WIP: Initial proposed search method for hashdb (#7)

* Initial proposed search method for hashdb

Author: PyDataBlog

.gitignore

@@ -1,2 +1,3 @@
 /target
 Session.vim
+.vscode/

Cargo.lock

@@ -1,6 +1,6 @@
 [package]
 name = "simstring_rust"
-version = "0.1.0"
+version = "0.1.1"
 description = "A native Rust implementation of the SimString algorithm"
 license = "MIT"
 repository = "https://github.com/PyDataBlog/simstring_rs"

Cargo.toml

@@ -1,4 +1,9 @@
-# simstring_rs
+# simstring_rust
+
+[![Build Status](https://github.com/PyDataBlog/simstring_rs/actions/workflows/CI.yml/badge.svg)](https://github.com/PyDataBlog/simstring_rs/actions)
+[![Crates.io](https://img.shields.io/crates/v/simstring_rust.svg)](https://crates.io/crates/simstring_rust)
+[![Documentation](https://docs.rs/simstring_rust/badge.svg)](https://docs.rs/simstring_rust)
+[![Rust](https://img.shields.io/badge/rust-1.63.0%2B-blue.svg?maxAge=3600)](https://github.com/PyDataBlog/simstring_rs)
 
 A native Rust implementation of the CPMerge algorithm, designed for approximate string matching. This crate is particularly useful for natural language processing tasks that require the retrieval of strings/texts from very large corpora (big amounts of texts). Currently, this crate supports both character and word-based N-grams feature generation, with plans to allow custom user-defined feature generation methods.
 
@@ -9,7 +14,6 @@ A native Rust implementation of the CPMerge algorithm, designed for approximate
 - ✅ Support for Unicode
 - [ ] Support for building databases directly from text files
 - [ ] Mecab-based tokenizer support
-- [ ] Support for persistent databases like MongoDB
 
 ## Supported String Similarity Measures
 
@@ -21,18 +25,18 @@ A native Rust implementation of the CPMerge algorithm, designed for approximate
 
 ## Installation
 
-Add `simstring_rs` to your `Cargo.toml`:
+Add `simstring_rust` to your `Cargo.toml`:
 
 ```toml
 [dependencies]
-simstring_rs = "0.1.0"
+simstring_rust = "0.1.0" # change version accordingly
 ```
 
 For the latest features, you can add the master branch by specifying the Git repository:
 
 ```toml
 [dependencies]
-simstring_rs = { git = "https://github.com/PyDataBlog/simstring_rs.git", branch = "main" }
+simstring_rust = { git = "https://github.com/PyDataBlog/simstring_rs.git", branch = "main" }
 ```
 
 Note: Using the master branch may include experimental features and potential breakages. Use with caution!

README.md

@@ -1,39 +1,29 @@
-use simstring_rust::database::{HashDB, SimStringDB};
-use simstring_rust::extractors::{CharacterNGrams, FeatureExtractor};
+use simstring_rust::database::HashDB;
+use simstring_rust::extractors::CharacterNGrams;
 use simstring_rust::measures::Cosine;
 
 fn main() {
-    let _cs = Cosine::new();
-
     let feature_extractor = CharacterNGrams {
-        n: 3,
+        n: 2,
         padder: " ".to_string(),
     };
-
-    let mut db = HashDB::new(feature_extractor);
+    let measure = Cosine::new();
+    let mut db = HashDB::new(feature_extractor, measure);
 
     db.insert("hello".to_string());
     db.insert("help".to_string());
     db.insert("halo".to_string());
     db.insert("world".to_string());
 
-    let (total_collection, avg_size_ngrams, total_ngrams) = db.describe_collection();
-    println!(
-        "Database contains {} strings, average n-gram size {:.2}, total n-grams {}.",
-        total_collection, avg_size_ngrams, total_ngrams
-    );
-
-    //println!("Complete DB State: {:?}", db); # FIX: db needs a fmt.debug implementation
-
-    let query = "prepress";
-
-    let query_features = db.feature_extractor.extract(query);
-    let query_size = query_features.len();
-
-    println!("Query size: {}", query_size);
+    let threshold = 0.5;
+    let results = db.search("hell", threshold);
 
-    println!("Extracted features from query '{}':", query);
-    for (feature, count) in &query_features {
-        println!(" - Feature: '{}', Count: {}", feature, count);
+    if results.is_empty() {
+        println!("No results found with threshold {}", threshold);
+    } else {
+        println!("Results with threshold {}:", threshold);
+        for result in results {
+            println!("Match: '{}' (score: {})", result.value, result.score);
+        }
     }
 }