parquet 0.4.2 → 0.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8e05c4544ed72011e1a877befa04e9c29f9d61d6f5663095f3356735c2411299
-  data.tar.gz: 6642f5575e9802a3eb05af6a4523fcc198644a6b465a2fa911c35985f27943f2
+  metadata.gz: 0d72c16371c10a011af5118f2915de9bbeb33cde133369bdac2050e3c035572e
+  data.tar.gz: b39c6ec9a8232eca5b5b156bf28992ed59c05e9a36e4c13db2b8933a74485ba0
 SHA512:
-  metadata.gz: b68013d8de3a6454d4ebddaae549fb4c02d0a6102718259b9a43133ceed8803060fc04fd06287e041ee0afdf0cd6c3556ff2c6a41d61a6acd226ef239caab090
-  data.tar.gz: 074f9faf08f2a178322cf74667ca93c24561cb49b4b91f7f98b653ea61a561628c3b06c4afe9d0a6e13410479fbd87482b88ee09d0dfbc91c554b820350fdad3
+  metadata.gz: c7f338b1d010fa59c2344065b233ff20a08d4a17c6ca987ef72677150dd1cbf55d134855585d68e187b748dc5121f13d5e86cb82aabc1eeb3562a3326aca459c
+  data.tar.gz: 69eaa6b133123944138a826612a7b48d9f87acb202ecbe172e253be02a1a1c7009e3d7182e8bb31ae423098bc34bb5dddc4ce042453f0d1cb41505d56d02c21e

data/Cargo.lock

@@ -63,9 +63,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-array"
-version = "54.1.0"
+version = "54.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fb4a06d507f54b70a277be22a127c8ffe0cec6cd98c0ad8a48e77779bbda8223"
+checksum = "57a4a6d2896083cfbdf84a71a863b22460d0708f8206a8373c52e326cc72ea1a"
 dependencies = [
  "ahash",
  "arrow-buffer",
@@ -79,9 +79,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-buffer"
-version = "54.1.0"
+version = "54.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d69d326d5ad1cb82dcefa9ede3fee8fdca98f9982756b16f9cb142f4aa6edc89"
+checksum = "cef870583ce5e4f3b123c181706f2002fb134960f9a911900f64ba4830c7a43a"
 dependencies = [
  "bytes",
  "half",
@@ -90,9 +90,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-cast"
-version = "54.1.0"
+version = "54.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "626e65bd42636a84a238bed49d09c8777e3d825bf81f5087a70111c2831d9870"
+checksum = "1ac7eba5a987f8b4a7d9629206ba48e19a1991762795bbe5d08497b7736017ee"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -110,9 +110,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-data"
-version = "54.1.0"
+version = "54.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1858e7c7d01c44cf71c21a85534fd1a54501e8d60d1195d0d6fbcc00f4b10754"
+checksum = "b095e8a4f3c309544935d53e04c3bfe4eea4e71c3de6fe0416d1f08bb4441a83"
 dependencies = [
  "arrow-buffer",
  "arrow-schema",
@@ -122,9 +122,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-ipc"
-version = "54.1.0"
+version = "54.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a6bb3f727f049884c7603f0364bc9315363f356b59e9f605ea76541847e06a1e"
+checksum = "65c63da4afedde2b25ef69825cd4663ca76f78f79ffe2d057695742099130ff6"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -135,15 +135,15 @@ dependencies = [
 
 [[package]]
 name = "arrow-schema"
-version = "54.1.0"
+version = "54.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "105f01ec0090259e9a33a9263ec18ff223ab91a0ea9fbc18042f7e38005142f6"
+checksum = "0f40f6be8f78af1ab610db7d9b236e21d587b7168e368a36275d2e5670096735"
 
 [[package]]
 name = "arrow-select"
-version = "54.1.0"
+version = "54.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f690752fdbd2dee278b5f1636fefad8f2f7134c85e20fd59c4199e15a39a6807"
+checksum = "ac265273864a820c4a179fc67182ccc41ea9151b97024e1be956f0f2369c2539"
 dependencies = [
  "ahash",
  "arrow-array",
@@ -247,9 +247,9 @@ checksum = "f61dac84819c6588b558454b194026eb1f09c293b9036ae9b159e74e73ab6cf9"
 
 [[package]]
 name = "cc"
-version = "1.2.11"
+version = "1.2.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e4730490333d58093109dc02c23174c3f4d490998c3fed3cc8e82d57afedb9cf"
+checksum = "c736e259eea577f443d5c86c304f9f4ae0295c43f3ba05c21f1d66b5f06001af"
 dependencies = [
  "jobserver",
  "libc",
@@ -273,14 +273,14 @@ checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
 [[package]]
 name = "chrono"
-version = "0.4.39"
+version = "0.4.40"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7e36cc9d416881d2e24f9a963be5fb1cd90966419ac844274161d10488b3e825"
+checksum = "1a7964611d71df112cb1730f2ee67324fcf4d0fc6606acbbe9bfe06df124637c"
 dependencies = [
  "android-tzdata",
  "iana-time-zone",
  "num-traits",
- "windows-targets",
+ "windows-link",
 ]
 
 [[package]]
@@ -337,9 +337,9 @@ checksum = "43da5946c66ffcc7745f48db692ffbb10a83bfe0afd96235c5c2a4fb23994929"
 
 [[package]]
 name = "either"
-version = "1.13.0"
+version = "1.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "60b1af1c220855b6ceac025d3f6ecdd2b7c4894bfe9cd9bda4fbb4bc7c0d4cf0"
+checksum = "b7914353092ddf589ad78f25c5c1c21b7f80b0ff8621e7c814c3485b5306da9d"
 
 [[package]]
 name = "errno"
@@ -369,9 +369,9 @@ dependencies = [
 
 [[package]]
 name = "flate2"
-version = "1.0.35"
+version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c936bfdafb507ebbf50b8074c54fa31c5be9a1e7e5f467dd659697041407d07c"
+checksum = "11faaf5a5236997af9848be0bef4db95824b1d534ebc64d0f0c6cf3e67bd38dc"
 dependencies = [
  "crc32fast",
  "miniz_oxide",
@@ -498,9 +498,9 @@ dependencies = [
 
 [[package]]
 name = "jiff"
-version = "0.1.29"
+version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c04ef77ae73f3cf50510712722f0c4e8b46f5aaa1bf5ffad2ae213e6495e78e5"
+checksum = "3590fea8e9e22d449600c9bbd481a8163bef223e4ff938e5f55899f8cf1adb93"
 dependencies = [
  "jiff-tzdb-platform",
  "log",
@@ -622,9 +622,9 @@ dependencies = [
 
 [[package]]
 name = "libc"
-version = "0.2.169"
+version = "0.2.170"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5aba8db14291edd000dfcc4d620c7ebfb122c613afb886ca8803fa4e128a20a"
+checksum = "875b3680cb2f8f71bdcf9a30f38d48282f5d3c95cbf9b3fa57269bb5d5c06828"
 
 [[package]]
 name = "libloading"
@@ -660,9 +660,9 @@ checksum = "d26c52dbd32dccf2d10cac7725f8eae5296885fb5703b261f7d0a0739ec807ab"
 
 [[package]]
 name = "log"
-version = "0.4.25"
+version = "0.4.26"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "04cbf5b083de1c7e0222a7a51dbfdba1cbe1c6ab0b15e29fff3f6c077fd9cd9f"
+checksum = "30bde2b3dc3671ae49d8e2e9f044c7c005836e7a023ee57cffa25ab82764bb9e"
 
 [[package]]
 name = "lz4_flex"
@@ -719,9 +719,9 @@ checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
 
 [[package]]
 name = "miniz_oxide"
-version = "0.8.3"
+version = "0.8.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b8402cab7aefae129c6977bb0ff1b8fd9a04eb5b51efc50a70bea51cda0c7924"
+checksum = "8e3e04debbb59698c15bacbb6d93584a8c0ca9cc3213cb423d31f760d8843ce5"
 dependencies = [
  "adler2",
 ]
@@ -812,9 +812,9 @@ dependencies = [
 
 [[package]]
 name = "once_cell"
-version = "1.20.2"
+version = "1.20.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1261fe7e33c73b354eab43b1273a57c8f967d0391e80353e51f764ac02cf6775"
+checksum = "945462a4b81e43c4e3ba96bd7b49d834c6f61198356aa858733bc4acf3cbe62e"
 
 [[package]]
 name = "ordered-float"
@@ -833,12 +833,13 @@ dependencies = [
  "arrow-array",
  "arrow-schema",
  "bytes",
+ "either",
  "itertools 0.14.0",
  "jemallocator",
  "jiff",
  "magnus",
  "mimalloc",
- "parquet 54.1.0",
+ "parquet 54.2.0",
  "rand",
  "rb-sys",
  "simdutf8",
@@ -848,9 +849,9 @@ dependencies = [
 
 [[package]]
 name = "parquet"
-version = "54.1.0"
+version = "54.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a01a0efa30bbd601ae85b375c728efdb211ade54390281628a7b16708beb235"
+checksum = "761c44d824fe83106e0600d2510c07bf4159a4985bf0569b513ea4288dc1b4fb"
 dependencies = [
  "ahash",
  "arrow-array",
@@ -895,9 +896,9 @@ checksum = "953ec861398dccce10c670dfeaf3ec4911ca479e9c02154b3a215178c5f566f2"
 
 [[package]]
 name = "portable-atomic"
-version = "1.10.0"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "280dc24453071f1b63954171985a0b0d30058d287960968b9b2aca264c8d4ee6"
+checksum = "350e9b48cbc6b0e028b0473b114454c6316e57336ee184ceab6e53f72c178b3e"
 
 [[package]]
 name = "portable-atomic-util"
@@ -943,7 +944,7 @@ checksum = "3779b94aeb87e8bd4e834cee3650289ee9e0d5677f976ecdb6d219e5f4f6cd94"
 dependencies = [
  "rand_chacha",
  "rand_core",
- "zerocopy 0.8.15",
+ "zerocopy 0.8.20",
 ]
 
 [[package]]
@@ -958,12 +959,12 @@ dependencies = [
 
 [[package]]
 name = "rand_core"
-version = "0.9.0"
+version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b08f3c9802962f7e1b25113931d94f43ed9725bebc59db9d0c3e9a23b67e15ff"
+checksum = "7a509b1a2ffbe92afab0e55c8fd99dea1c280e8171bd2d88682bb20bc41cbc2c"
 dependencies = [
  "getrandom 0.3.1",
- "zerocopy 0.8.15",
+ "zerocopy 0.8.20",
 ]
 
 [[package]]
@@ -1079,18 +1080,18 @@ checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
 
 [[package]]
 name = "serde"
-version = "1.0.217"
+version = "1.0.218"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "02fc4265df13d6fa1d00ecff087228cc0a2b5f3c0e87e258d8b94a156e984c70"
+checksum = "e8dfc9d19bdbf6d17e22319da49161d5d0108e4188e8b680aef6299eed22df60"
 dependencies = [
  "serde_derive",
 ]
 
 [[package]]
 name = "serde_derive"
-version = "1.0.217"
+version = "1.0.218"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5a9bf7cf98d04a2b28aead066b7496853d4779c9cc183c440dbac457641e19a0"
+checksum = "f09503e191f4e797cb8aac08e9a4a4695c5edf6a2e70e376d961ddd5c969f82b"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -1099,9 +1100,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.138"
+version = "1.0.139"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d434192e7da787e94a6ea7e9670b26a036d0ca41e0b7efb2676dd32bae872949"
+checksum = "44f86c3acccc9c65b153fe1b85a3be07fe5515274ec9f0653b4a0875731c72a6"
 dependencies = [
  "itoa",
  "memchr",
@@ -1152,9 +1153,9 @@ dependencies = [
 
 [[package]]
 name = "tempfile"
-version = "3.16.0"
+version = "3.17.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38c246215d7d24f48ae091a2902398798e05d978b24315d6efbc00ede9a8bb91"
+checksum = "22e5a0acb1f3f55f65cc4a866c361b2fb2a0ff6366785ae6fbb5f85df07ba230"
 dependencies = [
  "cfg-if",
  "fastrand",
@@ -1216,9 +1217,9 @@ dependencies = [
 
 [[package]]
 name = "unicode-ident"
-version = "1.0.16"
+version = "1.0.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a210d160f08b701c8721ba1c726c11662f877ea6b7094007e1ca9a1041945034"
+checksum = "00e2473a93778eb0bad35909dff6a10d28e63f792f16ed15e404fca9d5eeedbe"
 
 [[package]]
 name = "version_check"
@@ -1308,6 +1309,12 @@ dependencies = [
  "windows-targets",
 ]
 
+[[package]]
+name = "windows-link"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6dccfd733ce2b1753b03b6d3c65edf020262ea35e20ccdf3e288043e6dd620e3"
+
 [[package]]
 name = "windows-sys"
 version = "0.59.0"
@@ -1402,11 +1409,11 @@ dependencies = [
 
 [[package]]
 name = "zerocopy"
-version = "0.8.15"
+version = "0.8.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a1e101d4bc320b6f9abb68846837b70e25e380ca2f467ab494bf29fcc435fcc3"
+checksum = "dde3bb8c68a8f3f1ed4ac9221aad6b10cece3e60a8e2ea54a6a2dec806d0084c"
 dependencies = [
- "zerocopy-derive 0.8.15",
+ "zerocopy-derive 0.8.20",
 ]
 
 [[package]]
@@ -1422,9 +1429,9 @@ dependencies = [
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.8.15"
+version = "0.8.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03a73df1008145cd135b3c780d275c57c3e6ba8324a41bd5e0008fe167c3bc7c"
+checksum = "eea57037071898bf96a6da35fd626f4f27e9cee3ead2a6c703cf09d472b2e700"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -1433,9 +1440,9 @@ dependencies = [
 
 [[package]]
 name = "zstd"
-version = "0.13.2"
+version = "0.13.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fcf2b778a664581e31e389454a7072dab1647606d44f7feea22cd5abb9c9f3f9"
+checksum = "e91ee311a569c327171651566e07972200e76fcfe2242a4fa446149a3881c08a"
 dependencies = [
  "zstd-safe",
 ]

data/README.md

@@ -194,4 +194,108 @@ The following data types are supported in the schema:
 - `date32`
 - `timestamp_millis`, `timestamp_micros`
 
-Note: Writing of List and Map types is not currently supported.
+### Schema DSL for Complex Data Types
+
+In addition to the hash-based schema definition shown above, this library provides a more expressive DSL for defining complex schemas with nested structures:
+
+```ruby
+require "parquet"
+
+# Define a complex schema using the Schema DSL
+schema = Parquet::Schema.define do
+  field :id, :int64, nullable: false  # Required field
+  field :name, :string                # Optional field (nullable: true is default)
+
+  # Nested struct
+  field :address, :struct do
+    field :street, :string
+    field :city, :string
+    field :zip, :string
+    field :coordinates, :struct do
+      field :latitude, :double
+      field :longitude, :double
+    end
+  end
+
+  # List of primitives
+  field :scores, :list, item: :float
+
+  # List of structs
+  field :contacts, :list, item: :struct do
+    field :name, :string
+    field :phone, :string
+    field :primary, :boolean
+  end
+
+  # Map with string values
+  field :metadata, :map, key: :string, value: :string
+
+  # Map with struct values
+  field :properties, :map, key: :string, value: :struct do
+    field :count, :int32
+    field :description, :string
+  end
+
+  # Nested lists
+  field :nested_lists, :list, item: :list do
+    field :item, :string  # For nested lists, inner item must be named 'item'
+  end
+
+  # Map of lists
+  field :map_of_lists, :map, key: :string, value: :list do
+    field :item, :int32  # For list items in maps, item must be named 'item'
+  end
+end
+
+# Sample data with nested structures
+data = [
+  [
+    1,                            # id
+    "John Doe",                   # name
+    {                             # address (struct)
+      "street" => "123 Main St",
+      "city" => "Springfield",
+      "zip" => "12345",
+      "coordinates" => {
+        "latitude" => 37.7749,
+        "longitude" => -122.4194
+      }
+    },
+    [85.5, 92.0, 78.5],          # scores (list of floats)
+    [                             # contacts (list of structs)
+      { "name" => "Contact 1", "phone" => "555-1234", "primary" => true },
+      { "name" => "Contact 2", "phone" => "555-5678", "primary" => false }
+    ],
+    { "created" => "2023-01-01", "status" => "active" },  # metadata (map)
+    {                             # properties (map of structs)
+      "feature1" => { "count" => 5, "description" => "Main feature" },
+      "feature2" => { "count" => 3, "description" => "Secondary feature" }
+    },
+    [["a", "b"], ["c", "d", "e"]],  # nested_lists
+    {                                # map_of_lists
+      "group1" => [1, 2, 3],
+      "group2" => [4, 5, 6]
+    }
+  ]
+]
+
+# Write to a parquet file using the schema
+Parquet.write_rows(data.each, schema: schema, write_to: "complex_data.parquet")
+
+# Read back the data
+Parquet.each_row("complex_data.parquet") do |row|
+  puts row.inspect
+end
+```
+
+The Schema DSL supports:
+
+- **Primitive types**: All standard Parquet types (`int32`, `string`, etc.)
+- **Complex types**: Structs, lists, and maps with arbitrary nesting
+- **Nullability control**: Specify which fields can contain null values with `nullable: false/true`
+- **List item nullability**: Control whether list items can be null with `item_nullable: false/true`
+- **Map key/value nullability**: Control whether map keys or values can be null with `value_nullable: false/true`
+
+Note: When using List and Map types, you need to provide at least:
+- For lists: The `item:` parameter specifying the item type
+- For maps: Both `key:` and `value:` parameters specifying key and value types

data/ext/parquet/Cargo.toml

@@ -11,15 +11,16 @@ ahash = "0.8"
 arrow-array = "54.0.0"
 arrow-schema = "54.0.0"
 bytes = "^1.9"
+either = "1.9"
 itertools = "^0.14"
-jiff = "0.1.19"
+jiff = "0.2"
 magnus = { version = "0.7", features = ["rb-sys"] }
 parquet = { version = "^54.0", features = ["json"] }
 rand = "0.9"
 rb-sys = "^0.9"
-thiserror = "2.0"
-tempfile = "^3.15"
 simdutf8 = "0.1.5"
+tempfile = "^3.15"
+thiserror = "2.0"
 
 [target.'cfg(target_os = "linux")'.dependencies]
 jemallocator = { version = "0.5", features = ["disable_initial_exec_tls"] }

data/ext/parquet/src/enumerator.rs

@@ -7,6 +7,7 @@ pub struct RowEnumeratorArgs {
     pub result_type: ParserResultType,
     pub columns: Option<Vec<String>>,
     pub strict: bool,
+    pub logger: Option<Value>,
 }
 
 /// Creates an enumerator for lazy Parquet row parsing
@@ -22,6 +23,9 @@ pub fn create_row_enumerator(args: RowEnumeratorArgs) -> Result<magnus::Enumerat
     if args.strict {
         kwargs.aset(Symbol::new("strict"), true)?;
     }
+    if let Some(logger) = args.logger {
+        kwargs.aset(Symbol::new("logger"), logger)?;
+    }
     Ok(args
         .rb_self
         .enumeratorize("each_row", (args.to_read, KwArgs(kwargs))))
@@ -34,6 +38,7 @@ pub struct ColumnEnumeratorArgs {
     pub columns: Option<Vec<String>>,
     pub batch_size: Option<usize>,
     pub strict: bool,
+    pub logger: Option<Value>,
 }
 
 #[inline]
@@ -54,6 +59,9 @@ pub fn create_column_enumerator(
     if args.strict {
         kwargs.aset(Symbol::new("strict"), true)?;
     }
+    if let Some(logger) = args.logger {
+        kwargs.aset(Symbol::new("logger"), logger)?;
+    }
     Ok(args
         .rb_self
         .enumeratorize("each_column", (args.to_read, KwArgs(kwargs))))

data/ext/parquet/src/header_cache.rs

@@ -6,10 +6,7 @@
 /// so this optimization could be removed if any issues arise.
 use std::{
     collections::HashMap,
-    sync::{
-        atomic::{AtomicU32, Ordering},
-        LazyLock, Mutex,
-    },
+    sync::{LazyLock, Mutex},
 };
 
 use magnus::{IntoValue, RString, Ruby, Value};
@@ -20,9 +17,11 @@ use thiserror::Error;
 pub enum CacheError {
     #[error("Failed to acquire lock: {0}")]
     LockError(String),
+    #[error("Failed to convert Ruby String to interned string: {0}")]
+    RStringConversion(String),
 }
 
-static STRING_CACHE: LazyLock<Mutex<HashMap<&'static str, (StringCacheKey, AtomicU32)>>> =
+static STRING_CACHE: LazyLock<Mutex<HashMap<&'static str, StringCacheKey>>> =
     LazyLock::new(|| Mutex::new(HashMap::with_capacity(100)));
 
 pub struct StringCache;
@@ -31,10 +30,12 @@ pub struct StringCache;
 pub struct StringCacheKey(&'static str);
 
 impl StringCacheKey {
-    pub fn new(string: &str) -> Self {
+    pub fn new(string: &str) -> Result<Self, CacheError> {
         let rstr = RString::new(string);
         let fstr = rstr.to_interned_str();
-        Self(fstr.as_str().unwrap())
+        Ok(Self(fstr.as_str().map_err(|e| {
+            CacheError::RStringConversion(e.to_string())
+        })?))
     }
 }
 
@@ -80,18 +81,16 @@ impl StringCache {
     pub fn intern_many<AsStr: AsRef<str>>(
         strings: &[AsStr],
     ) -> Result<Vec<StringCacheKey>, CacheError> {
-        let mut cache = STRING_CACHE
+        let cache = STRING_CACHE
             .lock()
             .map_err(|e| CacheError::LockError(e.to_string()))?;
 
         let mut result: Vec<StringCacheKey> = Vec::with_capacity(strings.len());
         for string in strings {
-            if let Some((_, (interned_string, counter))) = cache.get_key_value(string.as_ref()) {
-                counter.fetch_add(1, Ordering::Relaxed);
+            if let Some((_, interned_string)) = cache.get_key_value(string.as_ref()) {
                 result.push(*interned_string);
             } else {
-                let interned = StringCacheKey::new(string.as_ref());
-                cache.insert(interned.0, (interned, AtomicU32::new(1)));
+                let interned = StringCacheKey::new(string.as_ref())?;
                 result.push(interned);
             }
         }

data/ext/parquet/src/lib.rs

@@ -1,6 +1,7 @@
 mod allocator;
 mod enumerator;
 pub mod header_cache;
+mod logger;
 mod reader;
 mod ruby_reader;
 mod types;