Files
keep/src/services/item_service.rs
Andrew Phillips 1f82be1f02 fix: remove unused meta plugin types and references
Co-authored-by: aider (openai/andrew/openrouter/deepseek/deepseek-chat-v3.1) <aider@aider.chat>
2025-08-26 18:03:13 -03:00

388 lines
15 KiB
Rust

use crate::common::PIPESIZE;
use crate::config::Settings;
use crate::services::compression_service::CompressionService;
use crate::services::error::CoreError;
use crate::services::meta_service::MetaService;
use crate::services::types::{ItemWithContent, ItemWithMeta};
use crate::meta_plugin::{get_meta_plugin, MetaPlugin, MetaPluginType};
use crate::db::{self, Meta};
use crate::compression_engine::{get_compression_engine, CompressionType};
use crate::modes::common::settings_compression_type;
use clap::Command;
use log::{debug, warn};
use rusqlite::Connection;
use std::collections::HashMap;
use std::fs;
use std::io::{IsTerminal, Read, Write};
use std::path::PathBuf;
pub struct ItemService {
data_path: PathBuf,
compression_service: CompressionService,
meta_service: MetaService,
}
impl ItemService {
pub fn new(data_path: PathBuf) -> Self {
debug!("ITEM_SERVICE: Creating new ItemService with data_path: {:?}", data_path);
Self {
data_path,
compression_service: CompressionService::new(),
meta_service: MetaService::new(),
}
}
pub fn get_item(&self, conn: &Connection, id: i64) -> Result<ItemWithMeta, CoreError> {
debug!("ITEM_SERVICE: Getting item with id: {}", id);
let item = db::get_item(conn, id)?.ok_or(CoreError::ItemNotFound(id))?;
debug!("ITEM_SERVICE: Found item: {:?}", item);
let tags = db::get_item_tags(conn, &item)?;
debug!("ITEM_SERVICE: Found {} tags for item {}", tags.len(), id);
let meta = db::get_item_meta(conn, &item)?;
debug!("ITEM_SERVICE: Found {} meta entries for item {}", meta.len(), id);
Ok(ItemWithMeta { item, tags, meta })
}
pub fn get_item_content(&self, conn: &Connection, id: i64) -> Result<ItemWithContent, CoreError> {
debug!("ITEM_SERVICE: Getting item content for id: {}", id);
let item_with_meta = self.get_item(conn, id)?;
let item_id = item_with_meta.item.id.ok_or_else(|| CoreError::InvalidInput("Item missing ID".to_string()))?;
if item_id <= 0 {
return Err(CoreError::InvalidInput(format!("Invalid item ID: {}", item_id)));
}
let mut item_path = self.data_path.clone();
item_path.push(item_id.to_string());
debug!("ITEM_SERVICE: Reading content from path: {:?}", item_path);
let content = self
.compression_service
.get_item_content(item_path, &item_with_meta.item.compression)?;
debug!("ITEM_SERVICE: Read {} bytes of content for item {}", content.len(), id);
Ok(ItemWithContent {
item_with_meta,
content,
})
}
pub fn get_item_content_info(&self, conn: &Connection, id: i64) -> Result<(Vec<u8>, String, bool), CoreError> {
let item_with_content = self.get_item_content(conn, id)?;
let metadata = item_with_content.item_with_meta.meta_as_map();
let mime_type = metadata
.get("mime_type")
.map(|s| s.to_string())
.unwrap_or_else(|| "application/octet-stream".to_string());
// Check if content is binary
let is_binary = if let Some(binary_val) = metadata.get("binary") {
binary_val == "true"
} else {
crate::common::is_binary::is_binary(&item_with_content.content)
};
Ok((item_with_content.content, mime_type, is_binary))
}
pub fn get_item_content_info_streaming(
&self,
conn: &Connection,
id: i64,
) -> Result<(Box<dyn Read + Send>, String, bool), CoreError> {
let item_with_meta = self.get_item(conn, id)?;
let item_id = item_with_meta.item.id.ok_or_else(|| CoreError::InvalidInput("Item missing ID".to_string()))?;
if item_id <= 0 {
return Err(CoreError::InvalidInput(format!("Invalid item ID: {}", item_id)));
}
let mut item_path = self.data_path.clone();
item_path.push(item_id.to_string());
let reader = self.compression_service.stream_item_content(item_path.clone(), &item_with_meta.item.compression)?;
let metadata = item_with_meta.meta_as_map();
let mime_type = metadata
.get("mime_type")
.map(|s| s.to_string())
.unwrap_or_else(|| "application/octet-stream".to_string());
// Check if content is binary using only the first 8192 bytes
let is_binary = if let Some(binary_val) = metadata.get("binary") {
binary_val == "true"
} else {
// Read only the first 8192 bytes for binary detection
let mut sample_reader = self.compression_service.stream_item_content(
item_path,
&item_with_meta.item.compression
)?;
let mut sample_buffer = vec![0; 8192];
let bytes_read = sample_reader.read(&mut sample_buffer)?;
crate::common::is_binary::is_binary(&sample_buffer[..bytes_read])
};
Ok((reader, mime_type, is_binary))
}
pub fn find_item(&self, conn: &Connection, ids: &[i64], tags: &[String], meta: &HashMap<String, String>) -> Result<ItemWithMeta, CoreError> {
debug!("ITEM_SERVICE: Finding item with ids: {:?}, tags: {:?}, meta: {:?}", ids, tags, meta);
let item_maybe = match (ids.is_empty(), tags.is_empty() && meta.is_empty()) {
(false, _) => {
debug!("ITEM_SERVICE: Finding by ID: {}", ids[0]);
db::get_item(conn, ids[0])?
},
(true, true) => {
debug!("ITEM_SERVICE: Finding last item");
db::get_item_last(conn)?
},
(true, false) => {
debug!("ITEM_SERVICE: Finding by tags/meta");
db::get_item_matching(conn, &tags.to_vec(), meta)?
}
};
let item = item_maybe.ok_or(CoreError::ItemNotFoundGeneric)?;
debug!("ITEM_SERVICE: Found matching item: {:?}", item);
// Get tags and meta directly instead of calling get_item which makes redundant queries
let item_id = item.id.ok_or_else(|| CoreError::InvalidInput("Item missing ID".to_string()))?;
let tags = db::get_item_tags(conn, &item)?;
debug!("ITEM_SERVICE: Found {} tags for item {}", tags.len(), item_id);
let meta = db::get_item_meta(conn, &item)?;
debug!("ITEM_SERVICE: Found {} meta entries for item {}", meta.len(), item_id);
Ok(ItemWithMeta { item, tags, meta })
}
pub fn list_items(&self, conn: &Connection, tags: &[String], meta: &HashMap<String, String>) -> Result<Vec<ItemWithMeta>, CoreError> {
debug!("ITEM_SERVICE: Listing items with tags: {:?}, meta: {:?}", tags, meta);
let items = db::get_items_matching(conn, &tags.to_vec(), meta)?;
debug!("ITEM_SERVICE: Found {} matching items", items.len());
let item_ids: Vec<i64> = items.iter().filter_map(|item| item.id).collect();
if item_ids.is_empty() {
debug!("ITEM_SERVICE: No items found, returning empty list");
return Ok(Vec::new());
}
debug!("ITEM_SERVICE: Getting tags and meta for {} items", item_ids.len());
let tags_map = db::get_tags_for_items(conn, &item_ids)?;
let meta_map_db = db::get_meta_for_items(conn, &item_ids)?;
let mut result = Vec::new();
for item in items {
let item_id = item.id.unwrap();
let tags = tags_map.get(&item_id).cloned().unwrap_or_default();
let meta_hm = meta_map_db.get(&item_id).cloned().unwrap_or_default();
let meta = meta_hm.into_iter().map(|(name, value)| Meta { id: item_id, name, value }).collect();
result.push(ItemWithMeta { item, tags, meta });
}
debug!("ITEM_SERVICE: Returning {} items with full metadata", result.len());
Ok(result)
}
pub fn delete_item(&self, conn: &mut Connection, id: i64) -> Result<(), CoreError> {
debug!("ITEM_SERVICE: Deleting item with id: {}", id);
if id <= 0 {
return Err(CoreError::InvalidInput(format!("Invalid item ID: {}", id)));
}
let item = db::get_item(conn, id)?.ok_or(CoreError::ItemNotFound(id))?;
debug!("ITEM_SERVICE: Found item to delete: {:?}", item);
let mut item_path = self.data_path.clone();
item_path.push(id.to_string());
debug!("ITEM_SERVICE: Deleting file at path: {:?}", item_path);
let tx = conn.transaction()?;
db::delete_item(&tx, item)?;
fs::remove_file(&item_path).or_else(|e| if e.kind() == std::io::ErrorKind::NotFound { Ok(()) } else { Err(e) })?;
tx.commit()?;
debug!("ITEM_SERVICE: Successfully deleted item {}", id);
Ok(())
}
pub fn save_item<R: Read>(
&self,
mut input: R,
cmd: &mut Command,
settings: &Settings,
tags: &mut Vec<String>,
conn: &mut Connection,
) -> Result<i64, CoreError> {
debug!("ITEM_SERVICE: Starting save_item with tags: {:?}", tags);
if tags.is_empty() {
tags.push("none".to_string());
debug!("ITEM_SERVICE: No tags provided, using default 'none' tag");
}
let compression_type = settings_compression_type(cmd, settings);
debug!("ITEM_SERVICE: Using compression type: {:?}", compression_type);
let compression_engine = get_compression_engine(compression_type.clone())?;
let tx = conn.transaction()?;
let item_id;
let mut item;
{
item = db::create_item(&tx, compression_type.clone())?;
item_id = item.id.unwrap();
debug!("ITEM_SERVICE: Created new item with id: {}", item_id);
db::set_item_tags(&tx, item.clone(), tags)?;
debug!("ITEM_SERVICE: Set tags for item {}", item_id);
let item_meta = self.meta_service.collect_initial_meta();
debug!("ITEM_SERVICE: Collected {} initial meta entries", item_meta.len());
for (k, v) in item_meta.iter() {
db::add_meta(&tx, item_id, k, v)?;
}
}
// Print the "KEEP: New item" message before starting to read input
if !settings.quiet {
if std::io::stderr().is_terminal() {
let mut t = term::stderr().unwrap();
let _ = t.reset();
let _ = t.attr(term::Attr::Bold);
let _ = write!(t, "KEEP:");
let _ = t.reset();
let _ = write!(t, " New item ");
let _ = t.attr(term::Attr::Bold);
let _ = write!(t, "{item_id}");
let _ = t.reset();
let _ = write!(t, " tags: ");
let _ = t.attr(term::Attr::Bold);
let _ = write!(t, "{}", tags.join(" "));
let _ = t.reset();
let _ = writeln!(t);
let _ = std::io::stderr().flush();
} else {
let mut t = std::io::stderr();
let _ = writeln!(t, "KEEP: New item: {} tags: {:?}", item_id, tags);
}
}
let mut plugins = self.meta_service.get_plugins(cmd, settings);
debug!("ITEM_SERVICE: Got {} meta plugins", plugins.len());
self.meta_service.initialize_plugins(&mut plugins, &tx, item_id);
let mut item_path = self.data_path.clone();
item_path.push(item_id.to_string());
debug!("ITEM_SERVICE: Writing item to path: {:?}", item_path);
let mut item_out = compression_engine.create(item_path.clone())?;
let mut buffer = [0; PIPESIZE];
let mut total_bytes = 0;
debug!("ITEM_SERVICE: Starting to read and process input data");
loop {
let n = input.read(&mut buffer)?;
if n == 0 { break; }
total_bytes += n as i64;
item_out.write_all(&buffer[..n])?;
self.meta_service.process_chunk(&mut plugins, &buffer[..n], &tx, item_id);
}
debug!("ITEM_SERVICE: Processed {} bytes total", total_bytes);
item_out.flush()?;
drop(item_out);
debug!("ITEM_SERVICE: Finalizing meta plugins");
self.meta_service.finalize_plugins(&mut plugins, &tx, item_id);
item.size = Some(total_bytes);
db::update_item(&tx, item.clone())?;
tx.commit()?;
debug!("ITEM_SERVICE: Transaction committed successfully");
Ok(item_id)
}
pub fn save_item_from_mcp(
&self,
content: &[u8],
tags: &Vec<String>,
metadata: &HashMap<String, String>,
conn: &mut Connection,
) -> Result<ItemWithMeta, CoreError> {
debug!("ITEM_SERVICE: Starting save_item_from_mcp with {} bytes, {} tags, {} metadata entries",
content.len(), tags.len(), metadata.len());
let compression_type = CompressionType::LZ4;
let compression_engine = get_compression_engine(compression_type.clone())?;
let tx = conn.transaction()?;
let item_id;
let mut item;
{
item = db::create_item(&tx, compression_type.clone())?;
item_id = item.id.unwrap();
debug!("ITEM_SERVICE: Created MCP item with id: {}", item_id);
// Add tags
for tag in tags {
db::add_tag(&tx, item_id, tag)?;
}
debug!("ITEM_SERVICE: Added {} tags to MCP item", tags.len());
// Add custom metadata
for (key, value) in metadata {
db::add_meta(&tx, item_id, key, value)?;
}
debug!("ITEM_SERVICE: Added {} custom metadata entries to MCP item", metadata.len());
}
let mut item_path = self.data_path.clone();
item_path.push(item_id.to_string());
debug!("ITEM_SERVICE: Writing MCP item to path: {:?}", item_path);
let mut writer = compression_engine.create(item_path.clone())?;
writer.write_all(content)?;
drop(writer);
let plugin_types = vec![
MetaPluginType::FileMime,
MetaPluginType::FileEncoding,
MetaPluginType::Binary,
MetaPluginType::LineCount,
MetaPluginType::WordCount,
MetaPluginType::DigestSha256,
MetaPluginType::User,
MetaPluginType::Hostname,
];
let mut plugins: Vec<Box<dyn MetaPlugin>> =
plugin_types.iter().map(|p| get_meta_plugin(p.clone())).collect();
debug!("ITEM_SERVICE: Created {} meta plugins for MCP item", plugins.len());
self.meta_service
.initialize_plugins(&mut plugins, &tx, item_id);
self.meta_service
.process_chunk(&mut plugins, content, &tx, item_id);
self.meta_service.finalize_plugins(&mut plugins, &tx, item_id);
debug!("ITEM_SERVICE: Processed MCP item through meta plugins");
item.size = Some(content.len() as i64);
db::update_item(&tx, item.clone())?;
tx.commit()?;
debug!("ITEM_SERVICE: MCP item transaction committed successfully");
self.get_item(conn, item_id)
}
pub fn get_compression_service(&self) -> &CompressionService {
&self.compression_service
}
pub fn get_data_path(&self) -> &PathBuf {
&self.data_path
}
}