GH-49509: [Docs][Python][C++] Minimize warnings and docutils errors for Sphinx build html

cpp/apidoc/Doxyfile

@@ -2476,6 +2476,7 @@ PREDEFINED             = __attribute__(x)= \
                          __declspec(x)= \
                          ARROW_ACERO_EXPORT= \
                          ARROW_ARG_UNUSED(x)=x \
+                         ARROW_CUDA_EXPORT= \
                          ARROW_DEPRECATED(x)= \
                          ARROW_DS_EXPORT= \
                          ARROW_ENGINE_EXPORT= \

cpp/src/arrow/compute/kernels/scalar_arithmetic.cc

@@ -1347,13 +1347,13 @@ const FunctionDoc atan2_doc{"Compute the inverse tangent of y/x",
                             {"y", "x"}};
 
 const FunctionDoc atanh_doc{"Compute the inverse hyperbolic tangent",
-                            ("NaN is returned for input values x with |x| > 1.\n"
+                            ("NaN is returned for input values x with \\|x\\| > 1.\n"
                              "At x = +/- 1, returns +/- infinity.\n"
                              "To raise an error instead, see \"atanh_checked\"."),
                             {"x"}};
 
 const FunctionDoc atanh_checked_doc{"Compute the inverse hyperbolic tangent",
-                                    ("Input values x with |x| >= 1.0 raise an error\n"
+                                    ("Input values x with \\|x\\| >= 1.0 raise an error\n"
                                      "to return NaN instead, see \"atanh\"."),
                                     {"x"}};
 

cpp/src/arrow/compute/kernels/vector_pairwise.cc

@@ -111,23 +111,23 @@ Status PairwiseExec(KernelContext* ctx, const ExecSpan& batch, ExecResult* out)
 
 const FunctionDoc pairwise_diff_doc(
     "Compute first order difference of an array",
-    ("Computes the first order difference of an array, It internally calls \n"
-     "the scalar function \"subtract\" to compute \n differences, so its \n"
-     "behavior and supported types are the same as \n"
-     "\"subtract\". The period can be specified in :struct:`PairwiseOptions`.\n"
+    ("Computes the first order difference of an array. It internally calls\n"
+     "the scalar function \"subtract\" to compute differences, so its\n"
+     "behavior and supported types are the same as\n"
+     "\"subtract\". The period can be specified in `PairwiseOptions`.\n"
      "\n"
-     "Results will wrap around on integer overflow. Use function \n"
+     "Results will wrap around on integer overflow. Use function\n"
      "\"pairwise_diff_checked\" if you want overflow to return an error."),
     {"input"}, "PairwiseOptions");
 
 const FunctionDoc pairwise_diff_checked_doc(
     "Compute first order difference of an array",
-    ("Computes the first order difference of an array, It internally calls \n"
-     "the scalar function \"subtract_checked\" (or the checked variant) to compute \n"
-     "differences, so its behavior and supported types are the same as \n"
-     "\"subtract_checked\". The period can be specified in :struct:`PairwiseOptions`.\n"
+    ("Computes the first order difference of an array. It internally calls\n"
+     "the scalar function \"subtract_checked\" (or the checked variant) to compute\n"
+     "differences, so its behavior and supported types are the same as\n"
+     "\"subtract_checked\". The period can be specified in `PairwiseOptions`.\n"
      "\n"
-     "This function returns an error on overflow. For a variant that doesn't \n"
+     "This function returns an error on overflow. For a variant that doesn't\n"
      "fail on overflow, use function \"pairwise_diff\"."),
     {"input"}, "PairwiseOptions");
 

cpp/src/arrow/result.h

@@ -228,8 +228,8 @@ class [[nodiscard]] Result : public util::EqualityComparable<Result<T>> {
   }
 
   /// Templatized constructor which constructs a `Result<T>` by moving the
-  /// contents of a `Result<U>`. `T` must be implicitly constructible from `U
-  /// &&`.
+  /// contents of a `Result<U>`. `T` must be implicitly constructible from
+  /// `U&&`.
   ///
   /// Sets `other` to contain a non-OK status with a `StatusError::Invalid`
   /// error code.

docs/source/cpp/env_vars.rst

@@ -94,7 +94,7 @@ that changing their value later will have an effect.
    value "1"; use "0" to disable.
 
    If enabled, at-fork handlers make Arrow C++ compatible with the use of the
-   ``fork()`` system call, such as by Python's :python:mod:`multiprocessing`,
+   ``fork()`` system call, such as by Python's :py:mod:`multiprocessing`,
    but at the expense of executing
    `potentially unsafe code <https://pubs.opengroup.org/onlinepubs/9699919799/functions/pthread_atfork.html>`__
    in a forked child process if the parent process is multi-threaded.

docs/source/format/CanonicalExtensions.rst

@@ -546,6 +546,11 @@ Primitive Type Mappings
 | UUID extension type  | UUID                   |
 +----------------------+------------------------+
 
+.. toctree::
+   :maxdepth: 1
+
+   CanonicalExtensions/Examples
+
 .. _timestamp_with_offset_extension:
 
 Timestamp With Offset

docs/source/format/Security.rst

@@ -52,7 +52,7 @@ Columnar Format
 Invalid data
 ------------
 
-The Arrow :ref:`columnar format <_format_columnar>` is an efficient binary
+The Arrow :ref:`columnar format <format_columnar>` is an efficient binary
 representation with a focus on performance and efficiency. While the format
 does not store raw pointers, the contents of Arrow buffers are often
 combined and converted to pointers into the process' address space.
@@ -165,7 +165,7 @@ have bugs anyway.
 IPC Format
 ==========
 
-The :ref:`IPC format <_ipc-message-format>` is a serialization format for the
+The :ref:`IPC format <ipc-message-format>` is a serialization format for the
 columnar format with associated metadata. Reading an IPC stream or file from
 an untrusted source comes with similar caveats as reading the Arrow columnar
 format.

docs/source/implementations.rst

@@ -113,7 +113,7 @@ The source files for the Cookbook are maintained in the
    C++ <cpp/index>
    C GLib <c_glib/index>
    Go <https://arrow.apache.org/go/>
-   Java <java/index>
+   Java <https://arrow.apache.org/java/current/>
    JavaScript <https://arrow.apache.org/js/current/>
    Julia <https://arrow.apache.org/julia/>
    MATLAB <https://github.com/apache/arrow/blob/main/matlab/README.md>

docs/source/python/index.rst

@@ -67,5 +67,4 @@ files into Arrow structures.
    env_vars
    api
    getting_involved
-   benchmarks
    Python cookbook <https://arrow.apache.org/cookbook/py/>

python/pyarrow/_azurefs.pyx

@@ -59,6 +59,7 @@ cdef class AzureFileSystem(FileSystem):
     client_id : str, default None
         The client ID (Application ID) for Azure Active Directory authentication.
         Its interpretation depends on the credential type being used:
+
         - For `ClientSecretCredential`: It is the Application (client) ID of your
           registered Azure AD application (Service Principal). It must be provided
           together with `tenant_id` and `client_secret` to use ClientSecretCredential.
@@ -67,6 +68,7 @@ cdef class AzureFileSystem(FileSystem):
           user-assigned managed identity and need to explicitly specify which one
           (e.g., if the resource has multiple user-assigned identities). For
           system-assigned managed identities, this parameter is typically not required.
+
     client_secret : str, default None
         Client secret for Azure Active Directory authentication. Must be provided together
         with `tenant_id` and `client_id` to use ClientSecretCredential.

python/pyarrow/_compute.pyx

@@ -3160,7 +3160,7 @@ def register_vector_function(func, function_name, function_doc, in_types, out_ty
         all arguments are scalar, else it must return an Array.
 
         To define a varargs function, pass a callable that takes
-        *args. The last in_type will be the type of all varargs
+        ``*args``. The last in_type will be the type of all varargs
         arguments.
     function_name : str
         Name of the function. There should only be one function
@@ -3241,7 +3241,7 @@ def register_aggregate_function(func, function_name, function_doc, in_types, out
         in_types defined. It must return a Scalar matching the
         out_type.
         To define a varargs function, pass a callable that takes
-        *args. The in_type needs to match in type of inputs when
+        ``*args``. The in_type needs to match in type of inputs when
         the function gets called.
     function_name : str
         Name of the function. This name must be unique, i.e.,

python/pyarrow/array.pxi

@@ -2557,6 +2557,7 @@ cdef class BaseListArray(Array):
         --------
 
         Basic logical list-array's flatten
+
         >>> import pyarrow as pa
         >>> values = [1, 2, 3, 4]
         >>> offsets = [2, 1, 0]
@@ -4840,7 +4841,7 @@ cdef class Bool8Array(ExtensionArray):
     def from_numpy(obj):
         """
         Convert numpy array to a bool8 extension array without making a copy.
-        The input array must be 1-dimensional, with either bool_ or int8 dtype.
+        The input array must be 1-dimensional, with either ``bool_`` or ``int8`` dtype.
 
         Parameters
         ----------

python/pyarrow/parquet/core.py

@@ -859,6 +859,7 @@ def _sanitize_table(table, new_schema, flavor):
                 <element-repetition> <element-type> item;
             }
         }
+
 encryption_properties : FileEncryptionProperties, default None
     File encryption properties for Parquet Modular Encryption.
     If None, no encryption will be done.
@@ -898,6 +899,7 @@ def _sanitize_table(table, new_schema, flavor):
 store_decimal_as_integer : bool, default False
     Allow decimals with 1 <= precision <= 18 to be stored as integers.
     In Parquet, DECIMAL can be stored in any of the following physical types:
+
     - int32: for 1 <= precision <= 9.
     - int64: for 10 <= precision <= 18.
     - fixed_len_byte_array: precision is limited by the array size.
@@ -907,6 +909,7 @@ def _sanitize_table(table, new_schema, flavor):
 
     By default, this is DISABLED and all decimal types annotate fixed_len_byte_array.
     When enabled, the writer will use the following physical types to store decimals:
+
     - int32: for 1 <= precision <= 9.
     - int64: for 10 <= precision <= 18.
     - fixed_len_byte_array: for precision > 18.
@@ -927,6 +930,7 @@ def _sanitize_table(table, new_schema, flavor):
     before any Parquet encodings).
 
     A `dict` can be passed to adjust the chunker parameters with the following keys:
+
     - `min_chunk_size`: minimum chunk size in bytes, default 256 KiB
       The rolling hash will not be updated until this size is reached for each chunk.
       Note that all data sent through the hash function is counted towards the chunk
@@ -945,6 +949,7 @@ def _sanitize_table(table, new_schema, flavor):
       balance between deduplication ratio and fragmentation. Use norm_level=1 or
       norm_level=2 to reach a higher deduplication ratio at the expense of
       fragmentation.
+
 write_time_adjusted_to_utc : bool, default False
     Set the value of isAdjustedTOUTC when writing a TIME column.
     If True, this tells the Parquet reader that the TIME columns

python/pyarrow/table.pxi

@@ -3629,7 +3629,7 @@ cdef class RecordBatch(_Tabular):
         b: [10,20,30,40,null]
 
         Convert a RecordBatch to row-major Tensor with null values
-        written as ``NaN``s
+        written as NaN values
 
         >>> batch.to_tensor(null_to_nan=True)
         <pyarrow.Tensor>
@@ -5779,7 +5779,7 @@ cdef class Table(_Tabular):
         -------
         Table
 
-        Example
+        Examples
         --------
         >>> import pyarrow as pa
         >>> t1 = pa.table({'id': [1, 3, 2, 3, 3],