This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/arrow-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new f3df8a28842 Updating dev docs (build nightly-tests-2024-09-01-0)
f3df8a28842 is described below
commit f3df8a28842c1fe3d0a9c12360a0c80bb2174497
Author: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
AuthorDate: Mon Sep 2 00:28:04 2024 +0000
Updating dev docs (build nightly-tests-2024-09-01-0)
---
docs/dev/format/DissociatedIPC.html | 82 ++++++++++++++++++++++
docs/dev/format/Flight.html | 36 ----------
docs/dev/format/FlightSql.html | 61 +++++++++++++---
docs/dev/python/data.html | 46 ++++++------
docs/dev/python/dataset.html | 136 ++++++++++++++++++------------------
docs/dev/python/getstarted.html | 2 +-
docs/dev/python/memory.html | 8 +--
docs/dev/python/pandas.html | 6 +-
docs/dev/python/parquet.html | 12 ++--
docs/dev/r/pkgdown.yml | 2 +-
docs/dev/r/reference/to_duckdb.html | 10 +--
docs/dev/r/search.json | 2 +-
docs/dev/searchindex.js | 2 +-
13 files changed, 246 insertions(+), 159 deletions(-)
diff --git a/docs/dev/format/DissociatedIPC.html
b/docs/dev/format/DissociatedIPC.html
index 27ba4294d6d..b9baa57e38a 100644
--- a/docs/dev/format/DissociatedIPC.html
+++ b/docs/dev/format/DissociatedIPC.html
@@ -944,6 +944,50 @@ only have been tested using UCX and libfabric transports
so far, but that’s al
<li><p>The streams of metadata and body data are sent simultaneously across the
same connection</p></li>
</ol>
+<object data="../_images/mermaid-e962a4be5befa97b0166c4cae51c8201f88d2bb5.svg"
type="image/svg+xml">
+ <p class="warning">%% Licensed to the Apache Software Foundation
(ASF) under one
+%% or more contributor license agreements. See the NOTICE file
+%% distributed with this work for additional information
+%% regarding copyright ownership. The ASF licenses this file
+%% to you under the Apache License, Version 2.0 (the
+%% "License"); you may not use this file except in compliance
+%% with the License. You may obtain a copy of the License at
+%%
+%% http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied. See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+
+sequenceDiagram
+ participant C as Client
+ participant S as Server
+ activate C
+ C-->>+S: TaggedMessage(server.want_data, bytes=ID_of_desired_data)
+ S-->>C: Message(bytes([1]) + le_bytes(sequence_number) +
schema_metadata)
+ par
+ loop each chunk
+ S-->>C: Message(bytes([1]) + le_bytes(sequence_number) +
batch_metadata)
+ end
+ S-->>C: Message(bytes([0]) + le_bytes(sequence_number))
+ and
+ loop each chunk
+ alt
+ S-->>C: TaggedMessage((bytes[0] << 55) |
le_bytes(sequence_number),<br/>bytes=batch_data)
+ else
+ S-->>C: TaggedMessage((bytes[1] << 55) |
le_bytes(sequence_number),<br/>bytes=uint64_pairs)
+ end
+ end
+ end
+
+ loop
+ C-->>S: TaggedMessage(server.free_data, bytes=uint64_list)
+ end
+ deactivate S
+ deactivate C</p></object>
<section id="server-sequence">
<h3>Server Sequence<a class="headerlink" href="#server-sequence"
title="Permalink to this heading">#</a></h3>
<p>There can be either a single server handling both the IPC Metadata stream
and the
@@ -1054,6 +1098,44 @@ be freed.</p>
<p>A client for this protocol needs to concurrently handle both the data and
metadata streams of
messages which may either both come from the same server or different servers.
Below is a flowchart
showing how a client might handle the metadata and data streams:</p>
+<object data="../_images/mermaid-8ff51316a5bfe716c8346df112ea33beaa5228f4.svg"
type="image/svg+xml">
+ <p class="warning">%% Licensed to the Apache Software Foundation
(ASF) under one
+%% or more contributor license agreements. See the NOTICE file
+%% distributed with this work for additional information
+%% regarding copyright ownership. The ASF licenses this file
+%% to you under the Apache License, Version 2.0 (the
+%% "License"); you may not use this file except in compliance
+%% with the License. You may obtain a copy of the License at
+
+%% http://www.apache.org/licenses/LICENSE-2.0
+
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied. See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+
+graph LR
+client((Client))-->c1{{Send #60;want_data#gt; Msg}}
+subgraph meta [Meta Message]
+ direction LR
+ m1[/Msg Type #40;byte 0#41;<br/>Seq Num #40;bytes 1-5#41;/]-- type 1
-->m2[[Process IPC Header]]
+ m2-- IPC has body -->m3[Get Corresponding<br/>Tagged Msg]
+ m2-- Schema Msg -->m4[/Store Schema/]
+ m1-- type 0 -->e[Indicate End of Stream]
+end
+subgraph data [Data Stream]
+ direction LR
+ d1[Request Msg<br/>for Seq Num]-->d2{Most
Significant<br/>Byte}
+ d2-- 0 -->d3[Construct from<br/>Metadata and Body]
+ d2-- 1 -->d4[Get shared/remote<br/>buffers]
+ d4 -->d5[Construct from<br/>Metadata and buffers]
+ d3 & d5 -->e2[Output Batch]
+end
+
+client -- recv untagged msg --> meta
+client -- get tagged msg --> data</p></object>
<ol class="arabic simple">
<li><p>First the client sends a tagged message using the <code class="docutils
literal notranslate"><span class="pre"><want_data></span></code> value it
was provided in the
URI as the tag, and the opaque ID as the body.</p>
diff --git a/docs/dev/format/Flight.html b/docs/dev/format/Flight.html
index 5c22c6ad665..16dd4913dda 100644
--- a/docs/dev/format/Flight.html
+++ b/docs/dev/format/Flight.html
@@ -884,42 +884,6 @@ data. However, <code class="docutils literal
notranslate"><span class="pre">GetF
completes, so the client is blocked. In this situation, the client
can use <code class="docutils literal notranslate"><span
class="pre">PollFlightInfo</span></code> instead of <code class="docutils
literal notranslate"><span class="pre">GetFlightInfo</span></code>:</p>
<figure class="align-default" id="id2">
-<object data="../_images/mermaid-ebbcd076c75e58734773c06de07db3d1fcb27d86.svg"
type="image/svg+xml">
- <p class="warning">%% Licensed to the Apache Software Foundation
(ASF) under one
-%% or more contributor license agreements. See the NOTICE file
-%% distributed with this work for additional information
-%% regarding copyright ownership. The ASF licenses this file
-%% to you under the Apache License, Version 2.0 (the
-%% "License"); you may not use this file except in compliance
-%% with the License. You may obtain a copy of the License at
-%%
-%% http://www.apache.org/licenses/LICENSE-2.0
-%%
-%% Unless required by applicable law or agreed to in writing,
-%% software distributed under the License is distributed on an
-%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-%% KIND, either express or implied. See the License for the
-%% specific language governing permissions and limitations
-%% under the License.
-
-sequenceDiagram
-autonumber
-
-participant Client
-participant Metadata Server
-participant Data Server
-Client->>Metadata Server: PollFlightInfo(FlightDescriptor)
-Metadata Server->>Client: PollInfo{descriptor: FlightDescriptor', ...}
-Client->>Metadata Server: PollFlightInfo(FlightDescriptor')
-Metadata Server->>Client: PollInfo{descriptor: FlightDescriptor'', ...}
-Client->>Metadata Server: PollFlightInfo(FlightDescriptor'')
-Metadata Server->>Client: PollInfo{descriptor: null, info:
FlightInfo{endpoints: [FlightEndpoint{ticket: Ticket}, …]}
-Note over Client, Data Server: This may be parallelized
-Note over Client, Data Server: Some endpoints may be processed while polling
-loop for each endpoint in FlightInfo.endpoints
- Client->>Data Server: DoGet(Ticket)
- Data Server->>Client: stream of FlightData
-end</p></object>
<figcaption>
<p><span class="caption-text">Polling a long-running query by <code
class="docutils literal notranslate"><span
class="pre">PollFlightInfo</span></code>.</span><a class="headerlink"
href="#id2" title="Permalink to this image">#</a></p>
</figcaption>
diff --git a/docs/dev/format/FlightSql.html b/docs/dev/format/FlightSql.html
index 705016c6de7..9296e3baa49 100644
--- a/docs/dev/format/FlightSql.html
+++ b/docs/dev/format/FlightSql.html
@@ -936,7 +936,12 @@ Close and invalidate the current session context.</p>
<section id="sequence-diagrams">
<h2>Sequence Diagrams<a class="headerlink" href="#sequence-diagrams"
title="Permalink to this heading">#</a></h2>
<figure class="align-default" id="id1">
-<object data="../_images/mermaid-68e6410fa02f07a690f17dd881b5a8dfebb5b83a.svg"
type="image/svg+xml">
+<figcaption>
+<p><span class="caption-text">Listing available tables.</span><a
class="headerlink" href="#id1" title="Permalink to this image">#</a></p>
+</figcaption>
+</figure>
+<figure class="align-default" id="id2">
+<object data="../_images/mermaid-839ee0bcc66cb3a6d221d5223981c7f57515ea81.svg"
type="image/svg+xml">
<p class="warning">%% Licensed to the Apache Software Foundation
(ASF) under one
%% or more contributor license agreements. See the NOTICE file
%% distributed with this work for additional information
@@ -959,20 +964,56 @@ autonumber
participant Client
participant Server
-Client->>Server: GetFlightInfo(CommandGetTables)
-Server->>Client: FlightInfo{…Ticket…}
-Client->>Server: DoGet(Ticket)
-Server->>Client: stream of FlightData</p></object>
-<figcaption>
-<p><span class="caption-text">Listing available tables.</span><a
class="headerlink" href="#id1" title="Permalink to this image">#</a></p>
-</figcaption>
-</figure>
-<figure class="align-default" id="id2">
+Client->>Server: GetFlightInfo(CommandStatementQuery)
+Server->>Client: FlightInfo{endpoints: [FlightEndpoint{…}, …]}
+loop for each endpoint in FlightInfo.endpoints
+ Client->>Server: DoGet(endpoint.ticket)
+ Server->>Client: stream of FlightData
+end</p></object>
<figcaption>
<p><span class="caption-text">Executing an ad-hoc query.</span><a
class="headerlink" href="#id2" title="Permalink to this image">#</a></p>
</figcaption>
</figure>
<figure class="align-default" id="id3">
+<object data="../_images/mermaid-7f33ca04317a5eec3bc70d24adf5d28a69a174d3.svg"
type="image/svg+xml">
+ <p class="warning">%% Licensed to the Apache Software Foundation
(ASF) under one
+%% or more contributor license agreements. See the NOTICE file
+%% distributed with this work for additional information
+%% regarding copyright ownership. The ASF licenses this file
+%% to you under the Apache License, Version 2.0 (the
+%% "License"); you may not use this file except in compliance
+%% with the License. You may obtain a copy of the License at
+%%
+%% http://www.apache.org/licenses/LICENSE-2.0
+%%
+%% Unless required by applicable law or agreed to in writing,
+%% software distributed under the License is distributed on an
+%% "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+%% KIND, either express or implied. See the License for the
+%% specific language governing permissions and limitations
+%% under the License.
+
+sequenceDiagram
+autonumber
+
+participant Client
+participant Server
+Client->>Server: DoAction(ActionCreatePreparedStatementRequest)
+Server->>Client: ActionCreatePreparedStatementResult{handle}
+loop for each invocation of the prepared statement
+Client->>Server: DoPut(CommandPreparedStatementQuery)
+Client->>Server: stream of FlightData
+Server-->>Client: DoPutPreparedStatementResult{handle}
+Note over Client,Server: optional response with updated handle
+Client->>Server: GetFlightInfo(CommandPreparedStatementQuery)
+Server->>Client: FlightInfo{endpoints: [FlightEndpoint{…}, …]}
+ loop for each endpoint in FlightInfo.endpoints
+ Client->>Server: DoGet(endpoint.ticket)
+ Server->>Client: stream of FlightData
+ end
+end
+Client->>Server: DoAction(ActionClosePreparedStatementRequest)
+Server->>Client: ActionClosePreparedStatementRequest{}</p></object>
<figcaption>
<p><span class="caption-text">Creating a prepared statement, then executing
it.</span><a class="headerlink" href="#id3" title="Permalink to this
image">#</a></p>
</figcaption>
diff --git a/docs/dev/python/data.html b/docs/dev/python/data.html
index 2ed70300b1b..155431cac03 100644
--- a/docs/dev/python/data.html
+++ b/docs/dev/python/data.html
@@ -1695,7 +1695,7 @@ for you:</p>
<span class="gp">In [26]: </span><span class="n">arr</span>
<span class="gh">Out[26]: </span>
-<span class="go"><pyarrow.lib.Int64Array object at 0x7ff0799bb7c0></span>
+<span class="go"><pyarrow.lib.Int64Array object at 0x7ff7b23df8e0></span>
<span class="go">[</span>
<span class="go"> 1,</span>
<span class="go"> 2,</span>
@@ -1707,7 +1707,7 @@ for you:</p>
<p>But you may also pass a specific data type to override type inference:</p>
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [27]: </span><span
class="n">pa</span><span class="o">.</span><span class="n">array</span><span
class="p">([</span><span class="mi">1</span><span class="p">,</span> <span
class="mi">2</span><span class="p">],</span> <span class="nb">type</span><span
class="o">=</span><span class="n">pa</span><span class="o">.</span><span
class="n">uint16</span><span class="p">())</span>
<span class="gh">Out[27]: </span>
-<span class="go"><pyarrow.lib.UInt16Array object at
0x7ff0799bbee0></span>
+<span class="go"><pyarrow.lib.UInt16Array object at
0x7ff7b23dfe80></span>
<span class="go">[</span>
<span class="go"> 1,</span>
<span class="go"> 2</span>
@@ -1742,7 +1742,7 @@ nulls:</p>
<p>Arrays can be sliced without copying:</p>
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [33]: </span><span
class="n">arr</span><span class="p">[</span><span class="mi">1</span><span
class="p">:</span><span class="mi">3</span><span class="p">]</span>
<span class="gh">Out[33]: </span>
-<span class="go"><pyarrow.lib.Int64Array object at 0x7ff0799f8e80></span>
+<span class="go"><pyarrow.lib.Int64Array object at 0x7ff7b221cd60></span>
<span class="go">[</span>
<span class="go"> 2,</span>
<span class="go"> null</span>
@@ -1795,7 +1795,7 @@ This allows for ListView arrays to specify out-of-order
offsets:</p>
<span class="gp">In [42]: </span><span class="n">arr</span>
<span class="gh">Out[42]: </span>
-<span class="go"><pyarrow.lib.ListViewArray object at
0x7ff0799f88e0></span>
+<span class="go"><pyarrow.lib.ListViewArray object at
0x7ff7b221d8a0></span>
<span class="go">[</span>
<span class="go"> [</span>
<span class="go"> 5,</span>
@@ -1820,7 +1820,7 @@ This allows for ListView arrays to specify out-of-order
offsets:</p>
dictionaries:</p>
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [43]: </span><span
class="n">pa</span><span class="o">.</span><span class="n">array</span><span
class="p">([{</span><span class="s1">'x'</span><span class="p">:</span>
<span class="mi">1</span><span class="p">,</span> <span
class="s1">'y'</span><span class="p">:</span> <span
class="kc">True</span><span class="p">},</span> <span class="p">{</span><span
class="s1">'z& [...]
<span class="gh">Out[43]: </span>
-<span class="go"><pyarrow.lib.StructArray object at
0x7ff0799ba7a0></span>
+<span class="go"><pyarrow.lib.StructArray object at
0x7ff7b23deb00></span>
<span class="go">-- is_valid: all not null</span>
<span class="go">-- child 0 type: int64</span>
<span class="go"> [</span>
@@ -1847,7 +1847,7 @@ you must explicitly pass the type:</p>
<span class="gp">In [45]: </span><span class="n">pa</span><span
class="o">.</span><span class="n">array</span><span class="p">([{</span><span
class="s1">'x'</span><span class="p">:</span> <span
class="mi">1</span><span class="p">,</span> <span
class="s1">'y'</span><span class="p">:</span> <span
class="kc">True</span><span class="p">},</span> <span class="p">{</span><span
class="s1">'x'</span><span class="p">:</span> <span
class="mi">2</span><span class="p">,</span [...]
<span class="gh">Out[45]: </span>
-<span class="go"><pyarrow.lib.StructArray object at
0x7ff0799f8f40></span>
+<span class="go"><pyarrow.lib.StructArray object at
0x7ff7b221c9a0></span>
<span class="go">-- is_valid: all not null</span>
<span class="go">-- child 0 type: int8</span>
<span class="go"> [</span>
@@ -1862,7 +1862,7 @@ you must explicitly pass the type:</p>
<span class="gp">In [46]: </span><span class="n">pa</span><span
class="o">.</span><span class="n">array</span><span class="p">([(</span><span
class="mi">3</span><span class="p">,</span> <span class="kc">True</span><span
class="p">),</span> <span class="p">(</span><span class="mi">4</span><span
class="p">,</span> <span class="kc">False</span><span class="p">)],</span>
<span class="nb">type</span><span class="o">=</span><span
class="n">ty</span><span class="p">)</span>
<span class="gh">Out[46]: </span>
-<span class="go"><pyarrow.lib.StructArray object at
0x7ff0799f8940></span>
+<span class="go"><pyarrow.lib.StructArray object at
0x7ff7b221c940></span>
<span class="go">-- is_valid: all not null</span>
<span class="go">-- child 0 type: int8</span>
<span class="go"> [</span>
@@ -1881,7 +1881,7 @@ level and at the individual field level. If initializing
from a sequence
of Python dicts, a missing dict key is handled as a null value:</p>
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [47]: </span><span
class="n">pa</span><span class="o">.</span><span class="n">array</span><span
class="p">([{</span><span class="s1">'x'</span><span class="p">:</span>
<span class="mi">1</span><span class="p">},</span> <span
class="kc">None</span><span class="p">,</span> <span class="p">{</span><span
class="s1">'y'</span><span class="p">:</span> <span class="kc">None</s
[...]
<span class="gh">Out[47]: </span>
-<span class="go"><pyarrow.lib.StructArray object at
0x7ff0799f8d60></span>
+<span class="go"><pyarrow.lib.StructArray object at
0x7ff7b221c5e0></span>
<span class="go">-- is_valid:</span>
<span class="go"> [</span>
<span class="go"> true,</span>
@@ -1916,7 +1916,7 @@ individual arrays, and no copy is involved:</p>
<span class="gp">In [52]: </span><span class="n">arr</span>
<span class="gh">Out[52]: </span>
-<span class="go"><pyarrow.lib.StructArray object at
0x7ff0799bb700></span>
+<span class="go"><pyarrow.lib.StructArray object at
0x7ff7b221e4a0></span>
<span class="go">-- is_valid: all not null</span>
<span class="go">-- child 0 type: int16</span>
<span class="go"> [</span>
@@ -1943,7 +1943,7 @@ the type is explicitly passed into <a class="reference
internal" href="generated
<span class="gp">In [55]: </span><span class="n">pa</span><span
class="o">.</span><span class="n">array</span><span class="p">(</span><span
class="n">data</span><span class="p">,</span> <span class="nb">type</span><span
class="o">=</span><span class="n">ty</span><span class="p">)</span>
<span class="gh">Out[55]: </span>
-<span class="go"><pyarrow.lib.MapArray object at 0x7ff0799fa980></span>
+<span class="go"><pyarrow.lib.MapArray object at 0x7ff7b23b9180></span>
<span class="go">[</span>
<span class="go"> keys:</span>
<span class="go"> [</span>
@@ -1977,7 +1977,7 @@ their row, use the <a class="reference internal"
href="generated/pyarrow.ListArr
<span class="gp">In [57]: </span><span class="n">arr</span><span
class="o">.</span><span class="n">keys</span>
<span class="gh">Out[57]: </span>
-<span class="go"><pyarrow.lib.StringArray object at
0x7ff0799fabc0></span>
+<span class="go"><pyarrow.lib.StringArray object at
0x7ff7b221ec20></span>
<span class="go">[</span>
<span class="go"> "x",</span>
<span class="go"> "y",</span>
@@ -1986,7 +1986,7 @@ their row, use the <a class="reference internal"
href="generated/pyarrow.ListArr
<span class="gp">In [58]: </span><span class="n">arr</span><span
class="o">.</span><span class="n">items</span>
<span class="gh">Out[58]: </span>
-<span class="go"><pyarrow.lib.Int64Array object at 0x7ff0799fad40></span>
+<span class="go"><pyarrow.lib.Int64Array object at 0x7ff7b221ece0></span>
<span class="go">[</span>
<span class="go"> 4,</span>
<span class="go"> 5,</span>
@@ -1995,7 +1995,7 @@ their row, use the <a class="reference internal"
href="generated/pyarrow.ListArr
<span class="gp">In [59]: </span><span class="n">pa</span><span
class="o">.</span><span class="n">ListArray</span><span class="o">.</span><span
class="n">from_arrays</span><span class="p">(</span><span
class="n">arr</span><span class="o">.</span><span class="n">offsets</span><span
class="p">,</span> <span class="n">arr</span><span class="o">.</span><span
class="n">keys</span><span class="p">)</span>
<span class="gh">Out[59]: </span>
-<span class="go"><pyarrow.lib.ListArray object at 0x7ff0799fb0a0></span>
+<span class="go"><pyarrow.lib.ListArray object at 0x7ff7b221efe0></span>
<span class="go">[</span>
<span class="go"> [</span>
<span class="go"> "x",</span>
@@ -2008,7 +2008,7 @@ their row, use the <a class="reference internal"
href="generated/pyarrow.ListArr
<span class="gp">In [60]: </span><span class="n">pa</span><span
class="o">.</span><span class="n">ListArray</span><span class="o">.</span><span
class="n">from_arrays</span><span class="p">(</span><span
class="n">arr</span><span class="o">.</span><span class="n">offsets</span><span
class="p">,</span> <span class="n">arr</span><span class="o">.</span><span
class="n">items</span><span class="p">)</span>
<span class="gh">Out[60]: </span>
-<span class="go"><pyarrow.lib.ListArray object at 0x7ff0799fafe0></span>
+<span class="go"><pyarrow.lib.ListArray object at 0x7ff7b221ef80></span>
<span class="go">[</span>
<span class="go"> [</span>
<span class="go"> 4,</span>
@@ -2043,7 +2043,7 @@ selected:</p>
<span class="gp">In [66]: </span><span class="n">union_arr</span>
<span class="gh">Out[66]: </span>
-<span class="go"><pyarrow.lib.UnionArray object at 0x7ff0799fb460></span>
+<span class="go"><pyarrow.lib.UnionArray object at 0x7ff7b221f2e0></span>
<span class="go">-- is_valid: all not null</span>
<span class="go">-- type_ids: [</span>
<span class="go"> 0,</span>
@@ -2082,7 +2082,7 @@ each offset in the selected child array it can be
found:</p>
<span class="gp">In [73]: </span><span class="n">union_arr</span>
<span class="gh">Out[73]: </span>
-<span class="go"><pyarrow.lib.UnionArray object at 0x7ff07982c040></span>
+<span class="go"><pyarrow.lib.UnionArray object at 0x7ff7b221fe80></span>
<span class="go">-- is_valid: all not null</span>
<span class="go">-- type_ids: [</span>
<span class="go"> 0,</span>
@@ -2131,7 +2131,7 @@ consider an example:</p>
<span class="gp">In [77]: </span><span class="n">dict_array</span>
<span class="gh">Out[77]: </span>
-<span class="go"><pyarrow.lib.DictionaryArray object at
0x7ff0799bfe60></span>
+<span class="go"><pyarrow.lib.DictionaryArray object at
0x7ff7b23e3e60></span>
<span class="go">-- dictionary:</span>
<span class="go"> [</span>
@@ -2158,7 +2158,7 @@ consider an example:</p>
<span class="gp">In [79]: </span><span class="n">dict_array</span><span
class="o">.</span><span class="n">indices</span>
<span class="gh">Out[79]: </span>
-<span class="go"><pyarrow.lib.Int64Array object at 0x7ff0799fa5c0></span>
+<span class="go"><pyarrow.lib.Int64Array object at 0x7ff7b2250820></span>
<span class="go">[</span>
<span class="go"> 0,</span>
<span class="go"> 1,</span>
@@ -2172,7 +2172,7 @@ consider an example:</p>
<span class="gp">In [80]: </span><span class="n">dict_array</span><span
class="o">.</span><span class="n">dictionary</span>
<span class="gh">Out[80]: </span>
-<span class="go"><pyarrow.lib.StringArray object at
0x7ff0799b9d80></span>
+<span class="go"><pyarrow.lib.StringArray object at
0x7ff7b2250b20></span>
<span class="go">[</span>
<span class="go"> "foo",</span>
<span class="go"> "bar",</span>
@@ -2228,7 +2228,7 @@ instances. Let’s consider a collection of arrays:</p>
<span class="gp">In [87]: </span><span class="n">batch</span><span
class="p">[</span><span class="mi">1</span><span class="p">]</span>
<span class="gh">Out[87]: </span>
-<span class="go"><pyarrow.lib.StringArray object at
0x7ff07982d8a0></span>
+<span class="go"><pyarrow.lib.StringArray object at
0x7ff7b221c7c0></span>
<span class="go">[</span>
<span class="go"> "foo",</span>
<span class="go"> "bar",</span>
@@ -2242,7 +2242,7 @@ instances. Let’s consider a collection of arrays:</p>
<span class="gp">In [89]: </span><span class="n">batch2</span><span
class="p">[</span><span class="mi">1</span><span class="p">]</span>
<span class="gh">Out[89]: </span>
-<span class="go"><pyarrow.lib.StringArray object at
0x7ff07982dcc0></span>
+<span class="go"><pyarrow.lib.StringArray object at
0x7ff7b2251ea0></span>
<span class="go">[</span>
<span class="go"> "bar",</span>
<span class="go"> "baz",</span>
@@ -2286,7 +2286,7 @@ container for one or more arrays of the same type.</p>
<span class="gp">In [95]: </span><span class="n">c</span>
<span class="gh">Out[95]: </span>
-<span class="go"><pyarrow.lib.ChunkedArray object at
0x7ff079858cc0></span>
+<span class="go"><pyarrow.lib.ChunkedArray object at
0x7ff7b227c900></span>
<span class="go">[</span>
<span class="go"> [</span>
<span class="go"> 1,</span>
@@ -2320,7 +2320,7 @@ container for one or more arrays of the same type.</p>
<span class="gp">In [97]: </span><span class="n">c</span><span
class="o">.</span><span class="n">chunk</span><span class="p">(</span><span
class="mi">0</span><span class="p">)</span>
<span class="gh">Out[97]: </span>
-<span class="go"><pyarrow.lib.Int64Array object at 0x7ff07982c940></span>
+<span class="go"><pyarrow.lib.Int64Array object at 0x7ff7b221c040></span>
<span class="go">[</span>
<span class="go"> 1,</span>
<span class="go"> 2,</span>
diff --git a/docs/dev/python/dataset.html b/docs/dev/python/dataset.html
index 2d230613bb1..13b7b2872dd 100644
--- a/docs/dev/python/dataset.html
+++ b/docs/dev/python/dataset.html
@@ -1596,7 +1596,7 @@ can pass it the path to the directory containing the data
files:</p>
<span class="gp">In [12]: </span><span class="n">dataset</span> <span
class="o">=</span> <span class="n">ds</span><span class="o">.</span><span
class="n">dataset</span><span class="p">(</span><span class="n">base</span>
<span class="o">/</span> <span
class="s2">"parquet_dataset"</span><span class="p">,</span> <span
class="nb">format</span><span class="o">=</span><span
class="s2">"parquet"</span><span class="p">)</span>
<span class="gp">In [13]: </span><span class="n">dataset</span>
-<span class="gh">Out[13]: </span><span
class="go"><pyarrow._dataset.FileSystemDataset at 0x7ff0798bca60></span>
+<span class="gh">Out[13]: </span><span
class="go"><pyarrow._dataset.FileSystemDataset at 0x7ff7b22f4760></span>
</pre></div>
</div>
<p>In addition to searching a base directory, <a class="reference internal"
href="generated/pyarrow.dataset.dataset.html#pyarrow.dataset.dataset"
title="pyarrow.dataset.dataset"><code class="xref py py-func docutils literal
notranslate"><span class="pre">dataset()</span></code></a> accepts a path to a
@@ -1605,8 +1605,8 @@ single file or a list of file paths.</p>
needed, it only crawls the directory to find all the files:</p>
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [14]: </span><span
class="n">dataset</span><span class="o">.</span><span class="n">files</span>
<span class="gh">Out[14]: </span>
-<span
class="go">['/tmp/pyarrow-q6dawtle/parquet_dataset/data1.parquet',</span>
-<span class="go">
'/tmp/pyarrow-q6dawtle/parquet_dataset/data2.parquet']</span>
+<span
class="go">['/tmp/pyarrow-wwh84sxc/parquet_dataset/data1.parquet',</span>
+<span class="go">
'/tmp/pyarrow-wwh84sxc/parquet_dataset/data2.parquet']</span>
</pre></div>
</div>
<p>… and infers the dataset’s schema (by default from the first file):</p>
@@ -1627,23 +1627,23 @@ this can require a lot of memory, see below on
filtering / iterative loading):</
<span class="go">c: int64</span>
<span class="gt">----</span>
<span class="ne">a</span>: [[0,1,2,3,4],[5,6,7,8,9]]
-<span class="ne">b</span>:
[[0.4676570110528729,1.484525724672298,-0.7624637051544647,-0.6407222647756983,-0.30494949892481127],[-1.4502878979896479,-0.5318560404601885,1.2233579208949825,0.7450350724316274,-0.4076723087826772]]
+<span class="ne">b</span>:
[[-1.8193806988754855,0.5787015121070801,0.37218131323654985,-0.18299743314227973,-0.2707760241674394],[-0.3121990034537313,-2.692710808710322,1.202399283483902,-1.2484734656167271,-1.4805168469978525]]
<span class="ne">c</span>: [[1,2,1,2,1],[2,1,2,1,2]]
<span class="c1"># converting to pandas to see the contents of the scanned
table</span>
<span class="gp">In [17]: </span><span class="n">dataset</span><span
class="o">.</span><span class="n">to_table</span><span class="p">()</span><span
class="o">.</span><span class="n">to_pandas</span><span class="p">()</span>
<span class="gh">Out[17]: </span>
<span class="go"> a b c</span>
-<span class="go">0 0 0.467657 1</span>
-<span class="go">1 1 1.484526 2</span>
-<span class="go">2 2 -0.762464 1</span>
-<span class="go">3 3 -0.640722 2</span>
-<span class="go">4 4 -0.304949 1</span>
-<span class="go">5 5 -1.450288 2</span>
-<span class="go">6 6 -0.531856 1</span>
-<span class="go">7 7 1.223358 2</span>
-<span class="go">8 8 0.745035 1</span>
-<span class="go">9 9 -0.407672 2</span>
+<span class="go">0 0 -1.819381 1</span>
+<span class="go">1 1 0.578702 2</span>
+<span class="go">2 2 0.372181 1</span>
+<span class="go">3 3 -0.182997 2</span>
+<span class="go">4 4 -0.270776 1</span>
+<span class="go">5 5 -0.312199 2</span>
+<span class="go">6 6 -2.692711 1</span>
+<span class="go">7 7 1.202399 2</span>
+<span class="go">8 8 -1.248473 1</span>
+<span class="go">9 9 -1.480517 2</span>
</pre></div>
</div>
</section>
@@ -1666,11 +1666,11 @@ supported; more formats are planned in the future.</p>
<span class="gp">In [21]: </span><span class="n">dataset</span><span
class="o">.</span><span class="n">to_table</span><span class="p">()</span><span
class="o">.</span><span class="n">to_pandas</span><span
class="p">()</span><span class="o">.</span><span class="n">head</span><span
class="p">()</span>
<span class="gh">Out[21]: </span>
<span class="go"> a b c</span>
-<span class="go">0 0 0.467657 1</span>
-<span class="go">1 1 1.484526 2</span>
-<span class="go">2 2 -0.762464 1</span>
-<span class="go">3 3 -0.640722 2</span>
-<span class="go">4 4 -0.304949 1</span>
+<span class="go">0 0 -1.819381 1</span>
+<span class="go">1 1 0.578702 2</span>
+<span class="go">2 2 0.372181 1</span>
+<span class="go">3 3 -0.182997 2</span>
+<span class="go">4 4 -0.270776 1</span>
</pre></div>
</div>
</section>
@@ -1702,16 +1702,16 @@ supported; more formats are planned in the future.</p>
<span class="gp">In [23]: </span><span class="n">dataset</span><span
class="o">.</span><span class="n">to_table</span><span class="p">(</span><span
class="n">columns</span><span class="o">=</span><span class="p">[</span><span
class="s1">'a'</span><span class="p">,</span> <span
class="s1">'b'</span><span class="p">])</span><span
class="o">.</span><span class="n">to_pandas</span><span class="p">()</span>
<span class="gh">Out[23]: </span>
<span class="go"> a b</span>
-<span class="go">0 0 0.467657</span>
-<span class="go">1 1 1.484526</span>
-<span class="go">2 2 -0.762464</span>
-<span class="go">3 3 -0.640722</span>
-<span class="go">4 4 -0.304949</span>
-<span class="go">5 5 -1.450288</span>
-<span class="go">6 6 -0.531856</span>
-<span class="go">7 7 1.223358</span>
-<span class="go">8 8 0.745035</span>
-<span class="go">9 9 -0.407672</span>
+<span class="go">0 0 -1.819381</span>
+<span class="go">1 1 0.578702</span>
+<span class="go">2 2 0.372181</span>
+<span class="go">3 3 -0.182997</span>
+<span class="go">4 4 -0.270776</span>
+<span class="go">5 5 -0.312199</span>
+<span class="go">6 6 -2.692711</span>
+<span class="go">7 7 1.202399</span>
+<span class="go">8 8 -1.248473</span>
+<span class="go">9 9 -1.480517</span>
</pre></div>
</div>
<p>With the <code class="docutils literal notranslate"><span
class="pre">filter</span></code> keyword, rows which do not match the filter
predicate will
@@ -1720,18 +1720,18 @@ not be included in the returned table. The keyword
expects a boolean
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [24]: </span><span
class="n">dataset</span><span class="o">.</span><span
class="n">to_table</span><span class="p">(</span><span
class="nb">filter</span><span class="o">=</span><span class="n">ds</span><span
class="o">.</span><span class="n">field</span><span class="p">(</span><span
class="s1">'a'</span><span class="p">)</span> <span
class="o">>=</span> <span class="mi">7</sp [...]
<span class="gh">Out[24]: </span>
<span class="go"> a b c</span>
-<span class="go">0 7 1.223358 2</span>
-<span class="go">1 8 0.745035 1</span>
-<span class="go">2 9 -0.407672 2</span>
+<span class="go">0 7 1.202399 2</span>
+<span class="go">1 8 -1.248473 1</span>
+<span class="go">2 9 -1.480517 2</span>
<span class="gp">In [25]: </span><span class="n">dataset</span><span
class="o">.</span><span class="n">to_table</span><span class="p">(</span><span
class="nb">filter</span><span class="o">=</span><span class="n">ds</span><span
class="o">.</span><span class="n">field</span><span class="p">(</span><span
class="s1">'c'</span><span class="p">)</span> <span class="o">==</span>
<span class="mi">2</span><span class="p">)</span><span class="o">.</span><span
class="n">to_pandas</span><spa [...]
<span class="gh">Out[25]: </span>
<span class="go"> a b c</span>
-<span class="go">0 1 1.484526 2</span>
-<span class="go">1 3 -0.640722 2</span>
-<span class="go">2 5 -1.450288 2</span>
-<span class="go">3 7 1.223358 2</span>
-<span class="go">4 9 -0.407672 2</span>
+<span class="go">0 1 0.578702 2</span>
+<span class="go">1 3 -0.182997 2</span>
+<span class="go">2 5 -0.312199 2</span>
+<span class="go">3 7 1.202399 2</span>
+<span class="go">4 9 -1.480517 2</span>
</pre></div>
</div>
<p>The easiest way to construct those <a class="reference internal"
href="generated/pyarrow.dataset.Expression.html#pyarrow.dataset.Expression"
title="pyarrow.dataset.Expression"><code class="xref py py-class docutils
literal notranslate"><span class="pre">Expression</span></code></a> objects is
by using the
@@ -1776,11 +1776,11 @@ values:</p>
<span class="gp">In [30]: </span><span class="n">dataset</span><span
class="o">.</span><span class="n">to_table</span><span class="p">(</span><span
class="n">columns</span><span class="o">=</span><span
class="n">projection</span><span class="p">)</span><span
class="o">.</span><span class="n">to_pandas</span><span
class="p">()</span><span class="o">.</span><span class="n">head</span><span
class="p">()</span>
<span class="gh">Out[30]: </span>
<span class="go"> a_renamed b_as_float32 c_1</span>
-<span class="go">0 0 0.467657 True</span>
-<span class="go">1 1 1.484526 False</span>
-<span class="go">2 2 -0.762464 True</span>
-<span class="go">3 3 -0.640722 False</span>
-<span class="go">4 4 -0.304949 True</span>
+<span class="go">0 0 -1.819381 True</span>
+<span class="go">1 1 0.578701 False</span>
+<span class="go">2 2 0.372181 True</span>
+<span class="go">3 3 -0.182997 False</span>
+<span class="go">4 4 -0.270776 True</span>
</pre></div>
</div>
<p>The dictionary also determines the column selection (only the keys in the
@@ -1794,11 +1794,11 @@ build up the dictionary from the dataset schema:</p>
<span class="gp">In [33]: </span><span class="n">dataset</span><span
class="o">.</span><span class="n">to_table</span><span class="p">(</span><span
class="n">columns</span><span class="o">=</span><span
class="n">projection</span><span class="p">)</span><span
class="o">.</span><span class="n">to_pandas</span><span
class="p">()</span><span class="o">.</span><span class="n">head</span><span
class="p">()</span>
<span class="gh">Out[33]: </span>
<span class="go"> a b c b_large</span>
-<span class="go">0 0 0.467657 1 False</span>
-<span class="go">1 1 1.484526 2 True</span>
-<span class="go">2 2 -0.762464 1 False</span>
-<span class="go">3 3 -0.640722 2 False</span>
-<span class="go">4 4 -0.304949 1 False</span>
+<span class="go">0 0 -1.819381 1 False</span>
+<span class="go">1 1 0.578702 2 False</span>
+<span class="go">2 2 0.372181 1 False</span>
+<span class="go">3 3 -0.182997 2 False</span>
+<span class="go">4 4 -0.270776 1 False</span>
</pre></div>
</div>
</section>
@@ -1851,8 +1851,8 @@ should use a hive-like partitioning scheme with the <code
class="docutils litera
<span class="gp">In [37]: </span><span class="n">dataset</span><span
class="o">.</span><span class="n">files</span>
<span class="gh">Out[37]: </span>
-<span
class="go">['parquet_dataset_partitioned/part=a/b076590dba8549b1baf6e98ddc2f5e25-0.parquet',</span>
-<span class="go">
'parquet_dataset_partitioned/part=b/b076590dba8549b1baf6e98ddc2f5e25-0.parquet']</span>
+<span
class="go">['parquet_dataset_partitioned/part=a/a52c1e3493634ed4930abeef69c876fa-0.parquet',</span>
+<span class="go">
'parquet_dataset_partitioned/part=b/a52c1e3493634ed4930abeef69c876fa-0.parquet']</span>
</pre></div>
</div>
<p>Although the partition fields are not included in the actual Parquet files,
@@ -1860,9 +1860,9 @@ they will be added back to the resulting table when
scanning this dataset:</p>
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [38]: </span><span
class="n">dataset</span><span class="o">.</span><span
class="n">to_table</span><span class="p">()</span><span class="o">.</span><span
class="n">to_pandas</span><span class="p">()</span><span
class="o">.</span><span class="n">head</span><span class="p">(</span><span
class="mi">3</span><span class="p">)</span>
<span class="gh">Out[38]: </span>
<span class="go"> a b c part</span>
-<span class="go">0 0 -0.079283 1 a</span>
-<span class="go">1 1 -0.321465 2 a</span>
-<span class="go">2 2 -0.074143 1 a</span>
+<span class="go">0 0 1.664176 1 a</span>
+<span class="go">1 1 1.544288 2 a</span>
+<span class="go">2 2 0.935327 1 a</span>
</pre></div>
</div>
<p>We can now filter on the partition keys, which avoids loading files
@@ -1870,11 +1870,11 @@ altogether if they do not match the filter:</p>
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [39]: </span><span
class="n">dataset</span><span class="o">.</span><span
class="n">to_table</span><span class="p">(</span><span
class="nb">filter</span><span class="o">=</span><span class="n">ds</span><span
class="o">.</span><span class="n">field</span><span class="p">(</span><span
class="s2">"part"</span><span class="p">)</span> <span
class="o">==</span> <span class="s2">&qu [...]
<span class="gh">Out[39]: </span>
<span class="go"> a b c part</span>
-<span class="go">0 5 2.285640 2 b</span>
-<span class="go">1 6 0.063203 1 b</span>
-<span class="go">2 7 0.419773 2 b</span>
-<span class="go">3 8 0.754971 1 b</span>
-<span class="go">4 9 -0.664211 2 b</span>
+<span class="go">0 5 0.057663 2 b</span>
+<span class="go">1 6 -0.944920 1 b</span>
+<span class="go">2 7 -0.478445 2 b</span>
+<span class="go">3 8 -0.099119 1 b</span>
+<span class="go">4 9 -0.812110 2 b</span>
</pre></div>
</div>
<section id="different-partitioning-schemes">
@@ -2006,19 +2006,19 @@ is materialized as columns when reading the data and
can be used for filtering:<
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [47]: </span><span
class="n">dataset</span><span class="o">.</span><span
class="n">to_table</span><span class="p">()</span><span class="o">.</span><span
class="n">to_pandas</span><span class="p">()</span>
<span class="gh">Out[47]: </span>
<span class="go"> year col1 col2</span>
-<span class="go">0 2018 0 -0.235137</span>
-<span class="go">1 2018 1 -0.641264</span>
-<span class="go">2 2018 2 0.151977</span>
-<span class="go">3 2019 0 -0.235137</span>
-<span class="go">4 2019 1 -0.641264</span>
-<span class="go">5 2019 2 0.151977</span>
+<span class="go">0 2018 0 1.381583</span>
+<span class="go">1 2018 1 0.243853</span>
+<span class="go">2 2018 2 -0.485914</span>
+<span class="go">3 2019 0 1.381583</span>
+<span class="go">4 2019 1 0.243853</span>
+<span class="go">5 2019 2 -0.485914</span>
<span class="gp">In [48]: </span><span class="n">dataset</span><span
class="o">.</span><span class="n">to_table</span><span class="p">(</span><span
class="nb">filter</span><span class="o">=</span><span class="n">ds</span><span
class="o">.</span><span class="n">field</span><span class="p">(</span><span
class="s1">'year'</span><span class="p">)</span> <span
class="o">==</span> <span class="mi">2019</span><span class="p">)</span><span
class="o">.</span><span class="n">to_pandas</spa [...]
<span class="gh">Out[48]: </span>
<span class="go"> year col1 col2</span>
-<span class="go">0 2019 0 -0.235137</span>
-<span class="go">1 2019 1 -0.641264</span>
-<span class="go">2 2019 2 0.151977</span>
+<span class="go">0 2019 0 1.381583</span>
+<span class="go">1 2019 1 0.243853</span>
+<span class="go">2 2019 2 -0.485914</span>
</pre></div>
</div>
<p>Another benefit of manually listing the files is that the order of the files
@@ -2270,7 +2270,7 @@ to supply a visitor that will be called as each file is
created:</p>
<span class="gp"> ....: </span>
<span class="go">path=dataset_visited/c=1/part-0.parquet</span>
<span class="go">size=802 bytes</span>
-<span class="go">metadata=<pyarrow._parquet.FileMetaData object at
0x7ff077d38c70></span>
+<span class="go">metadata=<pyarrow._parquet.FileMetaData object at
0x7ff7b2248040></span>
<span class="go"> created_by: parquet-cpp-arrow version 18.0.0-SNAPSHOT</span>
<span class="go"> num_columns: 2</span>
<span class="go"> num_rows: 5</span>
@@ -2279,7 +2279,7 @@ to supply a visitor that will be called as each file is
created:</p>
<span class="go"> serialized_size: 0</span>
<span class="go">path=dataset_visited/c=2/part-0.parquet</span>
<span class="go">size=804 bytes</span>
-<span class="go">metadata=<pyarrow._parquet.FileMetaData object at
0x7ff077d38c70></span>
+<span class="go">metadata=<pyarrow._parquet.FileMetaData object at
0x7ff7b2248040></span>
<span class="go"> created_by: parquet-cpp-arrow version 18.0.0-SNAPSHOT</span>
<span class="go"> num_columns: 2</span>
<span class="go"> num_rows: 5</span>
diff --git a/docs/dev/python/getstarted.html b/docs/dev/python/getstarted.html
index 20d19ccb351..1cbec0c3ab4 100644
--- a/docs/dev/python/getstarted.html
+++ b/docs/dev/python/getstarted.html
@@ -1621,7 +1621,7 @@ it’s possible to apply transformations to the data</p>
<span class="gp">In [12]: </span><span class="n">pc</span><span
class="o">.</span><span class="n">value_counts</span><span
class="p">(</span><span class="n">birthdays_table</span><span
class="p">[</span><span class="s2">"years"</span><span
class="p">])</span>
<span class="gh">Out[12]: </span>
-<span class="go"><pyarrow.lib.StructArray object at
0x7ff03726b2e0></span>
+<span class="go"><pyarrow.lib.StructArray object at
0x7ff76fa031c0></span>
<span class="go">-- is_valid: all not null</span>
<span class="go">-- child 0 type: int16</span>
<span class="go"> [</span>
diff --git a/docs/dev/python/memory.html b/docs/dev/python/memory.html
index ed914498b90..d23c9bddaa2 100644
--- a/docs/dev/python/memory.html
+++ b/docs/dev/python/memory.html
@@ -1570,7 +1570,7 @@ a bytes object:</p>
<span class="gp">In [3]: </span><span class="n">buf</span> <span
class="o">=</span> <span class="n">pa</span><span class="o">.</span><span
class="n">py_buffer</span><span class="p">(</span><span
class="n">data</span><span class="p">)</span>
<span class="gp">In [4]: </span><span class="n">buf</span>
-<span class="gh">Out[4]: </span><span class="go"><pyarrow.Buffer
address=0x7ff0357ea4d0 size=26 is_cpu=True is_mutable=False></span>
+<span class="gh">Out[4]: </span><span class="go"><pyarrow.Buffer
address=0x7ff76f4929d0 size=26 is_cpu=True is_mutable=False></span>
<span class="gp">In [5]: </span><span class="n">buf</span><span
class="o">.</span><span class="n">size</span>
<span class="gh">Out[5]: </span><span class="go">26</span>
@@ -1583,7 +1583,7 @@ referenced using the <a class="reference internal"
href="generated/pyarrow.forei
<p>Buffers can be used in circumstances where a Python buffer or memoryview is
required, and such conversions are zero-copy:</p>
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [6]: </span><span
class="nb">memoryview</span><span class="p">(</span><span
class="n">buf</span><span class="p">)</span>
-<span class="gh">Out[6]: </span><span class="go"><memory at
0x7ff0358ecdc0></span>
+<span class="gh">Out[6]: </span><span class="go"><memory at
0x7ff76f57cdc0></span>
</pre></div>
</div>
<p>The Buffer’s <a class="reference internal"
href="generated/pyarrow.Buffer.html#pyarrow.Buffer.to_pybytes"
title="pyarrow.Buffer.to_pybytes"><code class="xref py py-meth docutils literal
notranslate"><span class="pre">to_pybytes()</span></code></a> method converts
the Buffer’s data to a
@@ -1782,7 +1782,7 @@ into Arrow Buffer objects, use <code class="docutils
literal notranslate"><span
<span class="gp">In [32]: </span><span class="n">buf</span> <span
class="o">=</span> <span class="n">mmap</span><span class="o">.</span><span
class="n">read_buffer</span><span class="p">(</span><span
class="mi">4</span><span class="p">)</span>
<span class="gp">In [33]: </span><span class="nb">print</span><span
class="p">(</span><span class="n">buf</span><span class="p">)</span>
-<span class="go"><pyarrow.Buffer address=0x7ff0d82de000 size=4 is_cpu=True
is_mutable=False></span>
+<span class="go"><pyarrow.Buffer address=0x7ff810caf000 size=4 is_cpu=True
is_mutable=False></span>
<span class="gp">In [34]: </span><span class="n">buf</span><span
class="o">.</span><span class="n">to_pybytes</span><span class="p">()</span>
<span class="gh">Out[34]: </span><span class="go">b'some'</span>
@@ -1804,7 +1804,7 @@ file interfaces that can read and write to Arrow
Buffers.</p>
<span class="gp">In [37]: </span><span class="n">buf</span> <span
class="o">=</span> <span class="n">writer</span><span class="o">.</span><span
class="n">getvalue</span><span class="p">()</span>
<span class="gp">In [38]: </span><span class="n">buf</span>
-<span class="gh">Out[38]: </span><span class="go"><pyarrow.Buffer
address=0x7ff0cec13000 size=14 is_cpu=True is_mutable=True></span>
+<span class="gh">Out[38]: </span><span class="go"><pyarrow.Buffer
address=0x7ff8076ba000 size=14 is_cpu=True is_mutable=True></span>
<span class="gp">In [39]: </span><span class="n">buf</span><span
class="o">.</span><span class="n">size</span>
<span class="gh">Out[39]: </span><span class="go">14</span>
diff --git a/docs/dev/python/pandas.html b/docs/dev/python/pandas.html
index 97b8855af12..2d099a181a1 100644
--- a/docs/dev/python/pandas.html
+++ b/docs/dev/python/pandas.html
@@ -1744,7 +1744,7 @@ same categories of the Pandas DataFrame.</p>
<span class="gp">In [10]: </span><span class="n">chunk</span><span
class="o">.</span><span class="n">dictionary</span>
<span class="gh">Out[10]: </span>
-<span class="go"><pyarrow.lib.StringArray object at
0x7ff035727580></span>
+<span class="go"><pyarrow.lib.StringArray object at
0x7ff769c9d840></span>
<span class="go">[</span>
<span class="go"> "a",</span>
<span class="go"> "b",</span>
@@ -1753,7 +1753,7 @@ same categories of the Pandas DataFrame.</p>
<span class="gp">In [11]: </span><span class="n">chunk</span><span
class="o">.</span><span class="n">indices</span>
<span class="gh">Out[11]: </span>
-<span class="go"><pyarrow.lib.Int8Array object at 0x7ff0c6ab5a20></span>
+<span class="go"><pyarrow.lib.Int8Array object at 0x7ff76fa028c0></span>
<span class="go">[</span>
<span class="go"> 0,</span>
<span class="go"> 1,</span>
@@ -1879,7 +1879,7 @@ converted to an Arrow <code class="docutils literal
notranslate"><span class="pr
<span class="gp">In [33]: </span><span class="n">arr</span>
<span class="gh">Out[33]: </span>
-<span class="go"><pyarrow.lib.Time64Array object at
0x7ff0c6ab6da0></span>
+<span class="go"><pyarrow.lib.Time64Array object at
0x7ff7b22f5180></span>
<span class="go">[</span>
<span class="go"> 01:01:01.000000,</span>
<span class="go"> 02:02:02.000000</span>
diff --git a/docs/dev/python/parquet.html b/docs/dev/python/parquet.html
index 0cf89b193e4..043cd8d904b 100644
--- a/docs/dev/python/parquet.html
+++ b/docs/dev/python/parquet.html
@@ -1715,7 +1715,7 @@ you may choose to omit it by passing <code
class="docutils literal notranslate">
<span class="gp">In [20]: </span><span class="n">parquet_file</span><span
class="o">.</span><span class="n">metadata</span>
<span class="gh">Out[20]: </span>
-<span class="go"><pyarrow._parquet.FileMetaData object at
0x7ff0c6984310></span>
+<span class="go"><pyarrow._parquet.FileMetaData object at
0x7ff7ff5c2d90></span>
<span class="go"> created_by: parquet-cpp-arrow version 18.0.0-SNAPSHOT</span>
<span class="go"> num_columns: 4</span>
<span class="go"> num_rows: 3</span>
@@ -1725,7 +1725,7 @@ you may choose to omit it by passing <code
class="docutils literal notranslate">
<span class="gp">In [21]: </span><span class="n">parquet_file</span><span
class="o">.</span><span class="n">schema</span>
<span class="gh">Out[21]: </span>
-<span class="go"><pyarrow._parquet.ParquetSchema object at
0x7ff0c698fc00></span>
+<span class="go"><pyarrow._parquet.ParquetSchema object at
0x7ff76f464a40></span>
<span class="go">required group field_id=-1 schema {</span>
<span class="go"> optional double field_id=-1 one;</span>
<span class="go"> optional binary field_id=-1 two (String);</span>
@@ -1783,7 +1783,7 @@ concatenate them into a single table. You can read
individual row groups with
<span class="gp">In [30]: </span><span class="n">metadata</span>
<span class="gh">Out[30]: </span>
-<span class="go"><pyarrow._parquet.FileMetaData object at
0x7ff0799e5300></span>
+<span class="go"><pyarrow._parquet.FileMetaData object at
0x7ff7ff405300></span>
<span class="go"> created_by: parquet-cpp-arrow version 18.0.0-SNAPSHOT</span>
<span class="go"> num_columns: 4</span>
<span class="go"> num_rows: 3</span>
@@ -1797,7 +1797,7 @@ concatenate them into a single table. You can read
individual row groups with
such as the row groups and column chunk metadata and statistics:</p>
<div class="highlight-ipython notranslate"><div
class="highlight"><pre><span></span><span class="gp">In [31]: </span><span
class="n">metadata</span><span class="o">.</span><span
class="n">row_group</span><span class="p">(</span><span
class="mi">0</span><span class="p">)</span>
<span class="gh">Out[31]: </span>
-<span class="go"><pyarrow._parquet.RowGroupMetaData object at
0x7ff0c69d4c20></span>
+<span class="go"><pyarrow._parquet.RowGroupMetaData object at
0x7ff769c2fec0></span>
<span class="go"> num_columns: 4</span>
<span class="go"> num_rows: 3</span>
<span class="go"> total_byte_size: 282</span>
@@ -1805,7 +1805,7 @@ such as the row groups and column chunk metadata and
statistics:</p>
<span class="gp">In [32]: </span><span class="n">metadata</span><span
class="o">.</span><span class="n">row_group</span><span class="p">(</span><span
class="mi">0</span><span class="p">)</span><span class="o">.</span><span
class="n">column</span><span class="p">(</span><span class="mi">0</span><span
class="p">)</span>
<span class="gh">Out[32]: </span>
-<span class="go"><pyarrow._parquet.ColumnChunkMetaData object at
0x7ff0c69d4ef0></span>
+<span class="go"><pyarrow._parquet.ColumnChunkMetaData object at
0x7ff7ff405f30></span>
<span class="go"> file_offset: 0</span>
<span class="go"> file_path: </span>
<span class="go"> physical_type: DOUBLE</span>
@@ -1813,7 +1813,7 @@ such as the row groups and column chunk metadata and
statistics:</p>
<span class="go"> path_in_schema: one</span>
<span class="go"> is_stats_set: True</span>
<span class="go"> statistics:</span>
-<span class="go"> <pyarrow._parquet.Statistics object at
0x7ff07986bc90></span>
+<span class="go"> <pyarrow._parquet.Statistics object at
0x7ff7ff405bc0></span>
<span class="go"> has_min_max: True</span>
<span class="go"> min: -1.0</span>
<span class="go"> max: 2.5</span>
diff --git a/docs/dev/r/pkgdown.yml b/docs/dev/r/pkgdown.yml
index 1ab234b9248..47bd413c9e4 100644
--- a/docs/dev/r/pkgdown.yml
+++ b/docs/dev/r/pkgdown.yml
@@ -21,7 +21,7 @@ articles:
read_write: read_write.html
developers/setup: developers/setup.html
developers/workflow: developers/workflow.html
-last_built: 2024-08-31T01:28Z
+last_built: 2024-09-01T01:31Z
urls:
reference: https://arrow.apache.org/docs/r/reference
article: https://arrow.apache.org/docs/r/articles
diff --git a/docs/dev/r/reference/to_duckdb.html
b/docs/dev/r/reference/to_duckdb.html
index 1b457877bd6..fe7d45fbf45 100644
--- a/docs/dev/r/reference/to_duckdb.html
+++ b/docs/dev/r/reference/to_duckdb.html
@@ -145,11 +145,11 @@ using them.</p>
<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#949494;"># Groups: cyl</span></span>
<span class="r-out co"><span class="r-pr">#></span> mpg cyl disp
hp drat wt qsec vs am gear carb</span>
<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#949494; font-style: italic;"><dbl></span> <span style="color: #949494;
font-style: italic;"><dbl></span> <span style="color: #949494;
font-style: italic;"><dbl></span> <span style="color: #949494;
font-style: italic;"><dbl></span> <span style="color: #949494;
font-style: italic;"><dbl></span> <span style="color: #949494;
font-style: italic;"><dbl></span> <span style="color: # [...]
-<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#BCBCBC;">1</span> 27.3 4 79 66 4.08 1.94 18.9 1 1 4
1</span>
-<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#BCBCBC;">2</span> 16.4 8 276. 180 3.07 4.07 17.4 0 0 3
3</span>
-<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#BCBCBC;">3</span> 17.3 8 276. 180 3.07 3.73 17.6 0 0 3
3</span>
-<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#BCBCBC;">4</span> 15.2 8 276. 180 3.07 3.78 18 0 0 3
3</span>
-<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#BCBCBC;">5</span> 19.7 6 145 175 3.62 2.77 15.5 0 1 5
6</span>
+<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#BCBCBC;">1</span> 19.7 6 145 175 3.62 2.77 15.5 0 1 5
6</span>
+<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#BCBCBC;">2</span> 27.3 4 79 66 4.08 1.94 18.9 1 1 4
1</span>
+<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#BCBCBC;">3</span> 16.4 8 276. 180 3.07 4.07 17.4 0 0 3
3</span>
+<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#BCBCBC;">4</span> 17.3 8 276. 180 3.07 3.73 17.6 0 0 3
3</span>
+<span class="r-out co"><span class="r-pr">#></span> <span style="color:
#BCBCBC;">5</span> 15.2 8 276. 180 3.07 3.78 18 0 0 3
3</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/docs/dev/r/search.json b/docs/dev/r/search.json
index b55e35f7fa3..74ee3b1818a 100644
--- a/docs/dev/r/search.json
+++ b/docs/dev/r/search.json
@@ -1 +1 @@
-[{"path":"https://arrow.apache.org/docs/r/PACKAGING.html","id":null,"dir":"","previous_headings":"","what":"Packaging
checklist for CRAN release","title":"Packaging checklist for CRAN
release","text":"high-level overview release process see Apache Arrow Release
Management
Guide.","code":""},{"path":"https://arrow.apache.org/docs/r/PACKAGING.html","id":"before-the-release-candidate-is-cut","dir":"","previous_headings":"","what":"Before
the release candidate is cut","title":"Packaging chec [...]
+[{"path":"https://arrow.apache.org/docs/r/PACKAGING.html","id":null,"dir":"","previous_headings":"","what":"Packaging
checklist for CRAN release","title":"Packaging checklist for CRAN
release","text":"high-level overview release process see Apache Arrow Release
Management
Guide.","code":""},{"path":"https://arrow.apache.org/docs/r/PACKAGING.html","id":"before-the-release-candidate-is-cut","dir":"","previous_headings":"","what":"Before
the release candidate is cut","title":"Packaging chec [...]
diff --git a/docs/dev/searchindex.js b/docs/dev/searchindex.js
index fec677cf40b..78b429ceb3a 100644
--- a/docs/dev/searchindex.js
+++ b/docs/dev/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"docnames": ["c_glib/arrow-cuda-glib/index",
"c_glib/arrow-dataset-glib/index", "c_glib/arrow-flight-glib/index",
"c_glib/arrow-flight-sql-glib/index", "c_glib/arrow-glib/index",
"c_glib/gandiva-glib/index", "c_glib/index", "c_glib/parquet-glib/index",
"cpp/acero/async", "cpp/acero/developer_guide", "cpp/acero/overview",
"cpp/acero/substrait", "cpp/acero/user_guide", "cpp/api", "cpp/api/acero",
"cpp/api/array", "cpp/api/async", "cpp/api/builder", "cpp/api/c_abi", "cpp/ap
[...]
\ No newline at end of file
+Search.setIndex({"docnames": ["c_glib/arrow-cuda-glib/index",
"c_glib/arrow-dataset-glib/index", "c_glib/arrow-flight-glib/index",
"c_glib/arrow-flight-sql-glib/index", "c_glib/arrow-glib/index",
"c_glib/gandiva-glib/index", "c_glib/index", "c_glib/parquet-glib/index",
"cpp/acero/async", "cpp/acero/developer_guide", "cpp/acero/overview",
"cpp/acero/substrait", "cpp/acero/user_guide", "cpp/api", "cpp/api/acero",
"cpp/api/array", "cpp/api/async", "cpp/api/builder", "cpp/api/c_abi", "cpp/ap
[...]
\ No newline at end of file
