feat: introduce fuzzy search for native indexer (#14109)

Cargo.lock

@@ -49,7 +49,7 @@ dependencies = [
  "assert-json-diff",
  "cc",
  "chrono",
- "criterion2",
+ "criterion",
  "docx-parser",
  "infer",
  "path-ext",
@@ -61,6 +61,7 @@ dependencies = [
  "serde_json",
  "sha3",
  "strum_macros",
+ "tempfile",
  "text-splitter",
  "thiserror 2.0.12",
  "tiktoken-rs",
@@ -153,16 +154,14 @@ dependencies = [
  "bincode",
  "chrono",
  "dotenvy",
- "jieba-rs",
+ "memory-indexer",
  "napi",
  "napi-build",
  "napi-derive",
- "once_cell",
  "serde",
  "serde_json",
  "sqlx",
  "thiserror 2.0.12",
- "tiniestsegmenter",
  "tokio",
  "uniffi",
  "uuid",
@@ -2642,6 +2641,22 @@ version = "2.7.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
 
+[[package]]
+name = "memory-indexer"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10feba381e2eeb6582f34379d62ee0658e57f63d776698150b985bd0f38664b3"
+dependencies = [
+ "jieba-rs",
+ "once_cell",
+ "pinyin",
+ "serde",
+ "serde_json",
+ "strsim",
+ "unicode-normalization",
+ "unicode-script",
+]
+
 [[package]]
 name = "mimalloc"
 version = "0.1.46"
@@ -3284,6 +3299,12 @@ version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184"
 
+[[package]]
+name = "pinyin"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "16f2611cd06a1ac239a0cea4521de9eb068a6ca110324ee00631aa68daa74fc0"
+
 [[package]]
 name = "pkcs1"
 version = "0.7.5"
@@ -4772,12 +4793,6 @@ dependencies = [
  "rustc-hash 1.1.0",
 ]
 
-[[package]]
-name = "tiniestsegmenter"
-version = "0.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f39721481fb54f0e9f3a1da5a6ac6063c61ec62ec828cd5e1860acce9458f40"
-
 [[package]]
 name = "tinystr"
 version = "0.8.1"
@@ -5141,6 +5156,12 @@ version = "0.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e70f2a8b45122e719eb623c01822704c4e0907e7e426a05927e1a1cfff5b75d0"
 
+[[package]]
+name = "unicode-script"
+version = "0.5.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "383ad40bb927465ec0ce7720e033cb4ca06912855fc35db31b5755d0de75b1ee"
+
 [[package]]
 name = "unicode-segmentation"
 version = "1.12.0"