clang-tidy fixes part 2 (#16938)

Subset of improvements to the code base proposed by the latest version of clang-tidy.

Authors:
  - Vyas Ramasubramani (https://github.com/vyasr)

Approvers:
  - Vukasin Milovanovic (https://github.com/vuule)

URL: #16938

cpp/src/datetime/timezone.cpp

@@ -38,7 +38,7 @@ std::string const tzif_system_directory = "/usr/share/zoneinfo/";
 struct timezone_file_header {
   uint32_t magic;          ///< "TZif"
   uint8_t version;         ///< 0:version1, '2':version2, '3':version3
-  uint8_t reserved15[15];  ///< unused, reserved for future use
+  uint8_t reserved15[15];  ///< unused, reserved for future use // NOLINT
   uint32_t isutccnt;       ///< number of UTC/local indicators contained in the body
   uint32_t isstdcnt;       ///< number of standard/wall indicators contained in the body
   uint32_t leapcnt;        ///< number of leap second records contained in the body

cpp/src/dictionary/dictionary_column_view.cpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2020, NVIDIA CORPORATION.
+ * Copyright (c) 2020-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -36,8 +36,7 @@ column_view dictionary_column_view::indices() const noexcept { return child(0);
 
 column_view dictionary_column_view::get_indices_annotated() const noexcept
 {
-  return column_view(
-    indices().type(), size(), indices().head(), null_mask(), null_count(), offset());
+  return {indices().type(), size(), indices().head(), null_mask(), null_count(), offset()};
 }
 
 column_view dictionary_column_view::keys() const noexcept { return child(1); }

cpp/src/interop/dlpack.cpp

@@ -118,8 +118,8 @@ DLDataType data_type_to_DLDataType(data_type type)
 
 // Context object to own memory allocated for DLManagedTensor
 struct dltensor_context {
-  int64_t shape[2];
-  int64_t strides[2];
+  int64_t shape[2];    // NOLINT
+  int64_t strides[2];  // NOLINT
   rmm::device_buffer buffer;
 
   static void deleter(DLManagedTensor* arg)

cpp/src/io/avro/avro.cpp

@@ -199,7 +199,7 @@ bool container::parse(file_metadata* md, size_t max_num_rows, size_t first_row)
     // Read the next sync markers and ensure they match the first ones we
     // encountered.  If they don't, we have to assume the data is corrupted,
     // and thus, we terminate processing immediately.
-    uint64_t const sync_marker[] = {get_raw<uint64_t>(), get_raw<uint64_t>()};
+    std::array const sync_marker = {get_raw<uint64_t>(), get_raw<uint64_t>()};
     bool valid_sync_markers =
       ((sync_marker[0] == md->sync_marker[0]) && (sync_marker[1] == md->sync_marker[1]));
     if (!valid_sync_markers) { return false; }

cpp/src/io/avro/avro.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -19,6 +19,7 @@
 #include "avro_common.hpp"
 
 #include <algorithm>
+#include <array>
 #include <cstddef>
 #include <cstdint>
 #include <cstdio>
@@ -100,15 +101,15 @@ struct column_desc {
  */
 struct file_metadata {
   std::map<std::string, std::string> user_data;
-  std::string codec         = "";
-  uint64_t sync_marker[2]   = {0, 0};
-  size_t metadata_size      = 0;
-  size_t total_data_size    = 0;
-  size_t selected_data_size = 0;
-  size_type num_rows        = 0;
-  size_type skip_rows       = 0;
-  size_type total_num_rows  = 0;
-  uint32_t max_block_size   = 0;
+  std::string codec                   = "";
+  std::array<uint64_t, 2> sync_marker = {0, 0};
+  size_t metadata_size                = 0;
+  size_t total_data_size              = 0;
+  size_t selected_data_size           = 0;
+  size_type num_rows                  = 0;
+  size_type skip_rows                 = 0;
+  size_type total_num_rows            = 0;
+  uint32_t max_block_size             = 0;
   std::vector<schema_entry> schema;
   std::vector<block_desc_s> block_list;
   std::vector<column_desc> columns;

cpp/src/io/comp/uncomp.cpp

@@ -42,7 +42,7 @@ struct gz_file_header_s {
   uint8_t id2;        // 0x8b
   uint8_t comp_mthd;  // compression method (0-7=reserved, 8=deflate)
   uint8_t flags;      // flags (GZIPHeaderFlag)
-  uint8_t mtime[4];   // If non-zero: modification time (Unix format)
+  uint8_t mtime[4];   // If non-zero: modification time (Unix format)  // NOLINT
   uint8_t xflags;     // Extra compressor-specific flags
   uint8_t os;         // OS id
 };
@@ -103,7 +103,7 @@ struct zip_lfh_s {
 };
 
 struct bz2_file_header_s {
-  uint8_t sig[3];  // "BZh"
+  uint8_t sig[3];  // "BZh" // NOLINT
   uint8_t blksz;   // block size 1..9 in 100kB units (post-RLE)
 };
 

cpp/src/io/parquet/parquet_gpu.hpp

@@ -294,7 +294,8 @@ struct PageInfo {
   int32_t uncompressed_page_size;  // uncompressed data size in bytes
   // for V2 pages, the def and rep level data is not compressed, and lacks the 4-byte length
   // indicator. instead the lengths for these are stored in the header.
-  int32_t lvl_bytes[level_type::NUM_LEVEL_TYPES];  // length of the rep/def levels (V2 header)
+  int32_t                                    // NOLINT
+    lvl_bytes[level_type::NUM_LEVEL_TYPES];  // length of the rep/def levels (V2 header)
   // Number of values in this data page or dictionary.
   // Important : the # of input values does not necessarily
   // correspond to the number of rows in the output. It just reflects the number
@@ -345,7 +346,7 @@ struct PageInfo {
   PageNestingDecodeInfo* nesting_decode;
 
   // level decode buffers
-  uint8_t* lvl_decode_buf[level_type::NUM_LEVEL_TYPES];
+  uint8_t* lvl_decode_buf[level_type::NUM_LEVEL_TYPES];  // NOLINT
 
   // temporary space for decoding DELTA_BYTE_ARRAY encoded strings
   int64_t temp_string_size;
@@ -431,14 +432,14 @@ struct ColumnChunkDesc {
   size_t num_values{};               // total number of values in this column
   size_t start_row{};                // file-wide, absolute starting row of this chunk
   uint32_t num_rows{};               // number of rows in this chunk
-  int16_t max_level[level_type::NUM_LEVEL_TYPES]{};  // max definition/repetition level
-  int16_t max_nesting_depth{};                       // max nesting depth of the output
-  int32_t type_length{};                             // type length from schema (for FLBA only)
-  Type physical_type{};                              // parquet physical data type
-  uint8_t
-    level_bits[level_type::NUM_LEVEL_TYPES]{};  // bits to encode max definition/repetition levels
-  int32_t num_data_pages{};                     // number of data pages
-  int32_t num_dict_pages{};                     // number of dictionary pages
+  int16_t max_level[level_type::NUM_LEVEL_TYPES]{};   // max definition/repetition level  // NOLINT
+  int16_t max_nesting_depth{};                        // max nesting depth of the output
+  int32_t type_length{};                              // type length from schema (for FLBA only)
+  Type physical_type{};                               // parquet physical data type
+  uint8_t level_bits[level_type::NUM_LEVEL_TYPES]{};  // bits to encode max   // NOLINT
+                                                      // definition/repetition levels
+  int32_t num_data_pages{};                           // number of data pages
+  int32_t num_dict_pages{};                           // number of dictionary pages
   PageInfo const* dict_page{};
   string_index_pair* str_dict_index{};  // index for string dictionary
   bitmask_type** valid_map_base{};      // base pointers of valid bit map for this column

cpp/src/jit/parser.cpp

@@ -19,16 +19,14 @@
 #include <cudf/utilities/error.hpp>
 
 #include <algorithm>
-#include <cctype>
-#include <map>
 #include <set>
 #include <string>
 #include <utility>
 #include <vector>
 
 namespace cudf {
 namespace jit {
-constexpr char percent_escape[] = "_";
+constexpr char percent_escape[] = "_";  // NOLINT
 
 inline bool is_white(char const c) { return c == ' ' || c == '\n' || c == '\r' || c == '\t'; }
 

cpp/src/strings/regex/regcomp.cpp

@@ -35,7 +35,7 @@ namespace strings {
 namespace detail {
 namespace {
 // Bitmask of all operators
-#define OPERATOR_MASK 0200
+enum { OPERATOR_MASK = 0200 };
 enum OperatorType : int32_t {
   START        = 0200,  // Start, used for marker on stack
   LBRA_NC      = 0203,  // non-capturing group
@@ -50,7 +50,7 @@ enum OperatorType : int32_t {
   COUNTED_LAZY = 0215,
   NOP          = 0302,  // No operation, internal use only
 };
-#define ITEM_MASK 0300
+enum { ITEM_MASK = 0300 };
 
 static reclass cclass_w(CCLASS_W);   // \w
 static reclass cclass_s(CCLASS_S);   // \s

cpp/src/utilities/stream_pool.cpp

@@ -82,7 +82,7 @@ class rmm_cuda_stream_pool : public cuda_stream_pool {
     return streams;
   }
 
-  std::size_t get_stream_pool_size() const override { return STREAM_POOL_SIZE; }
+  [[nodiscard]] std::size_t get_stream_pool_size() const override { return STREAM_POOL_SIZE; }
 };
 
 /**