lancelot 0.3.1 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 59a61f845bead9178dc6b7ca831b0cd1f3577969c189d723b085a706527bb9a9
-  data.tar.gz: f6941d534cc770393803c152f1718dad15639086b4ae78e84da93f8f8ab6f43f
+  metadata.gz: cda5bd00de23ad9f4840b1cc7f6e96b7eb4ec124ba902d3901ef36b37594de97
+  data.tar.gz: 23e84c317e5bcd0f52870c673d0b96f9abf4f3ab97f20eb4e5b8a8047dd1cf1f
 SHA512:
-  metadata.gz: 04f63038fe699b2441c22618daac20ef710df82a5d95c6c8258317a2600b23ea2844ab5c2f1bc01245fb4ff90d531f3ec09f7ddcb28876e758b983a0bcb1fdc2
-  data.tar.gz: 20b8c06914dc993b6868b7264cfcfba0eeb0a0a0c70b0473ac6e3b9e163c8ed3855c2eeae1ad02ab3f19125f80c844a0aebd2c26a91aafc005af0dfebd8d37d6
+  metadata.gz: 32cb3e852ed77b8ec2831b08f93252b5ccb176942c217a366079e1cb2a2a97c4be74247b5f8410a2892852456278a5ec8e5b556bd9ca3379d740b292cc32c15b
+  data.tar.gz: 718a99dbfcd51dce872feedb87265be86417faba152d6f2512a9391f28e5fc5e115deb0154be52dc029c2771611b71c685f1f143a4d2da5157aaafc28997ffa7

data/ext/lancelot/src/conversion.rs

@@ -159,9 +159,9 @@ pub fn build_record_batch(
         .map_err(|e| Error::new(magnus::exception::runtime_error(), e.to_string()))
 }
 
-pub fn convert_batch_to_ruby(batch: &RecordBatch) -> Result<Vec<RHash>, Error> {
+pub fn convert_batch_to_ruby(batch: &RecordBatch) -> Result<RArray, Error> {
     let ruby = Ruby::get().unwrap();
-    let mut documents = Vec::new();
+    let documents = ruby.ary_new();
     
     let num_rows = batch.num_rows();
     let schema = batch.schema();
@@ -173,6 +173,15 @@ pub fn convert_batch_to_ruby(batch: &RecordBatch) -> Result<Vec<RHash>, Error> {
             let column = batch.column(col_idx);
             let key = Symbol::new(field.name());
             
+            // CRITICAL: Add bounds checking for all array access
+            if row_idx >= column.len() {
+                return Err(Error::new(
+                    magnus::exception::runtime_error(), 
+                    format!("Row index {} out of bounds for column '{}' with length {}", 
+                            row_idx, field.name(), column.len())
+                ));
+            }
+            
             match field.data_type() {
                 DataType::Utf8 => {
                     let array = column.as_any().downcast_ref::<StringArray>()
@@ -225,9 +234,19 @@ pub fn convert_batch_to_ruby(batch: &RecordBatch) -> Result<Vec<RHash>, Error> {
                         let float_array = values.as_any().downcast_ref::<Float32Array>()
                             .ok_or_else(|| Error::new(magnus::exception::runtime_error(), "Failed to cast vector values to Float32Array"))?;
                         
+                        // CRITICAL: Verify the float_array has the expected size
+                        let expected_size = *list_size as usize;
+                        if float_array.len() != expected_size {
+                            return Err(Error::new(
+                                magnus::exception::runtime_error(),
+                                format!("Vector data corruption: expected {} elements but found {} for field '{}'",
+                                        expected_size, float_array.len(), field.name())
+                            ));
+                        }
+                        
                         let ruby_array = ruby.ary_new();
-                        for i in 0..*list_size {
-                            ruby_array.push(float_array.value(i as usize))?;
+                        for i in 0..expected_size {
+                            ruby_array.push(float_array.value(i))?;
                         }
                         doc.aset(key, ruby_array)?;
                     }
@@ -238,7 +257,7 @@ pub fn convert_batch_to_ruby(batch: &RecordBatch) -> Result<Vec<RHash>, Error> {
             }
         }
         
-        documents.push(doc);
+        documents.push(doc)?;
     }
     
     Ok(documents)

data/ext/lancelot/src/dataset.rs

@@ -1,4 +1,4 @@
-use magnus::{Error, Ruby, RHash, RArray, Symbol, TryConvert, function, method, RClass, Module, Object};
+use magnus::{Error, Ruby, RHash, RArray, Symbol, TryConvert, Value, function, method, RClass, Module, Object};
 use std::cell::RefCell;
 use std::sync::Arc;
 use tokio::runtime::Runtime;
@@ -157,9 +157,10 @@ impl LancelotDataset {
         let result_array = ruby.ary_new();
 
         for batch in batches {
-            let documents = convert_batch_to_ruby(&batch)?;
-            for doc in documents {
-                result_array.push(doc)?;
+            let batch_docs = convert_batch_to_ruby(&batch)?;
+            // Merge arrays by pushing each element
+            for i in 0..batch_docs.len() {
+                result_array.push(batch_docs.entry::<Value>(i as isize)?)?;
             }
         }
 
@@ -191,9 +192,10 @@ impl LancelotDataset {
         let result_array = ruby.ary_new();
 
         for batch in batches {
-            let documents = convert_batch_to_ruby(&batch)?;
-            for doc in documents {
-                result_array.push(doc)?;
+            let batch_docs = convert_batch_to_ruby(&batch)?;
+            // Merge arrays by pushing each element
+            for i in 0..batch_docs.len() {
+                result_array.push(batch_docs.entry::<Value>(i as isize)?)?;
             }
         }
 
@@ -265,9 +267,10 @@ impl LancelotDataset {
         let result_array = ruby.ary_new();
 
         for batch in batches {
-            let documents = convert_batch_to_ruby(&batch)?;
-            for doc in documents {
-                result_array.push(doc)?;
+            let batch_docs = convert_batch_to_ruby(&batch)?;
+            // Merge arrays by pushing each element
+            for i in 0..batch_docs.len() {
+                result_array.push(batch_docs.entry::<Value>(i as isize)?)?;
             }
         }
 
@@ -330,9 +333,10 @@ impl LancelotDataset {
         let result_array = ruby.ary_new();
 
         for batch in batches {
-            let documents = convert_batch_to_ruby(&batch)?;
-            for doc in documents {
-                result_array.push(doc)?;
+            let batch_docs = convert_batch_to_ruby(&batch)?;
+            // Merge arrays by pushing each element
+            for i in 0..batch_docs.len() {
+                result_array.push(batch_docs.entry::<Value>(i as isize)?)?;
             }
         }
 
@@ -380,9 +384,10 @@ impl LancelotDataset {
         let result_array = ruby.ary_new();
 
         for batch in batches {
-            let documents = convert_batch_to_ruby(&batch)?;
-            for doc in documents {
-                result_array.push(doc)?;
+            let batch_docs = convert_batch_to_ruby(&batch)?;
+            // Merge arrays by pushing each element
+            for i in 0..batch_docs.len() {
+                result_array.push(batch_docs.entry::<Value>(i as isize)?)?;
             }
         }
 
@@ -422,9 +427,10 @@ impl LancelotDataset {
         let result_array = ruby.ary_new();
 
         for batch in batches {
-            let documents = convert_batch_to_ruby(&batch)?;
-            for doc in documents {
-                result_array.push(doc)?;
+            let batch_docs = convert_batch_to_ruby(&batch)?;
+            // Merge arrays by pushing each element
+            for i in 0..batch_docs.len() {
+                result_array.push(batch_docs.entry::<Value>(i as isize)?)?;
             }
         }
 

data/lib/lancelot/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Lancelot
-  VERSION = "0.3.1"
+  VERSION = "0.3.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: lancelot
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.3.2
 platform: ruby
 authors:
 - Chris Petersen
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-08-10 00:00:00.000000000 Z
+date: 2025-08-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys