-01-10 [1] RSPM #>  farver         2.1.2    2024-05-13 [1] RSPM #>  fastmap        1.2.0    2024-05-15 [1] RSPM #>  fontawesome    0.5.3    2024-11-16 [1] RSPM #>  generics       0.1.3    2022-07-05 [1] RSPM #>  ggplot2        3.5.1    2024-04-23 [1] RSPM #>  glue           1.8.0    2024-09-30 [1] RSPM #>  gt           * 0.11.1   2024-10-04 [1] RSPM #>  gtable         0.3.6    2024-10-25 [1] RSPM #>  gtExtras     * 0.5.0    2023-09-15 [1] RSPM #>  htmltools      0.5.8.1  2024-04-04 [1] RSPM #>  jsonlite       1.9.0    2025-02-19 [1] RSPM #>  knitr          1.49     2024-11-08 [1] RSPM #>  labeling       0.4.3    2023-08-29 [1] RSPM #>  lifecycle      1.0.4    2023-11-07 [1] RSPM #>  magrittr       2.0.3    2022-03-30 [1] RSPM #>  markdown       1.13     2024-06-04 [1] RSPM #>  munsell        0.5.1    2024-04-01 [1] RSPM #>  nanoparquet    0.4.2    2025-02-22 [1] local #>  nycflights13   1.0.2    2021-04-12 [1] RSPM #>  paletteer      1.6.0    2024-01-21 [1] RSPM #>  pillar         1.10.1   2025-01-07 [1] RSPM #>  pkgconfig      2.0.3    2019-09-22 [1] RSPM #>  prettyunits    1.2.0    2023-09-24 [1] RSPM #>  purrr          1.0.4    2025-02-05 [1] RSPM #>  R6             2.6.1    2025-02-15 [1] RSPM #>  ragg           1.3.3    2024-09-11 [1] RSPM #>  rematch2       2.1.2    2020-05-01 [1] RSPM #>  rlang          1.1.5    2025-01-17 [1] RSPM #>  rmarkdown      2.29     2024-11-04 [1] RSPM #>  sass           0.4.9    2024-03-15 [1] RSPM #>  scales         1.3.0    2023-11-28 [1] RSPM #>  sessioninfo    1.2.3    2025-02-05 [1] any (@1.2.3) #>  svglite        2.1.3    2023-12-08 [1] RSPM #>  systemfonts    1.2.1    2025-01-20 [1] RSPM #>  textshaping    1.0.0    2025-01-20 [1] RSPM #>  tibble         3.2.1    2023-03-20 [1] RSPM #>  tidyselect     1.2.1    2024-03-11 [1] RSPM #>  utf8           1.2.4    2023-10-22 [1] RSPM #>  vctrs          0.6.5    2023-12-01 [1] RSPM #>  withr          3.0.2    2024-10-28 [1] RSPM #>  xfun           0.51     2025-02-19 [1] RSPM #>  xml2           1.3.6    2023-12-04 [1] RSPM #>  yaml           2.3.10   2024-07-26 [1] RSPM #> #>  [1] /home/runner/work/_temp/Library #>  [2] /opt/R/4.4.2/lib/R/site-library #>  [3] /opt/R/4.4.2/lib/R/library #>  * ── Packages attached to the search path. #> #> ──────────────────────────────────────────────────────────────────────────────"},{"path":"https://nanoparquet.r-lib.org/authors.html","id":null,"dir":"","previous_headings":"","what":"Authors","title":"Authors and Citation","text":"Gábor Csárdi. Author, maintainer. Hannes Mühleisen. Author, copyright holder. Google Inc.. Copyright holder. Apache Software Foundation. Copyright holder. . Copyright holder. RAD Game Tools. Copyright holder. Valve Software. Copyright holder. Tenacious Software LLC. Copyright holder. Facebook, Inc.. Copyright holder.","code":""},{"path":"https://nanoparquet.r-lib.org/authors.html","id":"citation","dir":"","previous_headings":"","what":"Citation","title":"Authors and Citation","text":"Csárdi G, Mühleisen H (2025). nanoparquet: Read Write 'Parquet' Files. R package version 0.4.2, https://nanoparquet.r-lib.org/, https://github.com/r-lib/nanoparquet.","code":"@Manual{,   title = {nanoparquet: Read and Write 'Parquet' Files},   author = {Gábor Csárdi and Hannes Mühleisen},   year = {2025},   note = {R package version 0.4.2,     https://nanoparquet.r-lib.org/},   url = {https://github.com/r-lib/nanoparquet}, }"},{"path":"https://nanoparquet.r-lib.org/index.html","id":"nanoparquet","dir":"","previous_headings":"","what":"Read and Write Parquet Files","title":"Read and Write Parquet Files","text":"nanoparquet reader writer common subset Parquet files.","code":""},{"path":"https://nanoparquet.r-lib.org/index.html","id":"features","dir":"","previous_headings":"","what":"Features:","title":"Read and Write Parquet Files","text":"Read write flat (.e. non-nested) Parquet files. Can read Parquet data types. Can read subset columns Parquet file. Can write many R data types, including factors temporal types Parquet. Can append data frame Parquet file without first reading rewriting whole file. Completely dependency free. Supports Snappy, Gzip Zstd compression. Competitive tools terms speed, memory use file size.","code":""},{"path":"https://nanoparquet.r-lib.org/index.html","id":"limitations","dir":"","previous_headings":"","what":"Limitations:","title":"Read and Write Parquet Files","text":"Nested Parquet types supported. Parquet logical types supported: INTERVAL, UNKNOWN. Snappy, Gzip Zstd compression supported. Encryption supported. Reading files URLs supported. nanoparquet always reads data (selected subset ) memory. work --memory data Parquet files like Apache Arrow DuckDB .","code":""},{"path":"https://nanoparquet.r-lib.org/index.html","id":"installation","dir":"","previous_headings":"","what":"Installation","title":"Read and Write Parquet Files","text":"Install R package CRAN:","code":"install.packages(\"nanoparquet\")"},{"path":[]},{"path":"https://nanoparquet.r-lib.org/index.html","id":"read","dir":"","previous_headings":"Usage","what":"Read","title":"Read and Write Parquet Files","text":"Call read_parquet() read Parquet file: see columns Parquet file types mapped R types read_parquet(), call read_parquet_schema() first: Folders similar-structured Parquet files (e.g. produced Spark) can read like :","code":"df <- nanoparquet::read_parquet(\"example.parquet\") nanoparquet::read_parquet_schema(\"example.parquet\") df <- data.table::rbindlist(lapply(   Sys.glob(\"some-folder/part-*.parquet\"),   nanoparquet::read_parquet ))"},{"path":"https://nanoparquet.r-lib.org/index.html","id":"write","dir":"","previous_headings":"Usage","what":"Write","title":"Read and Write Parquet Files","text":"Call write_parquet() write data frame Parquet file: see columns data frame mapped Parquet types write_parquet(), call infer_parquet_schema() first:","code":"nanoparquet::write_parquet(mtcars, \"mtcars.parquet\") nanoparquet::infer_parquet_schema(mtcars)"},{"path":"https://nanoparquet.r-lib.org/index.html","id":"inspect","dir":"","previous_headings":"Usage","what":"Inspect","title":"Read and Write Parquet Files","text":"Call read_parquet_info(), read_parquet_schema(), read_parquet_metadata() see various kinds metadata Parquet file: read_parquet_info() shows basic summary file. read_parquet_schema() shows columns, including non-leaf columns, mapped R types read_parquet(). read_parquet_metadata() shows complete metadata information: file meta data, schema, row groups column chunks file. find file supported isn’t, please open issue link file.","code":"nanoparquet::read_parquet_info(\"mtcars.parquet\") nanoparquet::read_parquet_schema(\"mtcars.parquet\") nanoparquet::read_parquet_metadata(\"mtcars.parquet\")"},{"path":"https://nanoparquet.r-lib.org/index.html","id":"options","dir":"","previous_headings":"","what":"Options","title":"Read and Write Parquet Files","text":"See also ?parquet_options() details. nanoparquet.class: extra class add data frames returned read_parquet(). defined, default \"tbl\", changes data frame printed pillar package loaded. nanoparquet.compression_level: See ?parquet_options() defaults possible values compression method. Inf selects maximum compression method. nanoparquet.num_rows_per_row_group: number rows put row group write_parquet(), row groups specified explicitly. integer scalar. Defaults 10 million. nanoparquet.use_arrow_metadata: unless set FALSE, read_parquet() make use Arrow metadata Parquet file. Currently used detect factor columns. nanoparquet.write_arrow_metadata: unless set FALSE, write_parquet() add Arrow metadata Parquet file. helps preserving classes columns, e.g. factors read back factors, nanoparquet Arrow. nanoparquet.write_data_page_version: Data version write default. Possible values 1 2. Default 1. nanoparquet.write_minmax_values: Whether write minimum maximum values per row group, data types support write_parquet().","code":""},{"path":"https://nanoparquet.r-lib.org/index.html","id":"license","dir":"","previous_headings":"","what":"License","title":"Read and Write Parquet Files","text":"MIT","code":""},{"path":"https://nanoparquet.r-lib.org/reference/append_parquet.html","id":null,"dir":"Reference","previous_headings":"","what":"Append a data frame to an existing Parquet file — append_parquet","title":"Append a data frame to an existing Parquet file — append_parquet","text":"schema data frame must compatible schema file.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/append_parquet.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Append a data frame to an existing Parquet file — append_parquet","text":"","code":"append_parquet(   x,   file,   compression = c(\"snappy\", \"gzip\", \"zstd\", \"uncompressed\"),   encoding = NULL,   row_groups = NULL,   options = parquet_options() )"},{"path":"https://nanoparquet.r-lib.org/reference/append_parquet.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Append a data frame to an existing Parquet file — append_parquet","text":"x Data frame append. file Path output file. compression Compression algorithm use newly written data. See write_parquet(). encoding Encoding use newly written data. encoding data file. See write_parquet() possible values. row_groups Row groups new, extended Parquet file. append_parquet() can change last existing row group, row_groups specified, respect . .e. existing file n rows, last row group starts k (k <= n), first row group row_groups refers new data must start k n+1. (simpler specify num_rows_per_row_group options, see parquet_options() instead row_groups. use row_groups need complete control.) options Nanoparquet options, new data, see parquet_options(). keep_row_groups option also affects whether append_parquet() overwrites existing row groups file.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/append_parquet.html","id":"warning","dir":"Reference","previous_headings":"","what":"Warning","title":"Append a data frame to an existing Parquet file — append_parquet","text":"function atomic! interrupted, may leave file corrupt state. work around create copy original file, append new data copy, rename new, extended file original one.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/append_parquet.html","id":"about-row-groups","dir":"Reference","previous_headings":"","what":"About row groups","title":"Append a data frame to an existing Parquet file — append_parquet","text":"Parquet file may partitioned multiple row groups, indeed large Parquet files . append_parquet() able update existing file along row group boundaries. two possibilities: append_parquet() keeps existing row groups file, creates new row groups new data. mode can forced keep_row_groups option options, see parquet_options(). Alternatively, write_parquet overwrite last row group file, existing contents plus (beginning ) new data. mode makes sense last row group small, many small row groups inefficient. default append_parquet chooses two modes automatically, aiming create row groups least num_rows_per_row_group (see parquet_options()) rows. can customize behavior keep_row_groups options row_groups argument.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/infer_parquet_schema.html","id":null,"dir":"Reference","previous_headings":"","what":"Infer Parquet schema of a data frame — infer_parquet_schema","title":"Infer Parquet schema of a data frame — infer_parquet_schema","text":"Infer Parquet schema data frame","code":""},{"path":"https://nanoparquet.r-lib.org/reference/infer_parquet_schema.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Infer Parquet schema of a data frame — infer_parquet_schema","text":"","code":"infer_parquet_schema(df, options = parquet_options())"},{"path":"https://nanoparquet.r-lib.org/reference/infer_parquet_schema.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Infer Parquet schema of a data frame — infer_parquet_schema","text":"df Data frame. options Return value parquet_options(), may modify R Parquet type mappings.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/infer_parquet_schema.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Infer Parquet schema of a data frame — infer_parquet_schema","text":"Data frame, inferred schema. columns return value read_parquet_schema(): file_name, name, r_type, type, type_length, repetition_type, converted_type, logical_type, num_children, scale, precision, field_id.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":null,"dir":"Reference","previous_headings":"","what":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Self-sufficient reader writer flat 'Parquet' files. Can read 'Parquet' data types. Can write many 'R' data types, including factors temporal types. See docs limitations.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"nanoparquet reader writer common subset Parquet files.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"features-","dir":"Reference","previous_headings":"","what":"Features:","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Read write flat (.e. non-nested) Parquet files. Can read Parquet data types. Can read subset columns Parquet file. Can write many R data types, including factors temporal types Parquet. Can append data frame Parquet file without first reading rewriting whole file. Completely dependency free. Supports Snappy, Gzip Zstd compression. Competitive tools terms speed, memory use file size.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"limitations-","dir":"Reference","previous_headings":"","what":"Limitations:","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Nested Parquet types supported. Parquet logical types supported: INTERVAL, UNKNOWN. Snappy, Gzip Zstd compression supported. Encryption supported. Reading files URLs supported. nanoparquet always reads data (selected subset ) memory. work --memory data Parquet files like Apache Arrow DuckDB .","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"installation","dir":"Reference","previous_headings":"","what":"Installation","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Install R package CRAN:","code":"install.packages(\"nanoparquet\")"},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"read","dir":"Reference","previous_headings":"","what":"Read","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Call read_parquet() read Parquet file:   see columns Parquet file types mapped R types read_parquet(), call read_parquet_schema() first:   Folders similar-structured Parquet files (e.g. produced Spark) can read like :","code":"df <- nanoparquet::read_parquet(\"example.parquet\") nanoparquet::read_parquet_schema(\"example.parquet\") df <- data.table::rbindlist(lapply(   Sys.glob(\"some-folder/part-*.parquet\"),   nanoparquet::read_parquet ))"},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"write","dir":"Reference","previous_headings":"","what":"Write","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Call write_parquet() write data frame Parquet file:   see columns data frame mapped Parquet types write_parquet(), call infer_parquet_schema() first:","code":"nanoparquet::write_parquet(mtcars, \"mtcars.parquet\") nanoparquet::infer_parquet_schema(mtcars)"},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"inspect","dir":"Reference","previous_headings":"","what":"Inspect","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Call read_parquet_info(), read_parquet_schema(), read_parquet_metadata() see various kinds metadata Parquet file: read_parquet_info() shows basic summary file. read_parquet_schema() shows columns, including non-leaf columns, mapped R types read_parquet(). read_parquet_metadata() shows complete metadata information: file meta data, schema, row groups column chunks file.   find file supported , please open issue link file.","code":"nanoparquet::read_parquet_info(\"mtcars.parquet\") nanoparquet::read_parquet_schema(\"mtcars.parquet\") nanoparquet::read_parquet_metadata(\"mtcars.parquet\")"},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"options","dir":"Reference","previous_headings":"","what":"Options","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"See also ?parquet_options() details. nanoparquet.class: extra class add data frames returned read_parquet(). defined, default \"tbl\", changes data frame printed pillar package loaded. nanoparquet.compression_level: See ?parquet_options() defaults possible values compression method. Inf selects maximum compression method. nanoparquet.num_rows_per_row_group: number rows put row group write_parquet(), row groups specified explicitly. integer scalar. Defaults 10 million. nanoparquet.use_arrow_metadata: unless set FALSE, read_parquet() make use Arrow metadata Parquet file. Currently used detect factor columns. nanoparquet.write_arrow_metadata: unless set FALSE, write_parquet() add Arrow metadata Parquet file. helps preserving classes columns, e.g. factors read back factors, nanoparquet Arrow. nanoparquet.write_data_page_version: Data version write default. Possible values 1 2. Default 1. nanoparquet.write_minmax_values: Whether write minimum maximum values per row group, data types support write_parquet().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"license","dir":"Reference","previous_headings":"","what":"License","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"MIT","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-package.html","id":"author","dir":"Reference","previous_headings":"","what":"Author","title":"nanoparquet: Read and Write 'Parquet' Files — nanoparquet-package","text":"Maintainer: Gábor Csárdi csardi.gabor@gmail.com Authors: Hannes Mühleisen (ORCID) [copyright holder] contributors: Google Inc. [copyright holder] Apache Software Foundation [copyright holder] Posit Software, PBC [copyright holder] RAD Game Tools [copyright holder] Valve Software [copyright holder] Tenacious Software LLC [copyright holder] Facebook, Inc. [copyright holder]","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-types.html","id":null,"dir":"Reference","previous_headings":"","what":"nanoparquet's type maps — nanoparquet-types","title":"nanoparquet's type maps — nanoparquet-types","text":"nanoparquet maps R types Parquet types.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-types.html","id":"r-s-data-types","dir":"Reference","previous_headings":"","what":"R's data types","title":"nanoparquet's type maps — nanoparquet-types","text":"writing data frame, nanoparquet maps R's data types Parquet logical types. following table summary mapping. details see . non-default mappings can selected via schema argument. E.g. write factor column called 'name' ENUM, use   detailed mapping rules listed , order preference. rules likely change nanoparquet reaches version 1.0.0. Factors (.e. vectors inherit factor class) converted character vectors using .character(), written STRSXP (character vector) type. fact column factor stored Arrow metadata (see ), unless nanoparquet.write_arrow_metadata option set FALSE. Dates (.e. Date class) written DATE logical type, INT32 type internally. hms objects (hms package) written TIME(true, MILLIS). logical type, internally INT32 Parquet type. Sub-milliseconds precision lost. POSIXct objects written TIMESTAMP(true, MICROS) logical type, internally INT64 Parquet type. Sub-microsecond precision lost. difftime objects (hms objects, see ), written INT64 Parquet type, noting Arrow metadata (see ) column type Duration NANOSECONDS unit. Integer vectors (INTSXP) written INT(32, true) logical type, corresponds INT32 type. Real vectors (REALSXP) written DOUBLE type. Character vectors (STRSXP) written STRING logical type, BYTE_ARRAY type. always converted UTF-8 writing. Logical vectors (LGLSXP) written BOOLEAN type. vectors error currently. can use infer_parquet_schema() data frame map R data types Parquet data types. change default R Parquet mapping, use parquet_schema() schema argument write_parquet(). Currently supported non-default mappings : integer INT64, integer INT96, double INT96, double FLOAT, character BYTE_ARRAY, character FIXED_LEN_BYTE_ARRAY, character ENUM, factor ENUM, integer DECIAML & INT32, integer DECIAML & INT64, double DECIAML & INT32, double DECIAML & INT64, integer INT(8, *), INT(16, *), INT(32, signed), double INT(*, *), character UUID, double FLOAT16, list raw vectors BYTE_ARRAY, list raw vectors FIXED_LEN_BYTE_ARRAY.","code":"write_parquet(..., schema = parquet_schema(name = \"ENUM\"))"},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-types.html","id":"parquet-s-data-types","dir":"Reference","previous_headings":"","what":"Parquet's data types","title":"nanoparquet's type maps — nanoparquet-types","text":"reading Parquet file nanoparquet also relies logical types Arrow metadata (present, see ) addition low level data types. following table summarizes mappings. See details . exact rules . rules likely change nanoparquet reaches version 1.0.0. BOOLEAN type read logical vector (LGLSXP). STRING logical type UTF8 converted type read character vector UTF-8 encoding. DATE logical type DATE converted type read Date R object. TIME logical type TIME_MILLIS TIME_MICROS converted types read hms object, see hms package. TIMESTAMP logical type TIMESTAMP_MILLIS TIMESTAMP_MICROS converted types read POSIXct objects. logical type UTC flag set, time zone POSIXct object set UTC. INT32 read integer vector (INTSXP). INT64, DOUBLE FLOAT read real vectors (REALSXP). INT96 read POSIXct read vector tzone attribute set \"UTC\". old convention store time stamps INT96 objects. DECIMAL converted type (FIXED_LEN_BYTE_ARRAY BYTE_ARRAY type) read real vector (REALSXP), potentially losing precision. ENUM logical type read character vector. UUID logical type read character vector uses 00112233-4455-6677-8899-aabbccddeeff form. FLOAT16 logical type read real vector (REALSXP). BYTE_ARRAY read factor object file written Arrow original data type column factor. (See 'Arrow metadata .) Otherwise BYTE_ARRAY read list raw vectors, missing values denoted NULL. logical converted types read annotated low level types: INT(8, true), INT(16, true) INT(32, true) read integer vectors INT32 internally Parquet. INT(64, true) read real vector (REALSXP). Unsigned integer types INT(8, false), INT(16, false) INT(32, false) read integer vectors (INTSXP). Large positive values may overflow negative values, known issue fix. INT(64, false) read real vector (REALSXP). Large positive values may overflow negative values, known issue fix. INTERVAL fixed length byte array, nanoparquet reads list raw vectors. Missing values denoted NULL. JSON columns read character vectors (STRSXP). BSON columns read raw vectors (RAWSXP). types yet supported: Nested types (LIST, MAP) supported. UNKNOWN logical type supported. can use read_parquet_schema() function see R read columns Parquet file. Look r_type column.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/nanoparquet-types.html","id":"the-arrow-metadata","dir":"Reference","previous_headings":"","what":"The Arrow metadata","title":"nanoparquet's type maps — nanoparquet-types","text":"Apache Arrow (.e. arrow R package) adds additional metadata Parquet files writing arrow::write_parquet(). , reading file arrow::read_parquet(), uses metadata recreate Arrow R data types writing. nanoparquet::write_parquet() also adds Arrow metadata Parquet files, unless nanoparquet.write_arrow_metadata option set FALSE. Similarly, nanoparquet::read_parquet() uses Arrow metadata Parquet file (present), unless nanoparquet.use_arrow_metadata option set FALSE. Arrow metadata stored file level key-value metadata, key ARROW:schema. Currently nanoparquet uses Arrow metadata two things: uses detect factors. Without Arrow metadata factors read string vectors. uses detect difftime objects. Without arrow metadata read INT64 columns, containing time difference nanoseconds.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":null,"dir":"Reference","previous_headings":"","what":"Parquet encodings — parquet-encodings","title":"Parquet encodings — parquet-encodings","text":"Various Parquet encodings","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"nanoparquet-defaults","dir":"Reference","previous_headings":"","what":"Nanoparquet defaults","title":"Parquet encodings — parquet-encodings","text":"Currently defaults decided based R types. might change future. general, defaults likely change nanoparquet reaches version 1.0.0. Current encoding defaults: Definition levels always use RLE. (Nanoparquet currently write repetition levels, also use RLE, implemented.) factor columns use RLE_DICTIONARY. logical columns use RLE average run length first 10,000 values least 15. Otherwise use PLAIN encoding. integer, double character columns use RLE_DICTIONARY least two third values repeated. Otherwise use PLAIN encoding. list columns raw vectors always use PLAIN encoding currently.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"parquet-encodings","dir":"Reference","previous_headings":"","what":"Parquet encodings","title":"Parquet encodings — parquet-encodings","text":"See https://github.com/apache/parquet-format/blob/master/Encodings.md details Parquet encodings.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"plain-encoding","dir":"Reference","previous_headings":"","what":"PLAIN encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: . general values written back back: Integer types little endian. Floating point types follow IEEE standard. BYTE_ARRAY: element, little endian 4-byte length bytes . FIXED_LEN_BYTE_ARRAY: bytes written back back. Nanoparquet can read write encoding primitive types.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"rle-dictionary-encoding","dir":"Reference","previous_headings":"","what":"RLE_DICTIONARY encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: dictionary indices data pages. encoding combines run-length encoding bit-packing. Repeated sequences value can run-length encoded, non-repeated parts bit packed. used data pages dictionaries. dictionary pages PLAIN encoded. deprecated PLAIN_DICTIONARY name treated RLE_DICTIONARY. Nanoparquet can read write encoding.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"rle-encoding","dir":"Reference","previous_headings":"","what":"RLE encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: BOOLEAN. Also definition repetition levels. encoding RLE_DICTIONARY, slightly different header. combines run-length encoding bit packing. used BOOLEAN columns, also definition repetition levels. Nanoparquet can read write encoding.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"bit-packed-encoding-deprecated-in-favor-of-rle-","dir":"Reference","previous_headings":"","what":"BIT_PACKED encoding (deprecated in favor of RLE)","title":"Parquet encodings — parquet-encodings","text":"Supported types: none. definition repetition levels, RLE used instead. simple bit packing encoding integers, previously used encoding definition repetition levels. used new Parquet files RLE encoding includes better. Nanoparquet currently read write BIT_PACKED encoding.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"delta-binary-packed-encoding","dir":"Reference","previous_headings":"","what":"DELTA_BINARY_PACKED encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: INT32, INT64. encoding efficiently encodes integer columns differences consecutive elements often , /differences consecutive elements small. extreme case arithmetic sequence can encoded O(1) space. Nanoparquet can read encoding, currently write .","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"delta-length-byte-array-encoding","dir":"Reference","previous_headings":"","what":"DELTA_LENGTH_BYTE_ARRAY encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: BYTE_ARRAY. encoding uses DELTA_BINARY_PACKED encode length byte array elements. especially efficient short byte array elements, .e. column short strings. Nanoparquet can read encoding, currently write .","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"delta-byte-array-encoding","dir":"Reference","previous_headings":"","what":"DELTA_BYTE_ARRAY encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: BYTE_ARRAY, FIXED_LEN_BYTE_ARRAY. encoding efficient consecutive byte array elements share prefix, element can reuse prefix previous element. Nanoparquet can read encoding, currently write .","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet-encodings.html","id":"byte-stream-split-encoding","dir":"Reference","previous_headings":"","what":"BYTE_STREAM_SPLIT encoding","title":"Parquet encodings — parquet-encodings","text":"Supported types: FLOAT, DOUBLE, INT32, INT64, FIXED_LEN_BYTE_ARRAY. encoding stores first bytes elements first, second bytes, etc. reduce size , may allow efficient compression. Nanoparquet can read encoding, currently write .","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/parquet_column_types.html","id":null,"dir":"Reference","previous_headings":"","what":"Map between R and Parquet data types — parquet_column_types","title":"Map between R and Parquet data types — parquet_column_types","text":"Note function now deprecated. Please use read_parquet_schema() files, infer_parquet_schema() data frames.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_column_types.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Map between R and Parquet data types — parquet_column_types","text":"","code":"parquet_column_types(x, options = parquet_options())"},{"path":"https://nanoparquet.r-lib.org/reference/parquet_column_types.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Map between R and Parquet data types — parquet_column_types","text":"x Path Parquet file, data frame. options Nanoparquet options, see parquet_options().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_column_types.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Map between R and Parquet data types — parquet_column_types","text":"Data frame columns: file_name: file name. name: column name. type: (low level) Parquet data type. r_type: R type corresponds Parquet type. Might NA read_parquet() read column. See nanoparquet-types type mapping rules. repetition_type: whether column REQUIRED (NA) OPTIONAL (may NA). REPEATED columns currently supported nanoparquet. logical_type: Parquet logical type list column. element least entry called type, potentially additional entries, e.g. bit_width, is_signed, etc.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_column_types.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Map between R and Parquet data types — parquet_column_types","text":"function works two ways. can map R types data frame Parquet types, see write_parquet() write data frame. can also map types Parquet file R types, see read_parquet() read file R.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/parquet_options.html","id":null,"dir":"Reference","previous_headings":"","what":"Nanoparquet options — parquet_options","title":"Nanoparquet options — parquet_options","text":"Create list nanoparquet options.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_options.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Nanoparquet options — parquet_options","text":"","code":"parquet_options(   class = getOption(\"nanoparquet.class\", \"tbl\"),   compression_level = getOption(\"nanoparquet.compression_level\", NA_integer_),   keep_row_groups = FALSE,   num_rows_per_row_group = getOption(\"nanoparquet.num_rows_per_row_group\", 10000000L),   use_arrow_metadata = getOption(\"nanoparquet.use_arrow_metadata\", TRUE),   write_arrow_metadata = getOption(\"nanoparquet.write_arrow_metadata\", TRUE),   write_data_page_version = getOption(\"nanoparquet.write_data_page_version\", 1L),   write_minmax_values = getOption(\"nanoparquet.write_minmax_values\", TRUE) )"},{"path":"https://nanoparquet.r-lib.org/reference/parquet_options.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Nanoparquet options — parquet_options","text":"class extra class classes add data frames created read_parquet(). default nanoparquet adds \"tbl\" class, data frames printed differently pillar package loaded. compression_level compression level write_parquet(). NA default, specifies default compression level method. Inf always selects highest possible compression level. details: Snappy support compression levels currently. GZIP supports levels 0 (uncompressed), 1 (fastest), 9 (best). default 6. ZSTD allows positive levels 22 currently. 20 require memory. Negative levels also allowed, lower level, faster speed, cost compression. Currently smallest level -131072. default level 3. keep_row_groups option used appending Parquet file append_parquet(). TRUE existing row groups file always kept nanoparquet creates new row groups new data. FALSE (default), last row group file overwritten smaller default row group size, .e. num_rows_per_row_group. num_rows_per_row_group number rows put row group, row groups specified explicitly. integer scalar. Defaults 10 million. use_arrow_metadata TRUE FALSE. TRUE, read_parquet() read_parquet_schema() make use Apache Arrow metadata assign R classes Parquet columns. currently used detect factor columns, detect \"difftime\" columns. option FALSE: \"factor\" columns read character vectors. \"difftime\" columns read real numbers, meaning one seconds, milliseconds, microseconds nanoseconds. Impossible tell without using Arrow metadata. write_arrow_metadata Whether add Apache Arrow types metadata file write_parquet(). write_data_page_version Data version write default. Possible values 1 2. Default 1. write_minmax_values Whether write minimum maximum values per row group, data types support write_parquet(). However, nanoparquet currently support minimum maximum values DECIMAL, UUID FLOAT16 logical types BOOLEAN, BYTE_ARRAY FIXED_LEN_BYTE_ARRAY primitive types writing without logical type. Currently default TRUE.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_options.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Nanoparquet options — parquet_options","text":"List nanoparquet options.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_options.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Nanoparquet options — parquet_options","text":"","code":"if (FALSE) { # the effect of using Arrow metadata tmp <- tempfile(fileext = \".parquet\") d <- data.frame(   fct = as.factor(\"a\"),   dft = as.difftime(10, units = \"secs\") ) write_parquet(d, tmp) read_parquet(tmp, options = parquet_options(use_arrow_metadata = TRUE)) read_parquet(tmp, options = parquet_options(use_arrow_metadata = FALSE)) }"},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":null,"dir":"Reference","previous_headings":"","what":"Create a Parquet schema — parquet_schema","title":"Create a Parquet schema — parquet_schema","text":"can use schema specify write data frame Parquet file write_parquet().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create a Parquet schema — parquet_schema","text":"","code":"parquet_schema(...)"},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create a Parquet schema — parquet_schema","text":"... Parquet type specifications, see . backwards compatibility, can supply file name , parquet_schema behaves read_parquet_schema().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Create a Parquet schema — parquet_schema","text":"Data frame columns read_parquet_schema(): file_name, name, r_type, type, type_length, repetition_type, converted_type, logical_type, num_children, scale, precision, field_id.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Create a Parquet schema — parquet_schema","text":"schema list potentially named type specifications. schema stored data frame. (potentially named) argument parquet_schema may character scalar, list. Parameterized types need specified list. Primitive Parquet types may specified string list.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"possible-types-","dir":"Reference","previous_headings":"","what":"Possible types:","title":"Create a Parquet schema — parquet_schema","text":"Special type: \"AUTO\": Parquet type, tells write_parquet() map R type Parquet automatically, using default mapping rules. Primitive Parquet types: \"BOOLEAN\" \"INT32\" \"INT64\" \"INT96\" \"FLOAT\" \"DOUBLE\" \"BYTE_ARRAY\" \"FIXED_LEN_BYTE_ARRAY\": fixed-length byte array. needs type_length parameter, integer 0 2^31-1. Parquet logical types: \"STRING\" \"ENUM\" \"UUID\" \"INTEGER\": signed unsigned integer. needs bit_width is_signed parameter. bit_width must 8, 16, 32 64. is_signed must TRUE FALSE. \"INT\": \"INTEGER\". Parquet documentation uses \"INT\", actual specification uses \"INTEGER\". supported nanoparquet. \"DECIMAL\": decimal number specified scale precision. needs precision primitive_type parameters. Also supports scale parameter, defaults zero specified. \"FLOAT16\" \"DATE\" \"TIME\": needs is_adjusted_utc (TRUE FALSE) unit parameter. unit must \"MILLIS\", \"MICROS\" \"NANOS\". \"TIMESTAMP\": needs is_adjusted_utc (TRUE FALSE) unit parameter. unit must \"MILLIS\", \"MICROS\" \"NANOS\". \"JSON\" \"BSON\" Logical types MAP, LIST UNKNOWN supported currently. Converted types deprecated Parquet specification favor logical types, parquet_schema() accepts converted types syntactic shortcut corresponding logical types: INT_8 mean list(\"INT\", bit_width = 8, is_signed = TRUE). INT_16 mean list(\"INT\", bit_width = 16, is_signed = TRUE). INT_32 mean list(\"INT\", bit_width = 32, is_signed = TRUE). INT_64 mean list(\"INT\", bit_width = 64, is_signed = TRUE). TIME_MICROS means list(\"TIME\", is_adjusted_utc = TRUE, unit = \"MICROS\"). TIME_MILLIS means list(\"TIME\", is_adjusted_utc = TRUE, unit = \"MILLIS\"). TIMESTAMP_MICROS means list(\"TIMESTAMP\", is_adjusted_utc = TRUE, unit = \"MICROS\"). TIMESTAMP_MILLIS means list(\"TIMESTAMP\", is_adjusted_utc = TRUE, unit = \"MILLIS\"). UINT_8 means list(\"INT\", bit_width = 8, is_signed = FALSE). UINT_16 means list(\"INT\", bit_width = 16, is_signed = FALSE). UINT_32 means list(\"INT\", bit_width = 32, is_signed = FALSE). UINT_64 means list(\"INT\", bit_width = 64, is_signed = FALSE).","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"missing-values","dir":"Reference","previous_headings":"","what":"Missing values","title":"Create a Parquet schema — parquet_schema","text":"type might also repetition_type parameter, possible values \"REQUIRED\", \"OPTIONAL\" \"REPEATED\". \"REQUIRED\" columns allow missing values. Missing values allowed \"OPTIONAL\" columns. \"REPEATED\" columns currently supported write_parquet().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/parquet_schema.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create a Parquet schema — parquet_schema","text":"","code":"parquet_schema(   c1 = \"INT32\",   c2 = list(\"INT\", bit_width = 64, is_signed = TRUE),   c3 = list(\"STRING\", repetition_type = \"OPTIONAL\") ) #> # A data frame: 3 × 12 #>   file_name name  r_type type       type_length repetition_type #> * <chr>     <chr> <chr>  <chr>            <int> <chr>           #> 1 NA        c1    NA     INT32               NA NA              #> 2 NA        c2    NA     INT64               NA NA              #> 3 NA        c3    NA     BYTE_ARRAY          NA OPTIONAL        #> # ℹ 6 more variables: converted_type <chr>, logical_type <I<list>>, #> #   num_children <int>, scale <int>, precision <int>, field_id <int>"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet.html","id":null,"dir":"Reference","previous_headings":"","what":"Read a Parquet file into a data frame — read_parquet","title":"Read a Parquet file into a data frame — read_parquet","text":"Converts contents named Parquet file R data frame.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Read a Parquet file into a data frame — read_parquet","text":"","code":"read_parquet(file, col_select = NULL, options = parquet_options())"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Read a Parquet file into a data frame — read_parquet","text":"file Path Parquet file. may also R connection, case first reads data connection, writes temporary file, reads temporary file, deletes . connection might open, case must binary connection. open, read_parquet() open also close end. col_select Columns read. can numeric vector column indices, character vector column names. error select column multiple times. order columns result order col_select. options Nanoparquet options, see parquet_options().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Read a Parquet file into a data frame — read_parquet","text":"data.frame file's contents.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Read a Parquet file into a data frame — read_parquet","text":"","code":"file_name <- system.file(\"extdata/userdata1.parquet\", package = \"nanoparquet\") parquet_df <- nanoparquet::read_parquet(file_name) print(str(parquet_df)) #> Classes ‘tbl’ and 'data.frame':\t1000 obs. of  13 variables: #>  $ registration: POSIXct, format: \"2016-02-03 07:55:29\" ... #>  $ id          : int  1 2 3 4 5 6 7 8 9 10 ... #>  $ first_name  : chr  \"Amanda\" \"Albert\" \"Evelyn\" \"Denise\" ... #>  $ last_name   : chr  \"Jordan\" \"Freeman\" \"Morgan\" \"Riley\" ... #>  $ email       : chr  \"ajordan0@com.com\" \"afreeman1@is.gd\" \"emorgan2@altervista.org\" \"driley3@gmpg.org\" ... #>  $ gender      : Factor w/ 2 levels \"Female\",\"Male\": 1 2 1 1 NA 1 2 2 2 1 ... #>  $ ip_address  : chr  \"1.197.201.2\" \"218.111.175.34\" \"7.161.136.94\" \"140.35.109.83\" ... #>  $ cc          : chr  \"6759521864920116\" NA \"6767119071901597\" \"3576031598965625\" ... #>  $ country     : chr  \"Indonesia\" \"Canada\" \"Russia\" \"China\" ... #>  $ birthdate   : Date, format: \"1971-03-08\" ... #>  $ salary      : num  49757 150280 144973 90263 NA ... #>  $ title       : chr  \"Internal Auditor\" \"Accountant IV\" \"Structural Engineer\" \"Senior Cost Accountant\" ... #>  $ comments    : chr  \"1E+02\" NA NA NA ... #> NULL"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_info.html","id":null,"dir":"Reference","previous_headings":"","what":"Short summary of a Parquet file — read_parquet_info","title":"Short summary of a Parquet file — read_parquet_info","text":"Short summary Parquet file","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_info.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Short summary of a Parquet file — read_parquet_info","text":"","code":"read_parquet_info(file)  parquet_info(file)"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_info.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Short summary of a Parquet file — read_parquet_info","text":"file Path Parquet file.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_info.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Short summary of a Parquet file — read_parquet_info","text":"Data frame columns: file_name: file name. num_cols: number (leaf) columns. num_rows: number rows. num_row_groups: number row groups. file_size: file size bytes. parquet_version: Parquet version. created_by: string scalar, usually name software created file. NA available.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_metadata.html","id":null,"dir":"Reference","previous_headings":"","what":"Read the metadata of a Parquet file — read_parquet_metadata","title":"Read the metadata of a Parquet file — read_parquet_metadata","text":"function work files, even read_parquet() unable read , unsupported schema, encoding, compression reason.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_metadata.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Read the metadata of a Parquet file — read_parquet_metadata","text":"","code":"read_parquet_metadata(file, options = parquet_options())  parquet_metadata(file)"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_metadata.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Read the metadata of a Parquet file — read_parquet_metadata","text":"file Path Parquet file. options Options potentially alter default Parquet R type mappings, see parquet_options().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_metadata.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Read the metadata of a Parquet file — read_parquet_metadata","text":"named list entries: file_meta_data: data frame file meta data: file_name: file name. version: Parquet version, integer. num_rows: total number rows. key_value_metadata: list column data frames two character columns called key value. key-value metadata file. Arrow stores schema . created_by: string scalar, usually name software created file. schema: data frame, schema file. one row node (inner node leaf node). flat files means one root node (inner node), always first one, one row \"real\" column. nested schemas, rows depth-first search order. important columns : file_name: file name. name: column name. r_type: R type corresponds Parquet type. Might NA read_parquet() read column. See nanoparquet-types type mapping rules. r_type: type: data type. One low level data types. type_length: length fixed length byte arrays. repettion_type: character, one REQUIRED, OPTIONAL REPEATED. logical_type: list column, logical types columns. element least entry called type, potentially additional entries, e.g. bit_width, is_signed, etc. num_children: number child nodes. non-negative integer root node, NA leaf node. $row_groups: data frame, information row groups. important columns: file_name: file name. id: row group id, integer zero number row groups minus one. total_byte_size: total uncompressed size column data. num_rows: number rows. file_offset: row group starts file. optional, might NA. total_compressed_size: total byte size compressed (potentially encrypted) column data row group. optional, might NA. ordinal: ordinal position row group file, starting zero. optional, might NA. NA, order row groups appear metadata. $column_chunks: data frame, information column chunks, across row groups. important columns: file_name: file name. row_group: row group chunk belongs . column: leaf column chunks belongs . order $schema, leaf columns (.e. columns NA children) counted. file_path: file chunk stored . NA means file. file_offset: column chunk begins file. type: low level parquet data type. encodings: encodings used store chunk. list column character vectors encoding names. Current possible encodings: \"PLAIN\", \"GROUP_VAR_INT\", \"PLAIN_DICTIONARY\", \"RLE\", \"BIT_PACKED\", \"DELTA_BINARY_PACKED\", \"DELTA_LENGTH_BYTE_ARRAY\", \"DELTA_BYTE_ARRAY\", \"RLE_DICTIONARY\", \"BYTE_STREAM_SPLIT\". path_in_scema: list column character vectors. simply path root node. simply column name flat schemas. codec: compression codec used column chunk. Possible values : \"UNCOMPRESSED\", \"SNAPPY\", \"GZIP\", \"LZO\", \"BROTLI\", \"LZ4\", \"ZSTD\". num_values: number values column chunk. total_uncompressed_size: total uncompressed size bytes. total_compressed_size: total compressed size bytes. data_page_offset: absolute position first data page column chunk file. index_page_offset: absolute position first index page column chunk file, NA index pages. dictionary_page_offset: absolute position first dictionary page column chunk file, NA dictionary pages. null_count: number missing values column chunk. may NA. min_value: list column raw vectors, minimum value column, binary. NULL, specified. column experimental. max_value: list column raw vectors, maximum value column, binary. NULL, specified. column experimental. is_min_value_exact: whether minimum value actual value column, bound. may NA. is_max_value_exact: whether maximum value actual value column, bound. may NA.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_metadata.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Read the metadata of a Parquet file — read_parquet_metadata","text":"","code":"file_name <- system.file(\"extdata/userdata1.parquet\", package = \"nanoparquet\") nanoparquet::read_parquet_metadata(file_name) #> $file_meta_data #> # A data frame: 1 × 5 #>   file_name              version num_rows key_value_metadata created_by #>   <chr>                    <int>    <dbl> <I<list>>          <chr>      #> 1 /home/runner/work/_te…       1     1000 <tbl [1 × 2]>      https://g… #>  #> $schema #> # A data frame: 14 × 12 #>    file_name             name  r_type type  type_length repetition_type #>    <chr>                 <chr> <chr>  <chr>       <int> <chr>           #>  1 /home/runner/work/_t… sche… NA     NA             NA NA              #>  2 /home/runner/work/_t… regi… POSIX… INT64          NA REQUIRED        #>  3 /home/runner/work/_t… id    integ… INT32          NA REQUIRED        #>  4 /home/runner/work/_t… firs… chara… BYTE…          NA OPTIONAL        #>  5 /home/runner/work/_t… last… chara… BYTE…          NA REQUIRED        #>  6 /home/runner/work/_t… email factor BYTE…          NA OPTIONAL        #>  7 /home/runner/work/_t… gend… chara… BYTE…          NA OPTIONAL        #>  8 /home/runner/work/_t… ip_a… chara… BYTE…          NA REQUIRED        #>  9 /home/runner/work/_t… cc    chara… BYTE…          NA OPTIONAL        #> 10 /home/runner/work/_t… coun… chara… BYTE…          NA REQUIRED        #> 11 /home/runner/work/_t… birt… Date   INT32          NA OPTIONAL        #> 12 /home/runner/work/_t… sala… double DOUB…          NA OPTIONAL        #> 13 /home/runner/work/_t… title chara… BYTE…          NA OPTIONAL        #> 14 /home/runner/work/_t… comm… chara… BYTE…          NA OPTIONAL        #> # ℹ 6 more variables: converted_type <chr>, logical_type <I<list>>, #> #   num_children <int>, scale <int>, precision <int>, field_id <int> #>  #> $row_groups #> # A data frame: 1 × 7 #>   file_name                     id total_byte_size num_rows file_offset #>   <chr>                      <int>           <dbl>    <dbl>       <dbl> #> 1 /home/runner/work/_temp/L…     0           71427     1000          NA #> # ℹ 2 more variables: total_compressed_size <dbl>, ordinal <int> #>  #> $column_chunks #> # A data frame: 13 × 24 #>    file_name row_group column file_path file_offset offset_index_offset #>    <chr>         <int>  <int> <chr>           <dbl>               <dbl> #>  1 /home/ru…         0      0 NA                  4                  NA #>  2 /home/ru…         0      1 NA               6741                  NA #>  3 /home/ru…         0      2 NA              12259                  NA #>  4 /home/ru…         0      3 NA              15211                  NA #>  5 /home/ru…         0      4 NA              16239                  NA #>  6 /home/ru…         0      5 NA              31759                  NA #>  7 /home/ru…         0      6 NA              32031                  NA #>  8 /home/ru…         0      7 NA              42952                  NA #>  9 /home/ru…         0      8 NA              55009                  NA #> 10 /home/ru…         0      9 NA              55925                  NA #> 11 /home/ru…         0     10 NA              59312                  NA #> 12 /home/ru…         0     11 NA              67026                  NA #> 13 /home/ru…         0     12 NA              71089                  NA #> # ℹ 18 more variables: offset_index_length <int>, #> #   column_index_offset <dbl>, column_index_length <int>, type <chr>, #> #   encodings <I<list>>, path_in_schema <I<list>>, codec <chr>, #> #   num_values <dbl>, total_uncompressed_size <dbl>, #> #   total_compressed_size <dbl>, data_page_offset <dbl>, #> #   index_page_offset <dbl>, dictionary_page_offset <dbl>, #> #   null_count <dbl>, min_value <I<list>>, max_value <I<list>>, … #>"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_page.html","id":null,"dir":"Reference","previous_headings":"","what":"Read a page from a Parquet file — read_parquet_page","title":"Read a page from a Parquet file — read_parquet_page","text":"Read page Parquet file","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_page.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Read a page from a Parquet file — read_parquet_page","text":"","code":"read_parquet_page(file, offset)"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_page.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Read a page from a Parquet file — read_parquet_page","text":"file Path Parquet file. offset Integer offset start page file. See read_parquet_pages() list pages offsets.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_page.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Read a page from a Parquet file — read_parquet_page","text":"Named list. Many entries correspond columns result read_parquet_pages(). Additional entries : codec: compression codec. Possible values: has_repetition_levels: whether page repetition levels. has_definition_levels: whether page definition levels. schema_column: schema column page corresponds . Note leaf columns pages. data_type: low level Parquet data type. Possible values: repetition_type: whether column page belongs REQUIRED, OPTIONAL REPEATED. page_header: bytes page header raw vector. num_null: number missing (NA) values. set V2 data pages. num_rows: num_values flat tables, .e. files without repetition levels. compressed_data: data page raw vector. includes repetition definition levels, . data: uncompressed data, nanoparquet supports compression codec file (GZIP SNAPPY time writing), file compressed. latter case compressed_data.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_page.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Read a page from a Parquet file — read_parquet_page","text":"","code":"file_name <- system.file(\"extdata/userdata1.parquet\", package = \"nanoparquet\") nanoparquet:::read_parquet_pages(file_name) #> # A data frame: 19 × 14 #>    file_name              row_group column page_type page_header_offset #>    <chr>                      <int>  <int> <chr>                  <dbl> #>  1 /home/runner/work/_te…         0      0 DATA_PAGE                  4 #>  2 /home/runner/work/_te…         0      1 DATA_PAGE               6741 #>  3 /home/runner/work/_te…         0      2 DICTIONA…              10766 #>  4 /home/runner/work/_te…         0      2 DATA_PAGE              12259 #>  5 /home/runner/work/_te…         0      3 DICTIONA…              13334 #>  6 /home/runner/work/_te…         0      3 DATA_PAGE              15211 #>  7 /home/runner/work/_te…         0      4 DATA_PAGE              16239 #>  8 /home/runner/work/_te…         0      5 DICTIONA…              31726 #>  9 /home/runner/work/_te…         0      5 DATA_PAGE              31759 #> 10 /home/runner/work/_te…         0      6 DATA_PAGE              32031 #> 11 /home/runner/work/_te…         0      7 DATA_PAGE              42952 #> 12 /home/runner/work/_te…         0      8 DICTIONA…              53749 #> 13 /home/runner/work/_te…         0      8 DATA_PAGE              55009 #> 14 /home/runner/work/_te…         0      9 DATA_PAGE              55925 #> 15 /home/runner/work/_te…         0     10 DATA_PAGE              59312 #> 16 /home/runner/work/_te…         0     11 DICTIONA…              65063 #> 17 /home/runner/work/_te…         0     11 DATA_PAGE              67026 #> 18 /home/runner/work/_te…         0     12 DICTIONA…              68019 #> 19 /home/runner/work/_te…         0     12 DATA_PAGE              71089 #> # ℹ 9 more variables: uncompressed_page_size <int>, #> #   compressed_page_size <int>, crc <int>, num_values <int>, #> #   encoding <chr>, definition_level_encoding <chr>, #> #   repetition_level_encoding <chr>, data_offset <dbl>, #> #   page_header_length <int> options(max.print = 100)  # otherwise long raw vector nanoparquet:::read_parquet_page(file_name, 4L) #> $page_type #> [1] \"DATA_PAGE\" #>  #> $row_group #> [1] 0 #>  #> $column #> [1] 0 #>  #> $page_header_offset #> [1] 4 #>  #> $data_page_offset #> [1] 24 #>  #> $page_header_length #> [1] 20 #>  #> $compressed_page_size #> [1] 6717 #>  #> $uncompressed_page_size #> [1] 8000 #>  #> $codec #> [1] \"SNAPPY\" #>  #> $num_values #> [1] 1000 #>  #> $encoding #> [1] \"PLAIN\" #>  #> $definition_level_encoding #> [1] \"PLAIN\" #>  #> $repetition_level_encoding #> [1] \"PLAIN\" #>  #> $has_repetition_levels #> [1] FALSE #>  #> $has_definition_levels #> [1] FALSE #>  #> $schema_column #> [1] 1 #>  #> $data_type #> [1] \"INT64\" #>  #> $repetition_type #> [1] \"REQUIRED\" #>  #> $page_header #>  [1] 15 00 15 80 7d 15 fa 68 2c 15 d0 0f 15 00 15 00 15 00 00 00 #>  #> $data #>   [1] 40 be 0c f1 d8 2a 05 00 c0 86 e0 9a e0 2a 05 00 c0 28 33 45 d3 2a #>  [23] 05 00 40 2b 96 ce d2 2a 05 00 c0 9c 33 91 d6 2a 05 00 80 a2 54 7b #>  [45] d8 2a 05 00 00 59 b2 77 d9 2a 05 00 80 ee 7d fc d7 2a 05 00 40 cf #>  [67] 71 8d d5 2a 05 00 c0 bc 7b cd e1 2a 05 00 80 e4 da 72 d2 2a 05 00 #>  [89] 80 30 4d 73 e1 2a 05 00 40 fe a4 0f #>  [ reached getOption(\"max.print\") -- omitted 7900 entries ] #>  #> $definition_levels_byte_length #> [1] NA #>  #> $repetition_levels_byte_length #> [1] NA #>  #> $num_nulls #> [1] NA #>  #> $num_rows #> [1] NA #>  #> $compressed_data #>   [1] c0 3e 30 40 be 0c f1 d8 2a 05 00 c0 86 e0 9a e0 01 08 2c 28 33 45 #>  [23] d3 2a 05 00 40 2b 96 ce d2 01 10 28 9c 33 91 d6 2a 05 00 80 a2 54 #>  [45] 7b 01 28 10 00 59 b2 77 d9 01 10 0c ee 7d fc d7 01 28 0c cf 71 8d #>  [67] d5 01 28 0c bc 7b cd e1 01 18 08 e4 da 72 01 38 0c 80 30 4d 73 01 #>  [89] 10 30 40 fe a4 0f e2 2a 05 00 00 eb #>  [ reached getOption(\"max.print\") -- omitted 6617 entries ] #>"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":null,"dir":"Reference","previous_headings":"","what":"Metadata of all pages of a Parquet file — read_parquet_pages","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"Metadata pages Parquet file","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"","code":"read_parquet_pages(file)"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"file Path Parquet file.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"Data frame columns: file_name: file name. row_group: id row group page belongs , integer 0 number row groups minus one. column: id column. integer number leaf columns minus one. Note leaf columns considered, non-leaf columns pages. page_type: DATA_PAGE, INDEX_PAGE, DICTIONARY_PAGE DATA_PAGE_V2. page_header_offset: offset data page (header) file. uncompressed_page_size: include page header, per Parquet spec. compressed_page_size: without page header. crc: integer, checksum, present file, can NA. num_values: number data values page, include NULL (NA R) values. encoding: encoding page, current possible encodings: \"PLAIN\", \"GROUP_VAR_INT\", \"PLAIN_DICTIONARY\", \"RLE\", \"BIT_PACKED\", \"DELTA_BINARY_PACKED\", \"DELTA_LENGTH_BYTE_ARRAY\", \"DELTA_BYTE_ARRAY\", \"RLE_DICTIONARY\", \"BYTE_STREAM_SPLIT\". definition_level_encoding: encoding definition levels, see encoding possible values. can missing V2 data pages, always RLE encoded. repetition_level_encoding: encoding repetition levels, see encoding possible values. can missing V2 data pages, always RLE encoded. data_offset: offset actual data file. page_header_length: size page header, bytes.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"Reading page headers might slow large files, especially file many small pages.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_pages.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Metadata of all pages of a Parquet file — read_parquet_pages","text":"","code":"file_name <- system.file(\"extdata/userdata1.parquet\", package = \"nanoparquet\") nanoparquet:::read_parquet_pages(file_name) #> # A data frame: 19 × 14 #>    file_name              row_group column page_type page_header_offset #>    <chr>                      <int>  <int> <chr>                  <dbl> #>  1 /home/runner/work/_te…         0      0 DATA_PAGE                  4 #>  2 /home/runner/work/_te…         0      1 DATA_PAGE               6741 #>  3 /home/runner/work/_te…         0      2 DICTIONA…              10766 #>  4 /home/runner/work/_te…         0      2 DATA_PAGE              12259 #>  5 /home/runner/work/_te…         0      3 DICTIONA…              13334 #>  6 /home/runner/work/_te…         0      3 DATA_PAGE              15211 #>  7 /home/runner/work/_te…         0      4 DATA_PAGE              16239 #>  8 /home/runner/work/_te…         0      5 DICTIONA…              31726 #>  9 /home/runner/work/_te…         0      5 DATA_PAGE              31759 #> 10 /home/runner/work/_te…         0      6 DATA_PAGE              32031 #> 11 /home/runner/work/_te…         0      7 DATA_PAGE              42952 #> 12 /home/runner/work/_te…         0      8 DICTIONA…              53749 #> 13 /home/runner/work/_te…         0      8 DATA_PAGE              55009 #> 14 /home/runner/work/_te…         0      9 DATA_PAGE              55925 #> 15 /home/runner/work/_te…         0     10 DATA_PAGE              59312 #> 16 /home/runner/work/_te…         0     11 DICTIONA…              65063 #> 17 /home/runner/work/_te…         0     11 DATA_PAGE              67026 #> 18 /home/runner/work/_te…         0     12 DICTIONA…              68019 #> 19 /home/runner/work/_te…         0     12 DATA_PAGE              71089 #> # ℹ 9 more variables: uncompressed_page_size <int>, #> #   compressed_page_size <int>, crc <int>, num_values <int>, #> #   encoding <chr>, definition_level_encoding <chr>, #> #   repetition_level_encoding <chr>, data_offset <dbl>, #> #   page_header_length <int>"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_schema.html","id":null,"dir":"Reference","previous_headings":"","what":"Read the schema of a Parquet file — read_parquet_schema","title":"Read the schema of a Parquet file — read_parquet_schema","text":"function work files, even read_parquet() unable read , unsupported schema, encoding, compression reason.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_schema.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Read the schema of a Parquet file — read_parquet_schema","text":"","code":"read_parquet_schema(file, options = parquet_options())"},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_schema.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Read the schema of a Parquet file — read_parquet_schema","text":"file Path Parquet file. options Return value parquet_options(), options potentially modify Parquet R type mappings.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/read_parquet_schema.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Read the schema of a Parquet file — read_parquet_schema","text":"","code":"Data frame, the schema of the file. It has one row for each node (inner node or leaf node). For flat files this means one root node (inner node), always the first one, and then one row for each \"real\" column. For nested schemas, the rows are in depth-first search order. Most important columns are: - `file_name`: file name. - `name`: column name. - `r_type`: the R type that corresponds to the Parquet type.   Might be `NA` if [read_parquet()] cannot read this column. See   [nanoparquet-types] for the type mapping rules. - `type`: data type. One of the low level data types. - `type_length`: length for fixed length byte arrays. - `repettion_type`: character, one of `REQUIRED`, `OPTIONAL` or   `REPEATED`. - `logical_type`: a list column, the logical types of the columns.   An element has at least an entry called `type`, and potentially   additional entries, e.g. `bit_width`, `is_signed`, etc. - `num_children`: number of child nodes. Should be a non-negative   integer for the root node, and `NA` for a leaf node."},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/rle_decode_int.html","id":null,"dir":"Reference","previous_headings":"","what":"RLE decode integers — rle_decode_int","title":"RLE decode integers — rle_decode_int","text":"RLE decode integers","code":""},{"path":"https://nanoparquet.r-lib.org/reference/rle_decode_int.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"RLE decode integers — rle_decode_int","text":"","code":"rle_decode_int(   x,   bit_width = attr(x, \"bit_width\"),   length = attr(x, \"length\") %||% NA )"},{"path":"https://nanoparquet.r-lib.org/reference/rle_decode_int.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"RLE decode integers — rle_decode_int","text":"x Raw vector encoded integers. bit_width Bit width used encoding. length Length output. NA assume x starts length output, encoded 4 byte integer.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/rle_decode_int.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"RLE decode integers — rle_decode_int","text":"decoded integer vector.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/rle_encode_int.html","id":null,"dir":"Reference","previous_headings":"","what":"RLE encode integers — rle_encode_int","title":"RLE encode integers — rle_encode_int","text":"RLE encode integers","code":""},{"path":"https://nanoparquet.r-lib.org/reference/rle_encode_int.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"RLE encode integers — rle_encode_int","text":"","code":"rle_encode_int(x)"},{"path":"https://nanoparquet.r-lib.org/reference/rle_encode_int.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"RLE encode integers — rle_encode_int","text":"x Integer vector.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/rle_encode_int.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"RLE encode integers — rle_encode_int","text":"Raw vector, encoded integers. two attributes: bit_length: number bits needed encode input, length: length original integer input.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":null,"dir":"Reference","previous_headings":"","what":"Write a data frame to a Parquet file — write_parquet","title":"Write a data frame to a Parquet file — write_parquet","text":"Writes contents R data frame Parquet file.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Write a data frame to a Parquet file — write_parquet","text":"","code":"write_parquet(   x,   file,   schema = NULL,   compression = c(\"snappy\", \"gzip\", \"zstd\", \"uncompressed\"),   encoding = NULL,   metadata = NULL,   row_groups = NULL,   options = parquet_options() )"},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Write a data frame to a Parquet file — write_parquet","text":"x Data frame write. file Path output file. string \":raw:\", data frame written memory buffer, memory buffer returned raw vector. schema Parquet schema. Specify schema tweak default nanoparquet R -> Parquet type mappings. Use parquet_schema() create schema can use , read_parquet_schema() use schema Parquet file. compression Compression algorithm use. Currently \"snappy\" (default), \"gzip\", \"zstd\", \"uncompressed\" supported. encoding Encoding use. Possible values: NULL, appropriate encoding selected automatically: RLE PLAIN BOOLEAN columns, RLE_DICTIONARY columns many repeated values, PLAIN otherwise. single (unnamed) character string, 'll used columns. unnamed character vector encoding names length number columns data frame, encodings used column. named character vector, named must unique name must match column name, specify encoding column. special empty name (\"\") applies rest columns. empty name, rest columns use default encoding. NA_character_ specified column, default encoding used column. specified encoding invalid certain column type, nanoparquet implement , write_parquet() throws error. Currently write_parquet() supports following encodings: PLAIN column types, PLAIN_DICTIONARY RLE_DICTIONARY column types, RLE BOOLEAN columns. See parquet-encodings encodings. metadata Additional key-value metadata add file. must named character vector, data frame columns character columns called key value. row_groups Row groups Parquet file. NULL, num_rows_per_row_group option used options argument, see parquet_options(). Otherwise must integer vector, specifying starts row groups. options Nanoparquet options, see parquet_options().","code":""},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Write a data frame to a Parquet file — write_parquet","text":"NULL, unless file \":raw:\", case Parquet file returned raw vector.","code":""},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":"details","dir":"Reference","previous_headings":"","what":"Details","title":"Write a data frame to a Parquet file — write_parquet","text":"write_parquet() converts string columns UTF-8 encoding calling base::enc2utf8(). factor levels.","code":""},{"path":[]},{"path":"https://nanoparquet.r-lib.org/reference/write_parquet.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Write a data frame to a Parquet file — write_parquet","text":"","code":"if (FALSE) { # add row names as a column, because `write_parquet()` ignores them. mtcars2 <- cbind(name = rownames(mtcars), mtcars) write_parquet(mtcars2, \"mtcars.parquet\") }"},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-042","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.4.2","title":"nanoparquet 0.4.2","text":"CRAN release: 2025-02-22 write_parquet() now fail writing files zero-length first page (#122). read_parquet() can now read Parquet files contain dictionary page offset metadata. Polars creates files (#132).","code":""},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-041","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.4.1","title":"nanoparquet 0.4.1","text":"CRAN release: 2025-02-10 write_parquet() now correctly converts double Date columns integer columns (@eitsupi, #116). read_parquet() now correctly reads FLOAT columns files multiple row groups. read_parquet() now correctly reads Parquet files column chunks dictionary encoded dictionary encoded pages (#110).","code":""},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-040","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.4.0","title":"nanoparquet 0.4.0","text":"CRAN release: 2025-01-29 API changes: parquet_schema() now called read_parquet_schema(). new parquet_schema() function falls back read_parquet_schema() called single string argument, warning. parquet_info() now called read_parquet_info(). parquet_info( still works now, warning. parquet_metadata() now called read_parquet_metadata(). parquet_metadata() still works, warning. parquet_column_types() now deprecated, issues warning. Use read_parquet_schema() new infer_parquet_schema() function instead. improvements: new parquet_schema() function creates Parquet schema scratch. can use schema new schema argument write_parquet(), specify columns data frame mapped Parquet types. New append_parquet() function append data frame existing Parquet file. New col_select argument read_parquet() read subset columns Parquet file. write_parquet() can now write multiple row groups. default puts 10 million rows single row group. can choose row groups manually row_groups argument. write_parquet() now writes minimum maximum values per row group types. See ?parquet_options() turning . also writes number non-missing values. Newly supported type conversions write_parquet() via schema argument: integer INT64, integer INT96, double INT96, double FLOAT, character BYTE_ARRAY, character FIXED_LEN_BYTE_ARRAY, character ENUM, factor ENUM. integer DECIMAL, INT32, integer DECIMAL, INT64, double DECIMAL, INT32, double DECIMAL, INT64, integer INT(8, *), INT(16, *), INT(32, signed), double INT(*, *), character UUID, double FLOAT16, list raw vectors BYTE_ARRAY, list raw vectors FIXED_LEN_BYTE_ARRAY. write_parquet() can now write version 2 data pages. default still version 1, might change future. write_parquet(file = \":raw:\") now works correctly larger data frames (#77). New compression_level option select compression level manually. See ?parquet_options details. (#91). read_parquet() can now read R connection (#71). read_parquet() now reads DECIMAL values correctly INT32 INT64 columns scale zero. read_parquet() now reads JSON columns character vectors, documented. read_parquet() now reads FLOAT16 logical type real (double) vector. class argument parquet_options() nanoparquet.class option now work (#104).","code":""},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-031","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.3.1","title":"nanoparquet 0.3.1","text":"CRAN release: 2024-07-01 version fixes write_parquet() crash (#73).","code":""},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-030","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.3.0","title":"nanoparquet 0.3.0","text":"CRAN release: 2024-06-17 read_parquet() type mapping changes: STRING logical type UTF8 converted type still read character vector, BYTE_ARRAY types without converted logical types , read list raw vectors. Missing values indicated NULL values. DECIMAL converted type read REALSXP now, even type FIXED_LEN_BYTE_ARRAY. (just BYTE_ARRAY). UUID logical type now read character vector, formatted 00112233-4455-6677-8899-aabbccddeeff. BYTE_ARRAY FIXED_LEN_BYTE_ARRAY types without logical converted types; unsupported ones: FLOAT16, INTERVAL; now read list raw vectors. Missing values denoted NULL. write_parquet() now automatically uses dictionary encoding columns many repeated values. first 10k rows used decide dictionary used . Similarly, logical columns written RLE encoding contain runs repeated values. NA values ignored selecting encoding (#18). write_parquet() can now write data frame memory buffer, returned raw vector, special \":raw:\" filename used (#31). read_parquet() can now read Parquet files V2 data pages (#37). read_parquet() write_parquet() now support GZIP ZSTD compressed Parquet files. read_parquet() now supports RLE encoding BOOLEAN columns also supports DELTA_BINARY_PACKED, DELTA_LENGTH_BYTE_ARRAY, DELTA_BYTE_ARRAY BYTE_STREAM_SPLIT encodings. parquet_columns() function now called parquet_column_types() can now map column types data frame Parquet types. parquet_info(), parquet_metadata() parquet_column_types() now work created_by metadata field unset. New parquet_options() function can use set nanoparquet options single read_parquet() write_parquet() call.","code":""},{"path":"https://nanoparquet.r-lib.org/news/index.html","id":"nanoparquet-020","dir":"Changelog","previous_headings":"","what":"nanoparquet 0.2.0","title":"nanoparquet 0.2.0","text":"CRAN release: 2024-05-30 First release CRAN. contains Parquet reader https://github.com/hannes/miniparquet, Parquet writer, functions read Parquet metadata, many improvements.","code":""}]