rok · Sep 25, 2026
diff --git a/c_glib/doc/arrow-glib.toml.in b/c_glib/doc/arrow-glib.toml.in
@@ -73,7 +73,7 @@ docs_url = "https://arrow.apache.org/docs/c_glib/gandiva-glib/"
 [related."Parquet-1.0"]
 name = "Apache Parquet GLib"
 description = "Apache Parquet GLib API"
-docs_url = "https://arrow.apache.org/docs/c_glib/arrow-parquet-glib/"
+docs_url = "https://arrow.apache.org/docs/c_glib/parquet-glib/"
 
 [source-location]
 base_url = "https://github.com/apache/arrow/blob/@SOURCE_REFERENCE@/c_glib/arrow-glib"

diff --git a/c_glib/doc/gandiva-glib.toml.in b/c_glib/doc/gandiva-glib.toml.in
@@ -36,7 +36,7 @@ docs_url = "https://arrow.apache.org/docs/c_glib/arrow-glib/"
 [related."Parquet-1.0"]
 name = "Apache Parquet GLib"
 description = "Apache Parquet GLib API"
-docs_url = "https://arrow.apache.org/docs/c_glib/arrow-parquet-glib/"
+docs_url = "https://arrow.apache.org/docs/c_glib/parquet-glib/"
 
 [related."GObject-2.0"]
 name = "GObject"

diff --git a/cpp/src/arrow/compute/kernels/vector_rank.cc b/cpp/src/arrow/compute/kernels/vector_rank.cc
@@ -297,7 +297,7 @@ const FunctionDoc rank_quantile_doc(
      "NaNs are considered greater than any other non-null value, but smaller\n"
      "than null values.\n"
      "The results are real values strictly between 0 and 1. They are\n"
-     "computed as in https://en.wikipedia.org/wiki/Quantile_rank\n"
+     "computed as in https://en.wikipedia.org/wiki/Percentile_rank\n"
      "but without multiplying by 100.\n"
      "\n"
      "The handling of nulls and NaNs can be changed in RankQuantileOptions."),

diff --git a/docs/source/_redirects/python/parquet.html b/docs/source/_redirects/python/parquet.html
@@ -0,0 +1,12 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="utf-8">
+    <title>Redirecting…</title>
+    <link rel="canonical" href="parquet/index.html">
+    <meta http-equiv="refresh" content="0; url=parquet/index.html">
+  </head>
+  <body>
+    <p>This page has moved to <a href="parquet/index.html">parquet/index.html</a>.</p>
+  </body>
+</html>
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -414,7 +414,8 @@
 # .htaccess) here, relative to this directory. These files are copied
 # directly to the root of the documentation.
 #
-# html_extra_path = []
+# _redirects/ holds stub pages that redirect from moved or removed pages.
+html_extra_path = ['_redirects']
 
 # If not None, a 'Last updated on:' timestamp is inserted at every page
 # bottom, using the given strftime format.
@@ -614,6 +615,16 @@ def setup(app):
     app.add_config_value('cuda_enabled', cuda_enabled, 'env')
     app.add_config_value('flight_enabled', flight_enabled, 'env')
     app.add_directive('arrow-computefuncs', ComputeFunctionsTableDirective)
+    app.connect('html-page-context', _hide_edit_button_on_generated_pages)
+
+
+def _hide_edit_button_on_generated_pages(app, pagename, templatename,
+                                         context, doctree):
+    # autosummary stubs under */generated/ are created at build time and
+    # are not checked in, so an "Edit on GitHub" link would point to a
+    # non-existent file.
+    if '/generated/' in f'/{pagename}':
+        context['theme_use_edit_page_button'] = False
 
 
 class ComputeFunctionsTableDirective(Directive):

diff --git a/docs/source/cpp/memory.rst b/docs/source/cpp/memory.rst
@@ -141,7 +141,7 @@ The default memory pool depends on how Arrow C++ was compiled:
 
 - if enabled at compile time, a `mimalloc <https://github.com/microsoft/mimalloc>`_
   heap;
-- otherwise, if enabled at compile time, a `jemalloc <http://jemalloc.net/>`_ heap;
+- otherwise, if enabled at compile time, a `jemalloc <https://jemalloc.net/>`_ heap;
 - otherwise, the C library ``malloc`` heap.
 
 Overriding the Default Memory Pool

diff --git a/docs/source/cpp/orc.rst b/docs/source/cpp/orc.rst
@@ -24,13 +24,13 @@
 Reading and Writing ORC files
 =============================
 
-The `Apache ORC <http://orc.apache.org/>`_ project provides a
+The `Apache ORC <https://orc.apache.org/>`_ project provides a
 standardized open-source columnar storage format for use in data analysis
 systems. It was created originally for use in `Apache Hadoop
-<http://hadoop.apache.org/>`_ with systems like `Apache Drill
-<http://drill.apache.org>`_, `Apache Hive <http://hive.apache.org>`_, `Apache
-Impala <http://impala.apache.org>`_, and `Apache Spark
-<http://spark.apache.org>`_ adopting it as a shared standard for high
+<https://hadoop.apache.org/>`_ with systems like `Apache Drill
+<https://drill.apache.org>`_, `Apache Hive <https://hive.apache.org>`_, `Apache
+Impala <https://impala.apache.org>`_, and `Apache Spark
+<https://spark.apache.org>`_ adopting it as a shared standard for high
 performance data IO.
 
 Apache Arrow is an ideal in-memory representation layer for data that is being read

diff --git a/docs/source/developers/continuous_integration/crossbow.rst b/docs/source/developers/continuous_integration/crossbow.rst
@@ -25,7 +25,6 @@ The content of ``arrow/dev/tasks`` directory aims for automating the process of
 Arrow packaging and integration testing.
 
 Packages:
-  - C++ and Python `conda-forge packages`_ for Linux, macOS and Windows
   - Python `Wheels`_ for Linux, macOS and Windows
   - C++ and GLib `Linux packages`_ for multiple distributions
   - Java for Gandiva
@@ -230,9 +229,8 @@ see its help page:
   $ archery crossbow submit --help
 
 
-.. _conda-forge packages: conda-recipes
-.. _Wheels: python-wheels
-.. _Linux packages: linux-packages
+.. _Wheels: https://github.com/apache/arrow/tree/main/dev/tasks/python-wheels
+.. _Linux packages: https://github.com/apache/arrow/tree/main/dev/tasks/linux-packages
 .. _Create the queue repository: https://docs.github.com/en/repositories/creating-and-managing-repositories/creating-a-new-repository
 .. _GitHub Actions: https://docs.github.com/en/actions/quickstart
 .. _Travis CI: https://travis-ci.com/getting-started/

diff --git a/docs/source/developers/cpp/acero.rst b/docs/source/developers/cpp/acero.rst
@@ -465,7 +465,7 @@ In order to use the tracing that is present today you will need to build with Ar
 Then you will need to set the environment variable ``ARROW_TRACING_BACKEND=otlp_http``.  This will configure open telemetry
 to export trace results (as OTLP) to the HTTP endpoint http://localhost:4318/v1/traces.  You will need to configure an
 open telemetry collector to collect results on that endpoint and you will need to configure a trace viewer of some kind
-such as Jaeger: https://www.jaegertracing.io/docs/1.21/opentelemetry/
+such as Jaeger: https://www.jaegertracing.io/docs/latest/
 
 Benchmarking
 ============

diff --git a/docs/source/developers/documentation.rst b/docs/source/developers/documentation.rst
@@ -23,8 +23,8 @@ Building the Documentation
 Prerequisites
 -------------
 
-The documentation build process uses `Doxygen <http://www.doxygen.nl/>`_ and
-`Sphinx <http://www.sphinx-doc.org/>`_ along with a few extensions.
+The documentation build process uses `Doxygen <https://www.doxygen.nl/>`_ and
+`Sphinx <https://www.sphinx-doc.org/>`_ along with a few extensions.
 
 If you're using Conda, the required software can be installed in a single line:
 
@@ -36,7 +36,7 @@ If you're using Conda, the required software can be installed in a single line:
 
    ``linuxdoc`` cannot be installed by Conda. It has to be installed via pip separately.
 
-Otherwise, you'll first need to install `Doxygen <http://www.doxygen.nl/>`_
+Otherwise, you'll first need to install `Doxygen <https://www.doxygen.nl/>`_
 yourself (for example from your distribution's official repositories, if
 using Linux).  Then you can install the Python-based requirements with the
 following command:

diff --git a/docs/source/developers/guide/resources.rst b/docs/source/developers/guide/resources.rst
@@ -56,7 +56,7 @@ Additional information
 
   It is possible to install the Arrow R package from the nightly builds which are daily development
   builds of the R package and are not the official releases. See more on the
-  `Install R package article <https://arrow.apache.org/docs/dev/r/articles/install.html#install-the-nightly-build>`_.
+  `Installing development versions article <https://arrow.apache.org/docs/r/articles/install_nightly.html>`_.
 
 - `Apache Arrow releases <https://arrow.apache.org/release/>`_
 

diff --git a/docs/source/developers/python/development.rst b/docs/source/developers/python/development.rst
@@ -42,7 +42,7 @@ Unit Testing
 ============
 
 We are using `pytest <https://docs.pytest.org/en/latest/>`_ to develop our unit
-test suite. After `building the project <build_pyarrow>`_ you can run its unit tests
+test suite. After :ref:`building the project <build_pyarrow>` you can run its unit tests
 like so:
 
 .. code-block::

diff --git a/docs/source/format/Columnar.rst b/docs/source/format/Columnar.rst
@@ -1758,7 +1758,7 @@ never exposed. Before sending data to another system expecting Arrow
 data, these custom vectors should be converted to a type that exist in
 the Arrow spec.
 
-.. _Flatbuffers: http://github.com/google/flatbuffers
+.. _Flatbuffers: https://github.com/google/flatbuffers
 .. _Flatbuffers protocol definition files: https://github.com/apache/arrow/tree/main/format
 .. _Schema.fbs: https://github.com/apache/arrow/blob/main/format/Schema.fbs
 .. _Message.fbs: https://github.com/apache/arrow/blob/main/format/Message.fbs

diff --git a/docs/source/format/DissociatedIPC.rst b/docs/source/format/DissociatedIPC.rst
@@ -399,7 +399,7 @@ improving it and finding the right generalizations to standardize on across tran
 
 Please chime in using the Arrow Developers Mailing list: https://arrow.apache.org/community/#mailing-lists
 
-.. _Flatbuffers: http://github.com/google/flatbuffers
+.. _Flatbuffers: https://github.com/google/flatbuffers
 .. _UCX: https://openucx.org/
 .. _libfabric: https://ofiwg.github.io/libfabric/
 .. _libcudf: https://docs.rapids.ai/api
diff --git a/docs/source/implementations.rst b/docs/source/implementations.rst
@@ -83,7 +83,7 @@ designed to help produce and consume Arrow data.
 
    * - nanoarrow
      - `nanoarrow Docs <https://arrow.apache.org/nanoarrow>`_ :fa:`external-link-alt`
-     - `nanoarrow Source <http://github.com/apache/arrow-nanoarrow>`_
+     - `nanoarrow Source <https://github.com/apache/arrow-nanoarrow>`_
 
 Implementation Status
 =====================

diff --git a/docs/source/python/getting_involved.rst b/docs/source/python/getting_involved.rst
@@ -29,7 +29,7 @@ integrations in other projects, we'd be happy to have you involved:
 * Join the mailing list: send an email to
   `dev-subscribe@arrow.apache.org <mailto:dev-subscribe@arrow.apache.org>`_.
   Share your ideas and use cases for the project or read through the
-  `Archive <http://mail-archives.apache.org/mod_mbox/arrow-dev/>`_.
+  `Archive <https://lists.apache.org/list.html?dev@arrow.apache.org>`_.
 * Follow our activity on `GitHub <https://github.com/apache/arrow/issues>`_
 * Learn the `Format / Specification
   <https://github.com/apache/arrow/tree/main/format>`_

diff --git a/docs/source/python/integration/cuda.rst b/docs/source/python/integration/cuda.rst
@@ -174,4 +174,4 @@ Of course, we can copy the CUDA buffer back to host memory:
    array([10, 11, 12, 13], dtype=int32)
 
 .. seealso::
-   Documentation for Numba's `CUDA support <https://numba.pydata.org/numba-doc/latest/cuda/index.html>`_.
+   Documentation for Numba's `CUDA support <https://numba.readthedocs.io/en/stable/cuda/index.html>`_.
diff --git a/docs/source/python/integration/python_java.rst b/docs/source/python/integration/python_java.rst
@@ -33,7 +33,7 @@ marshaling and unmarshaling data.
     The ``Arrow Java`` version must have been compiled with ``mvn -Parrow-c-data`` to
     ensure CData exchange support is enabled.
     See `Python Install Instructions <https://arrow.apache.org/docs/python/install.html>`_
-    and `Java Documentation <https://arrow.apache.org/docs/java/>`_
+    and `Java Documentation <https://arrow.apache.org/java/current/>`_
     for further details.
 
 Invoking Java methods from Python

diff --git a/docs/source/python/memory.rst b/docs/source/python/memory.rst
@@ -117,7 +117,7 @@ the buffer is garbage-collected, all of the memory is freed:
    0
 
 Besides the default built-in memory pool, there may be additional memory pools
-to choose from (such as `jemalloc <http://jemalloc.net/>`_)
+to choose from (such as `jemalloc <https://jemalloc.net/>`_)
 depending on how Arrow was built.  One can get the backend name for a memory
 pool::
 

diff --git a/docs/source/python/orc.rst b/docs/source/python/orc.rst
@@ -21,13 +21,13 @@
 Reading and Writing the Apache ORC Format
 =============================================
 
-The `Apache ORC <http://orc.apache.org/>`_ project provides a
+The `Apache ORC <https://orc.apache.org/>`_ project provides a
 standardized open-source columnar storage format for use in data analysis
 systems. It was created originally for use in `Apache Hadoop
-<http://hadoop.apache.org/>`_ with systems like `Apache Drill
-<http://drill.apache.org>`_, `Apache Hive <http://hive.apache.org>`_, `Apache
-Impala <http://impala.apache.org>`_, and `Apache Spark
-<http://spark.apache.org>`_ adopting it as a shared standard for high
+<https://hadoop.apache.org/>`_ with systems like `Apache Drill
+<https://drill.apache.org>`_, `Apache Hive <https://hive.apache.org>`_, `Apache
+Impala <https://impala.apache.org>`_, and `Apache Spark
+<https://spark.apache.org>`_ adopting it as a shared standard for high
 performance data IO.
 
 Apache Arrow is an ideal in-memory representation layer for data that is being read

diff --git a/docs/source/python/parquet/index.rst b/docs/source/python/parquet/index.rst
@@ -21,13 +21,13 @@
 Reading and Writing the Apache Parquet Format
 =============================================
 
-The `Apache Parquet <http://parquet.apache.org/>`_ project provides a
+The `Apache Parquet <https://parquet.apache.org/>`_ project provides a
 standardized open-source columnar storage format for use in data analysis
 systems. It was created originally for use in `Apache Hadoop
-<http://hadoop.apache.org/>`_ with systems like `Apache Drill
-<http://drill.apache.org>`_, `Apache Hive <http://hive.apache.org>`_, `Apache
-Impala <http://impala.apache.org>`_, and `Apache Spark
-<http://spark.apache.org>`_ adopting it as a shared standard for high
+<https://hadoop.apache.org/>`_ with systems like `Apache Drill
+<https://drill.apache.org>`_, `Apache Hive <https://hive.apache.org>`_, `Apache
+Impala <https://impala.apache.org>`_, and `Apache Spark
+<https://spark.apache.org>`_ adopting it as a shared standard for high
 performance data IO.
 
 Apache Arrow is an ideal in-memory transport layer for data that is being read

diff --git a/r/_pkgdown.yml b/r/_pkgdown.yml
@@ -88,7 +88,7 @@ home:
           [C++](https://arrow.apache.org/docs/cpp) <br>
           [Go](https://arrow.apache.org/go/) <br>
           [JavaScript](https://arrow.apache.org/js/) <br>
-          [Java](https://arrow.apache.org/docs/java) <br>
+          [Java](https://arrow.apache.org/java/current/) <br>
           [Julia](https://github.com/apache/arrow-julia/blob/main/README.md) <br>
           [MATLAB](https://github.com/apache/arrow/blob/main/matlab/README.md) <br>
           [Python](https://arrow.apache.org/docs/python) <br>

diff --git a/r/vignettes/data_wrangling.Rmd b/r/vignettes/data_wrangling.Rmd
@@ -183,4 +183,4 @@ sw |>
 
 - To learn more about multi-file datasets, see the [dataset article](./dataset.html).
 - To learn more about user-registered functions, see `help("register_scalar_function", package = "arrow")`.
-- To learn more about writing dplyr bindings as an arrow developer, see the [article on writing bindings](./developers/writing_bindings.html).
+- To learn more about writing dplyr bindings as an arrow developer, see the "Writing bindings" section of the `register_binding()` documentation in [`r/R/dplyr-funcs.R`](https://github.com/apache/arrow/blob/main/r/R/dplyr-funcs.R).
diff --git a/r/vignettes/developers/binary_features.Rmd b/r/vignettes/developers/binary_features.Rmd
@@ -10,7 +10,7 @@ package build configurations, and documents the decisions behind our default
 feature set. This is intended as internal developer documentation for understanding
 which features are enabled in which builds. It is not intended to be a guide for
 installing the Arrow R package; for that, see the
-[installation guide](../../install.html).
+[installation guide](../install.html).
 
 ## Overview
 

diff --git a/r/vignettes/developers/docker.Rmd b/r/vignettes/developers/docker.Rmd
@@ -93,12 +93,12 @@ R_ORG=rhub R_IMAGE=ubuntu-release R_TAG=latest docker compose run r
 
 ### Example - Using Archery
 
-Alternatively, you may prefer to use the [Archery tool to run docker images](https://arrow.apache.org/docs/developers/docker.html).
+Alternatively, you may prefer to use the [Archery tool to run docker images](https://arrow.apache.org/docs/developers/continuous_integration/docker.html).
 This has the advantage of making it simpler to build some of the existing Arrow
 CI jobs which have hierarchical dependencies, and so for example, you could
 build the R package on a container which already has the C++ code pre-built.
 
-This is the same tool which our CI uses - via a tool called [Crossbow](https://arrow.apache.org/docs/developers/crossbow.html).
+This is the same tool which our CI uses - via a tool called [Crossbow](https://arrow.apache.org/docs/developers/continuous_integration/crossbow.html).
 
 If you want to run the `r` workflow discussed above, you could run:
 

diff --git a/r/vignettes/developers/setup.Rmd b/r/vignettes/developers/setup.Rmd
@@ -73,7 +73,7 @@ There are five major steps to the process.
 
 When building libarrow, by default, system dependencies will be used if suitable versions are found.  If system dependencies are not present, libarrow will build them during its own build process. The only dependencies that you need to install _outside_ of the build process are [cmake](https://cmake.org/) (for configuring the build), [openssl](https://www.openssl.org/) and [curl](https://curl.se/libcurl/) if you are building with S3 and GCS support, and [libxml2](https://gitlab.gnome.org/GNOME/libxml2/-/wikis/home) if you're building with Azure support.
 
-For a faster build, you may choose to pre-install more C++ library dependencies (such as [lz4](http://lz4.github.io/lz4/), [zstd](https://facebook.github.io/zstd/), etc.) on the system  so that they don't need to be built from source in the libarrow build.
+For a faster build, you may choose to pre-install more C++ library dependencies (such as [lz4](https://lz4.github.io/lz4/), [zstd](https://facebook.github.io/zstd/), etc.) on the system  so that they don't need to be built from source in the libarrow build.
 
 #### Ubuntu
 ```{bash, save=run & ubuntu}
@@ -311,7 +311,7 @@ Execution halted
 ERROR: loading failed
 ```
 
-To resolve this, try [rebuilding the Arrow library](#step-3-building-arrow).
+To resolve this, try [rebuilding the Arrow library](#step-3---building-libarrow).
 
 ## Multiple versions of libarrow
 

diff --git a/r/vignettes/install.Rmd b/r/vignettes/install.Rmd
@@ -8,7 +8,7 @@ output: rmarkdown::html_vignette
 
 In most cases, `install.packages("arrow")` should just work. There are things you can do to make the installation faster, documented in this article. If for some reason installation does not work, set the environment variable `ARROW_R_DEV=true`, retry, and share the logs with us.
 
-Note that CRAN builds of arrow have some optional features disabled, including Google Cloud Storage (GCS) support. If you need these features, see the information below on [building with a libarrow binary](#r-source-package-with-libarrow-binary), or the [cloud storage article](./fs.html#s3-and-gcs-support) for alternative installation options.
+Note that CRAN builds of arrow have some optional features disabled, including Google Cloud Storage (GCS) support. If you need these features, see the information below on [building with a libarrow binary](#r-source-package-with-libarrow-binary), or the [cloud storage article](./fs.html#s3-gcs-and-azure-support) for alternative installation options.
 
 ## Background