Add Jieba segmentation for words count

Signed-off-by: hr567 <hr567@hr567.me>

Cargo.lock

@@ -17,6 +17,15 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
 
+[[package]]
+name = "aho-corasick"
+version = "1.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "anstream"
 version = "0.6.14"
@@ -49,11 +58,11 @@ dependencies = [
 
 [[package]]
 name = "anstyle-query"
-version = "1.0.3"
+version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a64c907d4e79225ac72e2a354c9ce84d50ebb4586dee56c82b3ee73004f537f5"
+checksum = "ad186efb764318d35165f1758e7dcef3b10628e26d41a44bc5550652e6804391"
 dependencies = [
- "windows-sys 0.52.0",
+ "windows-sys",
 ]
 
 [[package]]
@@ -63,7 +72,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "61a38449feb7068f52bb06c12759005cf459ee52bb4adc1d5a7c4322d716fb19"
 dependencies = [
  "anstyle",
- "windows-sys 0.52.0",
+ "windows-sys",
 ]
 
 [[package]]
@@ -93,6 +102,12 @@ version = "2.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cf4b9d6a944f767f8e5e0db018570623c85f3d925ac718db4e06d0187adb21c1"
 
+[[package]]
+name = "byteorder"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
+
 [[package]]
 name = "bytes"
 version = "1.6.0"
@@ -101,9 +116,18 @@ checksum = "514de17de45fdb8dc022b1a7975556c53c86f9f0aa5f534b98977b171857c2c9"
 
 [[package]]
 name = "cc"
-version = "1.0.98"
+version = "1.0.99"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41c270e7540d725e65ac7f1b212ac8ce349719624d7bcff99f8e2e488e8cf03f"
+checksum = "96c51067fd44124faa7f870b4b1c969379ad32b2ba805aa959430ceaa384f695"
+
+[[package]]
+name = "cedarwood"
+version = "0.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6d910bedd62c24733263d0bed247460853c9d22e8956bd4cd964302095e04e90"
+dependencies = [
+ "smallvec",
+]
 
 [[package]]
 name = "cfg-if"
@@ -113,9 +137,9 @@ checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
 [[package]]
 name = "clap"
-version = "4.5.4"
+version = "4.5.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "90bc066a67923782aa8515dbaea16946c5bcc5addbd668bb80af688e53e548a0"
+checksum = "5db83dced34638ad474f39f250d7fea9598bdd239eaced1bdf45d597da0f433f"
 dependencies = [
  "clap_builder",
  "clap_derive",
@@ -123,9 +147,9 @@ dependencies = [
 
 [[package]]
 name = "clap_builder"
-version = "4.5.2"
+version = "4.5.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ae129e2e766ae0ec03484e609954119f123cc1fe650337e155d03b022f24f7b4"
+checksum = "f7e204572485eb3fbf28f871612191521df159bc3e15a9f5064c66dba3a8c05f"
 dependencies = [
  "anstream",
  "anstyle",
@@ -135,9 +159,9 @@ dependencies = [
 
 [[package]]
 name = "clap_derive"
-version = "4.5.4"
+version = "4.5.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "528131438037fd55894f62d6e9f068b8f45ac57ffa77517819645d10aed04f64"
+checksum = "c780290ccf4fb26629baa7a1081e68ced113f1d3ec302fa5948f1c381ebf06c6"
 dependencies = [
  "heck",
  "proc-macro2",
@@ -147,9 +171,9 @@ dependencies = [
 
 [[package]]
 name = "clap_lex"
-version = "0.7.0"
+version = "0.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "98cc8fbded0c607b7ba9dd60cd98df59af97e84d24e49c8557331cfc26d301ce"
+checksum = "4b82cf0babdbd58558212896d1a4272303a57bdb245c2bf1147185fb45640e70"
 
 [[package]]
 name = "colorchoice"
@@ -167,7 +191,42 @@ dependencies = [
  "lazy_static",
  "libc",
  "unicode-width",
- "windows-sys 0.52.0",
+ "windows-sys",
+]
+
+[[package]]
+name = "darling"
+version = "0.20.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "83b2eb4d90d12bdda5ed17de686c2acb4c57914f8f921b8da7e112b5a36f3fe1"
+dependencies = [
+ "darling_core",
+ "darling_macro",
+]
+
+[[package]]
+name = "darling_core"
+version = "0.20.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "622687fe0bac72a04e5599029151f5796111b90f1baaa9b544d807a5e31cd120"
+dependencies = [
+ "fnv",
+ "ident_case",
+ "proc-macro2",
+ "quote",
+ "strsim",
+ "syn",
+]
+
+[[package]]
+name = "darling_macro"
+version = "0.20.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "733cabb43482b1a1b53eee8583c2b9e8684d592215ea83efd305dd31bc2f0178"
+dependencies = [
+ "darling_core",
+ "quote",
+ "syn",
 ]
 
 [[package]]
@@ -184,12 +243,49 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "derive_builder"
+version = "0.20.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0350b5cb0331628a5916d6c5c0b72e97393b8b6b03b47a9284f4e7f5a405ffd7"
+dependencies = [
+ "derive_builder_macro",
+]
+
+[[package]]
+name = "derive_builder_core"
+version = "0.20.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d48cda787f839151732d396ac69e3473923d54312c070ee21e9effcaa8ca0b1d"
+dependencies = [
+ "darling",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "derive_builder_macro"
+version = "0.20.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "206868b8242f27cecce124c19fd88157fbd0dd334df2587f36417bafbc85097b"
+dependencies = [
+ "derive_builder_core",
+ "syn",
+]
+
 [[package]]
 name = "encode_unicode"
 version = "0.3.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a357d28ed41a50f9c765dbfe56cbc04a64e53e5fc58ba79fbc34c10ef3df831f"
 
+[[package]]
+name = "fnv"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
+
 [[package]]
 name = "futures"
 version = "0.3.30"
@@ -279,6 +375,15 @@ dependencies = [
  "slab",
 ]
 
+[[package]]
+name = "fxhash"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c31b6d751ae2c7f11320402d34e41349dd1016f8d5d45e48c4312bc8625af50c"
+dependencies = [
+ "byteorder",
+]
+
 [[package]]
 name = "gimli"
 version = "0.29.0"
@@ -303,6 +408,12 @@ version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d231dfb89cfffdbc30e7fc41579ed6066ad03abda9e567ccafae602b97ec5024"
 
+[[package]]
+name = "ident_case"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
+
 [[package]]
 name = "indicatif"
 version = "0.17.8"
@@ -337,6 +448,21 @@ version = "1.0.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b"
 
+[[package]]
+name = "jieba-rs"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c1e2b0210dc78b49337af9e49d7ae41a39dceac6e5985613f1cf7763e2f76a25"
+dependencies = [
+ "cedarwood",
+ "derive_builder",
+ "fxhash",
+ "lazy_static",
+ "phf",
+ "phf_codegen",
+ "regex",
+]
+
 [[package]]
 name = "lazy_static"
 version = "1.4.0"
@@ -380,17 +506,6 @@ dependencies = [
  "adler",
 ]
 
-[[package]]
-name = "mio"
-version = "0.8.11"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a4a650543ca06a924e8b371db273b2756685faae30f8487da1b56505a8f78b0c"
-dependencies = [
- "libc",
- "wasi",
- "windows-sys 0.48.0",
-]
-
 [[package]]
 name = "nu-ansi-term"
 version = "0.46.0"
@@ -458,7 +573,45 @@ dependencies = [
  "libc",
  "redox_syscall",
  "smallvec",
- "windows-targets 0.52.5",
+ "windows-targets",
+]
+
+[[package]]
+name = "phf"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ade2d8b8f33c7333b51bcf0428d37e217e9f32192ae4772156f65063b8ce03dc"
+dependencies = [
+ "phf_shared",
+]
+
+[[package]]
+name = "phf_codegen"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e8d39688d359e6b34654d328e262234662d16cc0f60ec8dcbe5e718709342a5a"
+dependencies = [
+ "phf_generator",
+ "phf_shared",
+]
+
+[[package]]
+name = "phf_generator"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48e4cc64c2ad9ebe670cb8fd69dd50ae301650392e81c05f9bfcb2d5bdbc24b0"
+dependencies = [
+ "phf_shared",
+ "rand",
+]
+
+[[package]]
+name = "phf_shared"
+version = "0.11.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "90fcb95eef784c2ac79119d1dd819e162b5da872ce6f3c3abe1e8ca1c082f72b"
+dependencies = [
+ "siphasher",
 ]
 
 [[package]]
@@ -497,6 +650,21 @@ dependencies = [
  "proc-macro2",
 ]
 
+[[package]]
+name = "rand"
+version = "0.8.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
+dependencies = [
+ "rand_core",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.6.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
+
 [[package]]
 name = "redox_syscall"
 version = "0.5.1"
@@ -506,6 +674,35 @@ dependencies = [
  "bitflags",
 ]
 
+[[package]]
+name = "regex"
+version = "1.10.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b91213439dad192326a0d7c6ee3955910425f441d7038e0d6933b0aec5c4517f"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "38caf58cc5ef2fed281f89292ef23f6365465ed9a41b7a7754eb4e26496c92df"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a66a03ae7c801facd77a29370b4faec201768915ac14a721ba36f20bc9c209b"
+
 [[package]]
 name = "rustc-demangle"
 version = "0.1.24"
@@ -565,13 +762,10 @@ dependencies = [
 ]
 
 [[package]]
-name = "signal-hook-registry"
+name = "siphasher"
-version = "1.4.2"
+version = "0.3.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a9e9e0b4211b72e7b8b6e85c807d36c212bdb33ea8587f7569562a84df5465b1"
+checksum = "38b58827f4464d87d377d175e90bf58eb00fd8716ff0a62f80356b5e61555d0d"
-dependencies = [
- "libc",
-]
 
 [[package]]
 name = "slab"
@@ -588,16 +782,6 @@ version = "1.13.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3c5e1a9a646d36c3599cd173a41282daf47c44583ad367b8e6837255952e5c67"
 
-[[package]]
-name = "socket2"
-version = "0.5.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ce305eb0b4296696835b71df73eb912e0f1ffd2556a501fcede6e0c50349191c"
-dependencies = [
- "libc",
- "windows-sys 0.52.0",
-]
-
 [[package]]
 name = "strsim"
 version = "0.11.1"
@@ -633,15 +817,10 @@ checksum = "ba4f4a02a7a80d6f274636f0aa95c7e383b912d41fe721a31f29e29698585a4a"
 dependencies = [
  "backtrace",
  "bytes",
- "libc",
- "mio",
  "num_cpus",
  "parking_lot",
  "pin-project-lite",
- "signal-hook-registry",
- "socket2",
  "tokio-macros",
- "windows-sys 0.48.0",
 ]
 
 [[package]]
@@ -720,15 +899,15 @@ checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
 
 [[package]]
 name = "unicode-width"
-version = "0.1.12"
+version = "0.1.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "68f5e5f3158ecfd4b8ff6fe086db7c8467a2dfdac97fe420f2b7c4aa97af66d6"
+checksum = "0336d538f7abc86d282a4189614dfaa90810dfc2c6f6427eaf88e16311dd225d"
 
 [[package]]
 name = "utf8parse"
-version = "0.2.1"
+version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "711b9620af191e0cdc7468a8d14e709c3dcdb115b36f838e601583af800a370a"
+checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
 
 [[package]]
 name = "valuable"
@@ -736,12 +915,6 @@ version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "830b7e5d4d90034032940e4ace0d9a9a057e7a45cd94e6c007832e39edb82f6d"
 
-[[package]]
-name = "wasi"
-version = "0.11.0+wasi-snapshot-preview1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
-
 [[package]]
 name = "winapi"
 version = "0.3.9"
@@ -764,37 +937,13 @@ version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
 
-[[package]]
-name = "windows-sys"
-version = "0.48.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
-dependencies = [
- "windows-targets 0.48.5",
-]
-
 [[package]]
 name = "windows-sys"
 version = "0.52.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
 dependencies = [
- "windows-targets 0.52.5",
+ "windows-targets",
-]
-
-[[package]]
-name = "windows-targets"
-version = "0.48.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
-dependencies = [
- "windows_aarch64_gnullvm 0.48.5",
- "windows_aarch64_msvc 0.48.5",
- "windows_i686_gnu 0.48.5",
- "windows_i686_msvc 0.48.5",
- "windows_x86_64_gnu 0.48.5",
- "windows_x86_64_gnullvm 0.48.5",
- "windows_x86_64_msvc 0.48.5",
 ]
 
 [[package]]
@@ -803,46 +952,28 @@ version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6f0713a46559409d202e70e28227288446bf7841d3211583a4b53e3f6d96e7eb"
 dependencies = [
- "windows_aarch64_gnullvm 0.52.5",
+ "windows_aarch64_gnullvm",
- "windows_aarch64_msvc 0.52.5",
+ "windows_aarch64_msvc",
- "windows_i686_gnu 0.52.5",
+ "windows_i686_gnu",
  "windows_i686_gnullvm",
- "windows_i686_msvc 0.52.5",
+ "windows_i686_msvc",
- "windows_x86_64_gnu 0.52.5",
+ "windows_x86_64_gnu",
- "windows_x86_64_gnullvm 0.52.5",
+ "windows_x86_64_gnullvm",
- "windows_x86_64_msvc 0.52.5",
+ "windows_x86_64_msvc",
 ]
 
-[[package]]
-name = "windows_aarch64_gnullvm"
-version = "0.48.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
-
 [[package]]
 name = "windows_aarch64_gnullvm"
 version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7088eed71e8b8dda258ecc8bac5fb1153c5cffaf2578fc8ff5d61e23578d3263"
 
-[[package]]
-name = "windows_aarch64_msvc"
-version = "0.48.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
-
 [[package]]
 name = "windows_aarch64_msvc"
 version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9985fd1504e250c615ca5f281c3f7a6da76213ebd5ccc9561496568a2752afb6"
 
-[[package]]
-name = "windows_i686_gnu"
-version = "0.48.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
-
 [[package]]
 name = "windows_i686_gnu"
 version = "0.52.5"
@@ -855,48 +986,24 @@ version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "87f4261229030a858f36b459e748ae97545d6f1ec60e5e0d6a3d32e0dc232ee9"
 
-[[package]]
-name = "windows_i686_msvc"
-version = "0.48.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
-
 [[package]]
 name = "windows_i686_msvc"
 version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "db3c2bf3d13d5b658be73463284eaf12830ac9a26a90c717b7f771dfe97487bf"
 
-[[package]]
-name = "windows_x86_64_gnu"
-version = "0.48.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
-
 [[package]]
 name = "windows_x86_64_gnu"
 version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4e4246f76bdeff09eb48875a0fd3e2af6aada79d409d33011886d3e1581517d9"
 
-[[package]]
-name = "windows_x86_64_gnullvm"
-version = "0.48.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
-
 [[package]]
 name = "windows_x86_64_gnullvm"
 version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "852298e482cd67c356ddd9570386e2862b5673c85bd5f88df9ab6802b334c596"
 
-[[package]]
-name = "windows_x86_64_msvc"
-version = "0.48.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
-
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.52.5"
@@ -911,6 +1018,7 @@ dependencies = [
  "dashmap",
  "futures",
  "indicatif",
+ "jieba-rs",
  "once_cell",
  "serde_json",
  "tokio",

Cargo.toml

@@ -6,13 +6,23 @@ edition = "2021"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-clap = { version = "4.5.4", features = ["derive"] }
+clap = { version = "4.5.7", features = ["derive"] }
 dashmap = { version = "5.5.3", features = ["serde"] }
 futures = "0.3.30"
 indicatif = "0.17.8"
+jieba-rs = { version = "0.7.0", default-features = false }
 once_cell = "1.19.0"
 serde_json = "1.0.117"
-tokio = { version = "1.38.0", features = ["full"] }
+tokio = { version = "1.38.0", features = [
+    "rt",
+    "rt-multi-thread",
+    "io-util",
+    "time",
+    "macros",
+    "sync",
+    "fs",
+    "parking_lot",
+] }
 tracing = "0.1.40"
 tracing-subscriber = "0.3.18"
 

src/main.rs

@@ -3,7 +3,7 @@ use std::collections::{BTreeMap, HashMap, VecDeque};
 use std::env::current_dir;
 use std::fmt::Write;
 use std::fs::read_to_string;
-use std::io;
+use std::io::{self, Cursor};
 use std::path::PathBuf;
 use std::rc::{Rc, Weak};
 use std::sync::{
@@ -15,6 +15,7 @@ use std::time::Duration;
 use clap::Parser;
 use dashmap::DashMap;
 use indicatif::{ProgressBar, ProgressState, ProgressStyle};
+use jieba_rs::Jieba;
 use once_cell::{sync::Lazy, unsync::OnceCell};
 use tokio::{fs, sync::Semaphore, time::sleep};
 use tracing::Instrument;
@@ -40,6 +41,10 @@ static ARGS: Lazy<Args> = Lazy::new(|| {
     }
     args
 });
+static SEGMENTATION: Lazy<Jieba> = Lazy::new(|| {
+    const DICT_CONTENT: &[u8] = include_bytes!("../dict.txt.big");
+    Jieba::with_dict(&mut Cursor::new(DICT_CONTENT)).expect("failed to open jieba with dict")
+});
 thread_local! {
     static ANALYZER: OnceCell<AhoCorasick> = const { OnceCell::new() };
 }
@@ -98,10 +103,13 @@ async fn main() -> io::Result<()> {
                 let content = String::from_utf8_lossy(&buf);
 
                 tracing::debug!("Start to analyze");
+                let words_cnt = SEGMENTATION.cut(&content, true).len();
                 let result = ANALYZER.with(|analyzer| {
-                    analyzer
+                    let mut res = analyzer
                         .get_or_init(|| AhoCorasick::new(&ARGS.keywords))
-                        .analyze(&content)
+                        .analyze(&content);
+                    res.insert("_total", words_cnt);
+                    res
                 });
                 for (word, count) in result.iter() {
                     tracing::trace!(word = %word, count = %count, "Analyzed");
@@ -110,13 +118,13 @@ async fn main() -> io::Result<()> {
                         .and_modify(|e| *e += count)
                         .or_insert(*count);
                 }
-                tracing::debug!("Finished analysis");
 
+                tracing::info!("Write result to file");
                 let json_result = serde_json::to_vec(&result).unwrap();
                 fs::write(task.file.with_extension("json"), json_result).await?;
-                tracing::info!("Write result to file");
 
                 analyzed_size.fetch_add(len, Ordering::Release);
+                tracing::debug!("Finished analysis");
 
                 io::Result::Ok(())
             }