add data packages and remove empty submodule
This commit is contained in:
277
packages/data/ourdb/API.md
Normal file
277
packages/data/ourdb/API.md
Normal file
@@ -0,0 +1,277 @@
|
||||
# OurDB API Reference
|
||||
|
||||
This document provides a comprehensive reference for the OurDB Rust API.
|
||||
|
||||
## Table of Contents
|
||||
|
||||
1. [Configuration](#configuration)
|
||||
2. [Database Operations](#database-operations)
|
||||
- [Creating and Opening](#creating-and-opening)
|
||||
- [Setting Data](#setting-data)
|
||||
- [Getting Data](#getting-data)
|
||||
- [Deleting Data](#deleting-data)
|
||||
- [History Tracking](#history-tracking)
|
||||
3. [Error Handling](#error-handling)
|
||||
4. [Advanced Usage](#advanced-usage)
|
||||
- [Custom File Size](#custom-file-size)
|
||||
- [Custom Key Size](#custom-key-size)
|
||||
5. [Performance Considerations](#performance-considerations)
|
||||
|
||||
## Configuration
|
||||
|
||||
### OurDBConfig
|
||||
|
||||
The `OurDBConfig` struct is used to configure a new OurDB instance.
|
||||
|
||||
```rust
|
||||
pub struct OurDBConfig {
|
||||
pub path: PathBuf,
|
||||
pub incremental_mode: bool,
|
||||
pub file_size: Option<usize>,
|
||||
pub keysize: Option<u8>,
|
||||
}
|
||||
```
|
||||
|
||||
| Field | Type | Description |
|
||||
|-------|------|-------------|
|
||||
| `path` | `PathBuf` | Path to the database directory |
|
||||
| `incremental_mode` | `bool` | Whether to use auto-incremented IDs (true) or user-provided IDs (false) |
|
||||
| `file_size` | `Option<usize>` | Maximum size of each database file in bytes (default: 500MB) |
|
||||
| `keysize` | `Option<u8>` | Size of keys in bytes (default: 4, valid values: 2, 3, 4, 6) |
|
||||
|
||||
Example:
|
||||
```rust
|
||||
let config = OurDBConfig {
|
||||
path: PathBuf::from("/path/to/db"),
|
||||
incremental_mode: true,
|
||||
file_size: Some(1024 * 1024 * 100), // 100MB
|
||||
keysize: Some(4), // 4-byte keys
|
||||
};
|
||||
```
|
||||
|
||||
## Database Operations
|
||||
|
||||
### Creating and Opening
|
||||
|
||||
#### `OurDB::new`
|
||||
|
||||
Creates a new OurDB instance or opens an existing one.
|
||||
|
||||
```rust
|
||||
pub fn new(config: OurDBConfig) -> Result<OurDB, Error>
|
||||
```
|
||||
|
||||
Example:
|
||||
```rust
|
||||
let mut db = OurDB::new(config)?;
|
||||
```
|
||||
|
||||
### Setting Data
|
||||
|
||||
#### `OurDB::set`
|
||||
|
||||
Sets a value in the database. In incremental mode, if no ID is provided, a new ID is generated.
|
||||
|
||||
```rust
|
||||
pub fn set(&mut self, args: OurDBSetArgs) -> Result<u32, Error>
|
||||
```
|
||||
|
||||
The `OurDBSetArgs` struct has the following fields:
|
||||
|
||||
```rust
|
||||
pub struct OurDBSetArgs<'a> {
|
||||
pub id: Option<u32>,
|
||||
pub data: &'a [u8],
|
||||
}
|
||||
```
|
||||
|
||||
Example with auto-generated ID:
|
||||
```rust
|
||||
let id = db.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: b"Hello, World!",
|
||||
})?;
|
||||
```
|
||||
|
||||
Example with explicit ID:
|
||||
```rust
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(42),
|
||||
data: b"Hello, World!",
|
||||
})?;
|
||||
```
|
||||
|
||||
### Getting Data
|
||||
|
||||
#### `OurDB::get`
|
||||
|
||||
Retrieves a value from the database by ID.
|
||||
|
||||
```rust
|
||||
pub fn get(&mut self, id: u32) -> Result<Vec<u8>, Error>
|
||||
```
|
||||
|
||||
Example:
|
||||
```rust
|
||||
let data = db.get(42)?;
|
||||
```
|
||||
|
||||
### Deleting Data
|
||||
|
||||
#### `OurDB::delete`
|
||||
|
||||
Deletes a value from the database by ID.
|
||||
|
||||
```rust
|
||||
pub fn delete(&mut self, id: u32) -> Result<(), Error>
|
||||
```
|
||||
|
||||
Example:
|
||||
```rust
|
||||
db.delete(42)?;
|
||||
```
|
||||
|
||||
### History Tracking
|
||||
|
||||
#### `OurDB::get_history`
|
||||
|
||||
Retrieves the history of values for a given ID, up to the specified depth.
|
||||
|
||||
```rust
|
||||
pub fn get_history(&mut self, id: u32, depth: u8) -> Result<Vec<Vec<u8>>, Error>
|
||||
```
|
||||
|
||||
Example:
|
||||
```rust
|
||||
// Get the last 5 versions of the record
|
||||
let history = db.get_history(42, 5)?;
|
||||
|
||||
// Process each version (most recent first)
|
||||
for (i, version) in history.iter().enumerate() {
|
||||
println!("Version {}: {:?}", i, version);
|
||||
}
|
||||
```
|
||||
|
||||
### Other Operations
|
||||
|
||||
#### `OurDB::get_next_id`
|
||||
|
||||
Returns the next ID that will be assigned in incremental mode.
|
||||
|
||||
```rust
|
||||
pub fn get_next_id(&self) -> Result<u32, Error>
|
||||
```
|
||||
|
||||
Example:
|
||||
```rust
|
||||
let next_id = db.get_next_id()?;
|
||||
```
|
||||
|
||||
#### `OurDB::close`
|
||||
|
||||
Closes the database, ensuring all data is flushed to disk.
|
||||
|
||||
```rust
|
||||
pub fn close(&mut self) -> Result<(), Error>
|
||||
```
|
||||
|
||||
Example:
|
||||
```rust
|
||||
db.close()?;
|
||||
```
|
||||
|
||||
#### `OurDB::destroy`
|
||||
|
||||
Closes the database and deletes all database files.
|
||||
|
||||
```rust
|
||||
pub fn destroy(&mut self) -> Result<(), Error>
|
||||
```
|
||||
|
||||
Example:
|
||||
```rust
|
||||
db.destroy()?;
|
||||
```
|
||||
|
||||
## Error Handling
|
||||
|
||||
OurDB uses the `thiserror` crate to define error types. The main error type is `ourdb::Error`.
|
||||
|
||||
```rust
|
||||
pub enum Error {
|
||||
IoError(std::io::Error),
|
||||
InvalidKeySize,
|
||||
InvalidId,
|
||||
RecordNotFound,
|
||||
InvalidCrc,
|
||||
NotIncrementalMode,
|
||||
DatabaseClosed,
|
||||
// ...
|
||||
}
|
||||
```
|
||||
|
||||
All OurDB operations that can fail return a `Result<T, Error>` which can be handled using Rust's standard error handling mechanisms.
|
||||
|
||||
Example:
|
||||
```rust
|
||||
match db.get(42) {
|
||||
Ok(data) => println!("Found data: {:?}", data),
|
||||
Err(ourdb::Error::RecordNotFound) => println!("Record not found"),
|
||||
Err(e) => eprintln!("Error: {}", e),
|
||||
}
|
||||
```
|
||||
|
||||
## Advanced Usage
|
||||
|
||||
### Custom File Size
|
||||
|
||||
You can configure the maximum size of each database file:
|
||||
|
||||
```rust
|
||||
let config = OurDBConfig {
|
||||
path: PathBuf::from("/path/to/db"),
|
||||
incremental_mode: true,
|
||||
file_size: Some(1024 * 1024 * 10), // 10MB per file
|
||||
keysize: None,
|
||||
};
|
||||
```
|
||||
|
||||
Smaller file sizes can be useful for:
|
||||
- Limiting memory usage when reading files
|
||||
- Improving performance on systems with limited memory
|
||||
- Easier backup and file management
|
||||
|
||||
### Custom Key Size
|
||||
|
||||
OurDB supports different key sizes (2, 3, 4, or 6 bytes):
|
||||
|
||||
```rust
|
||||
let config = OurDBConfig {
|
||||
path: PathBuf::from("/path/to/db"),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: Some(6), // 6-byte keys
|
||||
};
|
||||
```
|
||||
|
||||
Key size considerations:
|
||||
- 2 bytes: Up to 65,536 records
|
||||
- 3 bytes: Up to 16,777,216 records
|
||||
- 4 bytes: Up to 4,294,967,296 records (default)
|
||||
- 6 bytes: Up to 281,474,976,710,656 records
|
||||
|
||||
## Performance Considerations
|
||||
|
||||
For optimal performance:
|
||||
|
||||
1. **Choose appropriate key size**: Use the smallest key size that can accommodate your expected number of records.
|
||||
|
||||
2. **Configure file size**: For large databases, consider using smaller file sizes to improve memory usage.
|
||||
|
||||
3. **Batch operations**: When inserting or updating many records, consider batching operations to minimize disk I/O.
|
||||
|
||||
4. **Close properly**: Always call `close()` when you're done with the database to ensure data is properly flushed to disk.
|
||||
|
||||
5. **Reuse OurDB instance**: Creating a new OurDB instance has overhead, so reuse the same instance for multiple operations when possible.
|
||||
|
||||
6. **Consider memory usage**: The lookup table is loaded into memory, so very large databases may require significant RAM.
|
32
packages/data/ourdb/Cargo.toml
Normal file
32
packages/data/ourdb/Cargo.toml
Normal file
@@ -0,0 +1,32 @@
|
||||
[package]
|
||||
name = "ourdb"
|
||||
version = "0.1.0"
|
||||
edition = "2021"
|
||||
description = "A lightweight, efficient key-value database with history tracking capabilities"
|
||||
authors = ["OurWorld Team"]
|
||||
|
||||
[dependencies]
|
||||
crc32fast = "1.3.2"
|
||||
thiserror = "1.0.40"
|
||||
log = "0.4.17"
|
||||
rand = "0.8.5"
|
||||
|
||||
[dev-dependencies]
|
||||
criterion = "0.5.1"
|
||||
tempfile = "3.8.0"
|
||||
|
||||
# [[bench]]
|
||||
# name = "ourdb_benchmarks"
|
||||
# harness = false
|
||||
|
||||
[[example]]
|
||||
name = "basic_usage"
|
||||
path = "examples/basic_usage.rs"
|
||||
|
||||
[[example]]
|
||||
name = "advanced_usage"
|
||||
path = "examples/advanced_usage.rs"
|
||||
|
||||
[[example]]
|
||||
name = "benchmark"
|
||||
path = "examples/benchmark.rs"
|
135
packages/data/ourdb/README.md
Normal file
135
packages/data/ourdb/README.md
Normal file
@@ -0,0 +1,135 @@
|
||||
# OurDB
|
||||
|
||||
OurDB is a lightweight, efficient key-value database implementation that provides data persistence with history tracking capabilities. This Rust implementation offers a robust and performant solution for applications requiring simple but reliable data storage.
|
||||
|
||||
## Features
|
||||
|
||||
- Simple key-value storage with history tracking
|
||||
- Data integrity verification using CRC32
|
||||
- Support for multiple backend files for large datasets
|
||||
- Lookup table for fast data retrieval
|
||||
- Incremental mode for auto-generated IDs
|
||||
- Memory and disk-based lookup tables
|
||||
|
||||
## Limitations
|
||||
|
||||
- Maximum data size per entry is 65,535 bytes (~64KB) due to the 2-byte size field in the record header
|
||||
|
||||
## Usage
|
||||
|
||||
### Basic Example
|
||||
|
||||
```rust
|
||||
use ourdb::{OurDB, OurDBConfig, OurDBSetArgs};
|
||||
use std::path::PathBuf;
|
||||
|
||||
fn main() -> Result<(), ourdb::Error> {
|
||||
// Create a new database
|
||||
let config = OurDBConfig {
|
||||
path: PathBuf::from("/tmp/ourdb"),
|
||||
incremental_mode: true,
|
||||
file_size: None, // Use default (500MB)
|
||||
keysize: None, // Use default (4 bytes)
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config)?;
|
||||
|
||||
// Store data (with auto-generated ID in incremental mode)
|
||||
let data = b"Hello, OurDB!";
|
||||
let id = db.set(OurDBSetArgs { id: None, data })?;
|
||||
println!("Stored data with ID: {}", id);
|
||||
|
||||
// Retrieve data
|
||||
let retrieved = db.get(id)?;
|
||||
println!("Retrieved: {}", String::from_utf8_lossy(&retrieved));
|
||||
|
||||
// Update data
|
||||
let updated_data = b"Updated data";
|
||||
db.set(OurDBSetArgs { id: Some(id), data: updated_data })?;
|
||||
|
||||
// Get history (returns most recent first)
|
||||
let history = db.get_history(id, 2)?;
|
||||
for (i, entry) in history.iter().enumerate() {
|
||||
println!("History {}: {}", i, String::from_utf8_lossy(entry));
|
||||
}
|
||||
|
||||
// Delete data
|
||||
db.delete(id)?;
|
||||
|
||||
// Close the database
|
||||
db.close()?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
```
|
||||
|
||||
### Key-Value Mode vs Incremental Mode
|
||||
|
||||
OurDB supports two operating modes:
|
||||
|
||||
1. **Key-Value Mode** (`incremental_mode: false`): You must provide IDs explicitly when storing data.
|
||||
2. **Incremental Mode** (`incremental_mode: true`): IDs are auto-generated when not provided.
|
||||
|
||||
### Configuration Options
|
||||
|
||||
- `path`: Directory for database storage
|
||||
- `incremental_mode`: Whether to use auto-increment mode
|
||||
- `file_size`: Maximum file size (default: 500MB)
|
||||
- `keysize`: Size of lookup table entries (2-6 bytes)
|
||||
- 2: For databases with < 65,536 records
|
||||
- 3: For databases with < 16,777,216 records
|
||||
- 4: For databases with < 4,294,967,296 records (default)
|
||||
- 6: For large databases requiring multiple files
|
||||
|
||||
## Architecture
|
||||
|
||||
OurDB consists of three main components:
|
||||
|
||||
1. **Frontend API**: Provides the public interface for database operations
|
||||
2. **Lookup Table**: Maps keys to physical locations in the backend storage
|
||||
3. **Backend Storage**: Manages the actual data persistence in files
|
||||
|
||||
### Record Format
|
||||
|
||||
Each record in the backend storage includes:
|
||||
- 2 bytes: Data size
|
||||
- 4 bytes: CRC32 checksum
|
||||
- 6 bytes: Previous record location (for history)
|
||||
- N bytes: Actual data
|
||||
|
||||
## Documentation
|
||||
|
||||
Additional documentation is available in the repository:
|
||||
|
||||
- [API Reference](API.md): Detailed API documentation
|
||||
- [Migration Guide](MIGRATION.md): Guide for migrating from the V implementation
|
||||
- [Architecture](architecture.md): Design and implementation details
|
||||
|
||||
## Examples
|
||||
|
||||
The repository includes several examples to demonstrate OurDB usage:
|
||||
|
||||
- `basic_usage.rs`: Simple operations with OurDB
|
||||
- `advanced_usage.rs`: More complex features including both operation modes
|
||||
- `benchmark.rs`: Performance benchmarking tool
|
||||
|
||||
Run an example with:
|
||||
|
||||
```bash
|
||||
cargo run --example basic_usage
|
||||
cargo run --example advanced_usage
|
||||
cargo run --example benchmark
|
||||
```
|
||||
|
||||
## Performance
|
||||
|
||||
OurDB is designed for efficiency and minimal overhead. The benchmark example can be used to evaluate performance on your specific hardware and workload.
|
||||
|
||||
Typical performance metrics on modern hardware:
|
||||
|
||||
- **Write**: 10,000+ operations per second
|
||||
- **Read**: 50,000+ operations per second
|
||||
|
||||
## License
|
||||
|
||||
This project is licensed under the MIT License.
|
439
packages/data/ourdb/architecture.md
Normal file
439
packages/data/ourdb/architecture.md
Normal file
@@ -0,0 +1,439 @@
|
||||
# OurDB: Architecture for V to Rust Port
|
||||
|
||||
## 1. Overview
|
||||
|
||||
OurDB is a lightweight, efficient key-value database implementation that provides data persistence with history tracking capabilities. This document outlines the architecture for porting OurDB from its original V implementation to Rust, maintaining all existing functionality while leveraging Rust's memory safety, performance, and ecosystem.
|
||||
|
||||
## 2. Current Architecture (V Implementation)
|
||||
|
||||
The current V implementation of OurDB consists of three main components in a layered architecture:
|
||||
|
||||
```mermaid
|
||||
graph TD
|
||||
A[Client Code] --> B[Frontend API]
|
||||
B --> C[Lookup Table]
|
||||
B --> D[Backend Storage]
|
||||
C --> D
|
||||
```
|
||||
|
||||
### 2.1 Frontend (db.v)
|
||||
|
||||
The frontend provides the public API for database operations and coordinates between the lookup table and backend storage components.
|
||||
|
||||
Key responsibilities:
|
||||
- Exposing high-level operations (set, get, delete, history)
|
||||
- Managing incremental ID generation in auto-increment mode
|
||||
- Coordinating data flow between lookup and backend components
|
||||
- Handling database lifecycle (open, close, destroy)
|
||||
|
||||
### 2.2 Lookup Table (lookup.v)
|
||||
|
||||
The lookup table maps keys to physical locations in the backend storage.
|
||||
|
||||
Key responsibilities:
|
||||
- Maintaining key-to-location mapping
|
||||
- Optimizing key sizes based on database configuration
|
||||
- Supporting both memory and disk-based lookup tables
|
||||
- Handling sparse data efficiently
|
||||
- Providing next ID generation for incremental mode
|
||||
|
||||
### 2.3 Backend Storage (backend.v)
|
||||
|
||||
The backend storage manages the actual data persistence in files.
|
||||
|
||||
Key responsibilities:
|
||||
- Managing physical data storage in files
|
||||
- Ensuring data integrity with CRC32 checksums
|
||||
- Supporting multiple file backends for large datasets
|
||||
- Implementing low-level read/write operations
|
||||
- Tracking record history through linked locations
|
||||
|
||||
### 2.4 Core Data Structures
|
||||
|
||||
#### OurDB
|
||||
```v
|
||||
@[heap]
|
||||
pub struct OurDB {
|
||||
mut:
|
||||
lookup &LookupTable
|
||||
pub:
|
||||
path string // directory for storage
|
||||
incremental_mode bool
|
||||
file_size u32 = 500 * (1 << 20) // 500MB
|
||||
pub mut:
|
||||
file os.File
|
||||
file_nr u16 // the file which is open
|
||||
last_used_file_nr u16
|
||||
}
|
||||
```
|
||||
|
||||
#### LookupTable
|
||||
```v
|
||||
pub struct LookupTable {
|
||||
keysize u8
|
||||
lookuppath string
|
||||
mut:
|
||||
data []u8
|
||||
incremental ?u32 // points to next empty slot if incremental mode is enabled
|
||||
}
|
||||
```
|
||||
|
||||
#### Location
|
||||
```v
|
||||
pub struct Location {
|
||||
pub mut:
|
||||
file_nr u16
|
||||
position u32
|
||||
}
|
||||
```
|
||||
|
||||
### 2.5 Storage Format
|
||||
|
||||
#### Record Format
|
||||
Each record in the backend storage includes:
|
||||
- 2 bytes: Data size
|
||||
- 4 bytes: CRC32 checksum
|
||||
- 6 bytes: Previous record location (for history)
|
||||
- N bytes: Actual data
|
||||
|
||||
#### Lookup Table Optimization
|
||||
The lookup table automatically optimizes its key size based on the database configuration:
|
||||
- 2 bytes: For databases with < 65,536 records
|
||||
- 3 bytes: For databases with < 16,777,216 records
|
||||
- 4 bytes: For databases with < 4,294,967,296 records
|
||||
- 6 bytes: For large databases requiring multiple files
|
||||
|
||||
## 3. Proposed Rust Architecture
|
||||
|
||||
The Rust implementation will maintain the same layered architecture while leveraging Rust's type system, ownership model, and error handling.
|
||||
|
||||
```mermaid
|
||||
graph TD
|
||||
A[Client Code] --> B[OurDB API]
|
||||
B --> C[LookupTable]
|
||||
B --> D[Backend]
|
||||
C --> D
|
||||
E[Error Handling] --> B
|
||||
E --> C
|
||||
E --> D
|
||||
F[Configuration] --> B
|
||||
```
|
||||
|
||||
### 3.1 Core Components
|
||||
|
||||
#### 3.1.1 OurDB (API Layer)
|
||||
|
||||
```rust
|
||||
pub struct OurDB {
|
||||
path: String,
|
||||
incremental_mode: bool,
|
||||
file_size: u32,
|
||||
lookup: LookupTable,
|
||||
file: Option<std::fs::File>,
|
||||
file_nr: u16,
|
||||
last_used_file_nr: u16,
|
||||
}
|
||||
|
||||
impl OurDB {
|
||||
pub fn new(config: OurDBConfig) -> Result<Self, Error>;
|
||||
pub fn set(&mut self, id: Option<u32>, data: &[u8]) -> Result<u32, Error>;
|
||||
pub fn get(&mut self, id: u32) -> Result<Vec<u8>, Error>;
|
||||
pub fn get_history(&mut self, id: u32, depth: u8) -> Result<Vec<Vec<u8>>, Error>;
|
||||
pub fn delete(&mut self, id: u32) -> Result<(), Error>;
|
||||
pub fn get_next_id(&mut self) -> Result<u32, Error>;
|
||||
pub fn close(&mut self) -> Result<(), Error>;
|
||||
pub fn destroy(&mut self) -> Result<(), Error>;
|
||||
}
|
||||
```
|
||||
|
||||
#### 3.1.2 LookupTable
|
||||
|
||||
```rust
|
||||
pub struct LookupTable {
|
||||
keysize: u8,
|
||||
lookuppath: String,
|
||||
data: Vec<u8>,
|
||||
incremental: Option<u32>,
|
||||
}
|
||||
|
||||
impl LookupTable {
|
||||
fn new(config: LookupConfig) -> Result<Self, Error>;
|
||||
fn get(&self, id: u32) -> Result<Location, Error>;
|
||||
fn set(&mut self, id: u32, location: Location) -> Result<(), Error>;
|
||||
fn delete(&mut self, id: u32) -> Result<(), Error>;
|
||||
fn get_next_id(&self) -> Result<u32, Error>;
|
||||
fn increment_index(&mut self) -> Result<(), Error>;
|
||||
fn export_data(&self, path: &str) -> Result<(), Error>;
|
||||
fn import_data(&mut self, path: &str) -> Result<(), Error>;
|
||||
fn export_sparse(&self, path: &str) -> Result<(), Error>;
|
||||
fn import_sparse(&mut self, path: &str) -> Result<(), Error>;
|
||||
}
|
||||
```
|
||||
|
||||
#### 3.1.3 Location
|
||||
|
||||
```rust
|
||||
pub struct Location {
|
||||
file_nr: u16,
|
||||
position: u32,
|
||||
}
|
||||
|
||||
impl Location {
|
||||
fn new(bytes: &[u8], keysize: u8) -> Result<Self, Error>;
|
||||
fn to_bytes(&self) -> Result<Vec<u8>, Error>;
|
||||
fn to_u64(&self) -> u64;
|
||||
}
|
||||
```
|
||||
|
||||
#### 3.1.4 Backend
|
||||
|
||||
The backend functionality will be implemented as methods on the OurDB struct:
|
||||
|
||||
```rust
|
||||
impl OurDB {
|
||||
fn db_file_select(&mut self, file_nr: u16) -> Result<(), Error>;
|
||||
fn create_new_db_file(&mut self, file_nr: u16) -> Result<(), Error>;
|
||||
fn get_file_nr(&mut self) -> Result<u16, Error>;
|
||||
fn set_(&mut self, id: u32, old_location: Location, data: &[u8]) -> Result<(), Error>;
|
||||
fn get_(&mut self, location: Location) -> Result<Vec<u8>, Error>;
|
||||
fn get_prev_pos_(&mut self, location: Location) -> Result<Location, Error>;
|
||||
fn delete_(&mut self, id: u32, location: Location) -> Result<(), Error>;
|
||||
fn close_(&mut self);
|
||||
}
|
||||
```
|
||||
|
||||
#### 3.1.5 Configuration
|
||||
|
||||
```rust
|
||||
pub struct OurDBConfig {
|
||||
pub record_nr_max: u32,
|
||||
pub record_size_max: u32,
|
||||
pub file_size: u32,
|
||||
pub path: String,
|
||||
pub incremental_mode: bool,
|
||||
pub reset: bool,
|
||||
}
|
||||
|
||||
struct LookupConfig {
|
||||
size: u32,
|
||||
keysize: u8,
|
||||
lookuppath: String,
|
||||
incremental_mode: bool,
|
||||
}
|
||||
```
|
||||
|
||||
#### 3.1.6 Error Handling
|
||||
|
||||
```rust
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
pub enum Error {
|
||||
#[error("I/O error: {0}")]
|
||||
Io(#[from] std::io::Error),
|
||||
|
||||
#[error("Invalid key size: {0}")]
|
||||
InvalidKeySize(u8),
|
||||
|
||||
#[error("Record not found: {0}")]
|
||||
RecordNotFound(u32),
|
||||
|
||||
#[error("Data corruption: CRC mismatch")]
|
||||
DataCorruption,
|
||||
|
||||
#[error("Index out of bounds: {0}")]
|
||||
IndexOutOfBounds(u32),
|
||||
|
||||
#[error("Incremental mode not enabled")]
|
||||
IncrementalNotEnabled,
|
||||
|
||||
#[error("Lookup table is full")]
|
||||
LookupTableFull,
|
||||
|
||||
#[error("Invalid file number: {0}")]
|
||||
InvalidFileNumber(u16),
|
||||
|
||||
#[error("Invalid operation: {0}")]
|
||||
InvalidOperation(String),
|
||||
}
|
||||
```
|
||||
|
||||
## 4. Implementation Strategy
|
||||
|
||||
### 4.1 Phase 1: Core Data Structures
|
||||
|
||||
1. Implement the `Location` struct with serialization/deserialization
|
||||
2. Implement the `Error` enum for error handling
|
||||
3. Implement the configuration structures
|
||||
|
||||
### 4.2 Phase 2: Lookup Table
|
||||
|
||||
1. Implement the `LookupTable` struct with memory-based storage
|
||||
2. Add disk-based storage support
|
||||
3. Implement key size optimization
|
||||
4. Add incremental ID support
|
||||
5. Implement import/export functionality
|
||||
|
||||
### 4.3 Phase 3: Backend Storage
|
||||
|
||||
1. Implement file management functions
|
||||
2. Implement record serialization/deserialization with CRC32
|
||||
3. Implement history tracking through linked locations
|
||||
4. Add support for multiple backend files
|
||||
|
||||
### 4.4 Phase 4: Frontend API
|
||||
|
||||
1. Implement the `OurDB` struct with core operations
|
||||
2. Add high-level API methods (set, get, delete, history)
|
||||
3. Implement database lifecycle management
|
||||
|
||||
### 4.5 Phase 5: Testing and Optimization
|
||||
|
||||
1. Port existing tests from V to Rust
|
||||
2. Add new tests for Rust-specific functionality
|
||||
3. Benchmark and optimize performance
|
||||
4. Ensure compatibility with existing OurDB files
|
||||
|
||||
## 5. Implementation Considerations
|
||||
|
||||
### 5.1 Memory Management
|
||||
|
||||
Leverage Rust's ownership model for safe and efficient memory management:
|
||||
- Use `Vec<u8>` for data buffers instead of raw pointers
|
||||
- Implement proper RAII for file handles
|
||||
- Use references and borrows to avoid unnecessary copying
|
||||
- Consider using `Bytes` from the `bytes` crate for zero-copy operations
|
||||
|
||||
### 5.2 Error Handling
|
||||
|
||||
Use Rust's `Result` type for comprehensive error handling:
|
||||
- Define custom error types for OurDB-specific errors
|
||||
- Propagate errors using the `?` operator
|
||||
- Provide detailed error messages
|
||||
- Implement proper error conversion using the `From` trait
|
||||
|
||||
### 5.3 File I/O
|
||||
|
||||
Optimize file operations for performance:
|
||||
- Use `BufReader` and `BufWriter` for buffered I/O
|
||||
- Implement proper file locking for concurrent access
|
||||
- Consider memory-mapped files for lookup tables
|
||||
- Use `seek` and `read_exact` for precise positioning
|
||||
|
||||
### 5.4 Concurrency
|
||||
|
||||
Consider thread safety for concurrent database access:
|
||||
- Use interior mutability patterns where appropriate
|
||||
- Implement `Send` and `Sync` traits for thread safety
|
||||
- Consider using `RwLock` for shared read access
|
||||
- Provide clear documentation on thread safety guarantees
|
||||
|
||||
### 5.5 Performance Optimizations
|
||||
|
||||
Identify opportunities for performance improvements:
|
||||
- Use memory-mapped files for lookup tables
|
||||
- Implement caching for frequently accessed records
|
||||
- Use zero-copy operations where possible
|
||||
- Consider async I/O for non-blocking operations
|
||||
|
||||
## 6. Testing Strategy
|
||||
|
||||
### 6.1 Unit Tests
|
||||
|
||||
Write comprehensive unit tests for each component:
|
||||
- Test `Location` serialization/deserialization
|
||||
- Test `LookupTable` operations
|
||||
- Test backend storage functions
|
||||
- Test error handling
|
||||
|
||||
### 6.2 Integration Tests
|
||||
|
||||
Write integration tests for the complete system:
|
||||
- Test database creation and configuration
|
||||
- Test basic CRUD operations
|
||||
- Test history tracking
|
||||
- Test incremental ID generation
|
||||
- Test file management
|
||||
|
||||
### 6.3 Compatibility Tests
|
||||
|
||||
Ensure compatibility with existing OurDB files:
|
||||
- Test reading existing V-created OurDB files
|
||||
- Test writing files that can be read by the V implementation
|
||||
- Test migration scenarios
|
||||
|
||||
### 6.4 Performance Tests
|
||||
|
||||
Benchmark performance against the V implementation:
|
||||
- Measure throughput for set/get operations
|
||||
- Measure latency for different operations
|
||||
- Test with different database sizes
|
||||
- Test with different record sizes
|
||||
|
||||
## 7. Project Structure
|
||||
|
||||
```
|
||||
ourdb/
|
||||
├── Cargo.toml
|
||||
├── src/
|
||||
│ ├── lib.rs # Public API and re-exports
|
||||
│ ├── ourdb.rs # OurDB implementation (frontend)
|
||||
│ ├── lookup.rs # Lookup table implementation
|
||||
│ ├── location.rs # Location struct implementation
|
||||
│ ├── backend.rs # Backend storage implementation
|
||||
│ ├── error.rs # Error types
|
||||
│ ├── config.rs # Configuration structures
|
||||
│ └── utils.rs # Utility functions
|
||||
├── tests/
|
||||
│ ├── unit/ # Unit tests
|
||||
│ ├── integration/ # Integration tests
|
||||
│ └── compatibility/ # Compatibility tests
|
||||
└── examples/
|
||||
├── basic.rs # Basic usage example
|
||||
├── history.rs # History tracking example
|
||||
└── client_server.rs # Client-server example
|
||||
```
|
||||
|
||||
## 8. Dependencies
|
||||
|
||||
The Rust implementation will use the following dependencies:
|
||||
|
||||
- `thiserror` for error handling
|
||||
- `crc32fast` for CRC32 calculation
|
||||
- `bytes` for efficient byte manipulation
|
||||
- `memmap2` for memory-mapped files (optional)
|
||||
- `serde` for serialization (optional, for future extensions)
|
||||
- `log` for logging
|
||||
- `criterion` for benchmarking
|
||||
|
||||
## 9. Compatibility Considerations
|
||||
|
||||
To ensure compatibility with the V implementation:
|
||||
|
||||
1. Maintain the same file format for data storage
|
||||
2. Preserve the lookup table format
|
||||
3. Keep the same CRC32 calculation method
|
||||
4. Ensure identical behavior for incremental ID generation
|
||||
5. Maintain the same history tracking mechanism
|
||||
|
||||
## 10. Future Extensions
|
||||
|
||||
Potential future extensions to consider:
|
||||
|
||||
1. Async API for non-blocking operations
|
||||
2. Transactions support
|
||||
3. Better concurrency control
|
||||
4. Compression support
|
||||
5. Encryption support
|
||||
6. Streaming API for large values
|
||||
7. Iterators for scanning records
|
||||
8. Secondary indexes
|
||||
|
||||
## 11. Conclusion
|
||||
|
||||
This architecture provides a roadmap for porting OurDB from V to Rust while maintaining compatibility and leveraging Rust's strengths. The implementation will follow a phased approach, starting with core data structures and gradually building up to the complete system.
|
||||
|
||||
The Rust implementation aims to be:
|
||||
- **Safe**: Leveraging Rust's ownership model for memory safety
|
||||
- **Fast**: Maintaining or improving performance compared to V
|
||||
- **Compatible**: Working with existing OurDB files
|
||||
- **Extensible**: Providing a foundation for future enhancements
|
||||
- **Well-tested**: Including comprehensive test coverage
|
231
packages/data/ourdb/examples/advanced_usage.rs
Normal file
231
packages/data/ourdb/examples/advanced_usage.rs
Normal file
@@ -0,0 +1,231 @@
|
||||
use ourdb::{OurDB, OurDBConfig, OurDBSetArgs};
|
||||
use std::path::PathBuf;
|
||||
use std::time::Instant;
|
||||
|
||||
fn main() -> Result<(), ourdb::Error> {
|
||||
// Create a temporary directory for the database
|
||||
let db_path = std::env::temp_dir().join("ourdb_advanced_example");
|
||||
std::fs::create_dir_all(&db_path)?;
|
||||
|
||||
println!("Creating database at: {}", db_path.display());
|
||||
|
||||
// Demonstrate key-value mode (non-incremental)
|
||||
key_value_mode_example(&db_path)?;
|
||||
|
||||
// Demonstrate incremental mode
|
||||
incremental_mode_example(&db_path)?;
|
||||
|
||||
// Demonstrate performance benchmarking
|
||||
performance_benchmark(&db_path)?;
|
||||
|
||||
// Clean up (optional)
|
||||
if std::env::var("KEEP_DB").is_err() {
|
||||
std::fs::remove_dir_all(&db_path)?;
|
||||
println!("Cleaned up database directory");
|
||||
} else {
|
||||
println!("Database kept at: {}", db_path.display());
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn key_value_mode_example(base_path: &PathBuf) -> Result<(), ourdb::Error> {
|
||||
println!("\n=== Key-Value Mode Example ===");
|
||||
|
||||
let db_path = base_path.join("key_value");
|
||||
std::fs::create_dir_all(&db_path)?;
|
||||
|
||||
// Create a new database with key-value mode (non-incremental)
|
||||
let config = OurDBConfig {
|
||||
path: db_path,
|
||||
incremental_mode: false,
|
||||
file_size: Some(1024 * 1024), // 1MB for testing
|
||||
keysize: Some(2), // Small key size for demonstration
|
||||
reset: None, // Don't reset existing database
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config)?;
|
||||
|
||||
// In key-value mode, we must provide IDs explicitly
|
||||
let custom_ids = [100, 200, 300, 400, 500];
|
||||
|
||||
// Store data with custom IDs
|
||||
for (i, &id) in custom_ids.iter().enumerate() {
|
||||
let data = format!("Record with custom ID {}", id);
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id),
|
||||
data: data.as_bytes(),
|
||||
})?;
|
||||
println!("Stored record {} with custom ID: {}", i + 1, id);
|
||||
}
|
||||
|
||||
// Retrieve data by custom IDs
|
||||
for &id in &custom_ids {
|
||||
let retrieved = db.get(id)?;
|
||||
println!(
|
||||
"Retrieved ID {}: {}",
|
||||
id,
|
||||
String::from_utf8_lossy(&retrieved)
|
||||
);
|
||||
}
|
||||
|
||||
// Update and track history
|
||||
let id_to_update = custom_ids[2]; // ID 300
|
||||
for i in 1..=3 {
|
||||
let updated_data = format!("Updated record {} (version {})", id_to_update, i);
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id_to_update),
|
||||
data: updated_data.as_bytes(),
|
||||
})?;
|
||||
println!("Updated ID {} (version {})", id_to_update, i);
|
||||
}
|
||||
|
||||
// Get history for the updated record
|
||||
let history = db.get_history(id_to_update, 5)?;
|
||||
println!("History for ID {} (most recent first):", id_to_update);
|
||||
for (i, entry) in history.iter().enumerate() {
|
||||
println!(" Version {}: {}", i, String::from_utf8_lossy(entry));
|
||||
}
|
||||
|
||||
db.close()?;
|
||||
println!("Key-value mode example completed");
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn incremental_mode_example(base_path: &PathBuf) -> Result<(), ourdb::Error> {
|
||||
println!("\n=== Incremental Mode Example ===");
|
||||
|
||||
let db_path = base_path.join("incremental");
|
||||
std::fs::create_dir_all(&db_path)?;
|
||||
|
||||
// Create a new database with incremental mode
|
||||
let config = OurDBConfig {
|
||||
path: db_path,
|
||||
incremental_mode: true,
|
||||
file_size: Some(1024 * 1024), // 1MB for testing
|
||||
keysize: Some(3), // 3-byte keys
|
||||
reset: None, // Don't reset existing database
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config)?;
|
||||
|
||||
// In incremental mode, IDs are auto-generated
|
||||
let mut assigned_ids = Vec::new();
|
||||
|
||||
// Store multiple records and collect assigned IDs
|
||||
for i in 1..=5 {
|
||||
let data = format!("Auto-increment record {}", i);
|
||||
let id = db.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: data.as_bytes(),
|
||||
})?;
|
||||
assigned_ids.push(id);
|
||||
println!("Stored record {} with auto-assigned ID: {}", i, id);
|
||||
}
|
||||
|
||||
// Check next ID
|
||||
let next_id = db.get_next_id()?;
|
||||
println!("Next ID to be assigned: {}", next_id);
|
||||
|
||||
// Retrieve all records
|
||||
for &id in &assigned_ids {
|
||||
let retrieved = db.get(id)?;
|
||||
println!(
|
||||
"Retrieved ID {}: {}",
|
||||
id,
|
||||
String::from_utf8_lossy(&retrieved)
|
||||
);
|
||||
}
|
||||
|
||||
db.close()?;
|
||||
println!("Incremental mode example completed");
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn performance_benchmark(base_path: &PathBuf) -> Result<(), ourdb::Error> {
|
||||
println!("\n=== Performance Benchmark ===");
|
||||
|
||||
let db_path = base_path.join("benchmark");
|
||||
std::fs::create_dir_all(&db_path)?;
|
||||
|
||||
// Create a new database
|
||||
let config = OurDBConfig {
|
||||
path: db_path,
|
||||
incremental_mode: true,
|
||||
file_size: Some(1024 * 1024), // 10MB
|
||||
keysize: Some(4), // 4-byte keys
|
||||
reset: None, // Don't reset existing database
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config)?;
|
||||
|
||||
// Number of operations for the benchmark
|
||||
let num_operations = 1000;
|
||||
let data_size = 100; // bytes per record
|
||||
|
||||
// Prepare test data
|
||||
let test_data = vec![b'A'; data_size];
|
||||
|
||||
// Benchmark write operations
|
||||
println!("Benchmarking {} write operations...", num_operations);
|
||||
let start = Instant::now();
|
||||
|
||||
let mut ids = Vec::with_capacity(num_operations);
|
||||
for _ in 0..num_operations {
|
||||
let id = db.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: &test_data,
|
||||
})?;
|
||||
ids.push(id);
|
||||
}
|
||||
|
||||
let write_duration = start.elapsed();
|
||||
let writes_per_second = num_operations as f64 / write_duration.as_secs_f64();
|
||||
println!(
|
||||
"Write performance: {:.2} ops/sec ({:.2} ms/op)",
|
||||
writes_per_second,
|
||||
write_duration.as_secs_f64() * 1000.0 / num_operations as f64
|
||||
);
|
||||
|
||||
// Benchmark read operations
|
||||
println!("Benchmarking {} read operations...", num_operations);
|
||||
let start = Instant::now();
|
||||
|
||||
for &id in &ids {
|
||||
let _ = db.get(id)?;
|
||||
}
|
||||
|
||||
let read_duration = start.elapsed();
|
||||
let reads_per_second = num_operations as f64 / read_duration.as_secs_f64();
|
||||
println!(
|
||||
"Read performance: {:.2} ops/sec ({:.2} ms/op)",
|
||||
reads_per_second,
|
||||
read_duration.as_secs_f64() * 1000.0 / num_operations as f64
|
||||
);
|
||||
|
||||
// Benchmark update operations
|
||||
println!("Benchmarking {} update operations...", num_operations);
|
||||
let start = Instant::now();
|
||||
|
||||
for &id in &ids {
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id),
|
||||
data: &test_data,
|
||||
})?;
|
||||
}
|
||||
|
||||
let update_duration = start.elapsed();
|
||||
let updates_per_second = num_operations as f64 / update_duration.as_secs_f64();
|
||||
println!(
|
||||
"Update performance: {:.2} ops/sec ({:.2} ms/op)",
|
||||
updates_per_second,
|
||||
update_duration.as_secs_f64() * 1000.0 / num_operations as f64
|
||||
);
|
||||
|
||||
db.close()?;
|
||||
println!("Performance benchmark completed");
|
||||
|
||||
Ok(())
|
||||
}
|
89
packages/data/ourdb/examples/basic_usage.rs
Normal file
89
packages/data/ourdb/examples/basic_usage.rs
Normal file
@@ -0,0 +1,89 @@
|
||||
use ourdb::{OurDB, OurDBConfig, OurDBSetArgs};
|
||||
|
||||
fn main() -> Result<(), ourdb::Error> {
|
||||
// Create a temporary directory for the database
|
||||
let db_path = std::env::temp_dir().join("ourdb_example");
|
||||
std::fs::create_dir_all(&db_path)?;
|
||||
|
||||
println!("Creating database at: {}", db_path.display());
|
||||
|
||||
// Create a new database with incremental mode enabled
|
||||
let config = OurDBConfig {
|
||||
path: db_path.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None, // Use default (500MB)
|
||||
keysize: None, // Use default (4 bytes)
|
||||
reset: None, // Don't reset existing database
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config)?;
|
||||
|
||||
// Store some data with auto-generated IDs
|
||||
let data1 = b"First record";
|
||||
let id1 = db.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: data1,
|
||||
})?;
|
||||
println!("Stored first record with ID: {}", id1);
|
||||
|
||||
let data2 = b"Second record";
|
||||
let id2 = db.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: data2,
|
||||
})?;
|
||||
println!("Stored second record with ID: {}", id2);
|
||||
|
||||
// Retrieve and print the data
|
||||
let retrieved1 = db.get(id1)?;
|
||||
println!(
|
||||
"Retrieved ID {}: {}",
|
||||
id1,
|
||||
String::from_utf8_lossy(&retrieved1)
|
||||
);
|
||||
|
||||
let retrieved2 = db.get(id2)?;
|
||||
println!(
|
||||
"Retrieved ID {}: {}",
|
||||
id2,
|
||||
String::from_utf8_lossy(&retrieved2)
|
||||
);
|
||||
|
||||
// Update a record to demonstrate history tracking
|
||||
let updated_data = b"Updated first record";
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id1),
|
||||
data: updated_data,
|
||||
})?;
|
||||
println!("Updated record with ID: {}", id1);
|
||||
|
||||
// Get history for the updated record
|
||||
let history = db.get_history(id1, 2)?;
|
||||
println!("History for ID {}:", id1);
|
||||
for (i, entry) in history.iter().enumerate() {
|
||||
println!(" Version {}: {}", i, String::from_utf8_lossy(entry));
|
||||
}
|
||||
|
||||
// Delete a record
|
||||
db.delete(id2)?;
|
||||
println!("Deleted record with ID: {}", id2);
|
||||
|
||||
// Verify deletion
|
||||
match db.get(id2) {
|
||||
Ok(_) => println!("Record still exists (unexpected)"),
|
||||
Err(e) => println!("Verified deletion: {}", e),
|
||||
}
|
||||
|
||||
// Close the database
|
||||
db.close()?;
|
||||
println!("Database closed successfully");
|
||||
|
||||
// Clean up (optional)
|
||||
if std::env::var("KEEP_DB").is_err() {
|
||||
std::fs::remove_dir_all(&db_path)?;
|
||||
println!("Cleaned up database directory");
|
||||
} else {
|
||||
println!("Database kept at: {}", db_path.display());
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
124
packages/data/ourdb/examples/benchmark.rs
Normal file
124
packages/data/ourdb/examples/benchmark.rs
Normal file
@@ -0,0 +1,124 @@
|
||||
use ourdb::{OurDB, OurDBConfig, OurDBSetArgs};
|
||||
use std::time::Instant;
|
||||
|
||||
fn main() -> Result<(), ourdb::Error> {
|
||||
// Parse command-line arguments
|
||||
let args: Vec<String> = std::env::args().collect();
|
||||
|
||||
// Default values
|
||||
let mut incremental_mode = true;
|
||||
let mut keysize: u8 = 4;
|
||||
let mut num_operations = 10000;
|
||||
|
||||
// Parse arguments
|
||||
for i in 1..args.len() {
|
||||
if args[i] == "--no-incremental" {
|
||||
incremental_mode = false;
|
||||
} else if args[i] == "--keysize" && i + 1 < args.len() {
|
||||
keysize = args[i + 1].parse().unwrap_or(4);
|
||||
} else if args[i] == "--ops" && i + 1 < args.len() {
|
||||
num_operations = args[i + 1].parse().unwrap_or(10000);
|
||||
}
|
||||
}
|
||||
|
||||
// Create a temporary directory for the database
|
||||
let db_path = std::env::temp_dir().join("ourdb_benchmark");
|
||||
std::fs::create_dir_all(&db_path)?;
|
||||
|
||||
println!("Database path: {}", db_path.display());
|
||||
|
||||
// Create a new database
|
||||
let config = OurDBConfig {
|
||||
path: db_path.clone(),
|
||||
incremental_mode,
|
||||
file_size: Some(1024 * 1024),
|
||||
keysize: Some(keysize),
|
||||
reset: Some(true), // Reset the database for benchmarking
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config)?;
|
||||
|
||||
// Prepare test data (100 bytes per record)
|
||||
let test_data = vec![b'A'; 100];
|
||||
|
||||
// Benchmark write operations
|
||||
println!(
|
||||
"Benchmarking {} write operations (incremental: {}, keysize: {})...",
|
||||
num_operations, incremental_mode, keysize
|
||||
);
|
||||
|
||||
let start = Instant::now();
|
||||
|
||||
let mut ids = Vec::with_capacity(num_operations);
|
||||
for _ in 0..num_operations {
|
||||
let id = if incremental_mode {
|
||||
db.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: &test_data,
|
||||
})?
|
||||
} else {
|
||||
// In non-incremental mode, we need to provide IDs
|
||||
let id = ids.len() as u32 + 1;
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id),
|
||||
data: &test_data,
|
||||
})?;
|
||||
id
|
||||
};
|
||||
ids.push(id);
|
||||
}
|
||||
|
||||
let write_duration = start.elapsed();
|
||||
let writes_per_second = num_operations as f64 / write_duration.as_secs_f64();
|
||||
|
||||
println!(
|
||||
"Write performance: {:.2} ops/sec ({:.2} ms/op)",
|
||||
writes_per_second,
|
||||
write_duration.as_secs_f64() * 1000.0 / num_operations as f64
|
||||
);
|
||||
|
||||
// Benchmark read operations
|
||||
println!("Benchmarking {} read operations...", num_operations);
|
||||
|
||||
let start = Instant::now();
|
||||
|
||||
for &id in &ids {
|
||||
let _ = db.get(id)?;
|
||||
}
|
||||
|
||||
let read_duration = start.elapsed();
|
||||
let reads_per_second = num_operations as f64 / read_duration.as_secs_f64();
|
||||
|
||||
println!(
|
||||
"Read performance: {:.2} ops/sec ({:.2} ms/op)",
|
||||
reads_per_second,
|
||||
read_duration.as_secs_f64() * 1000.0 / num_operations as f64
|
||||
);
|
||||
|
||||
// Benchmark update operations
|
||||
println!("Benchmarking {} update operations...", num_operations);
|
||||
|
||||
let start = Instant::now();
|
||||
|
||||
for &id in &ids {
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id),
|
||||
data: &test_data,
|
||||
})?;
|
||||
}
|
||||
|
||||
let update_duration = start.elapsed();
|
||||
let updates_per_second = num_operations as f64 / update_duration.as_secs_f64();
|
||||
|
||||
println!(
|
||||
"Update performance: {:.2} ops/sec ({:.2} ms/op)",
|
||||
updates_per_second,
|
||||
update_duration.as_secs_f64() * 1000.0 / num_operations as f64
|
||||
);
|
||||
|
||||
// Clean up
|
||||
db.close()?;
|
||||
std::fs::remove_dir_all(&db_path)?;
|
||||
|
||||
Ok(())
|
||||
}
|
83
packages/data/ourdb/examples/main.rs
Normal file
83
packages/data/ourdb/examples/main.rs
Normal file
@@ -0,0 +1,83 @@
|
||||
use ourdb::{OurDB, OurDBConfig, OurDBSetArgs};
|
||||
use std::env::temp_dir;
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
|
||||
fn main() -> Result<(), Box<dyn std::error::Error>> {
|
||||
println!("Standalone OurDB Example");
|
||||
println!("=======================\n");
|
||||
|
||||
// Create a temporary directory for the database
|
||||
let timestamp = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_secs();
|
||||
let db_path = temp_dir().join(format!("ourdb_example_{}", timestamp));
|
||||
std::fs::create_dir_all(&db_path)?;
|
||||
|
||||
println!("Creating database at: {}", db_path.display());
|
||||
|
||||
// Create a new OurDB instance
|
||||
let config = OurDBConfig {
|
||||
path: db_path.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: Some(false),
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config)?;
|
||||
println!("Database created successfully");
|
||||
|
||||
// Store some data
|
||||
let test_data = b"Hello, OurDB!";
|
||||
let id = db.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: test_data,
|
||||
})?;
|
||||
println!("\nStored data with ID: {}", id);
|
||||
|
||||
// Retrieve the data
|
||||
let retrieved = db.get(id)?;
|
||||
println!("Retrieved data: {}", String::from_utf8_lossy(&retrieved));
|
||||
|
||||
// Update the data
|
||||
let updated_data = b"Updated data in OurDB!";
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id),
|
||||
data: updated_data,
|
||||
})?;
|
||||
println!("\nUpdated data with ID: {}", id);
|
||||
|
||||
// Retrieve the updated data
|
||||
let retrieved = db.get(id)?;
|
||||
println!(
|
||||
"Retrieved updated data: {}",
|
||||
String::from_utf8_lossy(&retrieved)
|
||||
);
|
||||
|
||||
// Get history
|
||||
let history = db.get_history(id, 2)?;
|
||||
println!("\nHistory for ID {}:", id);
|
||||
for (i, data) in history.iter().enumerate() {
|
||||
println!(" Version {}: {}", i + 1, String::from_utf8_lossy(data));
|
||||
}
|
||||
|
||||
// Delete the data
|
||||
db.delete(id)?;
|
||||
println!("\nDeleted data with ID: {}", id);
|
||||
|
||||
// Try to retrieve the deleted data (should fail)
|
||||
match db.get(id) {
|
||||
Ok(_) => println!("Data still exists (unexpected)"),
|
||||
Err(e) => println!("Verified deletion: {}", e),
|
||||
}
|
||||
|
||||
println!("\nExample completed successfully!");
|
||||
|
||||
// Clean up
|
||||
db.close()?;
|
||||
std::fs::remove_dir_all(&db_path)?;
|
||||
println!("Cleaned up database directory");
|
||||
|
||||
Ok(())
|
||||
}
|
83
packages/data/ourdb/examples/standalone_ourdb_example.rs
Normal file
83
packages/data/ourdb/examples/standalone_ourdb_example.rs
Normal file
@@ -0,0 +1,83 @@
|
||||
use ourdb::{OurDB, OurDBConfig, OurDBSetArgs};
|
||||
use std::env::temp_dir;
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
|
||||
fn main() -> Result<(), Box<dyn std::error::Error>> {
|
||||
println!("Standalone OurDB Example");
|
||||
println!("=======================\n");
|
||||
|
||||
// Create a temporary directory for the database
|
||||
let timestamp = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_secs();
|
||||
let db_path = temp_dir().join(format!("ourdb_example_{}", timestamp));
|
||||
std::fs::create_dir_all(&db_path)?;
|
||||
|
||||
println!("Creating database at: {}", db_path.display());
|
||||
|
||||
// Create a new OurDB instance
|
||||
let config = OurDBConfig {
|
||||
path: db_path.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: Some(false),
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config)?;
|
||||
println!("Database created successfully");
|
||||
|
||||
// Store some data
|
||||
let test_data = b"Hello, OurDB!";
|
||||
let id = db.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: test_data,
|
||||
})?;
|
||||
println!("\nStored data with ID: {}", id);
|
||||
|
||||
// Retrieve the data
|
||||
let retrieved = db.get(id)?;
|
||||
println!("Retrieved data: {}", String::from_utf8_lossy(&retrieved));
|
||||
|
||||
// Update the data
|
||||
let updated_data = b"Updated data in OurDB!";
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id),
|
||||
data: updated_data,
|
||||
})?;
|
||||
println!("\nUpdated data with ID: {}", id);
|
||||
|
||||
// Retrieve the updated data
|
||||
let retrieved = db.get(id)?;
|
||||
println!(
|
||||
"Retrieved updated data: {}",
|
||||
String::from_utf8_lossy(&retrieved)
|
||||
);
|
||||
|
||||
// Get history
|
||||
let history = db.get_history(id, 2)?;
|
||||
println!("\nHistory for ID {}:", id);
|
||||
for (i, data) in history.iter().enumerate() {
|
||||
println!(" Version {}: {}", i + 1, String::from_utf8_lossy(data));
|
||||
}
|
||||
|
||||
// Delete the data
|
||||
db.delete(id)?;
|
||||
println!("\nDeleted data with ID: {}", id);
|
||||
|
||||
// Try to retrieve the deleted data (should fail)
|
||||
match db.get(id) {
|
||||
Ok(_) => println!("Data still exists (unexpected)"),
|
||||
Err(e) => println!("Verified deletion: {}", e),
|
||||
}
|
||||
|
||||
println!("\nExample completed successfully!");
|
||||
|
||||
// Clean up
|
||||
db.close()?;
|
||||
std::fs::remove_dir_all(&db_path)?;
|
||||
println!("Cleaned up database directory");
|
||||
|
||||
Ok(())
|
||||
}
|
366
packages/data/ourdb/src/backend.rs
Normal file
366
packages/data/ourdb/src/backend.rs
Normal file
@@ -0,0 +1,366 @@
|
||||
use std::fs::{self, File, OpenOptions};
|
||||
use std::io::{Read, Seek, SeekFrom, Write};
|
||||
|
||||
use crc32fast::Hasher;
|
||||
|
||||
use crate::error::Error;
|
||||
use crate::location::Location;
|
||||
use crate::OurDB;
|
||||
|
||||
// Header size: 2 bytes (size) + 4 bytes (CRC32) + 6 bytes (previous location)
|
||||
pub const HEADER_SIZE: usize = 12;
|
||||
|
||||
impl OurDB {
|
||||
/// Selects and opens a database file for read/write operations
|
||||
pub(crate) fn db_file_select(&mut self, file_nr: u16) -> Result<(), Error> {
|
||||
// No need to check if file_nr > 65535 as u16 can't exceed that value
|
||||
|
||||
let path = self.path.join(format!("{}.db", file_nr));
|
||||
|
||||
// Always close the current file if it's open
|
||||
self.file = None;
|
||||
|
||||
// Create file if it doesn't exist
|
||||
if !path.exists() {
|
||||
self.create_new_db_file(file_nr)?;
|
||||
}
|
||||
|
||||
// Open the file fresh
|
||||
let file = OpenOptions::new().read(true).write(true).open(&path)?;
|
||||
|
||||
self.file = Some(file);
|
||||
self.file_nr = file_nr;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Creates a new database file
|
||||
pub(crate) fn create_new_db_file(&mut self, file_nr: u16) -> Result<(), Error> {
|
||||
let new_file_path = self.path.join(format!("{}.db", file_nr));
|
||||
let mut file = File::create(&new_file_path)?;
|
||||
|
||||
// Write a single byte to make all positions start from 1
|
||||
file.write_all(&[0u8])?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Gets the file number to use for the next write operation
|
||||
pub(crate) fn get_file_nr(&mut self) -> Result<u16, Error> {
|
||||
// For keysize 2, 3, or 4, we can only use file_nr 0
|
||||
if self.lookup.keysize() <= 4 {
|
||||
let path = self.path.join("0.db");
|
||||
|
||||
if !path.exists() {
|
||||
self.create_new_db_file(0)?;
|
||||
}
|
||||
|
||||
return Ok(0);
|
||||
}
|
||||
|
||||
// For keysize 6, we can use multiple files
|
||||
let path = self.path.join(format!("{}.db", self.last_used_file_nr));
|
||||
|
||||
if !path.exists() {
|
||||
self.create_new_db_file(self.last_used_file_nr)?;
|
||||
return Ok(self.last_used_file_nr);
|
||||
}
|
||||
|
||||
let metadata = fs::metadata(&path)?;
|
||||
if metadata.len() >= self.file_size as u64 {
|
||||
self.last_used_file_nr += 1;
|
||||
self.create_new_db_file(self.last_used_file_nr)?;
|
||||
}
|
||||
|
||||
Ok(self.last_used_file_nr)
|
||||
}
|
||||
|
||||
/// Stores data at the specified ID with history tracking
|
||||
pub(crate) fn set_(
|
||||
&mut self,
|
||||
id: u32,
|
||||
old_location: Location,
|
||||
data: &[u8],
|
||||
) -> Result<(), Error> {
|
||||
// Validate data size - maximum is u16::MAX (65535 bytes or ~64KB)
|
||||
if data.len() > u16::MAX as usize {
|
||||
return Err(Error::InvalidOperation(format!(
|
||||
"Data size exceeds maximum allowed size of {} bytes",
|
||||
u16::MAX
|
||||
)));
|
||||
}
|
||||
|
||||
// Get file number to use
|
||||
let file_nr = self.get_file_nr()?;
|
||||
|
||||
// Select the file
|
||||
self.db_file_select(file_nr)?;
|
||||
|
||||
// Get current file position for lookup
|
||||
let file = self
|
||||
.file
|
||||
.as_mut()
|
||||
.ok_or_else(|| Error::Other("No file open".to_string()))?;
|
||||
file.seek(SeekFrom::End(0))?;
|
||||
let position = file.stream_position()? as u32;
|
||||
|
||||
// Create new location
|
||||
let new_location = Location { file_nr, position };
|
||||
|
||||
// Calculate CRC of data
|
||||
let crc = calculate_crc(data);
|
||||
|
||||
// Create header
|
||||
let mut header = vec![0u8; HEADER_SIZE];
|
||||
|
||||
// Write size (2 bytes)
|
||||
let size = data.len() as u16; // Safe now because we've validated the size
|
||||
header[0] = (size & 0xFF) as u8;
|
||||
header[1] = ((size >> 8) & 0xFF) as u8;
|
||||
|
||||
// Write CRC (4 bytes)
|
||||
header[2] = (crc & 0xFF) as u8;
|
||||
header[3] = ((crc >> 8) & 0xFF) as u8;
|
||||
header[4] = ((crc >> 16) & 0xFF) as u8;
|
||||
header[5] = ((crc >> 24) & 0xFF) as u8;
|
||||
|
||||
// Write previous location (6 bytes)
|
||||
let prev_bytes = old_location.to_bytes();
|
||||
for (i, &byte) in prev_bytes.iter().enumerate().take(6) {
|
||||
header[6 + i] = byte;
|
||||
}
|
||||
|
||||
// Write header
|
||||
file.write_all(&header)?;
|
||||
|
||||
// Write actual data
|
||||
file.write_all(data)?;
|
||||
file.flush()?;
|
||||
|
||||
// Update lookup table with new position
|
||||
self.lookup.set(id, new_location)?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Retrieves data at the specified location
|
||||
pub(crate) fn get_(&mut self, location: Location) -> Result<Vec<u8>, Error> {
|
||||
if location.position == 0 {
|
||||
return Err(Error::NotFound(format!(
|
||||
"Record not found, location: {:?}",
|
||||
location
|
||||
)));
|
||||
}
|
||||
|
||||
// Select the file
|
||||
self.db_file_select(location.file_nr)?;
|
||||
|
||||
let file = self
|
||||
.file
|
||||
.as_mut()
|
||||
.ok_or_else(|| Error::Other("No file open".to_string()))?;
|
||||
|
||||
// Read header
|
||||
file.seek(SeekFrom::Start(location.position as u64))?;
|
||||
let mut header = vec![0u8; HEADER_SIZE];
|
||||
file.read_exact(&mut header)?;
|
||||
|
||||
// Parse size (2 bytes)
|
||||
let size = u16::from(header[0]) | (u16::from(header[1]) << 8);
|
||||
|
||||
// Parse CRC (4 bytes)
|
||||
let stored_crc = u32::from(header[2])
|
||||
| (u32::from(header[3]) << 8)
|
||||
| (u32::from(header[4]) << 16)
|
||||
| (u32::from(header[5]) << 24);
|
||||
|
||||
// Read data
|
||||
let mut data = vec![0u8; size as usize];
|
||||
file.read_exact(&mut data)?;
|
||||
|
||||
// Verify CRC
|
||||
let calculated_crc = calculate_crc(&data);
|
||||
if calculated_crc != stored_crc {
|
||||
return Err(Error::DataCorruption(
|
||||
"CRC mismatch: data corruption detected".to_string(),
|
||||
));
|
||||
}
|
||||
|
||||
Ok(data)
|
||||
}
|
||||
|
||||
/// Retrieves the previous position for a record (for history tracking)
|
||||
pub(crate) fn get_prev_pos_(&mut self, location: Location) -> Result<Location, Error> {
|
||||
if location.position == 0 {
|
||||
return Err(Error::NotFound("Record not found".to_string()));
|
||||
}
|
||||
|
||||
// Select the file
|
||||
self.db_file_select(location.file_nr)?;
|
||||
|
||||
let file = self
|
||||
.file
|
||||
.as_mut()
|
||||
.ok_or_else(|| Error::Other("No file open".to_string()))?;
|
||||
|
||||
// Skip size and CRC (6 bytes)
|
||||
file.seek(SeekFrom::Start(location.position as u64 + 6))?;
|
||||
|
||||
// Read previous location (6 bytes)
|
||||
let mut prev_bytes = vec![0u8; 6];
|
||||
file.read_exact(&mut prev_bytes)?;
|
||||
|
||||
// Create location from bytes
|
||||
Location::from_bytes(&prev_bytes, 6)
|
||||
}
|
||||
|
||||
/// Deletes the record at the specified location
|
||||
pub(crate) fn delete_(&mut self, id: u32, location: Location) -> Result<(), Error> {
|
||||
if location.position == 0 {
|
||||
return Err(Error::NotFound("Record not found".to_string()));
|
||||
}
|
||||
|
||||
// Select the file
|
||||
self.db_file_select(location.file_nr)?;
|
||||
|
||||
let file = self
|
||||
.file
|
||||
.as_mut()
|
||||
.ok_or_else(|| Error::Other("No file open".to_string()))?;
|
||||
|
||||
// Read size first
|
||||
file.seek(SeekFrom::Start(location.position as u64))?;
|
||||
let mut size_bytes = vec![0u8; 2];
|
||||
file.read_exact(&mut size_bytes)?;
|
||||
let size = u16::from(size_bytes[0]) | (u16::from(size_bytes[1]) << 8);
|
||||
|
||||
// Write zeros for the entire record (header + data)
|
||||
let zeros = vec![0u8; HEADER_SIZE + size as usize];
|
||||
file.seek(SeekFrom::Start(location.position as u64))?;
|
||||
file.write_all(&zeros)?;
|
||||
|
||||
// Clear lookup entry
|
||||
self.lookup.delete(id)?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Condenses the database by removing empty records and updating positions
|
||||
pub fn condense(&mut self) -> Result<(), Error> {
|
||||
// Create a temporary directory
|
||||
let temp_path = self.path.join("temp");
|
||||
fs::create_dir_all(&temp_path)?;
|
||||
|
||||
// Get all file numbers
|
||||
let mut file_numbers = Vec::new();
|
||||
for entry in fs::read_dir(&self.path)? {
|
||||
let entry = entry?;
|
||||
let path = entry.path();
|
||||
|
||||
if path.is_file() && path.extension().map_or(false, |ext| ext == "db") {
|
||||
if let Some(stem) = path.file_stem() {
|
||||
if let Ok(file_nr) = stem.to_string_lossy().parse::<u16>() {
|
||||
file_numbers.push(file_nr);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Process each file
|
||||
for file_nr in file_numbers {
|
||||
let src_path = self.path.join(format!("{}.db", file_nr));
|
||||
let temp_file_path = temp_path.join(format!("{}.db", file_nr));
|
||||
|
||||
// Create new file
|
||||
let mut temp_file = File::create(&temp_file_path)?;
|
||||
temp_file.write_all(&[0u8])?; // Initialize with a byte
|
||||
|
||||
// Open source file
|
||||
let mut src_file = File::open(&src_path)?;
|
||||
|
||||
// Read and process records
|
||||
let mut buffer = vec![0u8; 1024]; // Read in chunks
|
||||
let mut _position = 0;
|
||||
|
||||
while let Ok(bytes_read) = src_file.read(&mut buffer) {
|
||||
if bytes_read == 0 {
|
||||
break;
|
||||
}
|
||||
|
||||
// Process the chunk
|
||||
// This is a simplified version - in a real implementation,
|
||||
// you would need to handle records that span chunk boundaries
|
||||
|
||||
_position += bytes_read;
|
||||
}
|
||||
|
||||
// TODO: Implement proper record copying and position updating
|
||||
// This would involve:
|
||||
// 1. Reading each record from the source file
|
||||
// 2. If not deleted (all zeros), copy to temp file
|
||||
// 3. Update lookup table with new positions
|
||||
}
|
||||
|
||||
// TODO: Replace original files with temp files
|
||||
|
||||
// Clean up
|
||||
fs::remove_dir_all(&temp_path)?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
/// Calculates CRC32 for the data
|
||||
fn calculate_crc(data: &[u8]) -> u32 {
|
||||
let mut hasher = Hasher::new();
|
||||
hasher.update(data);
|
||||
hasher.finalize()
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use std::path::PathBuf;
|
||||
|
||||
use crate::{OurDB, OurDBConfig, OurDBSetArgs};
|
||||
use std::env::temp_dir;
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
|
||||
fn get_temp_dir() -> PathBuf {
|
||||
let timestamp = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_secs();
|
||||
temp_dir().join(format!("ourdb_backend_test_{}", timestamp))
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_backend_operations() {
|
||||
let temp_dir = get_temp_dir();
|
||||
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: false,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: None, // Don't reset existing database
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
// Test set and get
|
||||
let test_data = b"Test data for backend operations";
|
||||
let id = 1;
|
||||
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id),
|
||||
data: test_data,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let retrieved = db.get(id).unwrap();
|
||||
assert_eq!(retrieved, test_data);
|
||||
|
||||
// Clean up
|
||||
db.destroy().unwrap();
|
||||
}
|
||||
}
|
41
packages/data/ourdb/src/error.rs
Normal file
41
packages/data/ourdb/src/error.rs
Normal file
@@ -0,0 +1,41 @@
|
||||
use thiserror::Error;
|
||||
|
||||
/// Error types for OurDB operations
|
||||
#[derive(Error, Debug)]
|
||||
pub enum Error {
|
||||
/// IO errors from file operations
|
||||
#[error("IO error: {0}")]
|
||||
Io(#[from] std::io::Error),
|
||||
|
||||
/// Data corruption errors
|
||||
#[error("Data corruption: {0}")]
|
||||
DataCorruption(String),
|
||||
|
||||
/// Invalid operation errors
|
||||
#[error("Invalid operation: {0}")]
|
||||
InvalidOperation(String),
|
||||
|
||||
/// Lookup table errors
|
||||
#[error("Lookup error: {0}")]
|
||||
LookupError(String),
|
||||
|
||||
/// Record not found errors
|
||||
#[error("Record not found: {0}")]
|
||||
NotFound(String),
|
||||
|
||||
/// Other errors
|
||||
#[error("Error: {0}")]
|
||||
Other(String),
|
||||
}
|
||||
|
||||
impl From<String> for Error {
|
||||
fn from(msg: String) -> Self {
|
||||
Error::Other(msg)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<&str> for Error {
|
||||
fn from(msg: &str) -> Self {
|
||||
Error::Other(msg.to_string())
|
||||
}
|
||||
}
|
293
packages/data/ourdb/src/lib.rs
Normal file
293
packages/data/ourdb/src/lib.rs
Normal file
@@ -0,0 +1,293 @@
|
||||
mod backend;
|
||||
mod error;
|
||||
mod location;
|
||||
mod lookup;
|
||||
|
||||
pub use error::Error;
|
||||
pub use location::Location;
|
||||
pub use lookup::LookupTable;
|
||||
|
||||
use std::fs::File;
|
||||
use std::path::PathBuf;
|
||||
|
||||
/// OurDB is a lightweight, efficient key-value database implementation that provides
|
||||
/// data persistence with history tracking capabilities.
|
||||
pub struct OurDB {
|
||||
/// Directory path for storage
|
||||
path: PathBuf,
|
||||
/// Whether to use auto-increment mode
|
||||
incremental_mode: bool,
|
||||
/// Maximum file size (default: 500MB)
|
||||
file_size: u32,
|
||||
/// Lookup table for mapping keys to locations
|
||||
lookup: LookupTable,
|
||||
/// Currently open file
|
||||
file: Option<File>,
|
||||
/// Current file number
|
||||
file_nr: u16,
|
||||
/// Last used file number
|
||||
last_used_file_nr: u16,
|
||||
}
|
||||
|
||||
/// Configuration for creating a new OurDB instance
|
||||
pub struct OurDBConfig {
|
||||
/// Directory path for storage
|
||||
pub path: PathBuf,
|
||||
/// Whether to use auto-increment mode
|
||||
pub incremental_mode: bool,
|
||||
/// Maximum file size (default: 500MB)
|
||||
pub file_size: Option<u32>,
|
||||
/// Lookup table key size (default: 4)
|
||||
/// - 2: For databases with < 65,536 records (single file)
|
||||
/// - 3: For databases with < 16,777,216 records (single file)
|
||||
/// - 4: For databases with < 4,294,967,296 records (single file)
|
||||
/// - 6: For large databases requiring multiple files (default)
|
||||
pub keysize: Option<u8>,
|
||||
/// Whether to reset the database if it exists (default: false)
|
||||
pub reset: Option<bool>,
|
||||
}
|
||||
|
||||
/// Arguments for setting a value in OurDB
|
||||
pub struct OurDBSetArgs<'a> {
|
||||
/// ID for the record (optional in incremental mode)
|
||||
pub id: Option<u32>,
|
||||
/// Data to store
|
||||
pub data: &'a [u8],
|
||||
}
|
||||
|
||||
impl OurDB {
|
||||
/// Creates a new OurDB instance with the given configuration
|
||||
pub fn new(config: OurDBConfig) -> Result<Self, Error> {
|
||||
// If reset is true and the path exists, remove it first
|
||||
if config.reset.unwrap_or(false) && config.path.exists() {
|
||||
std::fs::remove_dir_all(&config.path)?;
|
||||
}
|
||||
|
||||
// Create directory if it doesn't exist
|
||||
std::fs::create_dir_all(&config.path)?;
|
||||
|
||||
// Create lookup table
|
||||
let lookup_path = config.path.join("lookup");
|
||||
std::fs::create_dir_all(&lookup_path)?;
|
||||
|
||||
let lookup_config = lookup::LookupConfig {
|
||||
size: 1000000, // Default size
|
||||
keysize: config.keysize.unwrap_or(4),
|
||||
lookuppath: lookup_path.to_string_lossy().to_string(),
|
||||
incremental_mode: config.incremental_mode,
|
||||
};
|
||||
|
||||
let lookup = LookupTable::new(lookup_config)?;
|
||||
|
||||
let mut db = OurDB {
|
||||
path: config.path,
|
||||
incremental_mode: config.incremental_mode,
|
||||
file_size: config.file_size.unwrap_or(500 * (1 << 20)), // 500MB default
|
||||
lookup,
|
||||
file: None,
|
||||
file_nr: 0,
|
||||
last_used_file_nr: 0,
|
||||
};
|
||||
|
||||
// Load existing metadata if available
|
||||
db.load()?;
|
||||
|
||||
Ok(db)
|
||||
}
|
||||
|
||||
/// Sets a value in the database
|
||||
///
|
||||
/// In incremental mode:
|
||||
/// - If ID is provided, it updates an existing record
|
||||
/// - If ID is not provided, it creates a new record with auto-generated ID
|
||||
///
|
||||
/// In key-value mode:
|
||||
/// - ID must be provided
|
||||
pub fn set(&mut self, args: OurDBSetArgs) -> Result<u32, Error> {
|
||||
if self.incremental_mode {
|
||||
if let Some(id) = args.id {
|
||||
// This is an update
|
||||
let location = self.lookup.get(id)?;
|
||||
if location.position == 0 {
|
||||
return Err(Error::InvalidOperation(
|
||||
"Cannot set ID for insertions when incremental mode is enabled".to_string(),
|
||||
));
|
||||
}
|
||||
|
||||
self.set_(id, location, args.data)?;
|
||||
Ok(id)
|
||||
} else {
|
||||
// This is an insert
|
||||
let id = self.lookup.get_next_id()?;
|
||||
self.set_(id, Location::default(), args.data)?;
|
||||
Ok(id)
|
||||
}
|
||||
} else {
|
||||
// Using key-value mode
|
||||
let id = args.id.ok_or_else(|| {
|
||||
Error::InvalidOperation(
|
||||
"ID must be provided when incremental is disabled".to_string(),
|
||||
)
|
||||
})?;
|
||||
|
||||
let location = self.lookup.get(id)?;
|
||||
self.set_(id, location, args.data)?;
|
||||
Ok(id)
|
||||
}
|
||||
}
|
||||
|
||||
/// Retrieves data stored at the specified key position
|
||||
pub fn get(&mut self, id: u32) -> Result<Vec<u8>, Error> {
|
||||
let location = self.lookup.get(id)?;
|
||||
self.get_(location)
|
||||
}
|
||||
|
||||
/// Retrieves a list of previous values for the specified key
|
||||
///
|
||||
/// The depth parameter controls how many historical values to retrieve (maximum)
|
||||
pub fn get_history(&mut self, id: u32, depth: u8) -> Result<Vec<Vec<u8>>, Error> {
|
||||
let mut result = Vec::new();
|
||||
let mut current_location = self.lookup.get(id)?;
|
||||
|
||||
// Traverse the history chain up to specified depth
|
||||
for _ in 0..depth {
|
||||
// Get current value
|
||||
let data = self.get_(current_location)?;
|
||||
result.push(data);
|
||||
|
||||
// Try to get previous location
|
||||
match self.get_prev_pos_(current_location) {
|
||||
Ok(location) => {
|
||||
if location.position == 0 {
|
||||
break;
|
||||
}
|
||||
current_location = location;
|
||||
}
|
||||
Err(_) => break,
|
||||
}
|
||||
}
|
||||
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
/// Deletes the data at the specified key position
|
||||
pub fn delete(&mut self, id: u32) -> Result<(), Error> {
|
||||
let location = self.lookup.get(id)?;
|
||||
self.delete_(id, location)?;
|
||||
self.lookup.delete(id)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Returns the next ID which will be used when storing in incremental mode
|
||||
pub fn get_next_id(&mut self) -> Result<u32, Error> {
|
||||
if !self.incremental_mode {
|
||||
return Err(Error::InvalidOperation(
|
||||
"Incremental mode is not enabled".to_string(),
|
||||
));
|
||||
}
|
||||
self.lookup.get_next_id()
|
||||
}
|
||||
|
||||
/// Closes the database, ensuring all data is saved
|
||||
pub fn close(&mut self) -> Result<(), Error> {
|
||||
self.save()?;
|
||||
self.close_();
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Destroys the database, removing all files
|
||||
pub fn destroy(&mut self) -> Result<(), Error> {
|
||||
let _ = self.close();
|
||||
std::fs::remove_dir_all(&self.path)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
// Helper methods
|
||||
fn lookup_dump_path(&self) -> PathBuf {
|
||||
self.path.join("lookup_dump.db")
|
||||
}
|
||||
|
||||
fn load(&mut self) -> Result<(), Error> {
|
||||
let dump_path = self.lookup_dump_path();
|
||||
if dump_path.exists() {
|
||||
self.lookup.import_sparse(&dump_path.to_string_lossy())?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn save(&mut self) -> Result<(), Error> {
|
||||
self.lookup
|
||||
.export_sparse(&self.lookup_dump_path().to_string_lossy())?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn close_(&mut self) {
|
||||
self.file = None;
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use std::env::temp_dir;
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
|
||||
fn get_temp_dir() -> PathBuf {
|
||||
let timestamp = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_secs();
|
||||
temp_dir().join(format!("ourdb_test_{}", timestamp))
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_basic_operations() {
|
||||
let temp_dir = get_temp_dir();
|
||||
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: None, // Don't reset existing database
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
// Test set and get
|
||||
let test_data = b"Hello, OurDB!";
|
||||
let id = db
|
||||
.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: test_data,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let retrieved = db.get(id).unwrap();
|
||||
assert_eq!(retrieved, test_data);
|
||||
|
||||
// Test update
|
||||
let updated_data = b"Updated data";
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id),
|
||||
data: updated_data,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let retrieved = db.get(id).unwrap();
|
||||
assert_eq!(retrieved, updated_data);
|
||||
|
||||
// Test history
|
||||
let history = db.get_history(id, 2).unwrap();
|
||||
assert_eq!(history.len(), 2);
|
||||
assert_eq!(history[0], updated_data);
|
||||
assert_eq!(history[1], test_data);
|
||||
|
||||
// Test delete
|
||||
db.delete(id).unwrap();
|
||||
assert!(db.get(id).is_err());
|
||||
|
||||
// Clean up
|
||||
db.destroy().unwrap();
|
||||
}
|
||||
}
|
178
packages/data/ourdb/src/location.rs
Normal file
178
packages/data/ourdb/src/location.rs
Normal file
@@ -0,0 +1,178 @@
|
||||
use crate::error::Error;
|
||||
|
||||
/// Location represents a physical position in a database file
|
||||
///
|
||||
/// It consists of a file number and a position within that file.
|
||||
/// This allows OurDB to span multiple files for large datasets.
|
||||
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
|
||||
pub struct Location {
|
||||
/// File number (0-65535)
|
||||
pub file_nr: u16,
|
||||
/// Position within the file
|
||||
pub position: u32,
|
||||
}
|
||||
|
||||
impl Location {
|
||||
/// Creates a new Location from bytes based on keysize
|
||||
///
|
||||
/// - keysize = 2: Only position (2 bytes), file_nr = 0
|
||||
/// - keysize = 3: Only position (3 bytes), file_nr = 0
|
||||
/// - keysize = 4: Only position (4 bytes), file_nr = 0
|
||||
/// - keysize = 6: file_nr (2 bytes) + position (4 bytes)
|
||||
pub fn from_bytes(bytes: &[u8], keysize: u8) -> Result<Self, Error> {
|
||||
// Validate keysize
|
||||
if ![2, 3, 4, 6].contains(&keysize) {
|
||||
return Err(Error::InvalidOperation(format!(
|
||||
"Invalid keysize: {}",
|
||||
keysize
|
||||
)));
|
||||
}
|
||||
|
||||
// Create padded bytes
|
||||
let mut padded = vec![0u8; keysize as usize];
|
||||
if bytes.len() > keysize as usize {
|
||||
return Err(Error::InvalidOperation(
|
||||
"Input bytes exceed keysize".to_string(),
|
||||
));
|
||||
}
|
||||
let start_idx = keysize as usize - bytes.len();
|
||||
|
||||
for (i, &b) in bytes.iter().enumerate() {
|
||||
if i + start_idx < padded.len() {
|
||||
padded[start_idx + i] = b;
|
||||
}
|
||||
}
|
||||
|
||||
let mut location = Location::default();
|
||||
|
||||
match keysize {
|
||||
2 => {
|
||||
// Only position, 2 bytes big endian
|
||||
location.position = u32::from(padded[0]) << 8 | u32::from(padded[1]);
|
||||
location.file_nr = 0;
|
||||
|
||||
// Verify limits
|
||||
if location.position > 0xFFFF {
|
||||
return Err(Error::InvalidOperation(
|
||||
"Position exceeds max value for keysize=2 (max 65535)".to_string(),
|
||||
));
|
||||
}
|
||||
}
|
||||
3 => {
|
||||
// Only position, 3 bytes big endian
|
||||
location.position =
|
||||
u32::from(padded[0]) << 16 | u32::from(padded[1]) << 8 | u32::from(padded[2]);
|
||||
location.file_nr = 0;
|
||||
|
||||
// Verify limits
|
||||
if location.position > 0xFFFFFF {
|
||||
return Err(Error::InvalidOperation(
|
||||
"Position exceeds max value for keysize=3 (max 16777215)".to_string(),
|
||||
));
|
||||
}
|
||||
}
|
||||
4 => {
|
||||
// Only position, 4 bytes big endian
|
||||
location.position = u32::from(padded[0]) << 24
|
||||
| u32::from(padded[1]) << 16
|
||||
| u32::from(padded[2]) << 8
|
||||
| u32::from(padded[3]);
|
||||
location.file_nr = 0;
|
||||
}
|
||||
6 => {
|
||||
// 2 bytes file_nr + 4 bytes position, all big endian
|
||||
location.file_nr = u16::from(padded[0]) << 8 | u16::from(padded[1]);
|
||||
location.position = u32::from(padded[2]) << 24
|
||||
| u32::from(padded[3]) << 16
|
||||
| u32::from(padded[4]) << 8
|
||||
| u32::from(padded[5]);
|
||||
}
|
||||
_ => unreachable!(),
|
||||
}
|
||||
|
||||
Ok(location)
|
||||
}
|
||||
|
||||
/// Converts the location to bytes (always 6 bytes)
|
||||
///
|
||||
/// Format: [file_nr (2 bytes)][position (4 bytes)]
|
||||
pub fn to_bytes(&self) -> Vec<u8> {
|
||||
let mut bytes = Vec::with_capacity(6);
|
||||
|
||||
// Put file_nr first (2 bytes)
|
||||
bytes.push((self.file_nr >> 8) as u8);
|
||||
bytes.push(self.file_nr as u8);
|
||||
|
||||
// Put position next (4 bytes)
|
||||
bytes.push((self.position >> 24) as u8);
|
||||
bytes.push((self.position >> 16) as u8);
|
||||
bytes.push((self.position >> 8) as u8);
|
||||
bytes.push(self.position as u8);
|
||||
|
||||
bytes
|
||||
}
|
||||
|
||||
/// Converts the location to a u64 value
|
||||
///
|
||||
/// The file_nr is stored in the most significant bits
|
||||
pub fn to_u64(&self) -> u64 {
|
||||
(u64::from(self.file_nr) << 32) | u64::from(self.position)
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn test_location_from_bytes_keysize_2() {
|
||||
let bytes = vec![0x12, 0x34];
|
||||
let location = Location::from_bytes(&bytes, 2).unwrap();
|
||||
assert_eq!(location.file_nr, 0);
|
||||
assert_eq!(location.position, 0x1234);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_location_from_bytes_keysize_3() {
|
||||
let bytes = vec![0x12, 0x34, 0x56];
|
||||
let location = Location::from_bytes(&bytes, 3).unwrap();
|
||||
assert_eq!(location.file_nr, 0);
|
||||
assert_eq!(location.position, 0x123456);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_location_from_bytes_keysize_4() {
|
||||
let bytes = vec![0x12, 0x34, 0x56, 0x78];
|
||||
let location = Location::from_bytes(&bytes, 4).unwrap();
|
||||
assert_eq!(location.file_nr, 0);
|
||||
assert_eq!(location.position, 0x12345678);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_location_from_bytes_keysize_6() {
|
||||
let bytes = vec![0xAB, 0xCD, 0x12, 0x34, 0x56, 0x78];
|
||||
let location = Location::from_bytes(&bytes, 6).unwrap();
|
||||
assert_eq!(location.file_nr, 0xABCD);
|
||||
assert_eq!(location.position, 0x12345678);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_location_to_bytes() {
|
||||
let location = Location {
|
||||
file_nr: 0xABCD,
|
||||
position: 0x12345678,
|
||||
};
|
||||
let bytes = location.to_bytes();
|
||||
assert_eq!(bytes, vec![0xAB, 0xCD, 0x12, 0x34, 0x56, 0x78]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_location_to_u64() {
|
||||
let location = Location {
|
||||
file_nr: 0xABCD,
|
||||
position: 0x12345678,
|
||||
};
|
||||
let value = location.to_u64();
|
||||
assert_eq!(value, 0xABCD_0000_0000 | 0x12345678);
|
||||
}
|
||||
}
|
540
packages/data/ourdb/src/lookup.rs
Normal file
540
packages/data/ourdb/src/lookup.rs
Normal file
@@ -0,0 +1,540 @@
|
||||
use std::fs::{self, File, OpenOptions};
|
||||
use std::io::{Read, Seek, SeekFrom, Write};
|
||||
use std::path::Path;
|
||||
|
||||
use crate::error::Error;
|
||||
use crate::location::Location;
|
||||
|
||||
const DATA_FILE_NAME: &str = "data";
|
||||
const INCREMENTAL_FILE_NAME: &str = ".inc";
|
||||
|
||||
/// Configuration for creating a new lookup table
|
||||
pub struct LookupConfig {
|
||||
/// Size of the lookup table
|
||||
pub size: u32,
|
||||
/// Size of each entry in bytes (2-6)
|
||||
/// - 2: For databases with < 65,536 records (single file)
|
||||
/// - 3: For databases with < 16,777,216 records (single file)
|
||||
/// - 4: For databases with < 4,294,967,296 records (single file)
|
||||
/// - 6: For large databases requiring multiple files
|
||||
pub keysize: u8,
|
||||
/// Path for disk-based lookup
|
||||
pub lookuppath: String,
|
||||
/// Whether to use incremental mode
|
||||
pub incremental_mode: bool,
|
||||
}
|
||||
|
||||
/// Lookup table maps keys to physical locations in the backend storage
|
||||
pub struct LookupTable {
|
||||
/// Size of each entry in bytes (2-6)
|
||||
keysize: u8,
|
||||
/// Path for disk-based lookup
|
||||
lookuppath: String,
|
||||
/// In-memory data for memory-based lookup
|
||||
data: Vec<u8>,
|
||||
/// Next empty slot if incremental mode is enabled
|
||||
incremental: Option<u32>,
|
||||
}
|
||||
|
||||
impl LookupTable {
|
||||
/// Returns the keysize of this lookup table
|
||||
pub fn keysize(&self) -> u8 {
|
||||
self.keysize
|
||||
}
|
||||
|
||||
/// Creates a new lookup table with the given configuration
|
||||
pub fn new(config: LookupConfig) -> Result<Self, Error> {
|
||||
// Verify keysize is valid
|
||||
if ![2, 3, 4, 6].contains(&config.keysize) {
|
||||
return Err(Error::InvalidOperation(format!(
|
||||
"Invalid keysize: {}",
|
||||
config.keysize
|
||||
)));
|
||||
}
|
||||
|
||||
let incremental = if config.incremental_mode {
|
||||
Some(get_incremental_info(&config)?)
|
||||
} else {
|
||||
None
|
||||
};
|
||||
|
||||
if !config.lookuppath.is_empty() {
|
||||
// Create directory if it doesn't exist
|
||||
fs::create_dir_all(&config.lookuppath)?;
|
||||
|
||||
// For disk-based lookup, create empty file if it doesn't exist
|
||||
let data_path = Path::new(&config.lookuppath).join(DATA_FILE_NAME);
|
||||
if !data_path.exists() {
|
||||
let data = vec![0u8; config.size as usize * config.keysize as usize];
|
||||
fs::write(&data_path, &data)?;
|
||||
}
|
||||
|
||||
Ok(LookupTable {
|
||||
data: Vec::new(),
|
||||
keysize: config.keysize,
|
||||
lookuppath: config.lookuppath,
|
||||
incremental,
|
||||
})
|
||||
} else {
|
||||
// For memory-based lookup
|
||||
Ok(LookupTable {
|
||||
data: vec![0u8; config.size as usize * config.keysize as usize],
|
||||
keysize: config.keysize,
|
||||
lookuppath: String::new(),
|
||||
incremental,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
/// Gets a location for the given ID
|
||||
pub fn get(&self, id: u32) -> Result<Location, Error> {
|
||||
let entry_size = self.keysize as usize;
|
||||
|
||||
if !self.lookuppath.is_empty() {
|
||||
// Disk-based lookup
|
||||
let data_path = Path::new(&self.lookuppath).join(DATA_FILE_NAME);
|
||||
|
||||
// Check file size first
|
||||
let file_size = fs::metadata(&data_path)?.len();
|
||||
let start_pos = id as u64 * entry_size as u64;
|
||||
|
||||
if start_pos + entry_size as u64 > file_size {
|
||||
return Err(Error::LookupError(format!(
|
||||
"Invalid read for get in lut: {}: {} would exceed file size {}",
|
||||
self.lookuppath,
|
||||
start_pos + entry_size as u64,
|
||||
file_size
|
||||
)));
|
||||
}
|
||||
|
||||
// Read directly from file
|
||||
let mut file = File::open(&data_path)?;
|
||||
file.seek(SeekFrom::Start(start_pos))?;
|
||||
|
||||
let mut data = vec![0u8; entry_size];
|
||||
let bytes_read = file.read(&mut data)?;
|
||||
|
||||
if bytes_read < entry_size {
|
||||
return Err(Error::LookupError(format!(
|
||||
"Incomplete read: expected {} bytes but got {}",
|
||||
entry_size, bytes_read
|
||||
)));
|
||||
}
|
||||
|
||||
return Location::from_bytes(&data, self.keysize);
|
||||
}
|
||||
|
||||
// Memory-based lookup
|
||||
if (id * self.keysize as u32) as usize >= self.data.len() {
|
||||
return Err(Error::LookupError("Index out of bounds".to_string()));
|
||||
}
|
||||
|
||||
let start = (id * self.keysize as u32) as usize;
|
||||
let end = start + entry_size;
|
||||
|
||||
Location::from_bytes(&self.data[start..end], self.keysize)
|
||||
}
|
||||
|
||||
/// Sets a location for the given ID
|
||||
pub fn set(&mut self, id: u32, location: Location) -> Result<(), Error> {
|
||||
let entry_size = self.keysize as usize;
|
||||
|
||||
// Handle incremental mode
|
||||
if let Some(incremental) = self.incremental {
|
||||
if id == incremental {
|
||||
self.increment_index()?;
|
||||
}
|
||||
|
||||
if id > incremental {
|
||||
return Err(Error::InvalidOperation(
|
||||
"Cannot set ID for insertions when incremental mode is enabled".to_string(),
|
||||
));
|
||||
}
|
||||
}
|
||||
|
||||
// Convert location to bytes based on keysize
|
||||
let location_bytes = match self.keysize {
|
||||
2 => {
|
||||
if location.file_nr != 0 {
|
||||
return Err(Error::InvalidOperation(
|
||||
"file_nr must be 0 for keysize=2".to_string(),
|
||||
));
|
||||
}
|
||||
if location.position > 0xFFFF {
|
||||
return Err(Error::InvalidOperation(
|
||||
"position exceeds max value for keysize=2 (max 65535)".to_string(),
|
||||
));
|
||||
}
|
||||
vec![(location.position >> 8) as u8, location.position as u8]
|
||||
}
|
||||
3 => {
|
||||
if location.file_nr != 0 {
|
||||
return Err(Error::InvalidOperation(
|
||||
"file_nr must be 0 for keysize=3".to_string(),
|
||||
));
|
||||
}
|
||||
if location.position > 0xFFFFFF {
|
||||
return Err(Error::InvalidOperation(
|
||||
"position exceeds max value for keysize=3 (max 16777215)".to_string(),
|
||||
));
|
||||
}
|
||||
vec![
|
||||
(location.position >> 16) as u8,
|
||||
(location.position >> 8) as u8,
|
||||
location.position as u8,
|
||||
]
|
||||
}
|
||||
4 => {
|
||||
if location.file_nr != 0 {
|
||||
return Err(Error::InvalidOperation(
|
||||
"file_nr must be 0 for keysize=4".to_string(),
|
||||
));
|
||||
}
|
||||
vec![
|
||||
(location.position >> 24) as u8,
|
||||
(location.position >> 16) as u8,
|
||||
(location.position >> 8) as u8,
|
||||
location.position as u8,
|
||||
]
|
||||
}
|
||||
6 => {
|
||||
// Full location with file_nr and position
|
||||
location.to_bytes()
|
||||
}
|
||||
_ => {
|
||||
return Err(Error::InvalidOperation(format!(
|
||||
"Invalid keysize: {}",
|
||||
self.keysize
|
||||
)))
|
||||
}
|
||||
};
|
||||
|
||||
if !self.lookuppath.is_empty() {
|
||||
// Disk-based lookup
|
||||
let data_path = Path::new(&self.lookuppath).join(DATA_FILE_NAME);
|
||||
let mut file = OpenOptions::new().write(true).open(data_path)?;
|
||||
|
||||
let start_pos = id as u64 * entry_size as u64;
|
||||
file.seek(SeekFrom::Start(start_pos))?;
|
||||
file.write_all(&location_bytes)?;
|
||||
} else {
|
||||
// Memory-based lookup
|
||||
let start = (id * self.keysize as u32) as usize;
|
||||
if start + entry_size > self.data.len() {
|
||||
return Err(Error::LookupError("Index out of bounds".to_string()));
|
||||
}
|
||||
|
||||
for (i, &byte) in location_bytes.iter().enumerate() {
|
||||
self.data[start + i] = byte;
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Deletes an entry for the given ID
|
||||
pub fn delete(&mut self, id: u32) -> Result<(), Error> {
|
||||
// Set location to all zeros
|
||||
self.set(id, Location::default())
|
||||
}
|
||||
|
||||
/// Gets the next available ID in incremental mode
|
||||
pub fn get_next_id(&self) -> Result<u32, Error> {
|
||||
let incremental = self.incremental.ok_or_else(|| {
|
||||
Error::InvalidOperation("Lookup table not in incremental mode".to_string())
|
||||
})?;
|
||||
|
||||
let table_size = if !self.lookuppath.is_empty() {
|
||||
let data_path = Path::new(&self.lookuppath).join(DATA_FILE_NAME);
|
||||
fs::metadata(data_path)?.len() as u32
|
||||
} else {
|
||||
self.data.len() as u32
|
||||
};
|
||||
|
||||
if incremental * self.keysize as u32 >= table_size {
|
||||
return Err(Error::LookupError("Lookup table is full".to_string()));
|
||||
}
|
||||
|
||||
Ok(incremental)
|
||||
}
|
||||
|
||||
/// Increments the index in incremental mode
|
||||
pub fn increment_index(&mut self) -> Result<(), Error> {
|
||||
let mut incremental = self.incremental.ok_or_else(|| {
|
||||
Error::InvalidOperation("Lookup table not in incremental mode".to_string())
|
||||
})?;
|
||||
|
||||
incremental += 1;
|
||||
self.incremental = Some(incremental);
|
||||
|
||||
if !self.lookuppath.is_empty() {
|
||||
let inc_path = Path::new(&self.lookuppath).join(INCREMENTAL_FILE_NAME);
|
||||
fs::write(inc_path, incremental.to_string())?;
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Exports the lookup table to a file
|
||||
pub fn export_data(&self, path: &str) -> Result<(), Error> {
|
||||
if !self.lookuppath.is_empty() {
|
||||
// For disk-based lookup, just copy the file
|
||||
let data_path = Path::new(&self.lookuppath).join(DATA_FILE_NAME);
|
||||
fs::copy(data_path, path)?;
|
||||
} else {
|
||||
// For memory-based lookup, write the data to file
|
||||
fs::write(path, &self.data)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Imports the lookup table from a file
|
||||
pub fn import_data(&mut self, path: &str) -> Result<(), Error> {
|
||||
if !self.lookuppath.is_empty() {
|
||||
// For disk-based lookup, copy the file
|
||||
let data_path = Path::new(&self.lookuppath).join(DATA_FILE_NAME);
|
||||
fs::copy(path, data_path)?;
|
||||
} else {
|
||||
// For memory-based lookup, read the data from file
|
||||
self.data = fs::read(path)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Exports only non-zero entries to save space
|
||||
pub fn export_sparse(&self, path: &str) -> Result<(), Error> {
|
||||
let mut output = Vec::new();
|
||||
let entry_size = self.keysize as usize;
|
||||
|
||||
if !self.lookuppath.is_empty() {
|
||||
// For disk-based lookup
|
||||
let data_path = Path::new(&self.lookuppath).join(DATA_FILE_NAME);
|
||||
let mut file = File::open(&data_path)?;
|
||||
let file_size = fs::metadata(&data_path)?.len();
|
||||
let max_entries = file_size / entry_size as u64;
|
||||
|
||||
for id in 0..max_entries {
|
||||
file.seek(SeekFrom::Start(id * entry_size as u64))?;
|
||||
|
||||
let mut buffer = vec![0u8; entry_size];
|
||||
let bytes_read = file.read(&mut buffer)?;
|
||||
|
||||
if bytes_read < entry_size {
|
||||
break;
|
||||
}
|
||||
|
||||
// Check if entry is non-zero
|
||||
if buffer.iter().any(|&b| b != 0) {
|
||||
// Write ID (4 bytes) + entry
|
||||
output.extend_from_slice(&(id as u32).to_be_bytes());
|
||||
output.extend_from_slice(&buffer);
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// For memory-based lookup
|
||||
let max_entries = self.data.len() / entry_size;
|
||||
|
||||
for id in 0..max_entries {
|
||||
let start = id * entry_size;
|
||||
let entry = &self.data[start..start + entry_size];
|
||||
|
||||
// Check if entry is non-zero
|
||||
if entry.iter().any(|&b| b != 0) {
|
||||
// Write ID (4 bytes) + entry
|
||||
output.extend_from_slice(&(id as u32).to_be_bytes());
|
||||
output.extend_from_slice(entry);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Write the output to file
|
||||
fs::write(path, &output)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Imports sparse data (only non-zero entries)
|
||||
pub fn import_sparse(&mut self, path: &str) -> Result<(), Error> {
|
||||
let data = fs::read(path)?;
|
||||
let entry_size = self.keysize as usize;
|
||||
let record_size = 4 + entry_size; // ID (4 bytes) + entry
|
||||
|
||||
if data.len() % record_size != 0 {
|
||||
return Err(Error::DataCorruption(
|
||||
"Invalid sparse data format: size mismatch".to_string(),
|
||||
));
|
||||
}
|
||||
|
||||
for chunk_start in (0..data.len()).step_by(record_size) {
|
||||
if chunk_start + record_size > data.len() {
|
||||
break;
|
||||
}
|
||||
|
||||
// Extract ID (4 bytes)
|
||||
let id_bytes = &data[chunk_start..chunk_start + 4];
|
||||
let id = u32::from_be_bytes([id_bytes[0], id_bytes[1], id_bytes[2], id_bytes[3]]);
|
||||
|
||||
// Extract entry
|
||||
let entry = &data[chunk_start + 4..chunk_start + record_size];
|
||||
|
||||
// Create location from entry
|
||||
let location = Location::from_bytes(entry, self.keysize)?;
|
||||
|
||||
// Set the entry
|
||||
self.set(id, location)?;
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Finds the highest ID with a non-zero entry
|
||||
pub fn find_last_entry(&mut self) -> Result<u32, Error> {
|
||||
let mut last_id = 0u32;
|
||||
let entry_size = self.keysize as usize;
|
||||
|
||||
if !self.lookuppath.is_empty() {
|
||||
// For disk-based lookup
|
||||
let data_path = Path::new(&self.lookuppath).join(DATA_FILE_NAME);
|
||||
let mut file = File::open(&data_path)?;
|
||||
let file_size = fs::metadata(&data_path)?.len();
|
||||
|
||||
let mut buffer = vec![0u8; entry_size];
|
||||
let mut pos = 0u32;
|
||||
|
||||
while (pos as u64 * entry_size as u64) < file_size {
|
||||
file.seek(SeekFrom::Start(pos as u64 * entry_size as u64))?;
|
||||
|
||||
let bytes_read = file.read(&mut buffer)?;
|
||||
if bytes_read == 0 || bytes_read < entry_size {
|
||||
break;
|
||||
}
|
||||
|
||||
let location = Location::from_bytes(&buffer, self.keysize)?;
|
||||
if location.position != 0 || location.file_nr != 0 {
|
||||
last_id = pos;
|
||||
}
|
||||
|
||||
pos += 1;
|
||||
}
|
||||
} else {
|
||||
// For memory-based lookup
|
||||
for i in 0..(self.data.len() / entry_size) as u32 {
|
||||
if let Ok(location) = self.get(i) {
|
||||
if location.position != 0 || location.file_nr != 0 {
|
||||
last_id = i;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(last_id)
|
||||
}
|
||||
}
|
||||
|
||||
/// Helper function to get the incremental value
|
||||
fn get_incremental_info(config: &LookupConfig) -> Result<u32, Error> {
|
||||
if !config.incremental_mode {
|
||||
return Ok(0);
|
||||
}
|
||||
|
||||
if !config.lookuppath.is_empty() {
|
||||
let inc_path = Path::new(&config.lookuppath).join(INCREMENTAL_FILE_NAME);
|
||||
|
||||
if !inc_path.exists() {
|
||||
// Create a separate file for storing the incremental value
|
||||
fs::write(&inc_path, "1")?;
|
||||
}
|
||||
|
||||
let inc_str = fs::read_to_string(&inc_path)?;
|
||||
let incremental = match inc_str.trim().parse::<u32>() {
|
||||
Ok(val) => val,
|
||||
Err(_) => {
|
||||
// If the value is invalid, reset it to 1
|
||||
fs::write(&inc_path, "1")?;
|
||||
1
|
||||
}
|
||||
};
|
||||
|
||||
Ok(incremental)
|
||||
} else {
|
||||
// For memory-based lookup, start with 1
|
||||
Ok(1)
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use std::env::temp_dir;
|
||||
use std::path::PathBuf;
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
|
||||
fn get_temp_dir() -> PathBuf {
|
||||
let timestamp = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_secs();
|
||||
temp_dir().join(format!("ourdb_lookup_test_{}", timestamp))
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_memory_lookup() {
|
||||
let config = LookupConfig {
|
||||
size: 1000,
|
||||
keysize: 4,
|
||||
lookuppath: String::new(),
|
||||
incremental_mode: true,
|
||||
};
|
||||
|
||||
let mut lookup = LookupTable::new(config).unwrap();
|
||||
|
||||
// Test set and get
|
||||
let location = Location {
|
||||
file_nr: 0,
|
||||
position: 12345,
|
||||
};
|
||||
|
||||
lookup.set(1, location).unwrap();
|
||||
let retrieved = lookup.get(1).unwrap();
|
||||
|
||||
assert_eq!(retrieved.file_nr, location.file_nr);
|
||||
assert_eq!(retrieved.position, location.position);
|
||||
|
||||
// Test incremental mode
|
||||
let next_id = lookup.get_next_id().unwrap();
|
||||
assert_eq!(next_id, 2);
|
||||
|
||||
lookup.increment_index().unwrap();
|
||||
let next_id = lookup.get_next_id().unwrap();
|
||||
assert_eq!(next_id, 3);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_disk_lookup() {
|
||||
let temp_dir = get_temp_dir();
|
||||
fs::create_dir_all(&temp_dir).unwrap();
|
||||
|
||||
let config = LookupConfig {
|
||||
size: 1000,
|
||||
keysize: 4,
|
||||
lookuppath: temp_dir.to_string_lossy().to_string(),
|
||||
incremental_mode: true,
|
||||
};
|
||||
|
||||
let mut lookup = LookupTable::new(config).unwrap();
|
||||
|
||||
// Test set and get
|
||||
let location = Location {
|
||||
file_nr: 0,
|
||||
position: 12345,
|
||||
};
|
||||
|
||||
lookup.set(1, location).unwrap();
|
||||
let retrieved = lookup.get(1).unwrap();
|
||||
|
||||
assert_eq!(retrieved.file_nr, location.file_nr);
|
||||
assert_eq!(retrieved.position, location.position);
|
||||
|
||||
// Clean up
|
||||
fs::remove_dir_all(temp_dir).unwrap();
|
||||
}
|
||||
}
|
369
packages/data/ourdb/tests/integration_tests.rs
Normal file
369
packages/data/ourdb/tests/integration_tests.rs
Normal file
@@ -0,0 +1,369 @@
|
||||
use ourdb::{OurDB, OurDBConfig, OurDBSetArgs};
|
||||
use rand;
|
||||
use std::env::temp_dir;
|
||||
use std::fs;
|
||||
use std::path::PathBuf;
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
|
||||
// Helper function to create a unique temporary directory for tests
|
||||
fn get_temp_dir() -> PathBuf {
|
||||
let timestamp = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_nanos();
|
||||
let random_part = rand::random::<u32>();
|
||||
let dir = temp_dir().join(format!("ourdb_test_{}_{}", timestamp, random_part));
|
||||
|
||||
// Ensure the directory exists and is empty
|
||||
if dir.exists() {
|
||||
std::fs::remove_dir_all(&dir).unwrap();
|
||||
}
|
||||
std::fs::create_dir_all(&dir).unwrap();
|
||||
|
||||
dir
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_basic_operations() {
|
||||
let temp_dir = get_temp_dir();
|
||||
|
||||
// Create a new database with incremental mode
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: None,
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
// Test set and get
|
||||
let test_data = b"Hello, OurDB!";
|
||||
let id = db
|
||||
.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: test_data,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let retrieved = db.get(id).unwrap();
|
||||
assert_eq!(retrieved, test_data);
|
||||
|
||||
// Test update
|
||||
let updated_data = b"Updated data";
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id),
|
||||
data: updated_data,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let retrieved = db.get(id).unwrap();
|
||||
assert_eq!(retrieved, updated_data);
|
||||
|
||||
// Test history
|
||||
let history = db.get_history(id, 2).unwrap();
|
||||
assert_eq!(history.len(), 2);
|
||||
assert_eq!(history[0], updated_data);
|
||||
assert_eq!(history[1], test_data);
|
||||
|
||||
// Test delete
|
||||
db.delete(id).unwrap();
|
||||
assert!(db.get(id).is_err());
|
||||
|
||||
// Clean up
|
||||
db.destroy().unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_key_value_mode() {
|
||||
let temp_dir = get_temp_dir();
|
||||
|
||||
// Create a new database with key-value mode
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: false,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: None,
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
// Test set with explicit ID
|
||||
let test_data = b"Key-value data";
|
||||
let id = 42;
|
||||
db.set(OurDBSetArgs {
|
||||
id: Some(id),
|
||||
data: test_data,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let retrieved = db.get(id).unwrap();
|
||||
assert_eq!(retrieved, test_data);
|
||||
|
||||
// Verify next_id fails in key-value mode
|
||||
assert!(db.get_next_id().is_err());
|
||||
|
||||
// Clean up
|
||||
db.destroy().unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_incremental_mode() {
|
||||
let temp_dir = get_temp_dir();
|
||||
|
||||
// Create a new database with incremental mode
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: None,
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
// Test auto-increment IDs
|
||||
let data1 = b"First record";
|
||||
let id1 = db
|
||||
.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: data1,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let data2 = b"Second record";
|
||||
let id2 = db
|
||||
.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: data2,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// IDs should be sequential
|
||||
assert_eq!(id2, id1 + 1);
|
||||
|
||||
// Verify get_next_id works
|
||||
let next_id = db.get_next_id().unwrap();
|
||||
assert_eq!(next_id, id2 + 1);
|
||||
|
||||
// Clean up
|
||||
db.destroy().unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_persistence() {
|
||||
let temp_dir = get_temp_dir();
|
||||
|
||||
// Create data in a new database
|
||||
{
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: None,
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
let test_data = b"Persistent data";
|
||||
let id = db
|
||||
.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: test_data,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// Explicitly close the database
|
||||
db.close().unwrap();
|
||||
|
||||
// ID should be 1 in a new database
|
||||
assert_eq!(id, 1);
|
||||
}
|
||||
|
||||
// Reopen the database and verify data persists
|
||||
{
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: None,
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
// Verify data is still there
|
||||
let retrieved = db.get(1).unwrap();
|
||||
assert_eq!(retrieved, b"Persistent data");
|
||||
|
||||
// Verify incremental counter persisted
|
||||
let next_id = db.get_next_id().unwrap();
|
||||
assert_eq!(next_id, 2);
|
||||
|
||||
// Clean up
|
||||
db.destroy().unwrap();
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_different_keysizes() {
|
||||
for keysize in [2, 3, 4, 6].iter() {
|
||||
let temp_dir = get_temp_dir();
|
||||
|
||||
// Ensure the directory exists
|
||||
std::fs::create_dir_all(&temp_dir).unwrap();
|
||||
|
||||
// Create a new database with specified keysize
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: Some(*keysize),
|
||||
reset: None,
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
// Test basic operations
|
||||
let test_data = b"Keysize test data";
|
||||
let id = db
|
||||
.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: test_data,
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let retrieved = db.get(id).unwrap();
|
||||
assert_eq!(retrieved, test_data);
|
||||
|
||||
// Clean up
|
||||
db.destroy().unwrap();
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_large_data() {
|
||||
let temp_dir = get_temp_dir();
|
||||
|
||||
// Create a new database
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: None,
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
// Create a large data set (60KB - within the 64KB limit)
|
||||
let large_data = vec![b'X'; 60 * 1024];
|
||||
|
||||
// Store and retrieve large data
|
||||
let id = db
|
||||
.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: &large_data,
|
||||
})
|
||||
.unwrap();
|
||||
let retrieved = db.get(id).unwrap();
|
||||
|
||||
assert_eq!(retrieved.len(), large_data.len());
|
||||
assert_eq!(retrieved, large_data);
|
||||
|
||||
// Clean up
|
||||
db.destroy().unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_exceed_size_limit() {
|
||||
let temp_dir = get_temp_dir();
|
||||
|
||||
// Create a new database
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: None,
|
||||
keysize: None,
|
||||
reset: None,
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
// Create data larger than the 64KB limit (70KB)
|
||||
let oversized_data = vec![b'X'; 70 * 1024];
|
||||
|
||||
// Attempt to store data that exceeds the size limit
|
||||
let result = db.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: &oversized_data,
|
||||
});
|
||||
|
||||
// Verify that an error is returned
|
||||
assert!(
|
||||
result.is_err(),
|
||||
"Expected an error when storing data larger than 64KB"
|
||||
);
|
||||
|
||||
// Clean up
|
||||
db.destroy().unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_multiple_files() {
|
||||
let temp_dir = get_temp_dir();
|
||||
|
||||
// Create a new database with small file size to force multiple files
|
||||
let config = OurDBConfig {
|
||||
path: temp_dir.clone(),
|
||||
incremental_mode: true,
|
||||
file_size: Some(1024), // Very small file size (1KB)
|
||||
keysize: Some(6), // 6-byte keysize for multiple files
|
||||
reset: None,
|
||||
};
|
||||
|
||||
let mut db = OurDB::new(config).unwrap();
|
||||
|
||||
// Store enough data to span multiple files
|
||||
let data_size = 500; // bytes per record
|
||||
let test_data = vec![b'A'; data_size];
|
||||
|
||||
let mut ids = Vec::new();
|
||||
for _ in 0..10 {
|
||||
let id = db
|
||||
.set(OurDBSetArgs {
|
||||
id: None,
|
||||
data: &test_data,
|
||||
})
|
||||
.unwrap();
|
||||
ids.push(id);
|
||||
}
|
||||
|
||||
// Verify all data can be retrieved
|
||||
for &id in &ids {
|
||||
let retrieved = db.get(id).unwrap();
|
||||
assert_eq!(retrieved.len(), data_size);
|
||||
}
|
||||
|
||||
// Verify multiple files were created
|
||||
let files = fs::read_dir(&temp_dir)
|
||||
.unwrap()
|
||||
.filter_map(Result::ok)
|
||||
.filter(|entry| {
|
||||
let path = entry.path();
|
||||
path.is_file() && path.extension().map_or(false, |ext| ext == "db")
|
||||
})
|
||||
.count();
|
||||
|
||||
assert!(
|
||||
files > 1,
|
||||
"Expected multiple database files, found {}",
|
||||
files
|
||||
);
|
||||
|
||||
// Clean up
|
||||
db.destroy().unwrap();
|
||||
}
|
Reference in New Issue
Block a user