Fix typos according to reviewdog report. (#21335)

### Description
Fix typos based on reviewdog report but with some
exceptions/corrections.

.gitattributes

@@ -1,4 +1,4 @@
-# This sets the default behaviour, overriding core.autocrlf
+# This sets the default behavior, overriding core.autocrlf
 * text=auto
 
 # All source files should have unix line-endings in the repository,

ThirdPartyNotices.txt

@@ -4820,7 +4820,7 @@ SOFTWARE.
 
 ----------------------------------------------------------------------------
 
-This is the MIT/Expat Licence. For more information see:
+This is the MIT/Expat License. For more information see:
 
 1. http://www.opensource.org/licenses/mit-license.php
 

cmake/onnxruntime.cmake

@@ -150,7 +150,7 @@ endif()
 
 if(CMAKE_SYSTEM_NAME STREQUAL "Android" AND onnxruntime_MINIMAL_BUILD)
   # target onnxruntime is a shared library, the dummy __cxa_demangle is only attach to it to avoid
-  # affecting downstream ort library users with the behaviour of dummy __cxa_demangle. So the dummy
+  # affecting downstream ort library users with the behavior of dummy __cxa_demangle. So the dummy
   # __cxa_demangle must not expose to libonnxruntime_common.a. It works as when the linker is
   # creating the DSO, our dummy __cxa_demangle always comes before libc++abi.a so the
   # __cxa_demangle in libc++abi.a is discarded, thus, huge binary size reduction.

cmake/patches/composable_kernel/Fix_Clang_Build.patch

@@ -44,7 +44,7 @@ index c23746e7f..bc326c8b5 100644
  find_package(HIP REQUIRED)
  # Override HIP version in config.h, if necessary.
 @@ -269,12 +248,6 @@ if( DEFINED CK_OVERRIDE_HIP_VERSION_PATCH )
-     message(STATUS "CK_HIP_VERSION_PATCH overriden with ${CK_OVERRIDE_HIP_VERSION_PATCH}")
+     message(STATUS "CK_HIP_VERSION_PATCH overridden with ${CK_OVERRIDE_HIP_VERSION_PATCH}")
  endif()
  message(STATUS "Build with HIP ${HIP_VERSION}")
 -link_libraries(hip::device)

csharp/ApiDocs/_exported_templates/default/partials/title.tmpl.partial

@@ -39,7 +39,7 @@ Event {{name.0.value}}
 Operator {{name.0.value}}
 {{/inOperator}}
 {{#inEii}}
-Explict Interface Implementation {{name.0.value}}
+Explicit Interface Implementation {{name.0.value}}
 {{/inEii}}
 {{#inVariable}}
 Variable {{name.0.value}}

dockerfiles/README.md

@@ -32,7 +32,7 @@
   docker run -it onnxruntime-source
   ```
 
-The docker file supports both x86_64 and ARM64(aarch64). You may use docker's "--platform" parameter to explictly specify which CPU architecture you want to build. For example:
+The docker file supports both x86_64 and ARM64(aarch64). You may use docker's "--platform" parameter to explicitly specify which CPU architecture you want to build. For example:
 
 ```bash
   docker build --platform linux/arm64/v8 -f Dockerfile.source
@@ -274,7 +274,7 @@ Note: You may add --use_tensorrt and --tensorrt_home options if you wish to use
 Note: Resulting Docker image will have ONNX Runtime installed in /usr, and ONNX Runtime wheel copied to /onnxruntime directory.
 Nothing else from ONNX Runtime source tree will be copied/installed to the image.
 
-Note: When running the container you built in Docker, please either use 'nvidia-docker' command instead of 'docker', or use Docker command-line options to make sure NVIDIA runtime will be used and appropiate files mounted from host. Otherwise, CUDA libraries won't be found. You can also [set NVIDIA runtime as default in Docker](https://github.com/dusty-nv/jetson-containers#docker-default-runtime).
+Note: When running the container you built in Docker, please either use 'nvidia-docker' command instead of 'docker', or use Docker command-line options to make sure NVIDIA runtime will be used and appropriate files mounted from host. Otherwise, CUDA libraries won't be found. You can also [set NVIDIA runtime as default in Docker](https://github.com/dusty-nv/jetson-containers#docker-default-runtime).
 
 ## MIGraphX
 **Ubuntu 20.04, ROCm6.0, MIGraphX**

docs/python/notebooks/onnx-inference-byoc-gpu-cpu-aks.ipynb

@@ -64,7 +64,7 @@
     "If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, please follow the [Azure ML configuration notebook](https://github.com/Azure/MachineLearningNotebooks/blob/master/configuration.ipynb) to set up your environment.\n",
     "\n",
     "### Install additional packages needed for this Notebook\n",
-    "You need to install the popular plotting library matplotlib, the image manipulation library opencv, and the onnx library in the conda environment where Azure Maching Learning SDK is installed.\n",
+    "You need to install the popular plotting library matplotlib, the image manipulation library opencv, and the onnx library in the conda environment where Azure Machine Learning SDK is installed.\n",
     "\n",
     "```\n",
     "(myenv) $ pip install matplotlib onnx opencv-python\n",
@@ -79,7 +79,7 @@
    "source": [
     "## 1. Obtain a model from the ONNX Model Zoo\n",
     "\n",
-    "For more information on the Facial Emotion Recognition (FER+) model, you can explore the notebook explaning how to deploy [FER+ with ONNX Runtime on an ACI Instance](onnx-inference-facial-expression-recognition-deploy.ipynb)."
+    "For more information on the Facial Emotion Recognition (FER+) model, you can explore the notebook explaining how to deploy [FER+ with ONNX Runtime on an ACI Instance](onnx-inference-facial-expression-recognition-deploy.ipynb)."
    ]
   },
   {

include/onnxruntime/core/platform/EigenNonBlockingThreadPool.h

@@ -1129,7 +1129,7 @@ class ThreadPoolTempl : public onnxruntime::concurrency::ExtendedThreadPoolInter
   //
   // Ensure that the ThreadPoolParallelSection has sufficient workers to
   // execute a loop with degree of parallelism n.  We track the number
-  // of workers already avaiable to the parallel section, prior to
+  // of workers already available to the parallel section, prior to
   // submitting tasks to the work queues to make up the total.
   //
   // Each worker will call in to worker_fn(idx) with a per-worker thread

include/onnxruntime/core/providers/cuda/cuda_context.h

@@ -53,21 +53,25 @@ struct CudaContext : public CustomOpContext {
     cudnn_conv_use_max_workspace = FetchResource<bool>(kernel_ctx, CudaResource::cudnn_conv_use_max_workspace_t);
 
     cudnn_conv1d_pad_to_nc1d = FetchResource<bool>(kernel_ctx, CudaResource::cudnn_conv1d_pad_to_nc1d_t);
-    enable_skip_layer_norm_strict_mode = FetchResource<bool>(kernel_ctx, CudaResource::enable_skip_layer_norm_strict_mode_t);
+    enable_skip_layer_norm_strict_mode = FetchResource<bool>(
+        kernel_ctx, CudaResource::enable_skip_layer_norm_strict_mode_t);
     prefer_nhwc = FetchResource<bool>(kernel_ctx, CudaResource::prefer_nhwc_t);
     use_tf32 = FetchResource<bool>(kernel_ctx, CudaResource::use_tf32_t);
   }
 
   template <typename T>
   T FetchResource(const OrtKernelContext& kernel_ctx, CudaResource resource_type) {
     if constexpr (sizeof(T) > sizeof(void*)) {
-      ORT_CXX_API_THROW("void* is not large enough to hold resource type: " + std::to_string(resource_type), OrtErrorCode::ORT_INVALID_ARGUMENT);
+      ORT_CXX_API_THROW("void* is not large enough to hold resource type: " + std::to_string(resource_type),
+                        OrtErrorCode::ORT_INVALID_ARGUMENT);
     }
     const auto& ort_api = Ort::GetApi();
     void* resource = {};
-    OrtStatus* status = ort_api.KernelContext_GetResource(&kernel_ctx, ORT_CUDA_RESOUCE_VERSION, resource_type, &resource);
+    OrtStatus* status = ort_api.KernelContext_GetResource(
+        &kernel_ctx, ORT_CUDA_RESOURCE_VERSION, resource_type, &resource);
     if (status) {
-      ORT_CXX_API_THROW("Failed to fetch cuda ep resource, resouce type: " + std::to_string(resource_type), OrtErrorCode::ORT_RUNTIME_EXCEPTION);
+      ORT_CXX_API_THROW("Failed to fetch cuda ep resource, resource type: " + std::to_string(resource_type),
+                        OrtErrorCode::ORT_RUNTIME_EXCEPTION);
     }
     T t = {};
     memcpy(&t, &resource, sizeof(T));

include/onnxruntime/core/providers/cuda/cuda_resource.h

@@ -3,7 +3,7 @@
 
 #include "core/providers/resource.h"
 
-#define ORT_CUDA_RESOUCE_VERSION 3
+#define ORT_CUDA_RESOURCE_VERSION 3
 
 enum CudaResource : int {
   cuda_stream_t = cuda_resource_offset,  // 10000

include/onnxruntime/core/providers/rocm/rocm_context.h

@@ -23,21 +23,24 @@ struct RocmContext : public CustomOpContext {
     void* resource = {};
     OrtStatus* status = nullptr;
 
-    status = ort_api.KernelContext_GetResource(&kernel_ctx, ORT_ROCM_RESOUCE_VERSION, RocmResource::hip_stream_t, &resource);
+    status = ort_api.KernelContext_GetResource(
+        &kernel_ctx, ORT_ROCM_RESOURCE_VERSION, RocmResource::hip_stream_t, &resource);
     if (status) {
       ORT_CXX_API_THROW("failed to fetch hip stream", OrtErrorCode::ORT_RUNTIME_EXCEPTION);
     }
     hip_stream = reinterpret_cast<hipStream_t>(resource);
 
     resource = {};
-    status = ort_api.KernelContext_GetResource(&kernel_ctx, ORT_ROCM_RESOUCE_VERSION, RocmResource::miopen_handle_t, &resource);
+    status = ort_api.KernelContext_GetResource(
+        &kernel_ctx, ORT_ROCM_RESOURCE_VERSION, RocmResource::miopen_handle_t, &resource);
     if (status) {
       ORT_CXX_API_THROW("failed to fetch miopen handle", OrtErrorCode::ORT_RUNTIME_EXCEPTION);
     }
     miopen_handle = reinterpret_cast<miopenHandle_t>(resource);
 
     resource = {};
-    status = ort_api.KernelContext_GetResource(&kernel_ctx, ORT_ROCM_RESOUCE_VERSION, RocmResource::rocblas_handle_t, &resource);
+    status = ort_api.KernelContext_GetResource(
+        &kernel_ctx, ORT_ROCM_RESOURCE_VERSION, RocmResource::rocblas_handle_t, &resource);
     if (status) {
       ORT_CXX_API_THROW("failed to fetch rocblas handle", OrtErrorCode::ORT_RUNTIME_EXCEPTION);
     }

include/onnxruntime/core/providers/rocm/rocm_resource.h

@@ -3,7 +3,7 @@
 
 #include "core/providers/resource.h"
 
-#define ORT_ROCM_RESOUCE_VERSION 1
+#define ORT_ROCM_RESOURCE_VERSION 1
 
 enum RocmResource : int {
   hip_stream_t = rocm_resource_offset,

include/onnxruntime/core/session/onnxruntime_c_api.h

@@ -473,13 +473,13 @@ typedef struct OrtCUDAProviderOptions {
 
   /** \brief Enable TunableOp for using.
    *   Set it to 1/0 to enable/disable TunableOp. Otherwise, it is disabled by default.
-   *   This option can be overriden by environment variable ORT_CUDA_TUNABLE_OP_ENABLE.
+   *   This option can be overridden by environment variable ORT_CUDA_TUNABLE_OP_ENABLE.
    */
   int tunable_op_enable;
 
   /** \brief Enable TunableOp for tuning.
    *   Set it to 1/0 to enable/disable TunableOp tuning. Otherwise, it is disabled by default.
-   *   This option can be overriden by environment variable ORT_CUDA_TUNABLE_OP_TUNING_ENABLE.
+   *   This option can be overridden by environment variable ORT_CUDA_TUNABLE_OP_TUNING_ENABLE.
    */
   int tunable_op_tuning_enable;
 
@@ -562,13 +562,13 @@ typedef struct OrtROCMProviderOptions {
 
   /** \brief Enable TunableOp for using.
    *   Set it to 1/0 to enable/disable TunableOp. Otherwise, it is disabled by default.
-   *   This option can be overriden by environment variable ORT_ROCM_TUNABLE_OP_ENABLE.
+   *   This option can be overridden by environment variable ORT_ROCM_TUNABLE_OP_ENABLE.
    */
   int tunable_op_enable;
 
   /** \brief Enable TunableOp for tuning.
    *   Set it to 1/0 to enable/disable TunableOp tuning. Otherwise, it is disabled by default.
-   *   This option can be overriden by environment variable ORT_ROCM_TUNABLE_OP_TUNING_ENABLE.
+   *   This option can be overridden by environment variable ORT_ROCM_TUNABLE_OP_TUNING_ENABLE.
    */
   int tunable_op_tuning_enable;
 
@@ -2798,7 +2798,7 @@ struct OrtApi {
    * "initial_growth_chunk_size_bytes": (Possible) Size of the second allocation in the arena.
    *  Only relevant if arena strategy is `kNextPowerOfTwo`. Use -1 to allow ORT to choose the default.
    * "max_power_of_two_extend_bytes": The maximum enxtend size if arena strategy is `kNextPowerOfTwo`.
-   *  It is not an allocation limit, it is only a limit for extention when requested byte is less than the limit.
+   *  It is not an allocation limit, it is only a limit for extension when requested byte is less than the limit.
    *  When requested bytes is more than the limit, allocator will still return as requested.
    *  Use -1 to allow ORT to choose the default 1GB for max_power_of_two_extend_bytes.
    *  Ultimately, the allocation size is determined by the allocation memory request.
@@ -4467,13 +4467,14 @@ struct OrtApi {
    * E.g. a cuda stream or a cublas handle
    *
    * \param context - Kernel context
-   * \param resouce_version - Version of the resource
+   * \param resource_version - Version of the resource
    * \param resource_id - Type of resource
    * \param resource - A pointer to returned resource
    *
    * \since Version 1.16.
    */
-  ORT_API2_STATUS(KernelContext_GetResource, _In_ const OrtKernelContext* context, _In_ int resouce_version, _In_ int resource_id, _Outptr_ void** resource);
+  ORT_API2_STATUS(KernelContext_GetResource, _In_ const OrtKernelContext* context, _In_ int resource_version,
+                  _In_ int resource_id, _Outptr_ void** resource);
 
   /** \brief Set user logging function
    *
@@ -4528,10 +4529,10 @@ struct OrtApi {
   ORT_API2_STATUS(ShapeInferContext_GetAttribute, _In_ const OrtShapeInferContext* context, _In_ const char* attr_name, _Outptr_ const OrtOpAttr** attr);
 
   /**
-   * Set type and shape info of an ouput
+   * Set type and shape info of an output
    *
    * \param[in] context
-   * \param[in] index The index of the ouput
+   * \param[in] index The index of the output
    * \param[out] info Type shape info of the output
    *
    * \since Version 1.17.

include/onnxruntime/core/session/onnxruntime_lite_custom_op.h

@@ -403,7 +403,7 @@ using Variadic = TensorArray;
 Note:
 OrtLiteCustomOp inherits from OrtCustomOp to bridge tween a custom func/struct and ort core.
 The lifetime of an OrtLiteCustomOp instance is managed by customer code, not ort, so:
-1. DO NOT cast OrtLiteCustomOp to OrtCustomOp and release since there is no virtual destructor in the hierachy.
+1. DO NOT cast OrtLiteCustomOp to OrtCustomOp and release since there is no virtual destructor in the hierarchy.
 2. OrtLiteCustomFunc and OrtLiteCustomStruct, as two sub-structs, can be released in form of OrtLiteCustomOp since all members are kept in the OrtLiteCustomOp,
    hence memory could still be recycled properly.
 Further, OrtCustomOp is a c struct bearing no v-table, so offspring structs are by design to be of zero virtual functions to maintain cast safety.

java/build.gradle

@@ -54,7 +54,7 @@ java {
 	targetCompatibility = JavaVersion.VERSION_1_8
 }
 
-// This jar tasks serves as a CMAKE signalling
+// This jar tasks serves as a CMAKE signaling
 // mechanism. The jar will be overwritten by allJar task
 jar {
 }

java/src/main/java/ai/onnxruntime/OnnxRuntime.java

@@ -438,7 +438,7 @@ private static String mapLibraryName(String library) {
   /**
    * Extracts the providers array from the C API, converts it into an EnumSet.
    *
-   * <p>Throws IllegalArgumentException if a provider isn't recognised (note this exception should
+   * <p>Throws IllegalArgumentException if a provider isn't recognized (note this exception should
    * only happen during development of ONNX Runtime, if it happens at any other point, file an issue
    * on <a href="https://github.com/microsoft/onnxruntime">GitHub</a>).
    *

java/src/main/java/ai/onnxruntime/providers/package-info.java

@@ -3,5 +3,5 @@
  * Licensed under the MIT License.
  */
 
-/** Classes for controlling the behaviour of ONNX Runtime Execution Providers. */
+/** Classes for controlling the behavior of ONNX Runtime Execution Providers. */
 package ai.onnxruntime.providers;

java/src/test/java/sample/ScoreMNIST.java

@@ -242,7 +242,7 @@ public static void writeDataSKL(float[][] data, int[] indices, float[] values) {
   /**
    * Find the maximum probability and return it's index.
    *
-   * @param probabilities The probabilites.
+   * @param probabilities The probabilities.
    * @return The index of the max.
    */
   public static int pred(float[] probabilities) {

js/web/lib/onnxjs/backends/webgl/glsl-coordinate-lib.ts

@@ -1234,7 +1234,7 @@ export class CoordsGlslLib extends GlslLib {
   }
 
   /**
-   * This is the main function to map from the given texture coordiantes (s,t)
+   * This is the main function to map from the given texture coordinates (s,t)
    * to logical indices for the output
    * There will only be one single variation of this
    * Also see coordsToOffset and offsetToIndices for input-specific versions

js/web/lib/onnxjs/backends/webgl/ops/pack.ts

@@ -85,7 +85,7 @@ function getOutOfBoundsCondition(rank: number, shape: readonly number[], dims: s
 }
 
 /**
- * code snippet to sample input texture with output coordiantes
+ * code snippet to sample input texture with output coordinates
  */
 function getOutput(shape: readonly number[], dims: string[]): string {
   const rank = shape.length;

onnxruntime/contrib_ops/cpu/attnlstm/deep_cpu_attn_lstm.h

@@ -19,7 +19,7 @@ using onnxruntime::rnn::detail::Direction;
 using onnxruntime::rnn::detail::MakeDirection;
 
 // The class represents DeepCPU implementation of a long short term memory (LSTM) plus a Bahdanau Attention wraper.
-// The equivilent python usage could be checked int the corresponding op test directory, attention_lstm_data_gen.py.
+// The equivalent python usage could be checked int the corresponding op test directory, attention_lstm_data_gen.py.
 // Also please note that detail implementation re-used lot of code from current ONNXRuntime LSTM operator, refactor
 // is needed in future if this is become part of ONNX.
 class DeepCpuAttnLstmOp final : public OpKernel {

onnxruntime/contrib_ops/cpu/transformers/sampling_cpu_helper.h

@@ -152,7 +152,7 @@ Status Sample(AllocatorPtr& allocator,
                                                         1,
                                                         generator,
                                                         *sampled_idx));
-  // TODO: update presense_mask()
+  // TODO: update presence_mask()
 #ifdef DEBUG_GENERATION
   dumper->Print("sampled_idx", *sampled_idx);
 #endif

onnxruntime/core/codegen/common/common.cc

@@ -159,7 +159,7 @@ std::unique_ptr<ComputeCapability> ToCapacity(const onnxruntime::GraphViewer& gr
     ORT_THROW_IF_ERROR(node.ForEachWithIndex(node.ImplicitInputDefs(), process_input_fn));
 
     // Handle outouts
-    // two cases are considerd as outputs
+    // two cases are considered as outputs
     // 1. Output NodeArg is not used by any Node
     // 2. Output NodeArg is used by at least one Node out of this subgraph.
     //    Note a NodeArg can be used by Nodes in and out of the subgraph at the same time.

onnxruntime/core/codegen/mti/common.h

@@ -8,7 +8,7 @@
 
 #define MTI_ASSERT(condition)                                           \
   if (!(condition)) {                                                   \
-    std::string error_msg = "Not satsified: " #condition                \
+    std::string error_msg = "Not satisfied: " #condition                \
                             ": line " +                                 \
                             std::to_string(__LINE__) +                  \
                             " in file " + std::string(__FILE__) + "\n"; \

onnxruntime/core/codegen/passes/scheduler/schedule_utils.cc

@@ -74,7 +74,7 @@ bool ShouldTryVectorization(
 // Check the schedule of tensor
 // If it is not scheduled, try to vectorize it.
 // Note TryVectorization has to use with compute_root.
-// Therefore, there is a safty check of tensor's schedule
+// Therefore, there is a safety check of tensor's schedule
 bool TryVectorization(
     const tvm::Tensor& tensor,
     int64_t natural_vector_size,
@@ -124,7 +124,7 @@ bool TryVectorization(
 // Check the schedule of tensor
 // If it is not scheduled, try to add compute_inline on it.
 // Note TryInlineSchedule cannot be used with compute_root.
-// Therefore, there is a safty check of tensor's schedule.
+// Therefore, there is a safety check of tensor's schedule.
 bool TryInlineSchedule(
     const tvm::Tensor& tensor,
     ScheduleContext& ctx) {

onnxruntime/core/codegen/passes/scheduler/schedule_utils.h

@@ -34,7 +34,7 @@ bool ShouldTryVectorization(
 // Check the schedule of tensor
 // If it is not scheduled, try to vectorize it.
 // Note TryVectorization has to use with compute_root.
-// Therefore, there is a safty check of tensor's schedule
+// Therefore, there is a safety check of tensor's schedule
 bool TryVectorization(
     const tvm::Tensor& tensor,
     int64_t natural_vector_size,
@@ -43,7 +43,7 @@ bool TryVectorization(
 // Check the schedule of tensor
 // If it is not scheduled, try to add compute_inline on it.
 // Note TryInlineSchedule cannot be used with compute_root.
-// Therefore, there is a safty check of tensor's schedule.
+// Therefore, there is a safety check of tensor's schedule.
 bool TryInlineSchedule(
     const tvm::Tensor& tensor,
     ScheduleContext& ctx);

onnxruntime/core/codegen/passes/scheduler/tvm_schedule_builder.cc

@@ -39,7 +39,7 @@ void TVMScheduleBuilder::DumpAllSchedulers() const {
 
     d->ForEach([&stream](const std::string& key, Scheduler* op) {
       stream << "Key " << key
-             << ", Creater " << op->Name() << std::endl;
+             << ", Creator " << op->Name() << std::endl;
     });
 
     ++count;

onnxruntime/core/codegen/passes/weight_layout/weight_layout.h

@@ -13,7 +13,7 @@ namespace tvm_codegen {
 
 using CoordTransFunc = std::function<tvm::Array<tvm::Expr>(const tvm::Array<tvm::Expr>&)>;
 
-// WeightLayout is data layout trasnformer for weight/initializer
+// WeightLayout is data layout transformer for weight/initializer
 class WeightLayout {
  public:
   // Static function to return unique string as a key