WIP

Author: habedi

README.md

@@ -7,7 +7,6 @@
 <h2>Gaggle</h2>
 
 [![Tests](https://img.shields.io/github/actions/workflow/status/CogitatorTech/gaggle/tests.yml?label=tests&style=flat&labelColor=282c34&logo=github)](https://github.com/CogitatorTech/gaggle/actions/workflows/tests.yml)
-[![Code Quality](https://img.shields.io/codefactor/grade/github/CogitatorTech/gaggle?label=quality&style=flat&labelColor=282c34&logo=codefactor)](https://www.codefactor.io/repository/github/CogitatorTech/gaggle)
 [![Examples](https://img.shields.io/badge/examples-view-green?style=flat&labelColor=282c34&logo=github)](https://github.com/CogitatorTech/gaggle/tree/main/docs/examples)
 [![Docs](https://img.shields.io/badge/docs-read-blue?style=flat&labelColor=282c34&logo=read-the-docs)](https://github.com/CogitatorTech/gaggle/tree/main/docs)
 [![License](https://img.shields.io/badge/license-MIT%2FApache--2.0-007ec6?style=flat&labelColor=282c34&logo=open-source-initiative)](https://github.com/CogitatorTech/gaggle)
@@ -98,7 +97,7 @@ make release
 select gaggle_version();
 
 -- List files in the dataset (recursively)
--- (Note that if the datasets is not downloaded, it will be downloaded and cached)
+-- (Note that if the dataset is not downloaded, it will be downloaded and cached)
 select *
 from gaggle_ls('habedi/flickr-8k-dataset-clean', true) limit 5;
 

gaggle/Cargo.lock

@@ -19,7 +19,7 @@ thiserror = "2.0"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
 reqwest = { version = "=0.12", features = ["blocking", "rustls-tls", "json", "multipart"], default-features = false }
-zip = { version = "7.2", default-features = false, features = ["deflate"] }
+zip = { version = "8.5.1", default-features = false, features = ["deflate"] }
 dirs = "6.0"
 urlencoding = "2.1"
 tracing = "0.1"
@@ -28,7 +28,6 @@ tracing-subscriber = { version = "0.3", features = ["fmt", "env-filter"] }
 [dev-dependencies]
 tempfile = "3.10"
 mockito = "1.7.0"
-tiny_http = "0.12.0"
 serial_test = "3.0"
 proptest = "1.5"
 

gaggle/Cargo.toml

@@ -40,6 +40,11 @@ namespace duckdb {
 using namespace gaggle;
 namespace fs = std::filesystem;
 
+template <typename T>
+static T *GetFlatVectorDataWritable(Vector &vector) {
+  return const_cast<T *>(FlatVector::GetData<T>(vector));
+}
+
 /**
  * @brief Retrieves the last error message from the Gaggle Rust core.
  * @return A string containing the error message, or "unknown error" if not set.
@@ -862,9 +867,9 @@ static void GaggleLsFunction(ClientContext &context, TableFunctionInput &data_p,
   idx_t remaining = bind.names.size() - state.pos;
   idx_t count = MinValue<idx_t>(STANDARD_VECTOR_SIZE, remaining);
   output.SetCardinality(count);
-  auto name_out = FlatVector::GetDataMutable<string_t>(output.data[0]);
-  auto size_out = FlatVector::GetDataMutable<int64_t>(output.data[1]);
-  auto path_out = FlatVector::GetDataMutable<string_t>(output.data[2]);
+  auto name_out = GetFlatVectorDataWritable<string_t>(output.data[0]);
+  auto size_out = GetFlatVectorDataWritable<int64_t>(output.data[1]);
+  auto path_out = GetFlatVectorDataWritable<string_t>(output.data[2]);
   for (idx_t i = 0; i < count; i++) {
     auto idx = state.pos + i;
     name_out[i] = StringVector::AddString(output.data[0], bind.names[idx]);